Proposed Energy Management Research Articles

Federated dueling DQN based microgrid energy management strategy in edge-cloud computing environment

In order to tackle the challenge of centralized reinforcement learning based microgrid energy management would impose severe privacy violation and consume a large number of communication resource, we address the problem of microgrid energy management strategy (EMS) based on edge-cloud assisted federated deep reinforcement learning (FDRL). We first present the microgrid operation model in edge-cloud computing scenario to optimize energy management strategy with economic benefits as the goal. Then, the federated dueling deep Q-network with novel action exploration (DDQN) is proposed to resolve the problem model and it is leveraging to design an innovative microgrid energy management strategy, and the convergence and computational complexity of the proposed energy management strategy is analyzed. Simulation results validate that the reward and profit obtained with the edge-cloud-assisted federated DDQN energy management strategy outperform the conventional deep reinforcement learning (DRL) method, and the communication efficiency and data privacy preservation can be attained.

Optimal Adaptive Fractional Order Integral Sliding Mode Controller-Energy Management Strategy for Electric Vehicles Based on Bald Eagle Search Algorithm

This research presents an optimal energy management system (EMS) for a lithium-ion battery-supercapacitor hybrid storage system used to power an electric vehicle. The storage systems are connected in parallel to the DC bus by bidirectional DC-DC converters and feed a synchronous reluctance motor through an inverter. The proposed energy management strategy is built on the idea to take full benefits of two combined methods: the bald eagle search algorithm and fractional order integral sliding mode control. To evaluate the effectiveness of the suggested optimal energy management strategy, an urban dynamometer driving schedule (UDDS) driving cycle is considered. The obtained results are compared to a classical fractional order integral sliding mode control-based energy management strategy in terms of voltage ripples, overshoots, and battery final state of charge. The ultimate results approve the ability of the proposed energy management system to enhance the power quality and enhance battery power consumption at the same time. Comprehensive processor-in-the-loop (PIL) cosimulations were conducted on the electric vehicle using the C2000 launchxl-f28379d digital signal processing (DSP) board to assess the practicability and effectiveness of the proposed EMS.

Design and control of LSTM-ANN controllers for an efficient energy management system in a smart grid based on hybrid renewable energy sources

Many isolated locations, including hilly areas, remote sites, and military camps, lack feasible access to the main power grid. In these conditions, locally established Microgrids can provide the necessary power supply. However, to meet the demands of these isolated areas, numerous individual Microgrids are required. Although some of these Microgrids might be integratable, geographical constraints may preclude full integration. Under these circumstances, the establishment of a smart grid—integrating multiple Microgrids with a battery management system—can potentially solve many power supply issues. A smart grid control system paired with a centralized battery management system is proposed in this paper. The system considers the use of multiple renewable energy sources at various locations for stable and reliable power generation. The proposed method incorporates a long short-term memory (LSTM)-based artificial neural network (ANN) to ensure a stable, high-quality power supply at different load buses. Additionally, this work introduces an artificial intelligence-based operating system designed to maintain energy management under various conditions. To enhance voltage quality, a 7-level aligned multilevel inverter is incorporated into the system. As compared with PI and Fuzzy controllers, the proposed method with LSTM-ANN controller is improved the power quality under sudden changes in the system which are also presented in results, Voltage variation of PI, Fuzzy, and LSTM-ANN is 370V,180V,and 70V . The effectiveness of the proposed energy management system (EMS) is verified by using a hardware-in the-loop approach with OPAL-RT modules, yielding realistic results.

Energy management strategy of urban rail hybrid energy storage system based on fuzzy logic system

Energy management is an important link in the effective functioning of hybrid energy storage systems (HESS) within urban rail trains. This factor significantly impacts the operational stability and economic efficiency of urban rail systems. Safety issues arise from DC bus voltage fluctuations due to varying train conditions. To address these issues, this paper proposes an energy management strategy for the urban rail HESS, which builds upon a traditional double closed-loop control strategy. This strategy incorporates a fuzzy logic system to regulate power distribution parameters and discharge thresholds dynamically. Real-time monitoring of the state of charge (SOC) of the energy storage device informs the decision-making process, utilizing a fuzzy inference system to effectively regulate power and energy distribution in response to the distinct characteristics of batteries and super-capacitors. This approach aims to mitigate power fluctuations within the traction network. To validate the effectiveness of the proposed energy management strategy, the study conducts a comprehensive simulation experiment using MATLAB/Simulink. The simulation results confirm the efficacy of the proposed strategy, highlighting its potential to enhance the stability and overall performance of urban rail train operations.

The energy management strategy of a loop microgrid with wind energy prediction and energy storage system day-ahead optimization

Microgrid has been extensively applied in the modern power system as a supplementary mode for the distributed energy resources. The microgrid with wind energy is usually vulnerable to the intermittence and uncertainty of the wind energy. To increase the robustness of the microgrid, the energy storage system (ESS) is necessary to compensate the power imbalance between the power supply and the load. To further maximize the economic efficiency of the system, the system level control for the microgrid is desired to be optimized when it is integrated with the utility grid. Aiming at the aforementioned problem, this paper comprehensively analyzes the power flow of a typical loop microgrid. A transformer-based wind power prediction (WPP) algorithm is proposed and compared with recurrent neural networks algorithm. With the historical weather data, it can accurately predict the 24 h average wind energy. Based on the predicted wind energy and the time-of-use (TOU) electricity price, a day-ahead daily cycling profile of the ESS with particle swarm optimization algorithm is introduced. It comprehensively considers the system capacity constraints and the battery degree of health. The functionality of the proposed energy management strategy is validated from three levels. First, WPP is conducted with the proposed algorithm and the true historical weather data. It has validated the accuracy of the transformer algorithm in prediction of the hourly level wind energy. Second, with the predicted wind energy, a case study is given to validate the day-ahead daily cycling profile. A typical 1 MVA microgrid is utilized as the simulation model to validate performance of the daily cycling optimization algorithm. The case study results show that the ESS daily cycling can effectively reduce the daily energy expense and help to shave the peak power demand in the grid.

PV and Energy Storage Systems Management for EV Charging Optimization in Residential Parks

With the rapid advancements in electric vehicle technology, there is expected to be a significant increase in the number of Electric Vehicle (EV) charging stations in the years to come. Residential parking is deemed to be the most appropriate solution to meet the charging demands of EVs. However, the charging process will present a significant challenge for the utility grid. This paper aims to optimize the charging of EVs in residential parking areas through the integration of energy storage systems (ESS) and photovoltaic (PV) systems. To achieve the objective, a smart charging management system has been developed that formulates the optimization of EV charging as a cost minimization problem and applies the particle swarm optimization algorithm to solve it. The proposed energy management scheme is evaluated through simulation case studies, and the resulting data is compared with uncoordinated charging. The data is then analyzed and discussed. The proposed algorithm has improved the utilization of the microgrid’s power sources, resulting in a 129% reduction in electricity costs compared to the predefined rules algorithm. Furthermore, the proposed strategy has alleviated strain on the power grid by reducing the peak load by 40%.

DSP‐based energy optimization management of household single‐phase electric energy router with historical and real‐time data

AbstractThe development and use of single‐phase electric energy router (SPEER) makes the household power system operate more reliably and bring economic income at the same time. This paper presents an economic energy optimization management method of SPEER with historical data of previous day and real‐time data in the grid‐connected mode of SPEER, which can be realized by DSP. First, based on the exchange power between the SPEER and the grid, the optimal charging and discharging power of the battery to make up for the energy difference between the previous day and the real time is obtained through the particle swarm intelligence algorithm, and the optimal economic model of SPEER operation is established. Then, on the hardware experimental platform, DSP is used to realize the real‐time optimization, and the optimal economic optimization algorithm proposed in this paper is implemented and verified on hardware experimental platform. The contradiction between the complexity of optimization algorithm and the limitation of hardware resources is solved in the proposed energy management system.

Hybrid method based energy management of electric vehicles using battery-super capacitor energy storage

This paper presents a hybrid technique for managing the Energy Management of a hybrid Energy Storage System (HESS), like Battery, Supercapacitor (SC), and integrated charging in Electric Vehicle (EV). The proposed hybrid method combines the Namib Beetle Optimization (NBO) and Quantum Neural Networks (QNN) technique and is commonly known as the NBO-QNN approach. The proposed energy management technique reduces EV power use and maximizes battery life. QNN forecasts and combines power supply and charge levels to fulfill load needs. EV energy management uses NBO to regulate the output voltage, generate references, and regulate current continuously. Higher energy density battery and power density SC meet vehicle needs. An uncontrolled rectifier with a DC-to-DC buck converter balances charging and ensures energy transmission. The Proposed technique is implemented using the MATLAB platform, and its performance is compared to existing methods. HESS performance is evaluated by comparing it to existing systems. The research shows that the proposed strategy reduces the primary and secondary source stress, enhances performance of charging unit, and extends the life of battery. Furthermore, the NBO-QNN technique outperforms other existing methods, such as the Cooperation Search Algorithm (CSA), Latent Semantic Analysis (LSA), and Grasshopper Optimization Algorithm (GOA). The proposed method displays the best output in all existing Cooperation Search Algorithm (CSA), Latent Semantic Analysis (LSA), and Grasshopper Optimization Algorithm (GOA) methods. The result concludes that the NBO-QNN approach based on THD value is less than existing methods.

Bi-objective optimal active and reactive power flow management in grid-connected AC/DC hybrid microgrids using metaheuristic–PSO

Abstract In the context of evolving energy needs and environmental concerns, efficient management of distributed energy resources within microgrids has gained prominence. This paper addresses the optimization of power flow management in a hybrid AC/DC microgrid through an energy management system driven by particle swarm optimization. Unlike traditional approaches that focus solely on active power distribution, our energy management system optimizes both active and reactive power allocation among sources. By leveraging 24-hour-ahead forecasting data encompassing load predictions, tariff rates and weather conditions, our strategy ensures an economically and environmentally optimized microgrid operation. Our proposed energy management system has dual objectives: minimizing costs and reducing greenhouse gas emissions. Through optimized operation of polluting sources and efficient utilization of the energy storage system, our approach achieved significant cost savings of ~15% compared with the genetic algorithm counterpart. This was largely attributed to the streamlined operation of the gas turbine system, which reduced fuel consumption and associated expenses. Moreover, particle swarm optimization maintained the efficiency of the gas turbine by operating at ~80% of its nominal power, effectively lowering greenhouse gas emissions. The effectiveness of our proposed strategy is validated through simulations conducted using the MATLAB® software environment.

Federated double DQN based multi-energy microgrid energy management strategy considering carbon emissions

Multi-energy microgrids (MEMG) play an important role in promoting carbon neutrality and achieving sustainable development. This study investigates an effective energy management strategy (EMS) for MEMG. First, an energy management system model that allows for intra-microgrid energy conversion is developed, and the corresponding Markov decision process (MDP) problem is formulated. Subsequently, an improved double deep Q network (iDDQN) algorithm is proposed to enhance the exploration ability by modifying the calculation of the Q value, and a prioritized experience replay (PER) is introduced into the iDDQN to improve the training speed and effectiveness. Finally, taking advantage of the federated learning (FL) and iDDQN algorithms, a federated iDDQN is proposed to design an MEMG energy management strategy to enable each microgrid to share its experiences in the form of local neural network (NN) parameters with the federation layer, thus ensuring the privacy and security of data. The simulation results validate the superior performance of the proposed energy management strategy in minimizing the economic costs of the MEMG while reducing CO2 emissions and protecting data privacy.

Practical prototype for energy management system in smart microgrid considering uncertainties and energy theft

The conventional electrical grid faces significant issues, which this paper aims to address one of most of them using a proposed prototype of a smart microgrid energy management system. In addition to relying too heavily on fossil fuels, electricity theft is another great issue. The proposed energy management system can simultaneously detect electricity theft and implement demand response tactics by employing time-of-use pricing principles and comparing real electricity consumption with grid data. The system uses the Al-Biruni earth radius (BER) optimization algorithm to make smart choices about how to distribute the load, intending to reduce energy consumption and costs without sacrificing comfort. As a bonus, it considers limitations imposed by battery charging/discharging and decentralized power generation. Incorporating sensors and SCADA-based monitoring, the system provides accurate measurement and management of energy usage through load monitoring and control. An intuitive mobile app also helps consumers connect, allowing for more active participation and better control over energy use. Extensive field testing of the prototype shows that by moving loads from peak period to another off-peak period, electricity expenditures can be reduced by up to 48.45%. The energy theft value was calculated to be 1199 W, proving that the system's theft detection model was effective.

Energy Management System for Smart Grid in the Presence of Energy Storage and Photovoltaic Systems

Today, the desire to use renewable energy as a source of clean and available energy in the grid has increased. Due to the unpredictable behavior of renewable resources, it is necessary to use energy storage resources in the microgrid structure. The power generation source and the storage source in microgrids should be selected in such a way that it has the ability to respond to the maximum demand in the state connected to the grid and operate independently. In this article, the optimal capacity and economic performance of a microgrid based on photovoltaic and battery system have been investigated. In this way, first, using the iterative optimization method, the optimal microgrid capacity has been obtained. Then, the dynamic planning method has been used for optimal microgrid energy management. The simulation results show the accuracy and efficiency of the proposed solutions. The proposed controller, while automatically and dynamically adapting to the solar cell output changes, is capable of responding to external requests, such as price signals or satisfying power system constraints or operator requests. In addition, the results indicate that by using the proposed energy management system, the microgrid system can regain stability during one to two cycles, during the occurrence of PV system radiation changes as well as ESS charge changes. And also, according to the ESS charge changes, the voltage changes should be within the defined permissible range between 0.95 and 1.05 pu, which is the result of the unique efficiency of the proposed energy management system.

Hybrid energy storage system and management strategy for motor drive with high torque overload

The demand for small-size motors with large output torque in fields such as mobile robotics is increasing, necessitating mobile power systems with greater output power and current within a specific volume and weight. However, conventional mobile power sources like lithium batteries face challenges in surpassing the dual limitations of weight and output power due to constraints imposed by materials and other factors. Therefore, this paper references the approach of high-power hybrid energy systems in automobiles and proposes a battery–supercapacitor hybrid energy storage system (BSHESS) and energy management strategy. The motor is powered by the battery during low torque operating conditions, while the additional output power of the battery is used to charge the supercapacitor. In cases of torque overload, the rapid discharge of the supercapacitor provides the motor with a high current, ensuring instantaneous high output power. Furthermore, the proposed energy management strategy is used to control the charging and discharging processes of the supercapacitor, guaranteeing that the charging process of the supercapacitor does not interfere with the battery’s power supply to the motor, as well as maintaining controllability and stability of the current in the discharge process. The feasibility of the principle is verified through simulations, and we also design a complete prototype of the proposed BSHESS and conduct experiments on the motor. The results demonstrate that the maximum output current to the motor is increased by 150% compared to the original level, and the weight is reduced by 64.7% compared to a pure battery-powered system with same maximum current output. Additionally, the energy management strategy enables a more stable charging and discharging process compared to the unmanaged state.

Energy management and performance analysis of an off-grid integrated hydrogen energy utilization system

In integrated hydrogen energy utilization systems, due to the low efficiency of hydrogen/electricity conversion, coordination of energy management and efficient waste heat recovery is required to optimize performance. To address this challenge, this paper presents a comprehensive and sophisticated modeling and energy management strategy to enhance the off-grid energy utilization rate while prolonging the main components’ lifetime. The developed model incorporates multiphase flow and heat transport balance for electricity and heat production, enabling a highly accurate representation of real-world behaviors of the system. The proposed off-grid operation strategy is complemented by a designed heat recovery scheme, ensuring the use of energy resources and waste heat. In addition, the proposed energy management strategy monitors the real-time status of each subsystem, actively reducing the number of harmful start-stop cycles of the hydrogen production system, thereby mitigating short-term power impacts and delaying its aging. Specifically, the voltage degradation of the reduction cell is reduced from 4.67 mV to 4.48 mV, the energy utilization rate is increased from 47.6 % to 53.9 %, and the energy efficiency of fuel cells significantly increases from 53.6 % to 78.1 %.

Stochastic management of electric vehicles in an intelligent parking lot in the presence of hydrogen storage system and renewable resources

The paper emphasizes the significance of sustainable energy solutions centered around electric vehicles (EVs). This involves Electric Intelligent Parking Lots (IPLs) that are interconnected with Renewable Energy Sources (RES) and Hydrogen Storage Systems (HSS) to achieve both technical and environmental goals. The study introduces a probabilistic approach to managing HSS-based energy in IPLs, employing the Probabilistic Two-Point Estimate Method (TPEM) to consider variables like sun radiation, temperature, wind speed, and IPL load. The Honey Badger Algorithm (HBA) is employed for optimization, striving to minimize operational costs related to energy distribution while maximizing profits by exploring revenue opportunities within the IPL system. This strategy enhances energy management and intelligent EV charging in IPLs, improving efficiency and economic viability. The approach is tested in a standard IPL environment integrated with RES and load demand, showcasing its successful technical and financial outcomes. Results reveal a 7.8 % profit increase from renewable resources and an additional 4.89 % when uncertainties are factored in. Ultimately, the proposed energy management framework utilizing HSS and RES integration proves effective in achieving objectives, with the potential for greater profitability through renewable resource incorporation and uncertainty consideration.

Semisupervised Learning-Based Occupancy Estimation for Real-Time Energy Management Using Ambient Data

Occupancy status information is essential for efficient energy management of deferrable and flexible electricity loads in both residential and commercial sectors. Motivated by the hardness to collect ground-truth occupancy data, we propose a new, semi-supervised learning based occupancy estimator, the Label-expanded Time-series Propensity Weighted Estimator (LTPWE), to improve the prediction accuracy using privacy-preserving ambient sensing data (in temperature, humidity, light, etc.), especially when the labelling frequency (the ratio of the labeled positive instances) is low. The proposed energy management scheme integrates the LTPWE occupancy estimator into a data-driven deep reinforcement learning algorithm, the Soft Actor Critic (SAC), to make real-time scheduling decisions without any prior knowledge on the dynamics of random renewable generation and electricity price. Simulation results on real-world datasets show that compared with multiple state-of-the-art baselines, the proposed energy management scheme can reduce the energy cost by 18.79-55.79% without sacrificing occupants’ thermal comfort.

Selection of power sharing factor for hybrid battery/ultracapacitor energy storage‐based EV through load emulation technique

AbstractThe hybrid battery/ultracapacitor (UC) energy storage system for electric vehicles (EVs) proved more reliable and cost‐effective. Even with the best possible sizing of these energy storage devices, unforeseen EV loading cycles are causing a single‐source transition. Mainly, the UC exhaustion in acceleration or transient loading shifts the loading to the battery, causing overdischarge and reducing the life span. This paper presents a deterministic current control algorithm to restrict the maximum allowable battery discharge current. The current discharge control in the battery/UC is implemented using symmetrical carrier‐based digital average current mode (DACM). The proposed energy management algorithm (EMA) with variable battery current sharing factor typically controls the current flow between the battery and the UC so that the battery current is always within safe limits. The DC‐DC converter with proposed novel EMA allows the system to regulate the voltage and current flow between the two power sources. By sharing the currents in this way and limiting the battery current to a safe value, the system helps to prolong the battery's life and ensures that the vehicle operates safely and reliably over the long term. The EV load profile emulator provides the current sharing under dynamic operating conditions. The hardware results are supported to validate the single‐source transition under hybrid energy sources.

A Novel Hybrid Imperialist Competitive Algorithm–Particle Swarm Optimization Metaheuristic Optimization Algorithm for Cost-Effective Energy Management in Multi-Source Residential Microgrids

The integration of renewable sources and energy storage in residential microgrids offers energy efficiency and emission reduction potential. Effective energy management is vital for optimizing resources and lowering costs. In this paper, we propose a novel approach, combining the imperialist competitive algorithm (ICA) with particle swarm optimization (PSO) as ICA-PSO to enhance energy management. The proposed energy management system operates in an offline mode, anticipating data for the upcoming 24 h, including consumption predictions, tariff rates, and meteorological data. This anticipatory approach facilitates optimal power distribution among the various connected sources within the microgrid. The performance of the proposed hybrid ICA-PSO algorithm is evaluated by comparing it with three selected benchmark algorithms, namely the genetic algorithm (GA), ICA, and PSO. This comparison aims to assess the effectiveness of the ICA-PSO algorithm in optimizing energy management in multi-source residential microgrids. The simulation results, obtained using Matlab 2023a, provide clear evidence of the effectiveness of the hybrid ICA-PSO algorithm in achieving optimal power flows and delivering substantial cost savings. The hybrid algorithm outperforms the benchmark algorithms with cost reductions of 4.47%, 14.93%, and 26% compared to ICA, PSO, and GA, respectively. Furthermore, it achieves a remarkable participation rate of 50.6% for renewable resources in the energy mix, surpassing the participation levels of the ICA (42.88%), PSO (40.51%), and GA (38.95%). This research contributes to the advancement of power flow management techniques in the context of multi-source residential microgrids, paving the way for further research and development in this field.

Energy Management of a Photovoltaic System with Hybrid Energy Storage Battery-Super capacitor

This paper describes a method for regulating the voltage of a DC bus of the hybrid power system pv/wind associated with storage devices. A hybrid energy storage system (HESS) that combines batteries and super capacitors (SCs) is an interesting solution. The batteries are employed to meet long-term energy requirements, while the using of SCs, to meet immediately the demand for instantaneous power. In this paper, we propose a new management strategy that manages energy flows between storage devices, by maintaining the SOC of super capacitor and the SOC of the batteries at acceptable levels and to reduce stress on batteries and improve their life cycle. the simulation results demonstrate the efficiency of the proposed energy management strategy for the sudden change in power generation and load demand.

Evaluation of technical and financial benefits of battery energy storage system control strategies

The recent increase in renewable energy generation can balance consumption and reduce carbon emissions. With battery energy storage optimizing supply and demand, it is more important than ever to manage charge control to the benefit of all stakeholders. In this paper, the developed and proposed energy management control methods based on the technical operating criteria of battery energy storage (BESS) and considering self-consumption rate (SCR), self-supply rate (SSR) and curtailment rate are compared in terms of environmental index and economics for daily and annual demand profiles for various household prosumer demand profiles in Istanbul and Antalya. Considering the supply-demand matching based on demand profile, feed-in damping, fixed feed-in, schedule mode, schedule mode with constant charging power and self-consumption control methods are proposed for optimum operation for each prosumer profile. The results show that feed-in damping and fixed feed-in methods can reduce household prosumer costs by up to 22.3% in the daily analysis. Moreover, similar control methods can increase SCR by up to 29.5% and reduce costs by up to 10.62% for higher irradiances in the annual analysis. Proper management of BESS charge control can facilitate sustainable development goals by assisting plans of many stakeholders.