Intelligent Energy Management System Research Articles

Design and implementation of an intelligent energy management system for smart home utilizing a multi-agent system

Green Hydrogen Microgrid System has been selected as a source of clean and renewable alternative energy because it is undergoing a global revolution and has been identified as a source of clean energy that may aid the country in achieving net-zero emissions in the coming years. The study proposes an innovative Microgrid Renewable hybrid system to achieve these targets. The proposed hybrid renewable energy system combines a photovoltaic generator (PVG), a fuel cell (FC), a supercapacitor (SC) and a home vehicle power supply (V2H) to provide energy for a predefined demand. The proposed architecture is connected to the grid and is highly dependent on solar energy during peak periods. During the night or shading period, it uses FC as a backup power source. The SC assists the FC with high charge power. SC performs this way during load transients or quick load changes. A multi-agent system (MAS) was used to build a real energy management system (RT-HEMS) for intelligent coordination between components (MAS). The scheduling algorithm reduces energy consumption by managing the required automation devices without the need for additional network power. It will meet household energy requirements regardless of weather conditions, including bright, cloudy or rainy conditions. Implementation and discussion of the RT-HEMS ensures that the GHS is functioning properly and that the charge request is satisfied.

Influence of the Reward Function on the Selection of Reinforcement Learning Agents for Hybrid Electric Vehicles Real-Time Control

The real-time control optimization of electrified vehicles is one of the most demanding tasks to be faced in the innovation progress of low-emissions mobility. Intelligent energy management systems represent interesting solutions to solve complex control problems, such as the maximization of the fuel economy of hybrid electric vehicles. In the recent years, reinforcement-learning-based controllers have been shown to outperform well-established real-time strategies for specific applications. Nevertheless, the effects produced by variation in the reward function have not been thoroughly analyzed and the potential of the adoption of a given RL agent under different testing conditions is still to be assessed. In the present paper, the performance of different agents, i.e., Q-learning, deep Q-Network and double deep Q-Network, are investigated considering a full hybrid electric vehicle throughout multiple driving missions and introducing two distinct reward functions. The first function aims at guaranteeing a charge-sustaining policy whilst reducing the fuel consumption (FC) as much as possible; the second function in turn aims at minimizing the fuel consumption whilst ensuring an acceptable battery state of charge (SOC) by the end of the mission. The novelty brought by the results of this paper lies in the demonstration of a non-trivial incapability of DQN and DDQN to outperform traditional Q-learning when a SOC-oriented reward is considered. On the contrary, optimal fuel consumption reductions are attained by DQN and DDQN when more complex FC-oriented minimization is deployed. Such an important outcome is particularly evident when the RL agents are trained on regulatory driving cycles and tested on unknown real-world driving missions.

Intelligent energy management systems: a review

Climate change has become a major problem for humanity in the last two decades. One of the reasons that caused it, is our daily energy waste. People consume electricity in order to use home/work appliances and devices and also reach certain levels of comfort while working or being at home. However, even though the environmental impact of this behavior is not immediately observed, it leads to increased CO2 emissions coming from energy generation from power plants. It has been shown that about 40% of these emissions come from the electricity consumption and also that about 20% of this percentage could have been saved if we started using energy more efficiently. Confronting such a problem efficiently will affect both the environment and our society. Monitoring energy consumption in real-time, changing energy wastage behavior of occupants and using automations with incorporated energy savings scenarios, are ways to decrease global energy footprint. In this review, we study intelligent systems for energy management in residential, commercial and educational buildings, classifying them in two major categories depending on whether they provide direct or indirect control. The article also discusses what the strengths and weaknesses are, which optimization techniques do they use and finally, provide insights about how these systems can be improved in the future.

Real-time self-adaptive Q-learning controller for energy management of conventional autonomous vehicles

Reducing emissions and energy consumption of autonomous vehicles is critical in the modern era. This paper presents an intelligent energy management system based on Reinforcement Learning (RL) for conventional autonomous vehicles. Furthermore, in order to improve the efficiency, a new exploration strategy is proposed to replace the traditional decayed ε-greedy strategy in the Q-learning algorithm associated with RL. Unlike traditional Q-learning algorithms, the proposed self-adaptive Q-learning (SAQ-learning) can be applied in real-time. The learning capability of the controllers can help the vehicle deal with unknown situations in real-time. Numerical simulations show that compared to other controllers, Q-learning and SAQ-learning controllers can generate the desired engine torque based on the vehicle road power demand and control the air/fuel ratio by changing the throttle angle efficiently in real-time. Also, the proposed real-time SAQ-learning is shown to improve the operational time by 23% compared to standard Q-learning. Our simulations reveal the effectiveness of the proposed control system compared to other methods, namely dynamic programming and fuzzy logic methods.

Towards modelling of energy storages for use in an intelligent energy management system

AbstractWith the transition towards renewable energy underway, demand‐side management together with the local generation of renewable energy is receiving growing attention. Optimizing the self‐consumption of locally produced renewable energy can not only have financial benefits for the respective household or business (and improve their autarky from increasingly unstable energy markets), but also help improve grid stability against the volatility of some sources of renewable energy. In order to optimize the self‐consumption of a given household or enterprise with an energy management system, the energy demand and generation, as well as the behaviour of all controlled devices have to be forecast. There are many different methods of mathematically modelling these different properties, but the task becomes especially challenging for dynamic systems like energy storage systems. Here, the state of charge at a specific time point depends on both external influences and the previous time point's state of charge, thus modelling errors quickly accumulate. In the context of small and medium agricultural enterprises, examples of such dynamic systems can be electrical storages, like a battery, or thermal storages like a milk cooling tank or a heat pump.In this work, a common way for the modelling of these systems is explored, namely parameter identification. Here, the parameters of an ordinary differential equation representing the assumed physical behaviour of the system are identified from measured data of states and controls in an optimization problem. The success of this approach, and with it the performance of the derived model depends on how well the physical equations actually describe the system, but also on the quality, quantity and content of the measurement data used. In the case of a household battery storage already a simple physical model with parameters identified from measurement data of state of charge and battery power provides useful results. The example of a milk cooling tank provides a situation where external forcing has an important influence on the system's state of charge, its temperature. The cleaning of the tank generates a large heat influx, and raises the temperature, while the filling and emptying of milk influences the heat capacity. While these influences are shown to also be representable by equations based on the physical processes, parameter identification becomes difficult when they are not included in the measurement data. Thus, different approaches to derive these external forcings from the available data are outlined.

An intelligent energy management system for optimum design and real-time operation

<span lang="EN-US">Planning and management of distribution networks has become a very difficult task, especially with the strong expansion of renewable energy sources (RES) which are intermittent in nature. Maintaining fluidity and reliability of real-time decisions while taking into consideration uncertainties related to production and increasing the profit of distribution network operators is the objective of the system proposed in this work. It is an intelligent energy management system dedicated to the management of grid-integrated RES and battery energy storage systems (BESS), composed of: i) a real-time control and data acquisition model, ii) a model for forecasting the intermittent parameters of RES based on neural networks, iii) a long-term planning model based on the optimal placement and size of RES and BESS, and iv) an hourly planning model for scheduling the energy distribution between energy sources. The non-dominated sorting genetic algorithm and the entropy-TOPSIS method (technique for order of preference by similarity to ideal solution) form the basic block of this model. To evaluate it, a modified IEEE 33 bus network was used for testing and the results, for short-term scheduling, proved that the system succeeds in maximizing profits and significantly minimizing CO<sub>2</sub> emissions, in addition to power losses and voltage drops.</span>

Intelligent Energy Management System Evaluation of Hybrid Electric Vehicle Based on Recurrent Wavelet Neural Network and PSO Algorithm

Intelligent Energy Management System Evaluation of Hybrid Electric Vehicle Based on Recurrent Wavelet Neural Network and PSO Algorithm

Decentralized energy management system for smart microgrids using reinforcement learning

AbstractThis paper presents a novel fully decentralized and intelligent energy management system (EMS) for a smart microgrid based on reinforcement learning (RL) strategy. The purpose of the proposed EMS is to maximize the benefit of all microgrid entities comprising customers and distributed energy resources (DERs). Due to unpredictable features of renewable energy sources and variability of consumers’ demands, designing the microgrid EMS is a complicated task. To overcome this issue, the multi‐agent hour‐ahead energy management problem is modelled as a finite Markov decision process. The microgrid entities are considered as intelligent agents. The optimal policy of agents is obtained through a newly developed framework of the model‐free Q‐learning algorithm to maximize the benefit of all renewable and non‐renewable energy resources and battery energy storage system. The degradation model of the battery is considered to reduce the number of battery replacements. To ensure customers’ comfort, customers’ expenses are decreased without demand curtailment via introducing two types of load shifting techniques. The microgrid operation is analysed under four scenarios comprising no‐learning, generator‐learning, customer‐learning, and whole‐learning. the performance of the proposed algorithm is compared to the Monte Carlo method and simulation results on the real power‐grid dataset show the superiority of the algorithm.

Data-driven multi-layered intelligent energy management system for domestic decentralized power distribution systems

Energy management techniques have been immensely adopted in residential, industrial, and commercial sectors to meritoriously flatten the load profile of consumers. In this article, a cutting-edge intelligent energy management system is proposed to analytically monitor and regulate the load demand of a residential area to meritoriously address the load balancing and scheduling optimization problem with an aim to design an autonomous domestic complex, less reliant on the focal power grid. To do so, single- and multi- objective functions are defined for the presented double-layered framework. In the first layer, a day-ahead scheduling problem is evaluated to achieve the mutual revenue of electricity utilities and consumers, while in the second layer, a real-time coordination scheme for robust energy transactions among appliances, multiple microgrids, and the main power system is examined. Herein, a 0−1 multiple knapsack problem incorporated with the mixed-integer linear programming method is used to formulate the system mathematical model. To evaluate the intended system model, three heuristic algorithms (genetic algorithm, wind-driven optimization, and their hybrid) are modified. Furthermore, the Monte–Carlo simulations are performed to mitigate the impact of randomness and avoid pre-convergence. From the results of extensive simulations, it is corroborated that the proposed methodology is robust, reliable, and eco-social compared to prior schemes. This article reveals that the hybrid approach outperformed the other two strategies in terms of energy consumption, electricity cost, peak-to-average ratio, and user comfort level.

Blockchain-Driven Real-Time Incentive Approach for Energy Management System

In the current era, the skyrocketing demand for energy necessitates a powerful mechanism to mitigate the supply–demand gap in intelligent energy infrastructure, i.e., the smart grid. To handle this issue, an intelligent and secure energy management system (EMS) could benefit end-consumers participating in the Demand–Response (DR) program. Therefore, in this paper, we proposed a real-time and secure incentive-based EMS for smart grid, i.e., RI-EMS approach using Reinforcement Learning (RL) and blockchain technology. In the RI-EMS approach, we proposed a novel reward mechanism for better convergence of the RL-based model using a Q-learning approach based on the greedy policy that guides the RL-agent for faster convergence. Then, the proposed RI-EMS approach designed a real-time incentive mechanism to minimize energy consumption in peak hours and reduce end-consumers’ energy bills to provide incentives to the end-consumers. Experimental results show that the proposed RI-EMS approach induces end-consumer participation and increases customer profitabilities compared to existing approaches considering the different performance evaluation metrics such as energy consumption for end-consumers, energy consumption reduction, and total cost comparison to end-consumers. Furthermore, blockchain-based results are simulated and analyzed with the help of deployed smart contracts in a Remix Integrated Development Environment (IDE) with the parameters such as transaction efficiency and data storage cost.

An Intelligent Energy Management System Solution for Multiple Renewable Energy Sources

This paper proposes an intelligent energy management system based on multiple renewable energy sources. The intelligent energy management system is defined as a flexible energy management system built by integrating multiple renewable energy sources and facilities for energy storage. The general objective of this paper is to propose a solution to increase the use of energy potential from renewable sources by embedding small-sized energy sources to behave as a higher-power energy source. The proposed system includes solar, wind, and hydro as renewable sources. As the system is not connected to the primary distribution grid, two alternatives for energy storage are also included: batteries and a water basin used for hydro energy. The system includes a diesel generator as a reserve. The system can be adjusted depending on the consumers it serves and the location where it is implemented (i.e., the potential of electricity, wind, and hydro). The main contribution of this paper is the use of an energy storage concept in the form of a “natural” battery system composed of a water storage basin into which water is pumped when we have a surplus of energy from renewable generators.

Radial basis function neural network MPPT controller-based microgrid for hybrid stand-alone energy system used for irrigation

PurposeThe main purpose of this controller is to carryout irrigation by the farmers with renewable energy resources.Design/methodology/approachThe proposed design includes the Deep learning based intelligent stand-alone energy management system used for irrigation purpose. The deep algorithm applied here is Radial basis function neural network which tracks the maximum power, maintains the battery as well as load system.FindingsThe Radial Basis Function Neural Network algorithm is used for carrying out the training process. In comparison with other conventional algorithms, this algorithm outperforms by higher efficiency and lower tracking time without oscillation.Research limitations/implicationsIt is little complex to implement the hardware setup of neural network in terms of training process but the work is under progress.Practical implicationsThe practical hardware implementation is under progress.Social implicationsIf controller are implemented in a real-time environment, definitely it helps the human-less farming and irrigation process.Originality/valueIf this system is implemented in real-time environment, every farmer gets benefitted.

Approach for a Global Route-Based Energy Management System for Electric Vehicles with a Hybrid Energy Storage System

The usage of batteries and supercapacitors in the field of electric vehicles is becoming increasingly prominent in both research and development. Due to the complementary advantages of the two systems, high energy density, and high power density, a combined battery/supercapacitor system offers potential. To effectively utilise the potential of such a hybrid energy storage system (HESS), one requires an intelligent energy management system (EMS). The EMS is responsible for controlling the electrical power between the battery and the supercapacitor in such a way that the required power can be optimally distributed at all times (currently and in the future). For this purpose, the energy management system utilises information on the driving route and, based on this information, shall calculate a global strategy for the continuous power distribution. The controlled power distribution should take place in real time and be robust against discrepancies so that unpredictable or unreliably predictable events do not significantly influence the functionality. For the implementation of the concept, a rule-based power distribution is implemented in combination with a predictive energy management. Here, the energy management is combined with a rule-based strategy calculation based on data on the route to be driven with a global optimization for the calculation of a route-specific strategy. Depending on the selected objective, the increase in energy efficiency, or lifetime, the operation of the power control is optimised. Due to the functional separation, the continuous power control can operate in real time, while more computational time can be spent on the calculations of the power management strategy, which accordingly does not need to be executed in real time. The results show that by using the presented EMS, especially in combination with a route-specific parameterisation, a significant effect on the energy efficiency and/or battery lifetime can be achieved. The average battery energy consumption can be reduced by up to 9.14% on urban routes. Regarding battery lifetime, the average battery usage can be reduced up to 13.35% and the battery energy losses even up to 62.72%.

Operational Validation of a Power Distribution Algorithm for a Modular Megawatt Battery Storage System

AbstractLarge‐scale battery storage systems have become popular for various grid services in recent years. A worldwide market growth for battery storage has led to increased competition in several grid service markets. Modular large‐scale battery storage systems require a safe, highly available, and intelligent energy management system (EMS) in order to be economically competitive. One component of this EMS is the control for distributing the power requests between individual battery units of the large‐scale battery storage system. As the EMS is usually undisclosed intellectual property of the system manufacturers, there is only little information on real‐world operation available. To contribute, we present a rule‐based power distribution algorithm (SPDA) in this paper and validate it through field tests on a 6 MW/7.5 MWh system that is providing frequency containment reserve to the German power grid. The results show that especially when combining different battery technologies, the SPDA can exploit individual technological strengths. In this way, the state of charge of the batteries, energy throughput and power load of the batteries can be controlled to extend the lifetime. Moreover, the SPDA managed to shift nearly 80 % of the energy throughput to one battery unit to protect less cyclic stable batteries and make use of the advantage of cyclic stable battery technologies, while fulfilling all grid service requirements. By shifting those large quantities of the energy throughput to more cyclic stable battery units, the large‐scale battery storage system experienced in sum up to 45 % less cyclic aging with the SPDA than with a symmetrical power distribution algorithm. Furthermore, the operational efficiency of a large‐scale battery storage system can be significantly improved via additional software adaptations of the power distribution, depending on the system layout.

Low Carbon Building Design Optimization Based on Intelligent Energy Management System

The construction of relevant standards for building carbon emission assessment in China has just started, and the quantitative analysis method and evaluation system are still imperfect, which hinders the development of lowcarbon building design. Therefore, the use of intelligent energy management system is very necessary. The purpose of this paper is to explore the design optimization of low-carbon buildings based on intelligent energy management systems. Based on the proposed quantitative method of building carbon emission, this paper establishes the quota theoretical system of building carbon emission analysis, and develops the quota based carbon emission calculation software. Smart energy management system is a low-carbon energy-saving system based on the reference of largescale building energy-saving system and combined with energy consumption. It provides a fast and effective calculation tool for the quantitative evaluation of carbon emission of construction projects, so as to realize the carbon emission control and optimization in the early stage of architectural design and construction. On this basis, the evaluation, analysis and calculation method of building structure based on carbon reduction target is proposed, combined with the carbon emission quota management standard proposed in this paper. Taking small high-rise residential buildings as an example, this paper compares and analyzes different building structural systems from the perspectives of structural performance, economy and carbon emission level. It provides a reference for the design and evaluation of low-carbon building structures. The smart energy management system collects user energy use parameters. It uses time period and time sequence to obtain a large amount of data for analysis and integration, which provides users with intuitive energy consumption data. Compared with the traditional architectural design method, the industrialized construction method can save 589.22 megajoules (MJ) per square meter. Based on 29270 megajoules (MJ) per ton of standard coal, the construction area of the case is about 8000 m2, and the energy saving of residential buildings is 161.04 tons of standard coal. This research is of great significance in reducing the carbon emission intensity of buildings.

SIEMS: A Secure Intelligent Energy Management System for Industrial IoT Applications

Microgrids are industrial technologies that can provide energy resources for the Internet of Things (IoT) demands in smart grids. Hybrid microgrids supply quality power to the IoT devices and ensure high resiliency in supply and demand for PV-based grid-tied microgrids. In this system, the usage of predictive energy management systems (EMS) is essential to dispatch power from different resources, while the battery energy storage system (BESS) is feeding the loads. In this article, we deploy a one-day-ahead prediction algorithm using a deep neural network for a fast-response BESS in an intelligent energy management system (I-EMS) that is called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SIEMS</i> . The main role of the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SIEMS</i> is to maintain the SOC at high rates based on the one-day-ahead information about solar power, which depends on meteorological conditions. The remaining power is supplied by the main grid for sustained power streaming between BESS and end-users. Considering the usage of information and communication technology components in the microgrids, the main objective of this article is focused on the hybrid microgrid performance under cyber-physical security adversarial attacks. Fast gradient sign, basic iterative, and DeepFool methods, which are investigated for the first time in power systems e.g., smart grid and microgrids, in order to produce perturbation for training data. To secure the microgrid’s <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SIEMS</i> , we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">two</i> Defence algorithms based on defensive distillation and adversarial training strategies for the first time in EMSs. We apply and evaluate these benchmark adversarial attack and Defence methods against the proposed machine learning models to increase the robustness of the models in the system against adversarial attacks.

Intelligent Energy Management System for Smart Grids Using Machine Learning Algorithms

Smart grid technology is rapidly advancing and providing various opportunities for efficient energy management. To achieve the full potential of smart grids, intelligent energy management systems (IEMS) are required that can optimally manage and control the distributed energy resources (DERs). In this paper, proposed an IEMS using the Deep Reinforcement Learning (DRL) algorithm to manage the energy consumption and production in a smart grid. The proposed methodology aims to minimize the energy cost while maintaining the stability and reliability of the grid. The performance of the proposed IEMS is evaluated on a simulated smart grid, and the results show that it can effectively manage the energy resources while minimizing the energy cost.

Emerging indoor photovoltaics for self-powered and self-aware IoT towards sustainable energy management.

As the number of Internet of Things devices is rapidly increasing, there is an urgent need for sustainable and efficient energy sources and management practices in ambient environments. In response, we developed a high-efficiency ambient photovoltaic based on sustainable non-toxic materials and present a full implementation of a long short-term memory (LSTM) based energy management using on-device prediction on IoT sensors solely powered by ambient light harvesters. The power is supplied by dye-sensitised photovoltaic cells based on a copper(ii/i) electrolyte with an unprecedented power conversion efficiency at 38% and 1.0 V open-circuit voltage at 1000 lux (fluorescent lamp). The on-device LSTM predicts changing deployment environments and adapts the devices' computational load accordingly to perpetually operate the energy-harvesting circuit and avoid power losses or brownouts. Merging ambient light harvesting with artificial intelligence presents the possibility of developing fully autonomous, self-powered sensor devices that can be utilized across industries, health care, home environments, and smart cities.

Design and Development of an Intelligent Energy Management System for a Smart Grid to Enhance the Power Quality

Design and Development of an Intelligent Energy Management System for a Smart Grid to Enhance the Power Quality

Design and Implementation of Smart Energy Management System

In order to optimize the energy management of the industrial park, the technical architecture and the function of intelligent energy management system are set up using information technology of use fixed number of year, load, capacity, cost of investment, etc. of various equipment in the industrial park. All the data monitoring, collection and analysis are based on the energy consumption index of scientific management, realizing the optimal operation, the effects of energy conservation and emissions reduction and refined energy management, and promoting the economic benefits of the park. Based on the Guangzhou City Project, in order to improve the comprehensive efficiency of energy use in the park, this paper carries out offline debugging and online commissioning of energy storage equipment in the park.