Real-time Energy Management System Research Articles

Optimization Strategies for Real-time Energy Management of Electric Vehicles Based on LSTM Network Learning

The orderly control of electric vehicle load can improve the load characteristics of regional power grid and reduce the charging cost. Since it is impossible to predict the accurate access time and charging demand of electric vehicles in the future, it is impossible to make a global optimal arrangement for accessing the grid when electric vehicles are charging. Aiming at this problem, a real-time energy management system and optimization strategy of electric vehicle based on deep long-term and short-term memory neural network are proposed. Firstly, a three-tier electric vehicle management architecture including power grid layer, regional energy management system and charging station energy management system is constructed to manage large-scale electric vehicles in layers and regions; Then, a region station interaction strategy based on deep long-term and short-term memory neural network is proposed. The historical optimal solution solved by historical load information is used to train the learning network to guide the new real-time optimization; The proposed strategy can further reduce the charging cost and improve the peak valley characteristics of regional load on the premise of ensuring the charging demand of users. Finally, a simulation example is given to verify the effectiveness and superiority of the proposed layered architecture and management strategy.

A reinforcement learning approach using Markov decision processes for battery energy storage control within a smart contract framework

With the increasing penetration of renewable energy sources (RESs), the necessity for employing smart methods to control and manage energy has become undeniable. This study introduces a real-time energy management system based on a multi-agent system supervised by a smart contract, employing a bottom-up approach for a grid-connected DC micro-grid equipped with solar photovoltaic panels (PV), wind turbines (WT), micro-turbines (MT), and battery energy storage (BES). Each unit is controlled and managed through a distributed decision-making structure. The BES agent is governed by an intelligent structure based on a reinforcement learning model. To facilitate interaction and coordination among agents, a tendering process is employed, where each agent, under its supervised control structure, presents its offer for the tendered item at each time period. The tendering organization allocates demand using the first-price sealed-bid algorithm among bidders to optimize energy cost in the Microgrid. The proposed approach offers a real-time intelligent system capable of ensuring fault tolerance, stability, and reliability in the Microgrid. The main achievement of this study is the development of a robust real-time energy management system that integrates various renewable energy sources and battery storage while ensuring efficient operation and resilience in the face of faults or disruptions.

Enhancing the performance of sustainable energy management of buildings in smart cities

Energy utilization has been the most influential parameter in recent decades, especially in the smart city model. The energy management system has been a more attractive research problem due to its utility, ability, and applications. This paper has an objective that the article discusses innovative energy management methods for sustainability and highlights the potential for integrated smart energy sources. The discussion also touches on the understanding of energy management and production, various storage systems, and their potential future applications. This paper explores challenges in sustainable smart energy management, focusing on methodologies like smart energy systems, PV calculations, electric grid models, and energy management strategies in smart cities. The passive infrared receiver (PIR) sensor has been used in real-time energy management systems to integrate these methodologies into the city's infrastructure. The energy management design aims to coordinate electrical appliances such as fans and lights to minimize energy consumption. The article proposes new energy management and security techniques based on data sources to enhance city intelligence, adaptability, and sustainability by reducing human involvement in controlling electrical appliances in residential buildings. The proposed design and development system optimizes energy utilization more efficiently and effectively than conventional systems, meeting real-time energy management objectives.

Experimental validation of a real-time energy management system using four frequency-based approaches

An innovative approach is introduced in this study for optimizing power distribution within a hybrid energy storage system, which encompasses batteries and supercapacitors. The method involves utilizing an adaptive wavelet technique within the energy management system dedicated to the EV. This technique customizes the wavelet decomposition level based on the supercapacitor's state of charge. As a result, optimal power sharing between the two real sources incorporated in a small-scale EV emulator is achieved. Notably, the approach adjusts the wavelet decomposition level during transient high peaks and when the supercapacitor has high reserves to alleviate battery workload. Through experimental validation and comparative analysis with three other frequency-based techniques, it is demonstrated that the adaptive wavelet control strategy significantly extends battery lifetime. This extension is achieved by reducing the root mean square (RMS) current by 34 % compared to fixed cut-off frequency approaches. Consequently, this minimizes losses and safeguards the battery from high peaks, resulting in a substantial decrease of 44.53 %. These results underscore the substantial potential of the adaptive wavelet approach as a suitable solution for effective energy management in hybrid electric vehicles.

Multi-agent-based real-time operation of microgrids employing plug-in electric vehicles and building prosumers

Real-time operation of microgrids holds significant importance due to its ability to enhance energy resilience and efficiency. Real-time control in conjunction with continuous monitoring and energy supply and demand fluctuations adaptation, ensures a stable and reliable power supply for local communities, even during grid disturbances or outages. Moreover, real-time operation supports demand response mechanisms, enabling users to actively manage their energy consumption and costs. Overall, it plays a pivotal role in modernizing and future-proofing contemporary energy infrastructure, making it more sustainable. In this paper, an efficient, easily applied multi-agent-based real-time energy management and control system for microgrids employing Plug-In Electric Vehicles (PEVs) and building prosumers is developed. The primary goal of this proposed approach is to determine the optimal power set-points for all microgrid components with the objective to reduce the overall daily operation expenses under fluctuating electricity price, while simultaneously satisfying a wide range of constraints. Well-defined flexibilities of all microgrid components to adjust their power are harnessed to execute optimal power dispatch. The implementation of the proposed method resulted in a noteworthy cost reduction of 14.3% when contrasted with a typical operation of the microgrid.

Hierarchical Control of Megawatt-Scale Charging Stations for Electric Trucks With Distributed Energy Resources

Electrifying medium- and heavy-duty trucks is critical to decarbonizing the transportation sector. Energy needs of electric trucks will likely require megawatt-scale charging stations, which could significantly stress the electric distribution grid. Distributed energy resources (DER) can alleviate this stress and reduce charging costs with proper management. To that end, this work develops a hierarchical predictive control algorithm for future multi-port megawatt-scale charging stations that can provide real-time energy management for stations, decide charging rates, dispatch energy storage system (ESS), and provide grid voltage support. We integrate three algorithmic components: (i) an energy management optimization (EMO) that provides supervisory control to DER assets and charging loads at minute scale, (ii) a real-time energy management system (RT-EMS) that heuristically compensates for fast disturbances at sub-second scale, and (iii) a model predictive control (MPC)-based battery management system (BMS) that communicates future charging demands to the EMO, to manage the overall megawatt-scale site. Validation in a controller hardware-in-the-loop (CHIL) environment shows that the hierarchical controller can reduce the total energy consumption from the grid by approximately 28% compared to an uncontrolled case for the station configuration in this paper, without impacting charging time.

Empirical Validation of Fuzzy Logic Based Predictive Load Scheduling in Mimic Home Energy Management System

<p>Load scheduling plays a vital role in the home energy management systems. The main objective of this load scheduling is to balance the power demand and supply power without degrading the performance of the loads and consumers tolerance. Though many research works concentrate on load scheduling, very few works concentrated on real time scenario. On the other hand, research work concentrated on optimal load scheduling through fuzzy logic requires incorporation of fuzzy based system in either simulated or real-time home energy management system. Hence, the proposal aims to schedule the loads in a simulated home energy management system through fuzzy logic controller using MATLAB Simscape with required subsystems. The proposed simulated environment considers four different resistive loads. Intelligent scheduling is aimed to achieve efficient load scheduling. A fuzzy controller has three inputs namely integrated source, state of charge of battery, and power demand whereas probability of scheduling is considered as output. The efficiency of the proposed fuzzy-based load scheduling scheme is evaluated under various load conditions for different sub-systems with varying input power. The results exhibit the efficacy of the proposed scheme.</p> <p> </p>

Bi-level power management strategies optimization for multi-stack fuel cell system-battery hybrid power systems

A bi-level multi-mode power management strategy (PMS) is proposed in this work to improve the efficiency, remaining useful life (RUL), life-cycle cost (LCC) of multi-stack fuel cell system-battery hybrid power systems (MHPSs). In the first level PMS, the output power allocated between the multi-stack fuel cell system (MFCS) and the battery is determined by smoothing the MHPS power demand. The smoothing effects of different MHPS power demands smoothing algorithms are analyzed. In the second level PMS, the multi-mode MFCS PMS is investigated. The second level PMS is validated through system efficiency and hydrogen consumption simulation in a specific application scenario. As a result, the proposed second level PMS could have lower hydrogen usage costs and higher efficiency than the equal allocation, daisy chain, and adaptive allocation PMSs. The proposed MHPS bi-level PMS can provide recommendations for the future MHPS advanced and efficient real-time energy management system design.

Powering Efficiency: Exploring Artificial Intelligence for Real-time Energy Management in Buildings

This paper emphasizes the need for efficient energy consumption in buildings due to the increase in pollution and economic growth, which has led to an increase in energy consumption worldwide. Therefore, a real-time energy management system is needed to overcome the deficiency of energy consumption and improve energy efficiency. Further to adopt modern architecture, we introduce artificial intelligence; to identify the factors involved in optimizing energy consumption in buildings is an important factor. The paper also suggests different machine learning (ML) based algorithms for data cleaning, processing, and analysis. This includes different studies that used AI-based techniques for real-time energy management systems, including reinforcement learning, rule-based approach, and mixed integer linear programming, to reduce energy consumption by 20%-30%. The use of AI in energy management in buildings holds great potential for world’s scientific community. This technology enables data-driven decision-making, fosters energy conservation, and promotes advancements in the field of energy science, contributing to a greener and more sustainable future. The paper concludes that the use of AI-based approaches for energy-efficient systems can predict future energy demands by using previous data and building characteristics, making it more efficient than previous monitoring and alert systems.

Optimized Energy Management Control of a Hybrid Electric Locomotive

Hybrid electric propulsion, using batteries for energy storage, is making significant inroads into railway transportation because of its potential for notable fuel savings and the related reductions in greenhouse gases emissions of hybrid railway traction over non-electrified railway lines. Due to the inherent complexity of hybridized powertrains, combining different power conversions and energy storage capabilities, the corresponding operation of their energy management needs to be precisely optimized in order to achieve the minimum possible fuel consumption. Having this in mind, this paper proposes a real-time energy management control strategy for a diesel–electric hybrid locomotive based on the optimization results obtained by means of a dynamic programming optimization algorithm aimed at fuel consumption minimization while honoring the battery state-of-charge constraints and powertrain physical constraints. The final optimization result, expressed in terms of the optimal battery state-of-charge reference (target), is used as an additional input into the state-of-charge controller within the real-time energy management system. The subsequent simulation analysis shows clear fuel economy improvement with 22.9% of fuel savings obtained for the locomotive featuring a hybrid powertrain equipped with batteries over the conventional one.

Energy Management System for Microgrid System using Improved Grey Wolf Optimization Algorithm

An Energy Management System (EMS) is indispensable to monitor the power flow and load matching inside a microgrid during grid-connected mode (GCM) and islanded modes (IM) of operation. Many conventional optimization algorithms show poor reliability for real time optimization problem solving where an objective function is non-linear. An optimization technique is necessary to reduce the cost of energy obtained from the grid, generated inside the grid, and consumed by the load. This article presents, an optimization scheme based on the improved Grey wolf optimization (GWO) algorithm that considers replacement of wounded/injured wolves of one pack by strong wolves of other pack for an EMS in micro-grid. The GWO optimization algorithm's effectiveness is demonstrated forGCM and IM operation. The proposed GWO shows fast, lost cost and precise optimization of the real time EMS for the grid connected and islanded micro-grid system.

Energy sustainability performance of a sliding-cover solar greenhouse: Captured energy management aspects

The utilization of solar energy as the unique source of green heat, during the cold period by solar greenhouses, is a crucial sustainability concern for off-season vegetables. This research effort serves to promote the modernization of the Solar Greenhouse industry, which is heavily practiced in northern countries. The heat collection and thermal performance of the harvested energy with the Water-cycling System (SWS) is analyzed and validated. The derivation of the heat storage/release experimental model was based on the diurnal water temperature cycle in the heat storage device. The energy cycle is based on the energy captured at the daytime and released at nighttime in the Sliding-cover Energy-saving solar Greenhouse (SEG), resulting in crop temperature surpassing a conventional Chinese Solar Greenhouse by 3℃. This is critical for a full production loss, at very low-temperature nights, appearing after sunny clear-sky cold winter days. The resulting energy model will be used by a Solar Greenhouse Designer program for the optimal design of Solar Greenhouses based on the locality climate and the targeted production facility to realize the smart specialization of climate zones. Further, a proactive, real-time energy management system will increase Production and Sustainability performance by maximizing energetic bio-efficiency.

Experimental validation of an AI-embedded FPGA-based Real-Time smart energy management system using Multi-Objective Reptile search algorithm and gorilla troops optimizer

This paper proposes an AI-embedded FPGA-based Smart Energy Management System (SEMS) that ensures intelligent, secure, consistent, and synchronous energy management in an isolated microgrid. The proposed techno-economic SEMS comprises two levels of control to achieve optimal management and operation for an isolated microgrid. The first level adopts the use of the FPGA as a central controller, which is characterized by its high processing speed and small settling time. The second level aims to develop a coordinated operation strategy based on the optimal operation and management of an isolated microgrid in order to optimize the coordinated use of backup sources. An efficient multi-objective optimization problem for optimal operation and management of the microgrid is formulated. Two multi-objective optimization algorithms namely, Gorilla Troops Optimizer (GTO) and Reptile Search Algorithm (RSA) are applied to solve the optimization problem. The three main objectives considered in this study are to minimize the operating costs, the loss of power supply probability (LPSP), and the surplus power consumed by the dummy load. The results prove the superiority of the RSA algorithm in achieving the goals of the objective functions. Within 100 min of the experimental testing, it achieves the lowest operating cost 166.2423 $. The cost savings reach about 6.467 % when using the RSA, while it is 6.0363 % when using the GTO. The developed SEMS reduces the wasted power in the dummy load. In addition, it achieves the lowest value of LPSP about zero, which is considered the best value as it ensures continuous supply.

Real-time energy management in an off-grid smart home: Flexible demand side control with electric vehicle and green hydrogen production

A real-time energy management system for an off-grid smart home is presented in this paper. The primary energy sources for the system are wind turbine and photovoltaics, with a fuel cell serving as a supporting energy source. Surplus power is used to generate hydrogen through an electrolyzer. Data on renewable energy and load demand is gathered from a real smart home located in the Yildiz Technical University Smart Home Laboratory. The aim of the study is to reduce hydrogen consumption and effectively utilize surplus renewable energy by managing controllable loads with fuzzy logic controller, all while maintaining the user's comfort level. Load shifting and tuning are used to increase the demand supplied by renewable energy sources by 10.8% and 13.65% from wind turbines and photovoltaics, respectively. As a result, annual hydrogen consumption is reduced by 7.03%, and the average annual efficiency of the fuel cell increases by 4.6%

Real-Time Economic Dispatch of CHP Systems with Battery Energy Storage for Behind-the-Meter Applications

The use of combined heat and power (CHP) systems has recently increased due to their high combined efficiency and low emissions. Using CHP systems in behind-the-meter applications, however, can introduce some challenges. Firstly, the CHP system must operate in load-following mode to prevent power export to the grid. Secondly, if the load drops below a predefined threshold, the engine will operate at a lower temperature and hence lower efficiency, as the fuel is only half-burnt, creating significant emissions. The aforementioned issues may be solved by combining CHP with a battery energy storage system (BESS); however, the dispatch of CHP and BESS must be optimised. Offline optimisation methods based on load prediction will not prevent power export to the grid due to prediction errors. Therefore, this paper proposes a real-time Energy Management System (EMS) using a combination of Long Short-Term Memory (LSTM) neural networks, Mixed Integer Linear Programming (MILP), and Receding Horizon (RH) control strategy. The RH control strategy is suggested to reduce the impact of prediction errors and enable real-time implementation of the EMS exploiting actual generation and demand data on the day. Simulation results show that the proposed method can prevent power export to the grid and reduce the operational cost by 8.75% compared to the offline method.

Full-deployed energy management system tested in a microgrid cluster

Under a hierarchical structure perspective, the integration of tools like the internet of things, cloud computing, and machine learning into a microgrid real-time energy management system involves superior capabilities like an autonomous and scalable design, massive storage capabilities, real-time information analysis and processing, and security issues control, to mention a few. This paper evaluates most of them using a cloud-based real-time energy management system integrated into a real-life hardware-in-the-loop testbed. The proposed cloud-based system is tested by solving an economic power dispatch problem including the equalization of the multiple battery-based energy storage systems interacting within a multi-microgrid environment. The test assessment combined reviewing and running microgrid models, incorporating these models into a real-life power-hardware-in-the-loop unit, linking the testbed to a cloud server, and merging the energy management system with on-demand computing tools, primarily machine learning and the internet of things. As established by the experimental evidence, this paper cites the benefits of combining machine learning techniques and internet of things tools with a scalable and autonomous real-life cloud-based energy management system architecture to improve the framework's functionality, enhance the energy forecasting for generation and usage, and cut down the price paid to the service provider.

Mixed-Integer Real-Time Control of a Building Energy Supply System

We present a methodology based on mixed-integer nonlinear model predictive control for a real-time building energy management system in application to a single-family house with a combined heat and power (CHP) unit. The developed strategy successfully deals with the switching behavior of the system components as well as minimum admissible operating time constraints by use of a special switch-cost-aware rounding procedure. The quality of the presented solution is evaluated in comparison to the globally optimal dynamic programming method and conventional rule-based control strategy. Based on a real-world scenario, we show that our approach is more than real-time capable while maintaining high correspondence with the globally optimal solution. We achieve an average optimality gap of 2.5% compared to 20% for a conventional control approach, and are faster and more scalable than a dynamic programming approach.

A distributed real-time energy management system for inverter-based microgrids

A novel distributed real-time energy management strategy for inverter-based microgrids based on dynamic algorithms with a low computational burden and without the requirement of offline forecast or a central optimizer is presented in this paper. A dynamic economic dispatch problem is solved while a stability performance is guaranteed. The algorithm is able to dynamically adjust the power references under sudden load changes, generator disconnection, and communication failures. In steady-state, the proposed real-time energy management strategy guarantees optimality conditions and frequency regulation. Finally, the effectiveness of the proposed strategy and its compatibility with the conventional proportional-resonant inner controllers and primary droop controllers are validated in experiments. • An experimental setup of a distributed real-time energy management for microgrids. • Stability and optimal power tracking are guaranteed under several failure scenarios. • Compatibility with the proportional-resonant and droop controllers are validated.

Assessment of supercapacitor performance in a hybrid energy storage system with an EMS based on the discrete wavelet transform

When battery and supercapacitor (SC) Energy Storage Systems (ESSs) coexist in electric vehicles, energy management is imperative to ensure efficient power distribution based on the strengths and weaknesses of each ESS. The decoupling of highly dynamic power demands into components that match the dynamic nature of each ESS is essential. The Discrete Wavelet Transform (DWT) has been widely recommended for this purpose as part of real time energy management systems. However, due to DWT signal processing, delays in the frequency components can undermine the benefits of hybridization. This paper analyses the contribution of the SC to alleviate the battery when the DWT is used with and without time delay compensation using future demand prediction. Four different implementation strategies for a DWT based EMS have been evaluated using different metrics to quantify energy circulation and SC assistance during acceleration and braking. Simulation results using urban and highway driving cycles, show that obtaining the SC current reference as the difference between the real time current demand and the DWT low frequency component enhances SC assistance during acceleration and braking at the expense of higher energy circulation. The complexity added by future demand prediction does not reap SC performance benefits.

Optimization strategies for real-time energy management of electric vehicles based on LSTM network learning

The orderly control of electric vehicle load can improve the load characteristics of regional power grid and reduce the charging cost. Since it is impossible to predict the accurate access time and charging demand of electric vehicles in the future, it is impossible to make a global optimal arrangement for accessing the grid when electric vehicles are charging. Aiming at this problem, a real-time energy management system and optimization strategy of electric vehicle based on deep long-term and short-term memory neural network are proposed. Firstly, a three-tier electric vehicle management architecture including power grid layer, regional energy management system and charging station energy management system is constructed to manage large-scale electric vehicles in layers and regions; Then, a region station interaction strategy based on deep long-term and short-term memory neural network is proposed. The historical optimal solution solved by historical load information is used to train the learning network to guide the new real-time optimization; The proposed strategy can further reduce the charging cost and improve the peak valley characteristics of regional load on the premise of ensuring the charging demand of users. Finally, a simulation example is given to verify the effectiveness and superiority of the proposed layered architecture and management strategy.