Smart Building Environment Research Articles

Improving Load Forecasting with Data Partitioning: A K-Means Approach to An Office Building

In recent years, the energy landscape has undergone significant transformations, characterized by the integration of renewable energy sources, smart grids, and the proliferation of IoT-enabled devices. As a result, the efficient management of energy resources has become paramount, requiring advanced methodologies in load forecasting and clustering. This article presents an enhanced methodology for short-term load forecasting that focuses on load consumption profile recognition within a smart building environment. The methodology is designed to analyze and identify recurring load consumption profiles and measures of sensors, thereby enhancing load consumption profile recognition capabilities within the smart building context. The interaction between single and grouped datasets is explored to enhance the accuracy and interpretability of predictions, contributing to optimized energy consumption and providing valuable information for demand response programs. The default forecasting methods used in the methodology are artificial neural networks and k-nearest neighbors. For comparing results and evaluating the proposed approach, XGBoost is also employed. The dataset is selected from a specific database, and the clustering method, partitioning type, is applied with k-means. The results, validated with error evaluation models and statistics, reveal the advantages of the proposed approach, especially with three clusters, where the results achieved by the Artificial Neural Network are the best. The clustering process, particularly the partitioning type, demonstrates a strong capability in improving load forecasting in smart buildings and helps understand load consumption patterns and achieve energy savings.

Unsupervised domain adaptation without source data for estimating occupancy and recognizing activities in smart buildings

Activities Recognition (AR) and Occupancy Estimation (OE) are topics of current interest. AR and OE help many smart building applications such as energy systems and provide good services for occupants. Prior research on AR and OE has typically focused on supervised machine learning methods. For a specific smart building domain, a model is trained using data collected from the current environment (domain). The created model will not generalize well when evaluated in a new related domain due to data distribution differences. Creating a model for each smart building environment is infeasible due to the lack of labeled data. Indeed, data collection is a tedious and time-consuming task. Unsupervised Domain Adaptation (UDA) is a good solution for the considered case. UDA solves the problem of the lack of labeled data in the target domain by allowing knowledge transfer across domains. Most of the previous research in UDA requires having access to source data while creating target models which leads to privacy problems. This work considers techniques that use only a trained source model instead of a huge amount of source data to make domain adaption. This research adapted and tested UDA methods called Source HypOthesis Transfer (SHOT), Higher-Order Moment Matching (HoMM), and Source data Free Domain Adaptation (SFDA) on smart building data. SHOT is a deep learning method that learns a feature encoding module for the target model to align the data representation of the target environment with the data representation of the source environment, and it freezes the hypothesis (classifier) of the source model. Data alignment is done using information maximization and self-supervised pseudo-labeling. HoMM is also a deep learning method, however, it freezes the feature encoding module, and it learns a classifier to perform data alignment. HoMM also performs pseudo-labeling to target samples to enhance data alignment. SFDA is a deep domain adaptation method that optimizes two losses to train the target model without using any source-labeled data. The target model updates its initialized weights from the source model by minimizing a first loss that uses pseudo labels of target samples using the pre-trained source model, and by minimizing a second loss that uses pseudo labels of target samples generated by the trainable target model. To prove the efficiency of SHOT, HoMM, and SFDA, this research tests them on AR and OE datasets for a different number of activities and levels of occupancy. The impressive obtained results, with scores up to 90% for OE and up to 97% for AR, show that the considered approaches can be used to transfer knowledge across different related domains.

Digital Twin and Blockchain Extension in Smart Buildings Platform as Cyber-Physical Systems

Cyber-physical systems is integrated computation with the physical world. CPS increasing in a wide range of applications, from smart homes to smart buildings. Digital twins are promising way to solve challenges with combination of CPS, 3D technology, and IoT. The system provides users with immersive interfaces to control and interact with devices within the smart building environment. Blockchain was chosen to secure user data using cryptographic algorithms and ensure data protection against manipulation, spying, and theft. Average load testing data for digital twin platform implemented in smart buildings range from 1 to 11 floors. The results reveal a gradual increase in average test times as the buildings' size and complexity grow, with the following values: 5.663s for 1 floor until 11 floors 7.294s. The data obtained from of the blockchain test using Hyperledger Besu provide essential insights into the system's performance with several bandwidth that used in the system. Average time for each test trial ranged from 1.066 seconds to 2.006 seconds, showing slight variations based on the bandwidth used. However, transactions per second (TPS) values were relatively fast, ranging from 1.066 tps to 0.499 tps with positive aspect of the retention rate for all trials was 100% success.

Blockchain Fog-based scheme for identity authentication in smart building

This paper presents a proposal for an authentication scheme for smart building systems and environments based on blockchain, its positive features, and fog computing. The most important feature that can be distinguished in the submitted proposal is its adoption of the principle of decentralization in contrast to traditional centralized documentation protocols, i.e. the proposed authentication system in which users and smart devices are implemented in a distributed and decentralized manner on the blockchain, that will provide a solution to a significant problem of low overall efficiency of the authentication process caused by a bottleneck in such important areas as computing capacity as well as centralized storage of a single authentication authority in the traditional model. There are also benefits from adding fog computing, and because it has higher computing and storage capabilities, it makes the data processing process more efficient, faster, more streamlined, and in line with the common necessities of the real-time IoT environment. The proposed scheme also provides solutions to protect the privacy of user data and increase the level of confidentiality, protection, and security, since a mysterious extractor was used to increase the confidentiality of the proposed model of the authentication system. Comparing a set of security schemes and conducting a security and performance analysis of the proposed scheme, the comparisons showed that the scheme can be characterized as having a good security level and an important efficiency level. The paper focused on specific aspects design of the authentication system, such as the registration and authentication process of all network entities, regardless of the specifics of the implementation of blockchain smart contracts.

Framework for Heterogeneous Sensor Data Stream Management with BIM and WSN

By the 2010s, BIM is highly popular research area that gathers researchers from various domains. We tackle the major challenge of BIM and the main barrier for the application of BIM in smart environments: integration of BIM and wireless sensor networks. Existing studies in the literature have various dependencies and propose limited solutions. These solutions are dedicated to specific applications and domains. However, it is highly required to have a generic solution for real time indoor and outdoor environmental monitoring with full integration with the digital model of the building. To fulfill this need, in this study, we propose a novel approach to monitor and fulfill user requirements by a numerical model of the building, a novel framework and a BIM-WSN integrated architecture based on the BIM principles for smart building environments. All the experiments are performed on a real testbed, physical sensor devices deployed on the classrooms of the university building. Such numerical model presents the digital model of the environment by gathering acquired data. Besides, data is gathered on a big data platform where it may be served to various other applications such as machine learning studies.

Sensing within Smart Buildings: A Survey

Increasingly, buildings are being fitted with sensors for the needs of different sectors, such as education, industry and business. Using Internet of Things devices combined with analysis of data being generated by these devices, it is possible to infer a number of metrics, e.g., building occupancy and activities of occupants. The information thus gathered can be used to develop software applications to support energy management, occupant comfort, and space utilization. This survey explores the use of sensors in smart building environments, identifying different approaches to employ sensors in buildings. The most commonly used data-driven approaches for activity recognition in such buildings is also investigated, concluding by highlighting current research challenges and future research directions in this area.

Predictive Energy Management in Internet of Things: Optimization of Smart Buildings for Energy Efficiency

As energy efficiency and sustainability become paramount in the face of growing urbanization and environmental concerns, predictive energy management in smart buildings has emerged as a promising avenue for mitigating energy consumption and optimizing resource utilization. In this paper, we investigate the application of advanced machine learning techniques, particularly a multi-layer Long Short-Term Memory (LSTM) model, within the framework of the Internet of Things (IoT), to predict and manage energy consumption. We rigorously evaluate our approach against a suite of machine learning baselines, including Linear Regression, Random Forest, Support Vector Machine, and Gradient Boosting, utilizing a comprehensive dataset encompassing power consumption data from smart home appliances and associated weather variables. Our experimental results demonstrate the superior predictive capabilities of the LSTM model, showcasing its ability to outperform traditional machine learning baselines across various metrics, including Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). These findings underscore the potential of deep learning models in capturing intricate temporal dependencies within energy consumption data, contributing to improved energy efficiency, cost savings, and environmental sustainability in smart building environments. The integration of predictive energy management models into IoT-enabled smart buildings holds the promise of a more intelligent and sustainable future in urban development and resource management.

Reliability Analysis and Economic Prospect of Wind Energy Sources Incorporated Microgrid System for Smart Buildings Environment

This work deals with assessing the reliability of wind energy sources incorporated into a microgrid system to increase grid stability. As the share of power generated from wind energy continues to increase due to environmental concerns and to reduce carbon footprints, the case study proposed is designing an effective wind energy system for a smart building environment to reduce the burden on the grid. Incorporating wind energy systems into grid-connected buildings increases the reliability of the microgrid system for smart building environments. Applying smart techniques with integrated automation in the built environment can play a key role in decreasing peak demand for load development in smart cities. This can also enhance the overall efficiency of power grids, reduce waste, and enable the effective use of energy resources. Furthermore, researchers are finding new ways to collect energy from renewable sources and power-built environments due to dwindling fossil fuel resources and increased environmental awareness. The analysis of wind-connected power systems has been initiated to satisfy the increasing demand for reliable supply systems by consumers. This has prompted the use of wind energy systems with controlled techniques to enhance the reliability of power systems and reduce carbon footprints generated by fossil fuel-based power systems. Therefore, the main purpose of this work is to understand the economic prospects of wind energy sources for smart building environments, reliability analysis of wind energy sources-based power systems, reduce carbon footprints, and balance power demand through wind energy systems. The Progressive Wind Model Taylor-Sequence Proliferation (PWMTSP) and Innovative Six Parameters Based Progressive Beta Creative Model (ISPBPBCM) approaches are proposed to understand the reliability of wind energy-based power systems in smart building environments. The work also provides an economic analysis of the proposed low-cost wind power system with different capacities for residential consumers in selected geographic location. Eight cases are considered for the proposed effective wind energy system for smart building environments ranging from 2 MW to 32 MW. Hence, the economic analysis of the proposed systems is discussed for residential users. All eight cases are eco-friendly and reduce carbon emissions as these generated units from wind energy sources need not be purchased from fossil fuel-based plants, which increases the reliability of the proposed system. The expected energy not supplied (EENS) in the planned work increases as wind power capacity increases. Loss of load expectation (LOLE), loss of load probability (LOLP), and failure rate all decrease with the installation of more wind power systems. Moreover, it can be seen that mean time to repair (MTTR) improves when wind energy capacity rises incrementally from 2 MW to 32 MW. The proposed method is anticipated to be adaptable to various types of wind energy systems where dependability is a crucial component of system design and scalable to large wind integrated power systems.

A multi-head Convolutional Neural Network based non-intrusive load monitoring algorithm under dynamic grid voltage conditions

In recent times, non-intrusive load monitoring (NILM) has emerged as an important tool for distribution-level energy management systems owing to its potential for energy conservation and management. However, load monitoring in smart building environments is challenging due to high variability of real-time load and varied load composition. Furthermore, as the volume and dimensionality of smart meters data increases, accuracy and computational time are key concerning factors. In view of these challenges, this paper proposes an improved NILM technique using multi-head (Mh-Net) convolutional neural network (CNN) under dynamic grid voltage conditions. An attention layer is introduced into the proposed CNN model, which helps in improving estimation accuracy of appliance power consumption. The performance of the developed model has been verified on an experimental laboratory setup for multiple appliance sets with varied power consumption levels, under dynamic grid voltages. Moreover, the effectiveness of the proposed model has been verified on widely used UK-DALE data, and its performance has been compared with existing NILM techniques. Results depict that the proposed model accurately identifies appliances, power consumptions and their time-of-use even during practical dynamic grid voltage conditions.

Automated infection risks assessments (AIRa) for decision-making using a blockchain-based alert system: A case study in a representative building

Indoor air quality (IAQ) is an important parameter in protecting the occupants of an indoor environment. Previous studies have shown that an indoor environment with poor ventilation increases airborne virus transmission. Existing research has concluded that high ventilation rates can reduce the risk of individuals in indoor environments being infected. However, most existing ventilation systems are designed to be efficient under non-pandemic conditions. Ultimately, indoor environments will become hotspots for the transmission of airborne viruses. Current infection risk assessments can estimate virus transmission via airborne routes, but with limited information sharing among stakeholders. Our own research did not identify any systems that integrate risk assessments with smart sensors in order to support information sharing with experts in indoor environments in their decision-making process. To fill this gap, we designed a blockchain-based prototype (AIRa) that integrates CO2 smart sensor data with infection risk assessments from a post-pandemic perspective. This system generates two types of alerts: (1) P-Alert and (2) R0-Alert for decision-making by building owners, such as increasing the ventilation rate or track and trace, as needed. AIRa shows various benefits over three existing infection-control alert systems. Our solution stores and shares information such as the timestamp and room number, instead of storing building user's personal information. Our approach does not require a QR code to be scanned or a mobile app to be downloaded in order to enable track and trace. However, AIRa is still an early prototype for evaluating the risks of airborne virus transmission in smart building environments. Multidisciplinary knowledge and technological research will be vital in formulating different alerts in the future.

Implementation of the FP-Growth Algorithm with RFID on the Monitoring System for Building Users in a Smart-Building Environment

Internet of Things (IoT) technology is developing rapidly and is widely applied to assist all human needs. Radio Frequency Identification (RFID) is a very popular IoT device. One application is to limit employee access in the office. In this study, RFID devices are used to limit room access rights, after the building user performs an RFID scan, the data will be stored in the database. The stored data is then used to find patterns of employee activity using the FP-Growth algorithm. The FP-Growth algorithm runs by tracing the tree from bottom to top and getting frequent itemsets obtained from the FP Tree based on the stored data. This study indicates that the time required for the RFID device to scan to determine whether the user has access or not is 2000ms. The hardware communication time with the information system using the API is 262ms then proceeding from the software to the database is 239ms. In the implementation of the FP-Growth algorithm, the time required for the FP-Growth algorithm to process 100 activity data divided into 10 days is 324 ms. From the 100 activity data, it can be concluded that if the employee enters the server room, server room, guest room, and guest room, the probability of the employee entering the multimedia room is 1 (100%). Furthermore, if the employee enters the multimedia room, multimedia room, server room, employee room, and the guest room then the probability of the employee entering the data room is 0.1 (10%).

Strategic placement of access points for message communication in a smart building environment

Strategic placement of access points for message communication in a smart building environment

Occupancy Estimation Using Thermal Imaging Sensors and Machine Learning Algorithms

Occupancy estimation has a broad range of applications in security, surveillance, traffic and resource management in smart building environments. Low-resolution thermal imaging sensors can be used for real-time non-intrusive occupancy estimation. Such sensors have a resolution that is too low to identify occupants, but it may provide sufficient data for real-time occupancy estimation. In this paper, we present a systematic study of three thermal imaging sensors with different resolutions, with a focus on sensor characterization, estimation algorithms, and comparative analysis of occupancy estimation performance. A unified processing algorithms pipeline for occupancy estimation is presented and the performance of three sensors are compared side-by-side. A number of specific algorithms are proposed for pre-processing of sensor data, feature extraction, and fine-tuning of the occupancy estimation algorithms. Our results show that it is possible to achieve about 99% accuracy for occupancy estimation with our proposed approach, which might be sufficient for many practical smart building applications.

SimulateIoT: Domain Specific Language to Design, Code Generation and Execute IoT Simulation Environments

Internet of Things (IoT) is being applied to areas as smart-cities, home environment, agriculture, industry, etc. Developing, deploying and testing IoT projects require high investments on devices, fog nodes, cloud nodes, analytic nodes, hardware and software. New projects require high investments on devices, fog nodes, cloud nodes, analytic nodes, hardware and software before each system can be developed. In addition, the systems should be developed to test them, which implies time, effort and development costs. However, in order to decrease the cost associated to develop and test the system the IoT system can be simulated. Thus, simulating environments help to model the system, reasoning about it, and take advantage of the knowledge obtained to optimize it. Designing IoT simulation environments has been tackled focusing on low level aspects such as networks, motes and so on more than focusing on the high level concepts related to IoT environments. Additionally, the simulation users require high IoT knowledge and usually programming capabilities in order to implement the IoT environment simulation. The concepts to manage in an IoT simulation includes the common layers of an IoT environment including Edge, Fog and Cloud computing and heterogeneous technology. Model-driven development is an emerging software engineering area which aims to develop the software systems from domain models which capture at high level the domain concepts and relationships, generating from them the software artefacts by using code-generators. In this paper, a model-driven development approach has been developed to define, generate code and deploy IoT systems simulation. This approach makes it possible to design complex IoT simulation environments and deploy them without writing code. To do this, a domain metamodel, a graphical concrete syntax and a model to text transformation have been developed. The IoT simulation environment generated from each model includes the sensors, actuators, fog nodes, cloud nodes and analytical characteristics, which are deployed as microservices and Docker containers and where elements are connected by using publish-subscribe communication protocol. Additionally, two case studies, focused on smart building and agriculture IoT environments, are presented to show the simulation expressiveness.

Advanced Fuzzy-Based Smart Energy Auditing Scheme for Smart Building Environment With Solar Integrated Systems

Energy audit is a method of knowing the energy used in a particular area and to recognize the area where energy consumption can be minimized. Energy audit involves many tasks and these can be carried out depending of audited capability and the types of audit methods. It started with assessment the old data of energy consumption because these data is vital to know the patterns of energy used in a particular area. Then by using different techniques, energy consumption can be reduced. Whereas; it is difficult to manage the different operating time of the loads by older methods particularly when solar energy system is involved reason being the solar energy system cannot provide power all the time. Consequently when grid power and solar energy systems are involved, there should be intelligent control to offer the energy efficacy and to lessen the total power consumption. In this paper, Fuzzy based auditing methodology is considered to provide the excellent results for residential buildings. The energy utilization of different electrical appliances in operation and their operating parameters like temperature, humidity, efficiency and energy consumption etc. are taken into consideration for the analysis. The objective of this paper is to use a fuzzy logic controller for the energy consumption reduction analysis in Kasganj city of Uttar Pradesh state in India, by employing the utilization hours of the solar powered system and the required load demand using the time for which the different appliances are in operation. This analysis has been started with the survey of different buildings in order to get the information on present energy utilization. The energy audit presented in this work only concentrated in the 5 buildings in the Kasganj in order to take the real life conditions. Whereas, the fuzzy controller can set a threshold of power from grid and solar energy system that could not be exceeded as well as controlling the working hours of different appliances, otherwise it will affect the energy efficacy of the smart buildings. Results of the study shows, the percentage saving in money for each building using graphical analysis. The overall 69% cost reduction is achieved with the 5 buildings when solar energy system and grid power are involved using the proposed technique. This would make the transition towards sustainable development smoother and faster and this technique could be reflected on the real life situations.

A Relearning Approach to Reinforcement Learning for control of Smart Buildings

This paper demonstrates that continual relearning of control policies using incremental deep reinforcement learning (RL) can improve policy learning for non-stationary processes. This approach has been demonstrated in a data-driven “smart building environment” that we use as a test-bed for developing HVAC controllers for reducing energy consumption of large buildings on our university campus. The non-stationarity in building operations and weather patterns makes it imperative to develop control strategies that are adaptive to changing conditions. On-policy RL algorithms, such as Proximal Policy Optimization (PPO) represent an approach for addressing this non-stationarity, but they cannot be applied to safety-critical systems. As an alternative, we develop an incremental RL technique that simultaneously reduces building energy consumption without sacrificing overall comfort. We compare the performance of our incremental RL controller to that of a static RL controller that does not implement the relearning function. The performance of the static controller diminishes significantly over time, but the relearning controller adjusts to changing conditions while ensuring comfort and optimal energy performance.

An Overview of IoT Sensor Data Processing, Fusion, and Analysis Techniques.

In the recent era of the Internet of Things, the dominant role of sensors and the Internet provides a solution to a wide variety of real-life problems. Such applications include smart city, smart healthcare systems, smart building, smart transport and smart environment. However, the real-time IoT sensor data include several challenges, such as a deluge of unclean sensor data and a high resource-consumption cost. As such, this paper addresses how to process IoT sensor data, fusion with other data sources, and analyses to produce knowledgeable insight into hidden data patterns for rapid decision-making. This paper addresses the data processing techniques such as data denoising, data outlier detection, missing data imputation and data aggregation. Further, it elaborates on the necessity of data fusion and various data fusion methods such as direct fusion, associated feature extraction, and identity declaration data fusion. This paper also aims to address data analysis integration with emerging technologies, such as cloud computing, fog computing and edge computing, towards various challenges in IoT sensor network and sensor data analysis. In summary, this paper is the first of its kind to present a complete overview of IoT sensor data processing, fusion and analysis techniques.

Design and Implementation of CoAP-based Standby Power Reduction System and Ecommended Power Status for each Device in a Smart Building Environment

Design and Implementation of CoAP-based Standby Power Reduction System and Ecommended Power Status for each Device in a Smart Building Environment

Multi-Protocol Gateway System for Heterogeneous Network on Internet of Things

One of the main problems on the Internet of Things is heterogeneity. One of them is diversity in communication protocols. Generally, we will need one gateway for each existing protocol which causes inefficient communication networks. With these problems, we propose to build a hybrid network infrastructure using the Multi-Protocol Gateway system, this allows existing gateways to accept more than one protocol. This system is divided into two parts, hardware and software. For hardware systems, we use a single board processor equipped with the necessary transceiver modules. Our software system uses Python scripts to manage all backend processes, MySQL as data storage, PHP as a web server and Progressive Web Application (PWA) web application so that all devices get the same experience. We also provide a dashboard on the gateway to show and ensure that all data from different protocols can be received simultaneously in real-time. As a result, the gateway we developed can receive all data from four different protocols. We also evaluate the performance of the gateway by testing hardware capabilities by measuring the transmit time and Packet Delivery Ratio (PDR). The result shows that all communication protocols show compliance with existing hardware specifications. In addition, we also test the load time performance of the PWA service and compare it to non-PWA. The load time on PWA is smaller than that of non-PWA, due to the fact that PWA has offline capabilities that can store caches temporarily so that the next load time will be lighter. Using hybrid network infrastructure with Multi-Protocol Gateway is the answer to the problem of the diversity of protocols that we often find in the implementation of IoT such as smart building, smart city and other smart environments, with the existence of this Multi-Protocol Gateway can make communication services in the IoT structure to be more efficient.

Intellevator: An Intelligent Elevator System Proactive in Traffic Control for Time-Efficiency Improvement

Elevator functioning as a vertical transport facility remains stand-alone and incapable of accessing the fine-grained traffic information. It significantly restricts the flexibility and efficiency of vertical transporting. In particular, while in peak-time, the limited elevator physical capacity with the momentary traffic increment gives rise to the vertical traffic bottleneck problem in large-scale buildings. The problem further results in the long waiting, dissatisfaction, frustration of passengers. In this paper, we present our proposal named Intellevator: an intelligent elevator system that enables the passively functioning elevator system be proactive and intelligent in traffic control for optimizing the transport efficiency. The proposal is an end-to-end architecture that composed of three aspects: Internet of things (IoT)-enabling technology on a conventional elevator; an agent server to enhance elevator computational capability and a novel user interface for delivering system intelligence to end-users. The proposal was experimented on a conventional elevator in a built smart-building environment. Numerical simulation results have demonstrated the system efficiency improvement. In addition, the system usability and user experience have been evaluated by a user study as well.