Energy Management Research Articles

Optimal Energy Management System Control of Permanent Magnet Direct Drive Linear Generator for Grid-Connected FC-Battery-Wave Energy Conversion

Optimal Energy Management System Control of Permanent Magnet Direct Drive Linear Generator for Grid-Connected FC-Battery-Wave Energy Conversion

Mixed‐Integer Optimal Control via Reinforcement Learning: A Case Study on Hybrid Electric Vehicle Energy Management

ABSTRACTMany optimal control problems require the simultaneous output of discrete and continuous control variables. These problems are typically formulated as mixed‐integer optimal control (MIOC) problems, which are challenging to solve due to the complexity of the solution space. Numerical methods such as branch‐and‐bound are computationally expensive and undesirable for real‐time control. This article proposes a novel hybrid‐action reinforcement learning (HARL) algorithm, twin delayed deep deterministic actor‐Q (TD3AQ), for MIOC problems. TD3AQ leverages actor‐critic and Q‐learning methods to manage discrete and continuous action spaces simultaneously. The proposed algorithm is evaluated on a plug‐in hybrid electric vehicle (PHEV) energy management problem, where real‐time control of the discrete variables, clutch engagement/disengagement and gear shift, and continuous variable, engine torque, is essential to maximize fuel economy while satisfying driving constraints. Simulation results show that TD3AQ achieves near‐optimal control, with only a 4.69% difference from dynamic programming (DP), and outperforms baseline reinforcement learning algorithms for hybrid action spaces. The sub‐millisecond execution time indicates potential applicability in other time‐critical scenarios, such as autonomous driving or robotic control.

Data-driven adaptive Lyapunov function based graphical deep convolutional neural network for smart grid congestion management

Optimal power flow by leveraging network grid topology will ensure stable operation of the smart grid. Energy management in grid-connected systems aimed to reduce computational non-linearities and ensure reliable operation of the smart grid. The conventional method manages congestion with optimal scheduling for every 10–15 min. Hence congestion in the smart grid occurs during secured energy distribution. In smart grid, instant congestion and energy management are needed. This research, work is devoted to a novel data-driven adaptive Lyapunov function with a Graphical Deep Convolutional Neural Network (GDCNN) regulated optimal flow by accurate energy management. By employing novel Graph theory-based network, the congestion data are obtained to train the proposed GDCNN. A Comparison of obtained results with existing baseline methods has been carried for claiming the novelties of proposed GDCNN. It is observed, that compared to existing machine learning-based extended subspace identification techniques. Our method has better optimal power regulation within 1.8 s by controlling power sources. Also, numerical simulation on IEEE 68 bus system shows the proposed GDCNN have superior performance, reliability, and optimal energy management. This by integrating the benefits of adaptive Lyapunov function and graphical convolutional network.

Voltage Deviation Improvement in Microgrid Operation through Demand Response Using Imperialist Competitive and Genetic Algorithms

In recent decades, with the expansion of distributed energy generation technologies and the increasing need for more flexibility and efficiency in energy distribution systems, microgrids have been considered a promising innovative solution for local energy supply and enhancing resilience against network fluctuations. One of the basic challenges in the operation of microgrids is the optimal management of voltage and frequency in the network, which has been the subject of extensive research in the field of microgrid operational optimization. The energy demand is considered a crucial element for energy management due to its fluctuating nature over the day. The use of demand response strategies for energy management is one of the most important factors in dealing with renewables. These strategies enable better energy management in microgrids, thereby improving system efficiency and stability. Given the complexity of optimization problems related to microgrid management, evolutionary optimization algorithms such as the Imperialist Competitive Algorithm (ICA) and Genetic Algorithm (GA) have gained great attention. These algorithms enable solving high-complexity optimization problems by considering various constraints and multiple objectives. In this paper, both ICA and GA, as well as their hybrid application, are used to significantly enhance the voltage regulation in microgrids. The integration of optimization techniques with demand response strategies improves the overall system efficiency and stability. The results proved that the hybrid method provides valuable insights for optimizing energy management systems.

County-level carbon emissions in the guanzhong area of Shaanxi province: towards achieving China’s dual carbon goals

China’s rapid urbanization has significantly impacted carbon emissions in rural areas, driving the need for region-specific carbon management strategies to achieve the country’s dual carbon goals. However, previous research has primarily focused on large urban centers, leaving a gap in understanding the spatial and temporal patterns of carbon emissions at the county level in rural regions. This study focuses on the Guanzhong region of Shaanxi Province and develops a county-level carbon emission accounting system based on geographic, socio-economic, and land-use data. The carbon emissions are categorized into energy, industrial processes, agriculture, and waste management. Key findings indicate that industrial and residential sectors are the primary contributors to carbon emissions, with Xi’an being the largest emitter. Carbon emission intensity follows a ranking of Xi’an < Weinan < Baoji < Xianyang < Tongchuan. Spatial patterns show a “core-edge” distribution, with higher emissions in urban centers and lower emissions in rural areas. The study also highlights the carbon sink potential in the southern Qinling National Park. This research provides a valuable framework for rural low-carbon development and offers critical insights for policymakers aiming to balance carbon reduction and economic growth in rural China.

Advanced energy management scheme for fuel cell-based microgrid using self–regulated controller and switched capacitor inverter

Clean energy production is now the main challenge for sustainable future which can be addressed by introducing renewable energy sources. Fuel cells are critical in providing sustainable energy solutions by enabling efficient energy conversion in microgrids. To enhance the performance of fuel cell-based microgrids, advanced controllers and inverters are necessary to manage power quality and stability. One of the key benefits of this fuel cell is the separation of energy conversion and management, which allows independent optimization for each function of microgrid's performance, cost, or other installation considerations. The ability to individually control of each component of a microgrid can significantly impact various applications positively. Beyond their technological and economic advantages, fuel cells are highly sensitivity to microgrid's characteristics such as current quality and harmonics which creates difficulties for their design and management. Therefore, the entire microgrid must be managed by an effective energy management strategy and integration of advanced inverter topologies. This study aims to improve fuel cell efficiency and power quality within the microgrid through an advanced energy management (AEM) strategy. The proposed AEM structure is developed focusing on two key components: a self-regulated controller (SRC) and a switched capacitor multilevel inverter (SCMLI). These elements work together to mitigate the disturbances and enhance the power quality of the system. The methodology includes simulation and hardware-in-the-loop (HIL) testing under non-linear load conditions. Initial grid-side current total harmonic distortion (THD) of 28.38% was reduced to 2.19% through the proposed system. An impact analysis is also presented to demonstrates that reducing current harmonics and voltage imbalance have improved the efficiency of fuel cell to 50.18% and fuel utilization to 98.05%. The findings show that the proposed scheme significantly reduces current harmonics and improves the overall performance benchmark of the microgrid and fuel cell.

Simultaneous Energy Optimization of Heating Systems by Multi-Zone Predictive Control—Application to a Residential Building

Climate change has made energy management a global priority. In France, the Grenelle Environment has set very ambitious progress targets for positive-energy buildings, particularly in terms of reducing and managing energy consumption. However, effective energy management in multi-zone buildings presents significant challenges, particularly when considering the inter-zone dynamics and heat transfer. This study examines multi-zone heating control, using a data-driven model for predictive indoor temperature modeling in intelligent buildings taking into account the influence of interconnected adjacent zones. The research methodology uses dynamic thermal simulation, parallel predictive models based on multiple linear regressions, and a multi-objective non-dominated sorting genetic algorithm II (NSGA-II) for the optimization process, which evaluates various generated heating strategies. This research introduces an approach to improve building energy efficiency by considering inter-zone dynamics and reducing heating-related energy consumption compared to a conventional heating strategy. By applying this model predictive control on a simulated case, a reduction in energy consumption due to heating is observed while respecting thermal comfort. This work contributes by implementing a method that independently controls temperatures in different building zones simultaneously while applying distinct constraints to each zone. This approach empowers occupants to manage heating consumption based on their preferences, ensuring personalized comfort. In addition, a comparison was made using a model that did not account for inter-zone interactions. This comparison demonstrates that incorporating these interactions into the predictive model enhances the effectiveness of the model predictive control approach. The multi-zone approach was also validated experimentally by using real experimental data, demonstrating significant reductions in energy consumption.

Efficient Method for Photovoltaic Power Generation Forecasting Based on State Space Modeling and BiTCN

As global carbon reduction initiatives progress and the new energy sector rapidly develops, photovoltaic (PV) power generation is playing an increasingly significant role in renewable energy. Accurate PV output forecasting, influenced by meteorological factors, is essential for efficient energy management. This paper presents an optimal hybrid forecasting strategy, integrating bidirectional temporal convolutional networks (BiTCN), dynamic convolution (DC), bidirectional long short-term memory networks (BiLSTM), and a novel mixed-state space model (Mixed-SSM). The mixed-SSM combines the state space model (SSM), multilayer perceptron (MLP), and multi-head self-attention mechanism (MHSA) to capture complementary temporal, nonlinear, and long-term features. Pearson and Spearman correlation analyses are used to select features strongly correlated with PV output, improving the prediction correlation coefficient (R2) by at least 0.87%. The K-Means++ algorithm further enhances input data features, achieving a maximum R2 of 86.9% and a positive R2 gain of 6.62%. Compared with BiTCN variants such as BiTCN-BiGRU, BiTCN-transformer, and BiTCN-LSTM, the proposed method delivers a mean absolute error (MAE) of 1.1%, root mean squared error (RMSE) of 1.2%, and an R2 of 89.1%. These results demonstrate the model’s effectiveness in forecasting PV power and supporting low-carbon, safe grid operation.

Adaptive Energy Management Strategy for Hybrid Electric Vehicles in Dynamic Environments Based on Reinforcement Learning

Energy management strategies typically employ reinforcement learning algorithms in a static state. However, during vehicle operation, the environment is dynamic and laden with uncertainties and unforeseen disruptions. This study proposes an adaptive learning strategy in dynamic environments that adapts actions to changing circumstances, drawing on past experience to enhance future real-world learning. We developed a memory library for dynamic environments, employed Dirichlet clustering for driving conditions, and incorporated the expectation maximization algorithm for timely model updating to fully absorb prior knowledge. The agent swiftly adapts to the dynamic environment and converges quickly, improving hybrid electric vehicle fuel economy by 5–10% while maintaining the final state of charge (SOC). Our algorithm’s engine operating point fluctuates less, and the working state is compact compared with Deep Q-Network (DQN) and Deterministic Policy Gradient (DDPG) algorithms. This study provides a solution for vehicle agents in dynamic environmental conditions, enabling them to logically evaluate past experiences and carry out situationally appropriate actions.

Electric Vehicle Energy Management via Traffic Light Detection and Segmental Velocity Forecasting

Abstract Predictive-based power control has been widely recognized as a promising approach to boost driving range and improve system-level energy efficiency for electric vehicles (EVs), in which vehicle velocity forecasting generally serves as a preliminary input to optimally schedule the operations of varying on-board electrical and thermal systems. A segment-based velocity forecasting approach for individual commuting vehicles developed in this study reveals that it is challenging to forecast the velocity at intersection segments only using the velocity data. To address this challenge, this study seeks to develop a YOLO-V2-based object detection deep network to recognize the traffic lights in advance, and leverage the detected signals to establish a forecasting model that integrates with the probability-based hybrid forecasting approach. The case study results show that the traffic light detection-based forecasting model can significantly improve the forecasting accuracy for intersection segments. Based on the forecasting velocity 5-15 seconds ahead, the effectiveness of model predictive control-based energy management strategy is further evaluated with a liquid-based battery thermal control system. The proposed Battery Thermal Management System (BTMS) model shows promising results in maintaining battery temperature within an appropriate range, thus improving the overall energy efficiency of the EV. Moreover, a traffic light-based real-time energy management framework is developed to directly control the power demand from the Air Conditioning (AC) system.

Optimizing Energy Management and Sizing of Photovoltaic Batteries for a Household in Granada, Spain: A Novel Approach Considering Time Resolution

As residential adoption of renewable energy sources increases, optimizing rooftop photovoltaic systems (RTPVs) with Battery Energy Storage Systems (BESSs) is key for enhancing self-sufficiency and reducing dependence on the grid. This study introduces a novel methodology for sizing Home Energy Management Systems (HEMS), with the objective of minimizing the cost of imported energy while accounting for battery degradation. The battery model integrated nonlinear degradation effects and was evaluated in a real case study, considering different temporal data resolutions and various energy management strategies. For BESS capacities ranging from 1 to 5 kWh, the economic analysis demonstrated cost-effectiveness, with a Net Present Value (NPV) ranging from 54.53 € to 181.40 € and discounted payback periods (DPBs) between 6 and 10 years. The proposed HEMS extended battery lifespan by 22.47% and improved profitability by 21.29% compared to the current HEMS when applied to a 10 kWh BESS. Sensitivity analysis indicated that using a 5 min resolution could reduce NPV by up to 184.68% and increase DPB by up to 43.12% compared to a 60 min resolution for batteries between 1 and 5 kWh. This underscores the critical impact of temporal resolution on BESS sizing and highlights the need to balance accuracy with computational efficiency.

Fuzzy Logic-Based Energy Management Strategy for Hybrid Fuel Cell Electric Ship Power and Propulsion System

The growing use of proton-exchange membrane fuel cells (PEMFCs) in hybrid propulsion systems is aimed at replacing traditional internal combustion engines and reducing greenhouse gas emissions. Effective power distribution between the fuel cell and the energy storage system (ESS) is crucial and has led to a growing emphasis on developing energy management systems (EMSs) to efficiently implement this integration. To address this goal, this study examines the performance of a fuzzy logic rule-based strategy for a hybrid fuel cell propulsion system in a small hydrogen-powered passenger vessel. The primary objective is to optimize fuel efficiency, with particular attention on reducing hydrogen consumption. The analysis is carried out under typical operating conditions encountered during a river trip. Comparisons between the proposed strategy with other approaches—control based, optimization based, and deterministic rule based—are conducted to verify the effectiveness of the proposed strategy. Simulation results indicated that the EMS based on fuzzy logic mechanisms was the most successful in reducing fuel consumption. The superior performance of this method stems from its ability to adaptively manage power distribution between the fuel cell and energy storage systems.

A Versatile Platform for PV System Integration into Microgrids

Advancing decarbonization critically depends on the integration of PV systems into microgrids. However, this integration faces challenges, including the variability of photovoltaic solar energy production, the demands of energy management, and the complexities of grid synchronization and communication. To address these challenges, a PV emulator platform is an essential tool. This paper presents a novel four-layer PV emulator platform that seamlessly integrates power systems, control systems, measurement instrumentation, and communication processes. The proposed platform enables the emulation of I-V curves and the dynamic adjustment of operating points—including both the maximum power point (MPP) and power reserve point (PRP)—as well as temperature and irradiance while providing sufficient power capacity for microgrid integration. To validate its effectiveness, the platform was assessed for its capability to adjust operating points, such as MPPs or PRPs, under varying irradiance and temperature conditions. The results show that the platform effectively adjusts operating points with a deviation of less than 5% from theoretical values and successfully tracks a sequence of operating points. This performance underscores the platform’s potential in integrating and managing PV systems within microgrid environments, thereby advancing the path to decarbonization.

Analysis and Design of a Battery and Supercapacitor‐Based Propulsion System for Electric Vehicles

ABSTRACTThis work deals with the design and development of a dual source based propulsion architecture for electric vehicles. The converter utilized for the propulsion system is derived from a conventional CuK converter, which operates in a bidirectional power flow mode. The proposed propulsion system has two energy sources: a battery and a supercapacitor (SC). The proposed system has continuous input and output currents at low and high voltage sides, which improves the cycle life of hybrid energy storage (SC and battery) and the DC‐link capacitor. Further, the proposed converter has magnetic reduction compared to a conventional two‐input bidirectional CuK converter. Moreover, an effective and simpler control strategy (only one switch is pulse width modulated (PWM) operated at a time) has been developed for energy management between sources during charging (regenerative braking) and discharging (propulsion), which is effectively verified by simulation and experimental results. Further, a frequency domain (bode plot)‐based technique is used for controller design and stability analysis of the proposed system.

Evaluation of Advances in Battery Health Prediction for Electric Vehicles from Traditional Linear Filters to Latest Machine Learning Approaches

In recent years, there has been growing interest in Li-ion battery State-of-Health (SOH) estimation due to its critical role in ensuring the safe and reliable operation of Electric Vehicles (EVs). Effective energy management and accurate SOH prediction are essential for the reliability and sustainability of EVs. This paper presents an in-depth review of SOH estimation techniques, starting with an overview of seminal methods that lay the theoretical groundwork for battery modeling and SOH prediction. The review then evaluates recent advancements in Machine Learning (ML) and Artificial Intelligence (AI) techniques, emphasizing their contributions to improving SOH estimation. Through a rigorous screening process, the paper systematically assesses the evolution of these advanced methods, addressing specific research questions to evaluate their effectiveness and practical implications. Key findings highlight the potential of hybrid models that integrate Equivalent Circuit Models (ECMs) with Deep Learning approaches, offering enhanced accuracy and real-time performance. Additionally, the paper discusses limitations of current methods, such as challenges in translating laboratory-based models to real-world conditions and the computational complexity of some prospective methods. In conclusion, this paper identifies promising future research directions aimed at optimizing hybrid models and overcoming existing constraints to advance SOH estimation and battery management in Electric Vehicles.

Energy management with adaptive moving average filter and deep deterministic policy gradient reinforcement learning for fuel cell hybrid electric vehicles

Fuel cell hybrid electric vehicles (FCHEV) with battery (BAT) and supercapacitor (SC) advance in flexible configuration and high energy efficiency. However, the complex coupling relationship among various power sources poses a severe challenge to the design of the energy management system (EMS), including multi-degrees of freedom power allocation, fuel economy, and power sources lifespan of the FCHEV. This paper proposes an EMS based on a dual-layer power distribution structure. In the upper layer, adaptive moving average filter (AMAF) is designed to separate different frequency power, where the energy supply of the SC is managed to attenuate fluctuating power and simplifies the optimization problem and reduces computational costs. The lower layer is constructed by the deep deterministic policy gradient (DDPG) algorithm, where fuel cell system (FCS) hydrogen consumption and degradation rewards are designed to simultaneously enhance fuel efficiency and degradation performance by regulating the FCS real-time power variation. The proposed strategy has been evaluated regarding FCHEV fuel economy and FCS durability under combined driving cycle simulation, which shows AMAF + DDPG strategy reduces fuel consumption by 7.24 % and 1.3 %, also the degradation reduces by 0.04 % and 0.02 % compared with different EMS. Simulation results demonstrate that AMAF + DDPG optimizes the output characteristics of power sources.

Deep reinforcement learning-based energy management system enhancement using digital twin for electric vehicles

Compared to conventional engine-based powertrains, electrified powertrain exhibit increased energy efficiency and reduced emissions, making electrification a key goal for the automotive industry. For a vehicle with a hybrid energy storage system, its performance and lifespan are substantially affected by the energy management system. Reinforcement learning-based methods are gaining popularity in vehicle energy management, but most of the literature in this area focuses on pure simulation, while hardware implementation is still limited. This paper introduces the digital twin methodology to enhance the reinforcement learning-based energy management system for battery and ultracapacitor electric vehicles. The digital twin model can exploit the bilateral interdependency between the virtual model and the actual system, which improves the control performance of the energy management system in real-time control. The physical model is established based on a hardware-in-the-loop simulation platform. In addition, battery degradation is also considered for prolonging the battery lifespan to reduce operating costs. The validation results of the trained reinforcement learning agent illustrate that the digital twin-enhanced Q-learning energy management system improves the energy efficiency by 7.08 % and reduces the battery degradation by 25.28 %.

Robust day-ahead scheduling of cooperative energy communities considering multiple aggregators

Future cities must play a vital role in reducing energy consumption and decarbonizing the electricity sector, thus evolving from passive structures towards more efficient smart cities. This transition can be facilitated by energy communities. This emerging paradigm consists of collectivizing a set of residential installations equipped with onsite renewable generators and storage assets (i.e., prosumers), which can eventually share resources to pursue collective welfare. This paper focuses on cooperative communities, where prosumers share resources without seeking selfish monetary counterparts. Despite their apparent advantages, energy management and scheduling of energy communities suppose a challenge for conventional tools due to the high level of uncertainty (especially due to intermittent renewable generation and random demand), and privacy concerns among prosumers. This paper addresses these issues. Specifically, a novel management structure based on multiple aggregators is proposed. This paradigm preserves users' confidential features while allowing them to extract the full potential of their assets. To efficiently manage the variety of assets available under uncertainty, an adaptive robust day-ahead scheduling model is developed, which casts as a solvable and portable Mixed Integer Linear Programming framework, which eases its implementation in real-world cases. The new proposal concerns uncertain generation and demand using a polyhedral representation of the uncertainty set. A case study is conducted to validate the developed model, showing promising results. Moreover, different results are obtained and analysed. Finally, it is worth remarking on how the level of robustness impacts the collective bill, incrementing it by 75 % when risk-averse conditions are assumed. In addition, the role of storage assets under pessimistic conditions is remarked, pointing out that these assets rule the scheduling plan of the community instead of renewable generators.

ENERGY MANAGEMENT IN HYBRID PV-WIND-BATTERY STORAGE-BASED MICROGRID USING DROOP CONTROL TECHNIQUE

The paper presents an efficient energy management system designed for a small-scale hybrid microgrid incorporating wind, solar, and battery-based energy generation systems using the droop control technique. The heart of the proposed system is the energy management system, which is responsible for maintaining power balance within the microgrid. The EMS continuously monitors variations in renewable energy generation and load demand and adjusts the operation of the energy conversion systems and battery storage to ensure optimal performance and reliability. The primary objective of the energy management system is to maintain power balance within the microgrid, even in the face of fluctuations in renewable energy generation and load demand. This involves dynamically adjusting the operation of the renewable energy sources and battery storage system to match the instantaneous power requirements of the microgrid. Overall, the paper presents a comprehensive approach to designing and implementing an efficient energy management system for a small-scale hybrid wind-solar-battery-based microgrid to extract maximum profit from electricity generation. By integrating renewable energy sources with energy storage and advanced control algorithms, the proposed system aims to enhance the reliability, stability, and sustainability of the microgrid's power supply.

Advanced Energy Management in a Sustainable Integrated Hybrid Power Network Using a Computational Intelligence Control Strategy

Advanced Energy Management in a Sustainable Integrated Hybrid Power Network Using a Computational Intelligence Control Strategy