Energy Management Algorithm Research Articles

Utilizing Hybrid Sine Cosine Shuffled Frog Leaping Algorithm for Optimal Energy Management in the Residential building with Renewable Energy Resources and Corresponding Uncertainties

Utilizing Hybrid Sine Cosine Shuffled Frog Leaping Algorithm for Optimal Energy Management in the Residential building with Renewable Energy Resources and Corresponding Uncertainties

Energy Management for Hybrid Electric Vehicles Using Safe Hybrid-Action Reinforcement Learning

Reinforcement learning has shown success in solving complex control problems, yet safety remains paramount in engineering applications like energy management systems (EMS), particularly in hybrid electric vehicles (HEVs). An effective EMS is crucial for coordinating power flow while ensuring safety, such as maintaining the battery state of charge within safe limits, which presents a challenging task. Traditional reinforcement learning struggles with safety constraints, and the penalty method often leads to suboptimal performance. This study introduces Lagrangian-based parameterized soft actor–critic (PASACLag), a novel safe hybrid-action reinforcement learning algorithm for HEV energy management. PASACLag utilizes a unique composite action representation to handle continuous actions (e.g., engine torque) and discrete actions (e.g., gear shift and clutch engagement) concurrently. It integrates a Lagrangian method to separately address control objectives and constraints, simplifying the reward function and enhancing safety. We evaluate PASACLag’s performance using the World Harmonized Vehicle Cycle (901 s), with a generalization analysis of four different cycles. The results indicate that PASACLag achieves a less than 10% increase in fuel consumption compared to dynamic programming. Moreover, PASACLag surpasses PASAC, an unsafe counterpart using penalty methods, in fuel economy and constraint satisfaction metrics during generalization. These findings highlight PASACLag’s effectiveness in acquiring complex EMS for control within a hybrid action space while prioritizing safety.

THE PARTICIPATION OF RESIDENTIAL CONSUMERS IN ENERGY MARKETS THROUGH DEMAND RESPONSE

Abstract. The article considers the approach to the interaction of the transmission system operator with consumers - the demand management mechanism, as well as its role and place in the energy markets. The tools and experience of implementation of demand management are described. With the help of a natural experiment, the possibility and effectiveness of the participation of consumers with household storage hot water boilers in the balancing market was evaluated. Optimizing the participation of large numbers of consumers in energy markets is a challenging problem, especially for portfolios with thousands or millions of flexible resources. One of the aggregator's tasks is to transform the functionality of automation technologies, such as a consumer's "smart" home, into products that could be traded on energy markets. The task of optimization consists in the effective and timely management of a large number of flexible resources. A key feature of demand management is the sale of managed load on a par with generating capacity. This is explained by the fact that, from the point of view of the balance, in the energy system, one kWh not consumed equals one kWh produced. As a result, the financial benefits of managing consumer electricity demand are equivalent to the prices of balancing services and the provision of capacity reserves from other market participants. The sale of a demand-side management resource can be implemented through balancing market (BM) and ancillary service market (SMS) instruments, which use TSOs to balance the power system. Attracting additional participants in RDP and BR should stimulate competition and allow TSOs to meet their needs for auxiliary and balancing services, which will positively affect the reliability of the energy system and increase competition. In general, the level of provision of the power system with reserves depends on a wide range of factors, including: different hours of the day, weather conditions or trading strategies of market participants, etc. The optimal way to involve household consumers in responding to demand is to use the services of aggregators. But this does not mean the simple accumulation of a certain resulting power of consumers. The quantitative and qualitative composition of the aggregator's portfolio should ensure the execution of OSP commands in full, even in conditions of unavailability of part of the boilers or other aggregated units. For this, it is necessary to have a certain reserve of regulating power, for example, other boilers or energy storage units for the possibility of their prompt replacement (reconfiguration) within the portfolio. Demand management in the power system can effectively reduce the peak load of the system and delay the necessary capital investment in additional generating capacity and transmission lines. In addition, demand management facilitates the integration of renewable energy sources and reduces the costs of setting up, starting or shutting down thermal power units during peak load periods. Consumer participation in demand management requires bidirectional communication infrastructure, advanced metering, efficient economic tariffs and energy management algorithms. With the rise of smart grid technologies and automated demand response systems, demand management systems are a key element expected to provide a cost-effective alternative to traditional generation-side solutions to meet increasing demand for electricity during peak load or high prices. Demand management competes with auxiliary services provided by "traditional" providers - power plants and is used by TSOs to stabilize UES parameters when the power grid faces unforeseen situations, accordingly, the development of this sector is an important component of energy security.

Artificial Neural Network (ANN) Method for the Integration of Solar and Wind Hybrid Energy Sources into Telecommunication Systems

In order to sustain monetary growth, the introduction of renewable energy into the electricity grid is crucial especially for many foreign African locations. Thus, in order to reap sustainable strength, these foreign locations may also outfit their airport electrical equipment with advanced synthetic intelligence technologies. For a distributive hybrid solar strength grid, the paper attempts to propose an actual-time energy management algorithm. It continues with the combining of photovoltaic and wind energy for network simulation. As a function of the number of wind aero-mills and photovoltaic solar panels, a multi-goal approach is proposed to optimize the spectral efficiency of the location and the energy performance. For the MATLAB software simulation, radio criteria for Cell Wireless Interoperability Medium Access (WiMAX) technologies are taken into account. The obtained effects are much mitigated however theoretically encouraging for the mixing of green energy integration into the modern telecommunication structures

Robust Control System for DFIG-Based WECS and Energy Storage in reel Wind Conditions

This research work focuses on addressing the challenges of controlling a wind energy conversion system (WECS) connected to the grid, particularly when faced with variable wind speed profiles. The system consists of a Doubly-Fed Induction Generator (DFIG) connected to the grid through an AC/DC/AC converter, along with a Li-ion battery storage system connected to the Back-to-Back converter DC link via a DC/DC converter. The non-linearity and internal parametric variation of the wind turbine can negatively impact energy production, battery charging performance, and battery lifespan. To overcome these issues, the study proposes a robust control approach called Integral action Sliding Mode Control (ISMC) to enhance the dynamic performance of the WECS based on DFIG. Additionally, the battery charging and discharging controllers play a crucial role in efficiently distributing power to the grid and storage unit based on the battery's state of charge, extracted energy, and power injected into the grid. Two current regulation modes, buck charging and boost discharging, are employed to ensure proper energy distribution. Furthermore, a storage system energy management algorithm is implemented to ensure battery safety during one of the charging modes. The effectiveness and robustness of the proposed control method were validated through simulations of a 1.5 MW wind power conversion system using Matlab/Simulink. The results confirmed the method's efficiency and efficacy.

AI-IOT-Based Adaptive Control Techniques for Electric Vehicles

The convergence of Artificial Intelligence (AI) and Internet of Things (IoT) technologies has transformed the field of sustainable transportation planning, notably in the context of Electric Vehicles (EVs). The Problems in all the Existing models are not having proper coordination of optimizing the elements of EV functioning. This research proposes a novel strategy to improving sustainable transportation planning by utilizing AI and IoT. AI-powered algorithms analyze real-time data from IoT sensors installed in EVs and the surrounding environment. These adaptive control algorithms are designed to solve issues including range anxiety, charging infrastructure optimization and energy efficiency. Predictive analytics, route optimization, energy management, and grid interface are all part of the proposed system. Energy management algorithms alter EV settings dynamically to maximize efficiency while taking into account real-time traffic conditions thereby increasing the range extension is upto 2.5% and the total energy efficiency is improved upto 92%. Furthermore, bidirectional connection allowed by IoT devices facilitates the integration of EVs into the energy grid. EVs may engage intelligently in Vehicle-to-Grid (V2G) interactions, providing grid services such as energy delivery during peak demand periods and grid stability.

Implementation of battery storage system in a solar PV-based EV charging station

Commercial production of solar-powered battery charging stations for electric vehicles has recently started largely as a result of the growing popularity of electric vehicle (EV) technology as well as the falling cost of photovoltaic (PV) systems. The rise in popularity of EVs may be attributed to both the progression of technology and rising awareness of environmental issues. In this work, a 400V DC bus voltage-based EV charging station is designed which is powered by both a PV system and a utility grid. Also, battery energy storage units are used to overcome the unpredictable behavior of the environment. An Energy management algorithm (EMA) has been presented to balance the power flow among PV, EVs, BESS, grid, and residential load. A sharing coefficient-based power sharing is done between the grid and battery to reduce the stress from the battery units. Then, a multi-step constant current charging method is used to charge the EVs in the charging station to maintain the proper state of charge (SOC) of EV batteries. During this study, different operating conditions are considered according to available PV power and load to validate the power management scheme in the EV charging station. The model is run using MATLAB simulation and opal-RT simulation. The obtained results have been demonstrated with an explanation and system performance verification.

Advancing energy efficiency: Harnessing machine learning for smart grid management

The concept of Smart Grids (SG) has emerged as a solution to address challenges in traditional power systems, including resource inefficiency, reliability issues, and instability. Since its inception in the early 21st century, Smart Grid technology has undergone significant development, integrating advanced information communication and automation technologies with conventional power infrastructure. This integration enhances efficiency, reliability, and sustainability, while enabling the integration of renewable energy sources and optimizing energy distribution and consumption. Machine learning algorithms play a pivotal role in the development of Smart Grids, facilitating energy consumption prediction, optimization, anomaly detection, and fault diagnosis. This paper explores methodologies for developing and improving machine learning algorithms for efficient energy consumption prediction and management within Smart Grids. It discusses the application of deep learning techniques, reinforcement learning, and integration with the Internet of Things (IoT) to enhance energy management systems. The study highlights the potential impact of deep convolutional neural networks (CNNs) on energy consumption regulation and emphasizes the need for further research to address challenges associated with model complexity and data requirements in Smart Grid contexts.

A Comparison of the State-of-the-Art Reinforcement Learning Algorithms for Health-Aware Energy and Emissions Management in Zero-Emission Ships

A Comparison of the State-of-the-Art Reinforcement Learning Algorithms for Health-Aware Energy and Emissions Management in Zero-Emission Ships

Optimizing Smart Grids with Advanced AI Algorithms for Real-time Energy Management

Using optimization techniques based on neural networks, this study explores how microgrids might integrate renewable energy sources. Dealing with problems caused by the uncertainty and unpredictability of renewable energy generation is the primary goal. Renewable energy generation has been showing encouraging trends, according to data analysis spanning many time periods. From 120 kWh to 140 kWh, there was a steady rise of 16.67% in solar energy utilization. Also, there was an 18.75% rise, from 80 kWh to 95 kWh, in the use of wind power. There was a 30% rise, from 50 kWh to 65 kWh, in the output of biomass energy. Microgrid load utilization analysis shows rising energy demands in commercial, industrial, and residential areas. Commercial and industrial loads climbed by 15% and 10%, respectively, while residential energy use increased by 10%, from 150 kWh to 165 kWh. With solar predictions at 98.4%, wind predictions at 95.5%, and biomass predictions at 97.3%, predictions made using neural networks were highly congruent with actual output of renewable energy.

A novel reinforcement learning based routing algorithm for energy management in networks

A novel reinforcement learning based routing algorithm for energy management in networks

Efficiency Optimization and Power Flow Control in a Wind Energy Conversion System with Storage via Vienna rectifier

The study addresses efficiency enhancement and power flow control in a wind energy conversion system. This system comprises a Permanant Magnet Synchronous Generator (PMSM) driven by a wind turbine, Vienna rectifier, Li-ion battery, and DC load. Fluctuations in wind and energy demand impact battery life and state of health (SOH). To mitigate this, a nonlinear controller regulates current for optimal battery charging. Three operating modes, including MPPT, Constant Current (CC) charging, and Constant Voltage (CV) charging, are considered. An energy management algorithm facilitates smooth switching between controllers. The perfomances are evaluated using MATLAB/SIMULINK environment.

РАЗРАБОТКА И ОПТИМИЗАЦИЯ ЭНЕРГОСБЕРЕГАЮЩИХ СХЕМ ДЛЯ ПОРТАТИВНЫХ ЭЛЕКТРОННЫХ УСТРОЙСТВ

The article discusses modern approaches to the development and optimization of energy-saving circuits for portable electronic devices. The main focus is on reducing energy consumption by using low-power modes of component operation, optimizing the power supply circuit and implementing energy management algorithms at the system level. An analysis of the effectiveness of the proposed solutions is provided using specific devices as an example, with an assessment of their impact on performance and battery life. The results show a significant reduction in power consumption without compromising performance, which confirms the promise of the proposed approaches.

Intelligent Renewable Energy Source Allocation Scheme for Internet of Things Enabled PHEVs Systems

Plug-in hybrid electric vehicles (PHEVs) have received a lot of interest because of their ability to cut fuel usage by using electricity from the grid as an alternative energy source. PHEVs differ from typical hybrid electric vehicles (HEVs) in terms of increased battery capacity, the availability of plug-in recharging, and improved battery state of charge (SOC) management systems. Efficient energy consumption and excellent performance are critical issues for hybrid powertrains. The estimation of SOC in PHEVs is a difficult NP-hard problem that is frequently tackled utilising metaheuristic techniques. In this paper, we offer an enhanced dingo optimisation with deep learning-based prediction (EDOA-DLP) model specifically tailored for PHEVs. The EDOA-DLP model includes an efficient SOC estimate algorithm for real-time energy management. The EDOA-DLP technique's performance has been thoroughly proven through considerable experimentation in a variety of circumstances. The results show that the proposed EDOA-DLP method beats other current methods in terms of predicting SOC accurately and reaching the targeted goals for PHEVs. Overall, this research presents a unique EDOA-DLP SOC prediction approach for PHEVs, with promising results in terms of energy management and performance optimisation. The experimental results highlight the EDOA-DLP model's improved performance. Overall, this research presents a unique EDOA-DLP SOC prediction approach for PHEVs, with promising results in terms of energy management and performance optimisation. The experimental results illustrate the EDOA-DLP model's improved performance when compared to competing methodologies, highlighting its potential to improve the efficiency and efficacy of PHEV systems.

Control and Management Approach of Photovoltaic-Battery-Ultra-Capacitor Energy System in Standalone and Grid-Connected Modes

This paper deals with energy management for the photovoltaic-battery-ultra-capacitor energy system for a standalone and grid-connected. The developed energy system can operate in an isolated or connected mode according to the required power. Indeed, the photovoltaic generator is coupled with the DC bus voltage via a DC–DC power converter, to provide the maximum power from the photovoltaic panels. An energy storage system presented by batteries and ultracapacitors is employed to regulate the DC bus voltage through both DC–DC bidirectional power converters. The DC bus is connected to the AC bus through a three-phase power inverter to control the operating modes and ensure the energy demands. In effect, an energy management algorithm is developed to control the energy flow in the system for a standalone and grid-connected. Hence, the output voltage DC bus is controlled by the energy storage system using a Lyapunov approach to ensure high performance under load and irradiance profile variations. In this context, simulations have been carried out to prove the effectiveness of the proposed photovoltaic system. The developed energy system has been tested in standalone and grid-connected modes with the following scenarios: PV generator supplies the load, PV generator power is limited due to less solar lighting, the electric grid supplies the high load power, the surplus energy of the PV generator is injected into the electric grid, and standalone mode operation.

An IoT-fog-cloud consensus-based energy management algorithm of multi-agent smart energy hubs considering packet losses and uncertainty

—As a result of the increasing demand for different energies with technological development, and with the rapid development of energy hubs (EHs), issues such as computation speed, big data and information privacy, robustness, etc. are becoming increasingly vital. Also, the problem of communication packet loss leads to an incompatibility between the generated and consumed energy. In response to the above problems, this paper proposes an Internet of things-Fog-Cloud distributed consensus-based energy management algorithm to optimally solve the energy mismatch problem in an EH environment considering communication information loss and uncertainties of some EH elements. A MATLAB/Simulink-based model of a hypothetical EH system is modified to support real-time communication. Two case studies are applied to explain the performance and effectiveness of the proposed algorithm under different packet loss scenarios. The system's sensitivity was studied depending on the number of iterations and the uncertainties of the renewable energy sources, energy prices, and load demands. Also, a comparison was made between the results obtained by the proposed method and the optimization results using the genetic algorithm and particle swarm optimization techniques. The results prove the applicability and feasibility of the proposed method for the demand management system in EHs. The results show that the proposed algorithm decreases the daily system operating cost from 372.421 to 369.941 $ and the total CO2 emissions cost from 4848.5 to 4103.1 $. In addition, the daily energy mismatch between the generated and consumed values decreases from 579.85 to 0 kWh in the electrical system and from 435.14 to 0.073 kWhth in the heating system. Based on the previous results, the proposed algorithm of EHs contributes significantly to the development of sustainable cities.

A novel distributed primal-dual control algorithm for energy management of DC microgrids considering network constraints

A discrete-time control method is presented for real-time energy management of DC microgrids, where each distributed controller only shares information with its neighbors. Controllers aim to achieve economic dispatch and voltage restoration while maintaining the generator outputs and line currents in their allowable ranges. The proposed control method is developed based on a primal–dual algorithm (PDA) to determine the optimal control variables, in which uncoordinated step-sizes and an adaptive mechanism are introduced to accelerate the algorithm. The convergence analysis is also provided. Finally, numerical tests show the high convergence rate of the algorithm, and the hardware experiments demonstrate the applicability of the proposed control method for real-time energy management.

Optimal battery scheduling in solar-plus-storage grid-connected microgrid for profit and cost efficiency: A use case on an Israeli microgrid

This paper presents an optimal energy management algorithm for solar-plus-storage grid-connected microgrid simulated on a real full-scale small town microgrid test-case, taking into account the daily solar energy generation as well as the electricity demand to ensure that the battery is charged and discharged at the optimal times to balance energy supply and demand. The optimization is performed using dynamic programming and finding the minimum-cost-path, to minimize the total cash-flow. The formulation is utilized with two variations such that two business models are considered, optimizing cost efficiency in both aspects of minimizing cost and maximizing profits, according to the scenario. The first model maximizes self-consumption, and the second model is the case of retail electricity providers. The results are compared to real data from a solar-plus-storage grid-connected microgrid located in Israel, that is currently managed by a rule-based scheduling procedure. The results show that by using the optimal control schedule, the revenue increases up to 8% during the spring and autumn when the weather conditions are typically moderate. In summer and winter, where the climate conditions are more extreme and the demand for energy is at its peak, the full revenue potential can be realized by using the suggested optimal control algorithm, offering an increased profit of up to 30%. Unlike prior studies which are restricted to small use-cases, this paper leverages a unique and private large-scale data-set from a small town, enabling a thorough exploration of the optimization’s real-world viability and scalability. Through rigorous simulations, the findings underscore the method’s exceptional potential in effectively integrating PV-plus-storage assets and optimizing energy use in power grids.

A Stackelberg game-based dynamic pricing and robust optimization strategy for microgrid operations

Energy management algorithms of microgrids have attracted growing attention for the efficient operation and coordination of active end-users. In developing these algorithms, leader–follower game approaches could provide effective strategies when the behavioral and operational characteristics of active end-users are integrated into the methodology. However, since these approaches require the exact implementation of the strategy determined by the leader, it is of great importance to deal with the uncertainty of renewable energy generation, charging/discharging energy of storage systems, and load consumption. Thus, possible negative effects of these uncertainties on the outcome can be minimized with an appropriate billing procedure. In this paper, a Stackelberg game approach is proposed for the energy sharing management of a microgrid including prosumers and plug-in electric vehicle (PEV) charging stations (CSs), and a proper billing scheme is designed to increase the robustness of the approach on real-time applications. In the hereby game-theoretic approach, the energy demands of PEV CSs are determined as variable demands considering the operational characteristics of CSs. The energy planning of CSs is based on determining the number of PEVs that each station can accept over the vehicle charging levels for a specified time interval. Also, by the necessary modifications identified for the presented approach, the microgrid can operate independently from the utility grid and satisfy the requirements of islanded mode for the time slots in which the microgrid exchanges energy with the grid based on the end-game results. The energy management strategy proposed in this study presents a comprehensive solution capable of optimizing energy sharing in microgrids while taking into account end-users’ operational characteristics and network requirements. Furthermore, the designed billing scheme ensures that the accuracy of the proposed game approach remains unaffected by the uncertainties, thus preserving the microgrid’s profit.

Energy management algorithm based on average power demand prediction for plug-in hybrid electric trucks

This paper examines potential fuel consumption savings through the implementation of a predictive equivalent consumption minimisation strategy, as a control algorithm in the energy management system of hybrid heavy-duty vehicles. A plug-in hybrid electric truck simulation model was developed as a demonstrator and was validated with experimental data. The baseline vehicle model was based on the same algorithm as VECTO, which is further extended in the current study by novel factors that contain the average predicted power demand. The potential benefits of the proposed algorithm are examined for different heavy-duty categories over regulatory mission profiles in both charge-sustain and charge-depletion modes. The results show that the fuel consumption can be reduced by up to 5.9 % and 4.4% in charge sustaining and charge depleting modes, respectively, depending on the mission profile. If such an algorithm is adopted by commercial vehicles, this could lead to substantial CO2 and fuel consumption savings on the road.