Open Access is an initiative that aims to make scientific research freely available to all. To date our community has made over 100 million downloads. It’s based on principles of collaboration, unobstructed discovery, and, most importantly, scientific progression. As PhD students, we found it difficult to access the research we needed, so we decided to create a new Open Access publisher that levels the playing field for scientists across the world. How? By making research easy to access, and puts the academic needs of the researchers before the business interests of publishers.
We are a community of more than 103,000 authors and editors from 3,291 institutions spanning 160 countries, including Nobel Prize winners and some of the world’s most-cited researchers. Publishing on IntechOpen allows authors to earn citations and find new collaborators, meaning more people see your work not only from your own field of study, but from other related fields too.
This chapter explores how smart cities can enhance building management through technologies like the Internet of Things (IoT) and advanced predictive models, focusing on energy efficiency and air quality. The escalating reliance on technology as the primary solution to contemporary and future challenges has highlighted Internet of Things (IoT), digitalization, and machine learning, among others, as new methodologies for assessing management in smart cities. Moreover, in the realm of defining innovative building management systems, pressing issues such as climate change and pandemic episodes like COVID-19 underscore the need to prioritize energy efficiency and air quality. This imperative has led to the emergence of digital twins, a technology integrating 3D models with real-time data, enabling a comprehensive understanding of building dynamics. In addition, automated prediction models leveraging advanced statistical and machine learning techniques contribute significantly to enhancing climatization control, energy efficiency, and air quality management. These predictive models analyze historical data, enabling accurate forecasts to assess future behavior, which is crucial for effective maintenance planning. The application of linear and non-linear regression models, alongside techniques like Support Vector Machines and neural networks, further refines predictions. Additionally, real-time monitoring and decision algorithms optimize information transmission during incidents, ensuring a rapid response to environmental factors or anomalies, thereby mitigating risks and maximizing operational efficiency.
*Address all correspondence to: cristina.rodriguez.sanchez@urjc.es
1. Introduction
European initiatives, such as the Energy Performance of Buildings Directive (EPBD) and national strategies, have laid the groundwork for achieving nearly zero-energy buildings by 2030. This regulatory push further underscores the need for smart building management systems. Moreover, along the last 3 years, there have been two main world trending topics among any other event: the pandemics of COVID-19 and the energy-climate crisis [1]. These global events have exposed a lack of solutions. In fact, many countries have been forced to change their policy strategies to implement quick measures to confront climate change, energy consumption, and public health difficulties. In this way, governments and institutions seek to put the focus on the most critical spaces: buildings. What makes these places so significant is the struggle to achieve proper air quality to maintain public health measures without losing the point on thermal and electric energy consumption needed to hold comfortable conditions inside. Technology plays an important role in a mesh of buildings that seems to not be prepared for nowadays concerns [2, 3].
The concern for the efficient management of buildings must follow the implementation of standards, such as RITE in Spain, on energy management systems [4]. All available information related to energy efficiency and air quality to categorize spaces inside buildings could be integrated into digital models in a unified, reliable, and updated manner and an open and interchangeable format with the rest of the organization’s systems. The model should be chosen based on the UNE-ISO 55001 asset management standard [5], the British standard PAS 1192 [6], and the UNE-ISO 19650 standard [7], the latter concerning the use of the Building Information Modeling (BIM) methodology. BIM modeling and technology of machine learning aim to generate and manage all the information of a building during its life cycle, using a digital model or digital twin (DT) of the building.
It remains necessary to consider the influence of occupants on the operation of buildings, especially on the HVAC (heating, ventilation, and air conditioning) system, and its impact on indoor air quality (IAQ). An important problem is that data on the real-time buildings’ occupancy are typically missing, and even that usually does not match the original design capacity. Also common is the lack of historical records of variables that affect IAQ and comfort, such as room temperature, humidity, CO2 concentration, and others such as pressure or total volatile organic compounds (TVOC). Although simulation tools can be used at the design stage of a new building or facility to make estimates, the actual measurement is necessary for efficient management in existing buildings. Moreover, both energy consumption and air quality are two of the application paradigms that are analyzed and applied to smart cities, or similar structures like a university smart campus [8].
A previous work presents a hybrid model to optimize energy consumption and user comfort in residential buildings [3]. In this chapter, the model proposed by the authors consisted of two widely used optimization algorithms: the firefly algorithm (FA) and the genetic algorithm (GA). The hybridization of two optimization approaches results in a better optimization process, leading to improved process performance in terms of minimum energy consumption and maximum occupant comfort. It would be interesting to analyze it for public buildings with outdated electrical installations. Moreover, in the work by Fiorotti et al. [9], GA is also used to plan the consumption in a smart home by acting in the appliances use, duration, frequency, and comfort index, in addition to the electrical power cost and the renewable energy generated.
Machine learning (ML), artificial neural network (ANN), and extreme gradient boosting (XGBOOST) have also been used for prediction in smart buildings. For instance, it was used to predict thermal comfort, ventilation, and air conditioning [10]. In addition, ANN is used to optimize the energy consumption by applying a monitoring system that manages the saving of energy produced by renewable sources [11]. Therefore, obtaining this information involves incorporating new measurement and control elements, which can be technically difficult and costly. Therefore, it would be desirable to have low-cost, low-maintenance, autonomous sensors and actuators capable of communicating wirelessly to minimize installation costs. For this reason, the integration of IoT capabilities is very convenient. The prediction for energy consumption plays an important role in improving building energy efficiency since it can facilitate the implementation of many building energy efficiency measures, namely demand response of buildings [12], urban energy planning [13], and fault detection [14]. It can also assist in operation strategies of different systems, such as HVAC systems [15], and indirect evaporative cooling energy recovery systems [16] to save energy.
The unavoidable reinvention of cities for the near future has the spotlight on the creation of smart buildings, where the international community must put forward Internet of Things (IoT), connectivity networks, virtual reality, and new tools for information gauging between other techniques, as ways out for the known problems.
This section assesses the effectiveness of current technologies for urban building management, focusing on air quality, energy efficiency, and predictive systems. A detailed review of scientific research and industry developments is essential. Key aspects such as data collection, transmission, air quality standards, thermal comfort, building management systems, and energy demand forecasting methods will be examined. Through a critical analysis, outcomes will be compared and discussed using traditional methodologies like Forrester Wave and comparative charts.
In fact, the challenges of recent times have led to the emergence of new ways of working. Digital transformation has influenced sectors such as education, health services, enterprises, and even tourism [11]. This situation has created an opportunity to invest in added value to improve day-to-day life in society.
From the perspective of energy and construction, numerous techniques merging with technology aim to make jobs easier and safer. This approach also brings extended control over procedures, quality, project and asset management, or Life Cycle Assessment (LCA). Utilizing existing digital tools in buildings provides an opportunity to rebuild smarter cities. Addressing this common concern, monitoring different information in buildings has become a demand in the EU policy for achieving nearly zero-energy buildings (nZEB) by 2030 [9].
The transformation of buildings and cities is made possible using the Internet of Things (IoT), advanced data networks, detailed thermal comfort and air quality control or even energy demand prediction.
2.1 Data collection and IoT applications in smart buildings
In recent times, data have become one of the most valued assets globally. Major companies have showcased the impact of using information of interest in their systems. In building management (BM), measurements inside the rooms of a building and its external environment make a difference in understanding the place’s needs. Gauging parameters such as temperature, humidity, carbon dioxide levels, people capacity, or climatology can contribute to a significant amount of information for use in energy management and environmental control. This section describes several key factors while collecting data through IoT.
Discussing new construction, the installation of several devices to read temperature, distance, luminosity, or others can be simple. However, many countries, such as Spain, face a paradigm where existing building renovation becomes a priority due to the characteristics of the real estate park [1]. Thus, preparing already-built spaces to collect data presents some limitations that must be overcome, with difficulties often found while connecting devices to electricity. On several occasions, internal energy storage systems must be used in gadgets.
The effectiveness of IoT in smart buildings depends heavily on the capabilities and specifications of the devices used to collect data. These devices need to meet certain technical requirements to ensure accurate and reliable data collection. The following are some of the key factors that influence device selection:
Resolution: The minimum amount by which the real variable must vary to be detected by the sensor. For example, sensors used for temperature control often require a resolution of 0.1°C to detect small changes in the indoor environment. Carbon dioxide sensors typically need a resolution of 0.01 ppm, as small fluctuations can significantly affect indoor air quality.
Accuracy: The proximity between the real and measured variable is essential for reliable data collection. Accuracy is often ensured through rigorous calibration of the equipment, with relative errors varying depending on the sensor type. For instance, high-accuracy sensors are critical for measuring indoor air quality to comply with regulatory standards.
Signal transmission: Sensors and actuators translate energy or signals into formats that can be processed by building management systems. The transmission can be simplex, half-duplex, or duplex, depending on whether communication occurs in one direction or two. For smart buildings, duplex systems are often preferred to enable both real-time monitoring and responsive actions.
Energy consumption and storage: Many sensors operate in buildings where access to electrical power is limited, making energy efficiency a priority. Devices need to be equipped with low-power systems or rely on internal energy storage like batteries. Certain operational algorithms can extend battery life by up to 90%, ensuring longer deployment periods without frequent maintenance. Technologies such as LoRaWAN and Sigfox, known for their low energy consumption, are commonly used in smart building environments.
2.2 Data transmission technologies for smart city networks
The way to communicate data can differ from one project to another depending on several issues such as space, buildings, and existence of electric power or connectivity between others. The properties to look at are defined in this section, and main technologies to cover smart cities’ necessities are proposed as well.
Technologies like LoRaWAN offer long-range and low-power communication, making them suitable for large buildings where energy efficiency is critical. However, the higher data rates of Wi-Fi may be necessary for more immediate real-time monitoring, especially in smaller, high-traffic areas. Establishing management systems for existing buildings can pose significant challenges. The task of connecting wires to devices and servers often involves strenuous efforts, rendering wired connectors impractical for a broader audience. Consequently, alternative methods of connection must be explored.
Wireless links emerge as a promising alternative in such scenarios. However, various technologies need to be thoroughly examined and compared against Smart Cities parameters, including:
Range: Wireless technologies exhibit varying ranges, typically measured in meters to kilometers. For instance, NFC operates in 1–2 meters range and Wi-Fi has an indoor range of around 30 meters, while technologies like LoRaWAN can reach several kilometers.
Data rate: The data rate, or the speed at which data are transmitted, is crucial for efficient communication. Wi-Fi offers high data rates, ranging from a few Mbps to several Gbps, suitable for applications requiring real-time data transfer. In contrast, LPWAN technologies like LoRaWAN provide lower data rates, usually in the range of a few Kbps to Mbps.
Energy consumption: The energy consumption of wireless technologies is a critical factor, particularly for battery-operated devices. Low-power wide-area network (LPWAN) technologies like Sigfox and LoRaWAN are designed for low energy consumption, enabling long battery life for connected devices. Wi-Fi and LTE-M, while providing higher data rates, may have higher energy requirements.
Communication technologies such as Bluetooth, LoRaWAN, Sigfox, ZigBee, Wi-Fi, and LTE-M demand a detailed exploration, providing examples, references, and product insights. These connectivity solutions can be classified into four distinct categories: WLAN, WAN, PAN, or LPWAN. A comparative table can be formulated, considering energy-saving systems for data transmission.
Among the examples shown in the Figure 1, Wi-Fi and LTE technologies stand out for their high data rates. These networks are widely deployed in most buildings, allowing for the transmission of large information packages. However, higher data rates correlate directly with increased power consumption. This poses challenges for systems operating without a direct power source, where adaptability is better achieved with electric energy storage systems, such as batteries. Additionally, the information typically consists of numerical values representing various variables measured within the building, making PAN and LPWAN networks more suitable for this context.
Figure 1.
Data rate vs. range comparison among the different connectivity technologies.
When considering coverage within a building, it is essential to account for gaps between corridors or rooms, even if significant distances are not necessary. Consequently, PAN options with limited ranges, which are insufficient for building requirements, should be excluded. This limitation is evident in both residential buildings and tertiary structures like shopping centers and schools.
After a market study of emerging technologies in building management, Figure 2 is presented in the style of a Forrester Wave. Lora appears to be the most disruptive technology of interest for building management, with its industry development growing in recent years, making it the most suitable option for the defined application considered in this chapter.
Figure 2.
Energy consumption vs. range comparison.
2.3 Standards for air quality and thermal comfort
Standards are important to shape sustainability among different criteria, being the rules to follow when achieving healthy spaces. This section develops the main used standards in Europe and Spain, understood as the followed standards among the international community.
The European Union has implemented various initiatives and strategies to promote healthy environments in buildings, focusing on indoor air quality, thermal comfort, and energy efficiency. Below are specific examples and relevant data:
Energy Performance of Buildings Directive (EPBD):
The EPBD establishes rigorous standards for energy efficiency in EU buildings.
It defines specific requirements for indoor air quality and the implementation of efficient heating and cooling systems.
The directive sets concrete targets for nearly zero-energy buildings (nZEB) by 2030.
Building renovation strategy:
The EU aims to renovate 35 million buildings by 2030 through its renovation strategy.
This strategy involves substantial improvements in thermal insulation, ventilation systems, and the integration of renewable energy sources.
Horizon Europe program for research and innovation:
This program provides funding for research and development projects focused on sustainable technologies for buildings.
Its focus is on innovative solutions to improve indoor air quality and energy efficiency in built environments.
Regulations on indoor air quality:
The EU establishes precise limits for the concentration of pollutants in enclosed spaces.
The Directive on Indoor Air Quality defines detailed requirements for ventilation systems and indoor air quality control in public buildings.
Data on energy consumption in buildings:
According to the European Environment Agency, buildings account for approximately 40% of the total energy consumption in the European Union.
It is anticipated that energy efficiency measures implemented in buildings will reduce greenhouse gas emissions by 60% by 2050.
These examples and data reflect the substantial efforts of the European Union to address sustainability in the construction sector, enhancing the quality of life in indoor spaces while working toward ambitious goals in energy efficiency and emission reduction.
On a regional scale within the EU, Spain shows a strong regulatory framework outlining thermal comfort conditions and environmental health as it is encapsulated within the Technical Building Code (CTE). The CTE, in turn, transposes and adapts essential guidelines set forth by the Regulation of Thermal Installations in Buildings (RITE). Both regulatory frameworks work in tandem to establish premises and standards that must be addressed in various types of buildings. Both address a range of aspects related to the design, construction, and use of buildings, ensuring the implementation of measures that promote thermal comfort and indoor environmental quality.
This regulation serves as an essential reference, providing specific guidelines in accordance with the unique climatic and environmental needs of Spain. Thus, they must be implemented for thermal comfort by defining an operational temperature, air humidity, and air velocity among other parameters (Table 1).
Op. temperature (°C)
Relative hum. (%)
Air velocity (m/s)
Summer
23–25
45–60
>0.2
Winter
21–23
40–50
Table 1.
Thermal comfort parameters.
RITE defines an Air Quality Index (IDA) that must be ensured based on the building’s usage type. For instance, hospitals or healthcare facilities have the strictest requirements, followed by schools, offices, hotels, and other spaces, with regulations gradually becoming less stringent for areas with very poor air quality where the norm does not apply.
In the context of air quality, the RITE outlines five distinct methods to ensure optimal conditions within buildings:
2.3.1 Indirect method for outdoor air flow per person
This method is applied in spaces where individuals have a metabolic activity of approximately 1.2 met, most emissions come from people, and smoking is not allowed. In spaces where smoking is allowed, the flow rates will double (Table 2).
Category
IDA 1
IDA 2
IDA 3
IDA 4
L/s per person
20
12.5
8
5
Table 2.
Method A’s parameters.
2.3.2 Direct method based on perceived air quality
This olfactory method, described in report CR 1752 and the standard UNE-EN13779:2004, calculates the required ventilation flow for well-being based on perceived air quality (Table 3).
This method is suitable for spaces where the main contaminants are from human bio-effluents and is not to be used in smoking-permitted areas. The concentration values listed are added to the outdoor air CO2 concentration (Table 4).
Category ppm
IDA 1
IDA 2
IDA 3
IDA 4
Concentration (ppm)
350
500
800
1200
Table 4.
Method C’s parameters.
2.3.4 Indirect method for air flow per unit of surface area
This method is applicable for spaces not dedicated to permanent human occupancy (Table 5).
Category
IDA 1
IDA 2
IDA 3
IDA 4
L/s per m2
n.a.
0.83
0.55
0.28
Table 5.
Method D’s parameters.
2.3.5 Dilution method
This method is employed when a space has known emissions of specific contaminants. The calculation is like the direct CO2 concentration method.
Most authors agree that Method C is the most restrictive and the only one that assesses the existing conditions regarding the building’s air quality. Therefore, it is presented as the suitable method to use in environmental management. Furthermore, existing buildings without air conditioning systems may lack the capability to calculate air renewals easily, but they still must comply with detailed health regulations.
2.4 Energy demand prediction in buildings through digital twins
In improving the energy performance of buildings, it is necessary to take into consideration the reduction of the environmental footprint of buildings by minimizing their energy consumption (SDG-13), reducing the costs associated with said consumption, creating and implementing management systems that promote constant improvement in the reduction of energy consumption and its optimal use in an efficient manner (SDG-13), and the application of technology (Industry 4.0, Digitalization, IoT, AI, etc.) (SDG-9), among other actions [17].
The prediction of energy consumption in buildings is a very useful tool for studying the energy performance of buildings. Predicting energy use in buildings is necessary for energy planning, management, and conservation [18]. Accurate and rapid prediction of energy consumption can help achieve the objectives of evaluating new building design alternatives and optimizing energy systems [19, 20]. The development of a high-accuracy energy prediction model is considered one of the most effective approaches to understanding the energy performance of buildings [21]. Knowledge based on energy consumption patterns from previous years could be used to predict the energy use of buildings and make energy consumption more efficient [22]. The monitoring and predictions of energy consumption are essential to manage the energy of a building [1, 23].
On the other hand, the application of artificial intelligence and statistical prediction models will generate important benefits in terms of energy efficiency and detection of abnormal behaviors in resource use. Using statistical models will identify trends in energy consumption, which will facilitate more accurate and efficient resource planning. Predictive AI will be particularly useful to detect any abnormal use of resources and provide alerts on potential problems or malfunctions. This would allow timely corrective action, maximizing operational efficiency and avoiding economic losses.
Digital twins (DTs) are virtual models of physical objects or processes, enabling real-time simulation, analysis, and optimization, including predicting energy demand. These replicas use sensor data and are continuously updated to reflect the current state of the system. In buildings, DTs can simulate and optimize systems and operations. In one approach, the system is modeled based on its mechanistic behavior through equations. In another, the DT learns from input-output examples using methods like machine learning, artificial neural networks, or statistical models [24]. Mathematical models of engineering systems have always been fundamental for their design, simulation, and control. Recent advances on the Internet of Things (IoT), data analytics, and machine learning promote the notion of “dynamic” and “interactive” models, that is, architectures that integrate and enrich the mathematical representation of a system with real-time data, evolve through the system’s life cycle, and allow for real-time interaction. Such kinds of models are currently referred to as DTs [25].
DT technology uses IoT data, AI, ML, and analytics for real-time and predictive analysis. Key components include [26]:
Data integration: DT relies on comprehensive data from sensors, RFID tags, cameras, and so on, transmitted in real-time or with minimal delay.
Simulation and modeling: Advanced tools model behaviors, enabling real-time interaction between virtual models and physical entities.
Analytics and intelligence: AI and ML are used for predictive analysis, anomaly detection, and optimization.
Visualization: User-friendly tools present data and simulation results clearly.
Artificial intelligence plays a crucial role in improving digital twins. AI algorithms can analyze large amounts of data generated by DTs, identifying patterns and trends that may not be obvious to the naked eye. AI-based DTs are used to analyze and optimize the energy consumption patterns of buildings based on sensor data and simulation results. The application of machine learning and deep learning technologies contributes to improving the energy efficiency of a building, and the implementation of an intelligent control system can optimize energy consumption [27, 28]. DTs collect data about physical buildings through BIM (Building Integrated Management), sensors, simulation tools, and AI, through which it enables optimization of the operation of the physical building.
Machine learning was found to be the most widely adopted sub-discipline of artificial intelligence IA, thanks to its ability to model complex relationships, handle large data sets, and perform forecasts spanning various time intervals. In addition, among the most prominent techniques used for power forecasting are artificial neural networks (ANNs), hybrid models, and support vector machines. These techniques have proven to be essential pillars in energy analysis and forecast generation. It is relevant to note that most of the studies analyzed employ ANNs in environments such as buildings or residential houses oriented to the optimization of energy consumption. These networks allow prediction of peak demand and self-adjustment of energy distribution to maximize efficiency and reduce costs [29].
Therefore, a sophisticated decision algorithm will optimize the transmission of critical information during energy efficiency incidents, and a real-time model degradation management system will continuously improve performance based on incoming data. These developments aim to mitigate risks to optimize responses in situations related to hazard assessment and response time. Digital twins, combined with virtual reality and artificial intelligence, are transforming energy demand prediction by providing advanced tools for simulation, analysis, and optimization. These technologies not only improve efficiency and reduce costs but also open up new possibilities for innovation and development.
3. Integrated discussion and case study: Smart campus energy management
This chapter combines a critical discussion of the challenges and opportunities in smart building energy management with a practical case study from Rey Juan Carlos University’s Smart Campus. By merging theory with application, the aim is to demonstrate how AI, IoT, and predictive models can be effectively used to optimize energy efficiency and air quality. The case study provides real-world insights that reinforce the points discussed, illustrating the tangible benefits of smart building technologies and how they align with broader urban energy management goals.
3.1 Discussion and comparison
This section analyzes critically the performance of different technological approaches in smart building management, focusing on IoT, AI, and data transmission techniques. By reviewing and comparing several notable studies, the effectiveness of current solutions in addressing energy efficiency, air quality control, and predictive maintenance in smart cities is explored. The comparison highlights the strengths and limitations of each approach, paving the way for a deeper understanding of how these technologies can be optimized in real-world scenarios. This discussion serves as a theoretical foundation for the subsequent case study.
Based on a literature survey on scientific articles that conduct research within the previously outlined scientific domains, a comparison is made between the most noteworthy studies, considering the different categories developed (Table 6).
Article
Summary
Topic
Exploring the potential, limitations, and future directions of wireless technologies in smart grid networks: A comparative analysis [30]
The potential of IoT in communication is explored, focusing on its ability to connect devices via technologies like LPWAN, Wi-Fi, and 5G. The choice of communication technology depends on power use and network range.
IoT potential
A comparative study of LPWAN technologies for large-scale IoT deployment [31]
LPWAN technologies (LoRaWAN, Sigfox, and NB-IoT) are compared in terms of coverage, power use, cost, and data capacity. LoRaWAN and Sigfox suit low-cost, low-power applications, while NB-IoT excels in data capacity and urban coverage. Selecting the right technology depends on the project’s specific needs
Protocol communication
A comprehensive digital twin framework for building environment monitoring with emphasis on real-time data connectivity and predictability [32]
The article proposes a comprehensive framework for implementing digital twins in environmental monitoring of buildings. It focuses on real-time connectivity and data predictability, utilizing IoT sensors and BIM models. A case study is presented at the University of North Florida, where this system was implemented to monitor environmental parameters such as temperature and humidity. It concludes that digital twins significantly enhance building environment management, although challenges remain in data integration and system interoperability.
Digital twins
Modeling the energy consumption for over-the-air software updates in LPWAN networks [33]
The document analyzes the feasibility of over-the-air (OTA) software updates in low-power wide-area networks (LPWAN) such as SigFox, LoRa, and IEEE 802.15.4 g. These technologies are key for applications in smart cities, logistics, and smart grids due to their ability to connect thousands of sensors to a single gateway. However, OTA updates present challenges in terms of energy consumption. The study compares the energy consumption of full and partial updates for firmware, applications, and network stacks. The results show that full updates consume significant energy, especially in low bit-rate technologies like SigFox. Partial updates are considerably more efficient, making OTA updates viable.
IoT potential
Secure and energy-efficient smart building architecture with emerging IoT technology [34]
A proposed IoT architecture for smart buildings is evaluated, optimizing security and energy efficiency. It employs the CoAP protocol to manage energy consumption and DTLS to secure communications. Simulation results show a 30.86% reduction in energy consumption, comparing favorably to other protocols like MQTT, thereby enhancing the sustainability of smart buildings.
Protocol communication
Current testing and performance evaluation methodologies of LoRa and LoRaWAN in IoT applications: Classification, issues, and future directives [35]
A performance comparison between LoRa and LoRaWAN in IoT applications is evaluated. LoRa is a modulation technique for long-range communication in unlicensed frequency bands, while LoRaWAN is a network protocol that manages communication between LoRa-enabled devices and the backend infrastructure. The study classifies and critically analyzes the testing methods based on their parameters, architectures, and performance evaluation methodologies. It also identifies the issues and challenges arising from the lack of standards in these areas. Nonetheless, both solutions are shown to be crucial for battery-powered IoT devices.
Protocol communication
IFC+: Toward the integration of IoT into early stages of building design [36]
This paper presents a solution to integrate the Internet of Things (IoT) into early-stage building design using Building Information Modeling (BIM). It proposes an extension of Industry Foundation Classes (IFC), called IFC+, which adds new methods for modeling IoT scenarios. Additionally, an object-based approach is introduced to transform smart-built environment specifications into consumable IFC+ software, facilitating the implementation of IoT scenarios.
Digital twins
Enhancing environmental and energy monitoring of residential buildings through IoT [37]
This article proposes an IoT-based solution to improve environmental and energy monitoring in residential buildings. A monitoring system is implemented in a passive house, using wired and wireless sensors to measure environmental, energy, air quality, and comfort parameters. The solution proved flexible and efficient in terms of data exchange and deployment time. The MQTT protocol was used for communication between IoT devices, and cloud storage and predictive analytics capabilities were integrated.
Thermal comfort and air quality
Is IoT monitoring key to improve building energy efficiency? Case study of a smart campus in Spain [38]
This paper presents an analysis of the implementation of a continuous monitoring system based on IoT in a university campus in Spain to improve building energy efficiency. The proposed methodology focuses on the real-time monitoring of HVAC systems to optimize performance and reduce energy consumption. It concludes that there is potential energy savings of between 40% and 70% associated with HVAC, as well as the prevention of overheating. The solution appears to be extensible to more buildings.
Thermal comfort and air quality
Thermal performance improvement for residential heritage building preservation based on digital twins [39]
The study presents a digital twin-based approach to improve the thermal performance and preservation of heritage buildings. Using digital twin technology, the placement and configuration of thermal equipment are optimized to improve the use of these buildings. BIM models are extended to heritage buildings to study simulations and improve decision-making. The digital model is used for computational fluid dynamics (CFD) and structural simulations to analyze thermal performance and building deformation. Results show that the use of this technology improves the structural preservation of the building by at least 62.9%.
Digital twins
An optimal design method for communication topology of wireless sensor networks to implement fully distributed optimal control in IoT-enabled smart buildings [40]
A method for optimal communication design of wireless sensor networks (WSN) in IoT-enabled smart buildings is proposed. This method integrates knowledge from wireless communication and distributed computing to ensure optimal and fully distributed control of HVAC systems. Communication design considers network energy consumption, network stability, and optimization convergence speed.
Protocol communication
Table 6.
Comparison of recently proposed solutions in addressing energy efficiency, air quality control, and predictive maintenance in smart cities.
3.2 Requirements for smart building management: Case of study at University Rey Juan Carlos
Building on the insights from the previous section, this case study will delve into the implementation of smart building management technologies at Rey Juan Carlos University’s Smart Campus. The study will focus on integrating IoT systems for continuous monitoring and the use of DTs for data analysis and optimization. Through this case, the goal is to demonstrate how the previously discussed theoretical concepts can be applied in a real-world environment, providing tangible benefits in terms of energy management and air quality control. The case study will also outline the technical and operational challenges anticipated and the strategies that will be adopted to address them.
The Smart Campus is a proof of concept and research of intelligent monitoring for smart services. The Smart Campus project was initiated because the need for management information on these assets was detected to make the right decisions on their efficient operation and management. This section outlines the technical and operational requirements for managing smart buildings, with a focus on air quality, energy use, and the integration of IoT systems. Here, a use case that reviews the ideas and applies the requirements for Smart Building Management is explained. The Smart Campus project, developed by the Institutional Chair SmartE2 of Rey Juan Carlos University, includes the creation of digital twins of the different buildings of the campus. In this example, the selected building was Laboratories III building at the campus (Móstoles-Madrid, Spain). Initially considering LIDAR scanning, the project opted for generating a 3D BIM (Building Information Modeling) file using Revit due to LIDAR’s complexities. A BIM file serves as a valuable tool for building information management, encompassing details like materials, dimensions, colors, and internal objects.
The methodology involves designing in Revit and implementing 3D views of the model from different angles. Revit is an Autodesk 3D design software widely used in architecture and construction. Rey Juan Carlos University provided 2D blueprints of the building basement, which were imported into Revit. The software facilitates the creation of a 3D model with precise details on walls, columns, windows, and doors. Various tools allow for the incorporation of material details, thickness, height, color, and manual input of additional features, such as object location and installation date. Asset families from the Smart Campus project were imported, including doors, windows, and furniture, with modifications to match reality. The room for the SmartE2 chair is defined as a “room” in Revit for further differentiation.
For this purpose, it was necessary to create the CDA application (Assets Digital Center), which is fully integrated in the digital twin using BIM models for intelligent and autonomous management of the building in a ubiquitous way. CDA is a home-designed web application based on web-responsive technologies, which acts as a remote monitoring system allowing ubiquitous access to data. In fact, it is a modular design that allows managing several databases from different locations and simultaneous access to them from different types of devices. Figure 3 shows representative screenshots from the CDA web platform. It includes images from the login page, the page where the user can choose the spaces and buildings, 3D view of the building, the real-time dashboard of the acquired parameters, plotting of historic data, and a realistic virtual representation of indoor spaces.
Figure 3.
Web platform of CDA for the Smart Campus project.
One of the primary objectives of the Smart Campus project is the continuous monitoring of ambient variables in indoor spaces and, especially, in classrooms and students’ laboratories. These variables mainly include CO2 concentration, temperature, and air humidity. Elsys RS CO2 sensors have been chosen for collecting data at this project. These devices have been used after comparing which protocol communication fits best for this environment. This technology has been placed over a LoRaWAN server infrastructure provided by Alai Secure. Data are collected in several servers before being treated. Data analysis results are crucial and must be developed to obtain as much information as possible; while setting alarms for exceeding defined limits will be a valuable tool, this alone will not provide a mechanism to actively influence climatic variables.
In the graphics shown in Figures 4 and 5, it can be seen how the system allows visualizing the data trends and using them to generate alarms that detect and warn of inefficient use of the system. These exemplary plots highlight how the Smart Campus infrastructure can monitor in real-time the most relevant ambient parameters and use this monitoring to detect anomalies and notify them to management administrators, so corrective actions can be taken, ensuring optimal building performance.
Figure 4.
Example of data collected by the CDA platform of the Smart Campus project: (a) air humidity and (b) air temperature.
Figure 5.
Example of data collected by the CDA platform of the Smart Campus project: CO2 time series. Peaks correspond to actual use of the analyzed space, correlating with the presence of people.
On the other hand, another objective of the Smart Campus project is the energy consumption optimization, through leveraging IoT, aiming to enhance and monitor energy consumption across different buildings and campuses. This objective is oriented to energy efficiency based on the European directives.
Prediction models will be implemented in this building model to take advantage of the real-time data obtained to save energy and preserve optimal air quality conditions. The most straightforward method to act on the ambient variables in older buildings, without HVAC systems, will be through harnessing natural ventilation provided by openings and windows. Information gathering will be pivotal for establishing a DT under this context, which implies data acquisition through sensors in the real environment.
The data flow will involve sensors transmitting to a gateway, which will then upload the information to a cloud platform and/or servers. While the sensor network setup, communication, and cloud storage will be managed by external entities, this research focuses on how the collected data will be exploited. The window’s operating logic will be governed by the concentration of CO2 present in the environment. Based on this concentration, the window will open in a specific manner for a certain duration, activating only when the value exceeds the limits established by regulations. For exploiting the collected information, real-time representation will be developed using various control panels. For this purpose, data acquisition will be developed at a submetering level, while other significant parameters for the inlet and outlet air mass balances will be obtained via API. After storing all the data on the database server, an algorithm will work according to the equations explained above, so the window/opening can open automatically in the desired way to modify air temperature, carbon dioxide concentration, or both.
The increasing complexity of urban challenges calls for innovative solutions in building management systems. Technologies like DTs, predictive AI models, and IoT sensor networks are central to the future of smart cities. One promising opportunity lies in the development of low-cost, energy efficient IoT systems that are easy to install and maintain, particularly for retrofitting older buildings, which make up a large proportion of urban environments.
DT technology, which integrates real-time data from IoT devices with 3D building models, offers a powerful tool for proactive maintenance and energy optimization. By simulating various scenarios, such as increased occupancy or changes in weather conditions, DTs allow building managers to anticipate energy consumption peaks and adapt building systems, accordingly, reducing costs and improving environmental sustainability. Additionally, by integrating AI-driven predictive models, smart buildings can not only respond to real-time changes in air quality and energy demand but also forecast future needs, thereby optimizing resources before issues arise.
Moreover, wireless technologies such as LoRaWAN and Sigfox present further opportunities for smart cities by enabling long-range, low-energy communication between sensors and building management systems. These technologies are particularly well-suited for large urban areas where traditional wired connections are either impractical or cost prohibitive. Integrating these into urban infrastructure will help overcome the limitations posed by older buildings and provide a scalable solution for widespread data collection and management.
The future of building management will likely be driven by a combination of AI-enhanced predictive systems, energy-efficient sensor networks, and a regulatory environment that pushes for greener, more sustainable cities. Collaboration between public institutions and private technology developers will be crucial in driving the adoption of these systems across various sectors, from residential buildings to large commercial facilities. Several cities have been developing through the last years different projects to achieve truly wireless-monitorized smart cities. Some clarifying examples can be Montevideo, capital of Uruguay, by using IoT over a LoRaWAN layer to control 70, 000 luminaires [40]; On the Spanish scope, the city of Valencia, where healthy environments are measured with 130 LoRaWAN IoT devices [41]; and in the region of Galicia, A Coruña’s townhall has deployed an IoT infrastructure for air quality and thermal comfort parameters upon 65% of public buildings [42], and so on.
Future opportunities on this area seem to be successful as big cities are working on LPWAN communication protocols, while infrastructure is being constructed by many server providers [43].
In summary, the integration of Internet of Things (IoT) technologies, advanced predictive artificial intelligence (AI) models, and digital twins represents a pivotal opportunity for revolutionizing urban building management systems. As outlined throughout this chapter, these innovations are not merely enhancements to existing frameworks but also fundamentally transformative, reshaping how urban living is approached in the context of sustainability, health, and efficiency. By enabling smart systems that continuously monitor and respond to dynamic changes in air quality, occupancy levels, and energy consumption, it is possible to mitigate significantly urban pollution challenges while improving overall quality of life for city inhabitants.
The urgency of addressing urban pollution cannot be overstated, as cities are increasingly becoming epicenters of environmental stress. The introduction of smart technologies, such as LoRaWAN and Sigfox, plays a crucial role in this transformation by providing the connectivity required for effective data collection and analysis. These wireless communication technologies facilitate real-time monitoring, enabling buildings to adaptively respond to environmental changes and optimize resource usage, which is key to minimizing energy waste while ensuring that indoor environments remain healthy and conducive to well-being.
However, to realize the full potential of these technologies, it is essential to focus on refining their capabilities for broader scalability and affordability. Older buildings, which constitute a significant portion of urban infrastructures, often face unique challenges that require retrofitting and upgrading to accommodate smart technologies. This chapter has emphasized the importance of developing tailored strategies that address these challenges, ensuring that smart building systems can be seamlessly integrated into existing structures without exorbitant costs or extensive overhauls.
Moreover, as urban areas continue to grow and evolve, implementing these smart technologies will be vital in fostering sustainable and resilient urban environments. The shift toward smart building management systems should not be viewed in isolation; rather, it must be part of a broader urban strategy that incorporates cross-sector collaboration. Partnerships between government bodies, technology developers, and urban planners are essential to drive innovation and ensure that smart city initiatives are effectively implemented and accessible to all stakeholders.
Future research must prioritize improving the integration of IoT and AI technologies within building management systems while also exploring their applications across diverse urban contexts. This includes examining the interplay between different technologies, assessing their collective impact on urban infrastructure, and investigating how they can be leveraged to support sustainability goals. Additionally, studies should focus on the socioeconomic implications of these technologies, ensuring that the benefits of smart building management systems are equitably distributed among all residents, particularly in underserved communities. By fostering environments that include innovation and collaboration, cities that are not only efficient and resilient but also vibrant and healthy for generations to come can be created. The present challenges require bold, forward-thinking solutions and smart management of buildings within urban landscapes, which represents a critical step for achieving a sustainable future.
The financial support from SmartE2 Institutional Chair and Instituto de Tecnologias para la Sostenibilidad (ITPS) from URJC are kindly acknowledged. Dr. Imene Yahyaoui is funded by project PID 2023-151697OA-100 of the Spanish State.
artificial intelligence technique for monitoring systems in smart buildings
ANN
artificial neural network
BM
building management
BIM
building information model
CDA
Active Digital Center
CoAP
constrained application protocol
CTE
technical building code
DT
digital twins
EPBD
energy performance of buildings directive
FA
firefly algorithm
GA
genetic algorithm
HVAC
heating, ventilation and air conditioning
IDA
indoor air quality
IFC
industry foundation classes
IOT
Internet of Things
LCA
life cycle assessment
LIDAR
light detection and ranging
LPWAN
low power wide area network
LTE
long term evolution
ML
machine learning
NZEB
nearly zero-energy buildings
OTAA
over the air activation
PAN
personal area network
RFID
radio frequency identification
RITE
thermal installation in buildings regulation
SDG
sustainable development goals
SVM
support vector machine
TVOC
total volatile organic compounds
WAN
wide area network
WLAN
wireless local area network
WSN
wireless sensor networks
References
1.Laayati O, Bouzi M, Chebak A. Smart energy management: Energy consumption metering, monitoring and prediction for mining industry. In: 2020 IEEE 2nd International Conference on Electronics, Control, Optimization and Computer Science (ICECOCS); 2020. United States: Editorial IEEE; 2020. DOI: 10.1109/ICECOCS50124.2020.9314532
2.Imran, Iqbal N, Kim DH. IoT task management mechanism based on predictive optimization for efficient energy consumption in smart residential buildings. Energy and Buildings. 2022;257:111762. DOI: 10.1016/J.ENBUILD.2021.111762
3.Wahid F, Fayaz M, Aljarbouh A, Mir M, Aamir M, Imran. Energy consumption optimization and user comfort maximization in smart buildings using a hybrid of the firefly and genetic algorithms. Energies. 2020;13(17):1-26. DOI: 10.3390/EN13174363
4.Ministerio de Industria, Energía y Turismo. Reglamento de Instalaciones Térmicas en los Edificios (RITE). Vol. 151. Boletín Oficial del Estado; 2013. pp. 45539-45559. Available from: https://www.boe.es/buscar/doc.php?id=BOE-A-2013-8300 [Spanish]
5.International Organization for Standardization. ISO 55001:2014—Asset Management—Management systems—Requirements. ISO; 2014 [Spanish]
6.British Standards Institution. PAS 1192-2:2013—Specification for Information Management for the Capital/Delivery Phase of Construction Projects Using Building Information Modelling. BSI; 2013 [British]
7.International Organization for Standardization. ISO 19650-1:2018—Organization of Information about Construction Works—Information Management Using Building Information Modelling—Part 1: Concepts and Principles. ISO; 2018
8.Rodríguez MC, Villoria P, Orellana J, Ramiro J, Morales G, Melero JA. CDA: IoT digital and intelligent management buildings for the smart campus project. In: IECON 2022—48th Annual Conference of the IEEE Industrial Electronics Society; Brussels, Belgium. 2022. pp. 1-6. DOI: 10.1109/IECON49645.2022.9969056
9.Fiorotti R, Yahyaoui I, Rocha HR, Honorato Í, Silva J, Tadeo F. Demand planning of a nearly zero energy building in a PV/grid-connected system. Renewable Energy Focus. 2023;45:220-233
10.Boutahri Y, Tilioua A. Machine learning-based predictive model for thermal comfort and energy optimization in smart buildings. Results in Engineering. 2024;22:102148
11.Selvaraj R, Kuthadi VM, Baskar S. Smart building energy management and monitoring system based on artificial intelligence in smart city. Sustainable Energy Technologies and Assessments. 2023;56:103090
12.Dawood N. Short-term prediction of energy consumption in demand response for blocks of buildings: DR-BoB approach. Buildings. 2019;9:221
13.Moghadam ST, Delmastro C, Corgnati SP, Lombardi P. Urban energy planning procedure for sustainable development in the built environment: A review of available spatial approaches. Journal of Cleaner Production. 2017;165:811-827
14.Kim J, Frank S, Braun JE, Goldwasser D. Representing small commercial building faults in EnergyPlus, Part I: Model development. Buildings. 2019;9:233
15.Du Y, Zandi H, Kotevska O, Kurte K, Munk J, Amasyali K, et al. Intelligent multi-zone residential HVAC control strategy based on deep reinforcement learning. Applied Energy. 2021;281:116117
16.Min Y, Chen Y, Yang H. A statistical modeling approach on the performance prediction of indirect evaporative cooling energy recovery systems. Applied Energy. 2019;255:113832
17.United Nations. Climate Change. Available from: https://www.un.org/sustainabledevelopment/es/climate-change-2
18.Ngo N-T, Pham A-D, Ha Truong TT, Truong N-S, Huynh N-T, Pham TM. An ensemble machine learning model for enhancing the prediction accuracy of energy consumption in buildings. Arabian Journal for Science and Engineering. 2022;47:4105-4117. DOI: 10.1007/s13369-021-05927-7
19.Chen Y, Guo M, Chen Z, Chen Z, Ji Y. Physical energy and data-driven models in building energy prediction: A review. Energy Reports. 2022;8:2656-2671. DOI: 10.1016/j.egyr.2022.01.162
20.Elbeltagi E, Wefki H. Predicting energy consumption for residential buildings using ANN through parametric modeling. Energy Reports. 2021;7:2534-2545. DOI: 10.1016/j.egyr.2021.04.053
21.Olu-Ajayi R, Alaka H, Sulaimon I, Sunmola F, Ajayi S. Machine learning for energy performance prediction at the design stage of buildings. Energy for Sustainable Development. 2022;66:12-25. DOI: 10.1016/j.esd.2021.11.002
22.Liao J-M, Chang M-J, Chang L-M. Prediction of air-conditioning energy consumption in R&D building using multiple machine learning techniques. Energies. 2020;13(7):1847. DOI: 10.3390/en13071847
23.Sun Y, Haghighat F, Fung BCM. A review of the-state-of-the-art in data-driven approaches for building energy prediction. Energy and Buildings. 2020:1-50. DOI: 10.1016/j.enbuild.2020.110022
24.Katsidoniotaki E, Psarommatis F, Göteman M. Digital twin for the prediction of extreme loads on a wave energy conversion system. Energies. 2022;15:5464. DOI: 10.3390/en15155464
25.Schena L, Marques PA, Poletti R, Ahizi S, Van den Berghe J, Mendez MA. Reinforcement twinning: From digital twins to model-based reinforcement learning. Journal of Computational Science. 2024;82:102421. ISSN: 1877-7503. DOI: 10.1016/j.jocs.2024.102421
26.Das O, Zafar MH, Sanfilippo F, Rudra S, Kolhe ML. Advancements in digital twin technology and machine learning for energy systems: A comprehensive review of applications in smart grids, renewable energy, and electric vehicle optimisation. Energy Conversion and Management: X. 2024;24:100715. ISSN: 2590-1745. DOI: 10.1016/j.ecmx.2024.100715
27.Yang S, Wan MP, Chen W, Ng BF, Dubey S. Model predictive control with adaptive machine-learning-based model for building energy efficiency and comfort optimization. Applied Energy. 2020. DOI: 10.1016/j.apenergy.2020.115147
28.Chrispim MC. Resource recovery from wastewater treatment: Challenges, opportunities and guidance for planning and implementation. Frontiers in Neuroscience. 2021
29.Yandar KL, Reveló-Sánchez O, Bolaños ME. Machine learning for electric power prediction: A systematic literature review. Ingenieria y Competitividad. 2024;26(2):e-304113875. DOI: 10.25100/iyc.v26i2.13875
30.Mekki K, Bajic E, Chaxel F, Meyer F. A comparative study of LPWAN technologies for large-scale IoT deployment. ICT Express. 2019;5(1):1-7. ISSN: 2405-9595. DOI: 10.1016/j.icte.2017.12.005
31.Kang TW, Mo Y. A comprehensive digital twin framework for building environment monitoring with emphasis on real-time data connectivity and predictability. Developments in the Built Environment. 2024;17:100309. ISSN: 2666-1659. DOI: 10.1016/j.dibe.2023.100309
32.Ruckebusch P, Giannoulis S, Moerman I, Hoebeke J, Poorter ED. Modelling the energy consumption for over-the-air software updates in LPWAN networks: SigFox, LoRa and IEEE 802.15.4g. Internet of Things. 2018;3-4:104-119
33.Kumar A, Sharma S, Goyal N, Singh A, Cheng X, Singh P. Secure and energy-efficient smart building architecture with emerging technology IoT. Computer Communications. 2021;176:207-217. ISSN: 0140-3664. DOI: 10.1016/j.comcom.2021.06.003
34.Alipio M, Bures M. Current testing and erformance evaluation methodologies of LoRa and LoRaWAN in IoT applications: Classification, issues, and future directives. Internet of Things. 2024;25:101053. ISSN 2542-6605. DOI: 10.1016/j.iot.2023.101053
35.Ruiz-Zafra A, Benghazi K, Noguera M. IFC+: Towards the integration of IoT into early stages of building design. Automation in Construction. 2022;136:104129. ISSN: 0926-5805. DOI: 10.1016/j.autcon.2022.104129
36.Tanasiev V, Pătru GC, Rosner D, Sava G, Necula H, Badea A. Enhancing environmental and energy monitoring of residential buildings through IoT. Automation in Construction. 2021;126:103662. ISSN: 0926-5805. DOI: 10.1016/j.autcon.2021.103662
37.García-Monge M, Zalba B, Casas R, Cano E, Guillén-Lambea S, López-Mesa B, et al. Is IoT monitoring key to improve building energy efficiency? Case study of a smart campus in Spain. Energy and Buildings. 2023;285:112882. ISSN 0378-7788. DOI: 10.1016/j.enbuild.2023.112882
38.Cheng JCP, Zhang J, Kwok HHL, Tong JCK. Thermal performance improvement for residential heritage building reservation based on digital twins. Journal of Building Engineering. 2024;82:108283. ISSN: 2352-7102. DOI: 10.1016/j.jobe.2023.108283
39.Li W, Tang R, Wang S, Zheng Z. An optimal design method for communication topology of wireless sensor networks to implement fully distributed optimal control in IoT-enabled smart buildings. Applied Energy. 2023;349:121539. ISSN: 0306-2619. DOI: 10.1016/j.apenergy.2023.121539
40.Avances en la Iniciativa de Alumbrado Público Inteligente de Montevideo. ESMARTCITY.ES. 15/02/2022. Available from: https://www.esmartcity.es/2022/02/15/avances-iniciativa-alumbrado-publico-inteligente-montevideo
41.Alberto N. Valencia Combate la Pobreza Energética con un Innovador Proyecto de Internet de las Cosas. Drivingeco. 02/12/2023. Available from: https://www.drivingeco.com/valencia-combate-pobreza-energetica-innovador-proyecto-internet-cosas/
42.Smart Buildings: Más del 65% de los Edificios Públicos de A Coruña son Inteligentes Gracias al IoT. Computing. 06/09/2024. Available from: https://www.computing.es/movilidad/iot-mas-del-65-de-edificios-publicos-de-a-coruna-son-inteligentes/
43.The Thing Networks—Communities. TTN. 22/10/2024. Available from: https://www.thethingsnetwork.org/
Written By
Alberto Cilleros García, Mª Cristina Rodríguez-Sánchez, Mª del Prado Díaz de Mera, Imene Yahyaoui and Gabriel Morales Sánchez
Submitted: 15 October 2024Reviewed: 18 October 2024Published: 15 January 2025
Open access peer-reviewed chapter - ONLINE FIRST
