Smart Building Energy Management System Research Articles

Enhancing Energy Efficiency With Smart Building Energy Management System Using Machine Learning and IOT

Enhancing Energy Efficiency With Smart Building Energy Management System Using Machine Learning and IOT

Optimizing smart building energy management systems through industry 4.0: A response surface methodology approach

Effective control of inner climatic conditions in a Heating ventilation and air conditioning (HVAC) system based on efficiency of the system is imperative to ensure occupant comfort, energy efficiency, and preservation of indoor air quality. The existing problems with HVAC system includes inefficient adjustment to internal room parameters and limited optimization based on varying loads. The current study investigates the influence of Industry 4.0 by assessing internal room parameters in an indoor ventilated room conditions for system output. Smart systems like AI and IoT, integrated with sensors, dynamically adjust indoor conditions based on external climate, enhancing HVAC system efficiency. Using Artificial Neural Networks (ANN) and Response Surface Methodology (RSM), integrated with AI and IoT sensors, optimally adjust indoor conditions in correlation with external climate, maximizing HVAC system efficiency. The study utilizes input parameters including Dry Bulb Temperature (DBT), Relative Humidity (RH), and Solar Radiation across diverse days to analyze system efficiency. ANN and RSM iteratively optimize system efficiency by training on RH, DBT, and air quality data. They converge on recommending 42% RH, 28 °C DBT, and 25 PM air quality, achieving 0.851 desirability. This approach enhances heat load (75.89%) and ventilation load (69.12%) efficiency significantly. Integration of Industry 4.0 sensors in the HVAC system resulted in a 16% efficiency increase and 15% cost effectiveness in the controlled room compared to prior measurements.

Machine learning-based energy use prediction for the smart building energy management system

Smart building is a building development approach utilizing digital and communication technology to improve occupants' comfort inside the building and help increase energy usage efficiency in building operations. Despite its benefits, the smart building concept is still slowly adopted, particularly in developing countries. The advancement of computational techniques such as machine learning (ML) has helped building owners simulate and optimize various building performances in the building design process more accurately. Therefore, this study aims to assist energy efficiency design strategies in a building by identifying the features of the smart building characteristics that can potentially foster building energy efficiency. Furthermore, an ML model based on the features identified is then developed to predict the level of energy use. K-Nearest Neighbor (k-NN) algorithm is employed to develop the model with the openly accessible smart building energy usage datasets from Chulalongkorn University Building Energy Management System (CU-BEMS) as the training and testing datasets. The validation result shows that the predictive model has an average relative error value of 17.76%. The energy efficiency levels obtained from applying identified features range from 34.5% to 45.3%, depending on the reviewed floor. This paper also proposed the dashboard interface design for ML-based smart building energy management.

GridLearn: Multiagent reinforcement learning for grid-aware building energy management

Increasing amounts of distributed generation in distribution networks can provide both challenges and opportunities for voltage regulation across the network. Intelligent control of smart inverters and other smart building energy management systems can be leveraged to alleviate these issues. GridLearn is a multiagent reinforcement learning platform that incorporates both building energy models and power flow models to achieve grid level goals, by controlling behind-the-meter resources. This study demonstrates how multi-agent reinforcement learning can preserve building owner privacy and comfort while pursuing grid-level objectives. Building upon the CityLearn framework which considers RL for building-level goals, this work expands the framework to a network setting where grid-level goals are additionally considered. As a case study, we consider voltage regulation on the IEEE-33 bus network using controllable building loads, energy storage, and smart inverters. The results show that the RL agents nominally reduce instances of undervoltages and reduce instances of overvoltages by 34%. • Feasibility study of multiagent reinforcement learning for voltage regulation. • Multiagent reinforcement learning for demand side management with power flow analysis. • Open source building energy management simulation.

Development and performance analysis of a ZigBee and LoRa-based smart building sensor network

A wireless sensor network employing ZigBee and LoRa (Long Range) communication protocols for integration into smart building energy management systems is presented in this article. The design and implementation details are provided, and the performance parameters of the communication network are defined and analyzed based on the test results obtained from different configurations. The developed embedded system can be used in smart environments so that the room temperature, humidity, lighting systems, and so on can be automatically monitored and controlled. By customizing the embedded code, a variety of Internet of Things (IoT) applications can be introduced owing to their scalability. Taking advantage of the complementing low-power and long-range features of ZigBee and LoRa communication technologies, a system comprising an end device, a multi-protocol gateway, and a central data collector (CDC) unit is developed. The end device collects temperature and humidity as well as light intensity data using low-power sensors and sends the data to the gateway via the LoRa wireless transceiver module. The gateway was designed as an intermediate device that allows data exchange between the LoRa and ZigBee transceiver modules. It receives sensor data from the end device via LoRa and sends them to the CDC unit via a ZigBee-based XBee S2 commercial wireless transceiver module. Sensor data are monitored in the CDC unit by using an open-source IoT software platform. A commercial STM32 integrated circuit (IC) was used as a microcontroller unit for the end device and gateway. Performance parameters such as communication range and throughput data were studied for both the ZigBee and LoRa wireless transceiver modules.

Systematic Review Analysis on Smart Building: Challenges and Opportunities

Smart building technology incorporates efficient and automated controls and applications that use smart energy products, networked sensors, and data analytics software to monitor environmental data and occupants’ energy consumption habits to improve buildings’ operation and energy performance. Smart technologies and controls are becoming increasingly important not only in research and development (R&D) but also in industrial and commercial domains, leading to a steady growth in their application in the building sector. This study examines the literature on SBEMS published between 2010 and 2020 with a systematic approach. It examines the trend with the annual number of the published studies before exploring the classification of publications in terms of factors such as domain of SBEMS, control approaches, smart technologies, and quality attributes. Recent developments around the smart building energy management systems (SBEMS) have focused on features that provide occupants with an interface to monitor, schedule, and modify building energy consumption profiles and allow a utility to participate in a communication grid through demand response programs and automatic self-report outage functionality. The study also explores future research avenues, especially in terms of improvements in privacy and security, and interoperability. It is also suggested that the smart building technologies’ smartness can be improved with the help of solutions such as real-time data monitoring and machine learning

Modeling and Optimization of Smart Building Energy Management System Considering Both Electrical and Thermal Load

Energy consumption in buildings is expected to increase by 40% over the next 20 years. Electricity remains the largest source of energy used by buildings, and the demand for it is growing. Building energy improvement strategies is needed to mitigate the impact of growing energy demand. Introducing a smart energy management system in buildings is an ambitious yet increasingly achievable goal that is gaining momentum across geographic regions and corporate markets in the world due to its potential in saving energy costs consumed by the buildings. This paper presents a Smart Building Energy Management system (SBEMS), which is connected to a bidirectional power network. The smart building has both thermal and electrical power loops. Renewable energy from wind and photo-voltaic, battery storage system, auxiliary boiler, a fuel cell-based combined heat and power system, heat sharing from neighboring buildings, and heat storage tank are among the main components of the smart building. A constraint optimization model has been developed for the proposed SBEMS and the state-of-the-art real coded genetic algorithm is used to solve the optimization problem. The main characteristics of the proposed SBEMS are emphasized through eight simulation cases, taking into account the various configurations of the smart building components. In addition, EV charging is also scheduled and the outcomes are compared to the unscheduled mode of charging which shows that scheduling of Electric Vehicle charging further enhances the cost-effectiveness of smart building operation.

Day-ahead Optimal Scheduling for Cluster Smart Buildings Considering Power Sharing

With the deregulation of power industry and increasing penetration of distributed energy resources, the study on the optimal schedule of demand-side resource under the electricty market environment has attracted wide attention from academia and industry. In this study, a market-based operational framework for cluster smart buildings is proposed. On this basis, a day-ahead optimal scheduling strategy and model for cluster smart buildings considering the overall power balance and consumer preferences and behaviors is proposed. The smart building energy management system comprising photovoltaic, electric vehicles and thermostatic controllable loads aims to minimize the total energy procurement cost. And then, the numerical results indicate that the proposed scheduling model can achieve local power sharing in the smart community. Finaly, the optimal scheduling results under consideration or no consideration of the transformer power limit are discussed.

A Heating Controller Designing Based on Living Space Heating Dynamic’s Model Approach in a Smart Building

Most already advanced developed heating control systems remain either in a prototype state (because of their relatively complex implementation requirements) or require very specific technologies not implementable in most existing buildings. On the other hand, the above-mentioned analysis has also pointed out that most smart building energy management systems deploy quite very basic heating control strategies limited to quite simplistic predesigned use-case scenarios. In the present paper, we propose a heating control strategy taking advantage of the overall identification of the living space by taking advantage of the consideration of the living space users’ presence as additional thermal sources. To handle this, an adaptive controller for the operation of heating transmitters on the basis of soft computing techniques by taking into account the diverse range of occupants in the heating chain is introduced. The strategy of the controller is constructed on a basis of the modeling heating dynamics of living spaces by considering occupants as an additional heating source. The proposed approach for modeling the heating dynamics of living spaces is on the basis of time series prediction by a multilayer perceptron neural network, and the controlling strategy regarding the heating controller takes advantage of a Fuzzy Inference System with the Takagi-Sugeno model. The proposed approach has been implemented for facing the dynamic heating conduct of a real five-floor building’s living spaces located at Senart Campus of University Paris-Est Créteil, taking into account the occupants of spaces in the control chain. The obtained results assessing the efficiency and adaptive functionality of the investigated fuzzy controller designed model-based approach are reported and discussed.

High Level Controller-Based Energy Management for a Smart Building Integrated Microgrid With Electric Vehicle

This paper presents an effective approach for the modelling and optimization of a smart building integrated microgrid (BIM). The main objective is the development of a smart building energy management system (BEMS) which is in charge of optimally controlling the operation of a building-integrated-microgrid. More specifically, we consider a BIM consisting of a roof-top solar photovoltaic, wind turbine, energy storage unit, electric vehicle, micro-CHP, metering infrastructure and loads. The BIM loads are associated to satisfy the electric needs of occupants as well as considering the operating flexibility of thermal load that includes building heating and hot water demand. The emphasis is given to the optimal performance of the BIM, where the objective is to ensure the power balance between production and loads in the microgrid (electric and thermal). A centralized algorithm is implemented for the power management of all components as well as power exchanges with the electrical grid. The developed algorithm is tested through a case study, where the effects of both loads and renewable resources variabilities on the operation of the BIM are analyzed via numerical simulations.

Energy Management-Based Predictive Controller for a Smart Building Powered by Renewable Energy

This paper presents a smart building energy management system (BEMS), which is in charge of optimally controlling the sustainable operation of a building-integrated-microgrid (BIM). The main objective is to develop an advanced high-level centralized control approach-based model predictive control (MPC) considering variations of renewable sources and loads. A finite-horizon planning optimization problem is developed to control the operation of the BIM. The model can be implemented as a BEMS for the BIM to manipulate the indoor temperature and optimize the operation of the system’s units. A centralized MPC-based algorithm is implemented for the power management scheduling of all sub-systems as well as power exchanges with the electrical grid. The MPC algorithm is verified over case studies applied to two floors residential building considering the climate condition of a typical day of March, where the effects of both loads and thermal resistance of building shell on the operation of the BIM are analyzed via numerical simulations. The analysis shows that 96% of the total electrical load has been fulfilled by the local production where 23% represents the total electric output of the micro-CHP and 73% is the renewable energy production. The deficit, which represents only 4%, is purchased from the electrical distribution network (EDN).

Data-Driven Living Spaces' Heating Dynamics Modeling in Smart Buildings using Machine Learning-Based Identification.

Modeling and control of the heating feature of living spaces remain challenging tasks because of the intrinsic nonlinear nature of the involved processes as well as the strong nonlinearity of the entailed dynamic parameters in those processes. Although nowadays, adaptive heating controllers represent a crucial need for smart building energy management systems (SBEMS) as well as an appealing perspective for their effectiveness in optimizing energy efficiency, unfortunately, the leakage of models competent in handling the complexity of real living spaces’ heating processes means the control strategies implemented in most SBEMSs are still conventional. Within this context and by considering that the living space’s occupation rate (i.e., by users or residents) may affect the model and the issued heating control strategy of the concerned living space, we have investigated the design and implementation of a data-driven machine learning-based identification of the building’s living space dynamic heating conduct, taking into account the occupancy (by the residents) of the heated space. In fact, the proposed modeling strategy takes advantage, on the one hand, of the forecasting capacity of the time-series of the nonlinear autoregressive exogenous (NARX) model, and on the other hand, from the multi-layer perceptron’s (MLP) learning and generalization skills. The proposed approach has been implemented and applied for modeling the dynamic heating conduct of a real five-floor building’s living spaces located at Senart Campus of University Paris-Est Créteil (UPEC), taking into account their occupancy (by users of this public building). The obtained results assessing the accuracy and addictiveness of the investigated hybrid machine learning-based approach are reported and discussed.

GOT Assisted Smart Building Energy Management System

GOT Assisted Smart Building Energy Management System

Commercial Technologies for Advanced Light Control in Smart Building Energy Management Systems: A Comparative Study

This work investigates the economic, social, and environmental impact of adopting different smart lighting architectures for home automation in two geographical and regulatory regions: Algiers, Algeria, and Stuttgart, Germany. Lighting consumes a considerable amount of energy, and devices for smart lighting solutions are among the most purchased smart home devices. As commercialized solutions come with variant features, we empirically evaluate through this study the impact of each one of the energy-related features and provide insights on those that have higher energy saving contribution. The study started by investigating the state-of-the-art of commercialized ICT-based light control solutions, which allowed the extraction of the energy-related features. Based on the outcomes of this study, we generated simulation scenarios and selected evaluations metrics to evaluate the impact of dimming, daylight harvesting, scheduling, and motion detection. The simulation study has been conducted using EnergyPlussimulation tool, which enables fine-grained realistic evaluation. The results show that adopting smart lighting technologies have a payback period of few years and that the use of these technologies has positive economic and societal impacts, as well as on the environment by considerably reducing gas emissions. However, this positive contribution is highly sensitive to the geographical location, energy prices, and the occupancy profile.

Improving energy efficiency via smart building energy management systems: A comparison with policy measures

To foster the transition to more sustainable energy systems, policymakers have been approving measures to improve energy efficiency as well as promoting smart grids. In this setting, building managers are encouraged to adapt their energy operations to real-time market and weather conditions. Yet, most fail to do so as they rely on conventional building energy management systems (BEMS) that have static temperature set points for heating and cooling equipment. In this paper, we investigate how effective policy measures are at improving building-level energy efficiency compared to a smart BEMS with dynamic temperature set points. To this end, we present an integrated optimisation model mimicking the smart BEMS that combines decisions on heating and cooling systems operations with decisions on energy sourcing. Using data from an Austrian and a Spanish building, we find that the smart BEMS results in greater reduction in energy consumption than a conventional BEMS with policy measures.

Conception and Validation of Smart Building Energy Management System BEMS Using the Discrete Event System Specification DEVS

The improvement of the energetic behavior of buildings has turned into a major issue due to the high level of energy consumption. In this context, the building is represented as a dynamical system and a system of data acquisition is developed, which allows the measurement of environmental and energetic parameters, so as to describe the behavior of the building interacting with its direct environment. Research related to energy management can be divided into two categories: predictive control (anticipative) and adaptive control (reactive). A new building energy management system (BEMS) which is the chosen system to validate, treats a long-term anticipative control and introduces a reactive control that adds another level of intelligence to the BEMS.The main goal of this paper is to propose a model using the formalism DEVS to describe and simulate the BEMS. Our motivation is explained by the fact that DEVS is a tool for modeling of discrete event systems and it divides the overall system into subsystems in order to facilitate the achievement which is consistent with the characteristics of multilayer architecture of the chosen system.

Plug-in electric vehicles as dispersed energy storage interactions with a smart office building

Renewable energy resources (RESs) with plug-in electric vehicles (PEVs) are being gradually accepted by society for their low carbon emission merits. However, reverse power from the RES will result in the grid node's voltage rise and cause protection malfunction. As large amount of PEVs plug in the grid, their overall charging power tends to be uncertain due to their complex charging behavior. At the same time, if the renewable energy is integrated into the same grid, the gird will face a great technological challenge. In this paper, a smart building energy management system (SBEMS) is proposed to mitigate negative impact of RES and PEVs to power grid and optimize the operation of the building. The proposed SBEMS is also capable with PEVs system integration, photovoltaic (PV) power forecasting, optimization algorithm implementation, and environmental evaluation criteria. Since PV's output is sensitive to the meteorology, a 1-day-ahead power forecasting model is needed and presented. The economic system of PEVs is particularly complex, because it needs optimization across multiple time steps and is strongly influenced by tariff structures. Furthermore, the optimization problem to minimize the total building operational cost including PEVs charging cost is formulated while satisfying the supply and demand balance and complicated operating constraints of every energy supply equipment and devices. The simulation results have shown that the SBEMS can effectively reduce the PEVs charging cost, building operation cost, and the environment punishment fee. It is also important for the SBEMS to be responsible for the power grid operational indices. So the trade-off between economic consideration and load factor should be made. It is verified that the SBEMS is beneficial to the PEVs owners, building operator, environment, and grid.