Effective Energy Management Strategy Research Articles

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.

Energy management strategy optimization for hybrid energy storage system of tram based on competitive particle swarm algorithms

Trams with energy storage are popular for their energy efficiency and reduced operational risk. An effective energy management strategy is optimized to enable a reasonable distribution of demand power among the storage elements, efficient use of energy as well as enhance the service life of the hybrid energy storage system (HESS). Thus, an energy management strategy optimization method of HESS based on a fixed power threshold is developed. Firstly, the energy management strategy optimization models based on single thresholds and multiple thresholds are developed. Then, the improved particle swarm optimization (PSO) algorithm with competing variable weights is proposed to solve optimization models. Finally, Guangzhou Haizhu tram is used to illustrate the performance of the developed method, the minimum charge state of the power battery under multiple thresholds is improved by 23.36 % over that of single threshold, and the total energy consumption of the power battery pack is reduced by 58.10 %, which shows that the energy management strategy based on multiple thresholds has better effects in giving full play to the power supply capacity of supercapacitor and reducing the energy consumption of power battery. Compared with other two methods, the improved PSO method has more reliable in utilizing more energy from supercapacitor.

A data-driven DRL-based home energy management system optimization framework considering uncertain household parameters

With the rise in household computing power and the increasing number of smart devices, more and more residents are able to participate in demand response (DR) management through the home energy management system (HEMS). However, HEMS has encountered challenges in developing the most effective energy management strategies, including the complexity of modeling user comfort, uncertainty in electricity price and photovoltaic (PV) output, and the challenge of solving high-dimensional time-coupled decision problems. To address these challenges, a novel data-driven deep reinforcement learning (DRL)-base HEMS optimization framework considering uncertain household parameters is proposed. Firstly, a thermal comfort evaluation model based on integrated learning is proposed. Then, a prediction model based on the bidirectional gated recurrent unit neural network (BiGRU-NN) algorithm is proposed to mine the time series PV output and electricity price data. Finally, combining the PV output and electricity price forecasting, along with the thermal comfort evaluation, an optimal decision-making method based on soft actor-critic (SAC) algorithm for the HEMS is established. The results of numerical experiments show that the proposed method can effectively solve the high-dimensional integrated decision-making problem with uncertainty. By participating in DR, the household electricity cost can be reduced by 17.7% and the total cost can be reduced by 8.4%. Furthermore, the comparison result shows that the method proposed in this paper performs better than the existing optimization models based on proximal policy optimization (PPO) algorithm and twin-delayed depth deterministic policy gradient (TD3) algorithm.

Effective Energy Management Strategy with Model-Free DC-Bus Voltage Control for Fuel Cell/Battery/Supercapacitor Hybrid Electric Vehicle System

This article presents a new design method of energy management strategy with model-free DC-Bus voltage control for the fuel-cell/battery/supercapacitor hybrid electric vehicle (FCHEV) system to enhance the power performance, fuel consumption, and fuel cell lifetime by considering regulation of DC-bus voltage. First, an efficient frequency-separating based-energy management strategy (EMS) is designed using Harr wavelet transform (HWT), adaptive low-pass filter, and interval type–2 fuzzy controller (IT2FC) to determine the appropriate power distribution for different power sources. Second, the ultra-local model (ULM) is introduced to re-formulate the FCHEV system by the knowledge of the input and output signals. Then, a novel adaptive model-free integral terminal sliding mode control (AMFITSMC) based on nonlinear disturbance observer (NDO) is proposed to force the actual values of the DC-link bus voltage and the power source’s currents track their obtained reference trajectories, wherein the NDO is used to approximate the unknown dynamics of the ULM. Moreover, the Lyapunov theorem is used to verify the stability of AMFITSMC via a closed-loop system. Finally, the FCHEV system with the presented method is modeled on a Matlab/Simulink environment, and different driving schedules like WLTP, UDDS, and HWFET driving cycles are utilized for investigation. The corresponding simulation results show that the proposed technique provides better results than the other methods, such as operational mode strategy and fuzzy logic control, in terms of the reduction of fuel consumption and fuel cell power fluctuations.

Fuzzy-based optimal energy management strategy of series hybrid-electric propulsion system for UAVs

Hybrid-electric propulsion system (HEPS) has gained significant attention in unmanned aerial vehicles (UAVs) due to its potential to significantly reduce fuel consumption and pollutant emissions. Effective energy management strategies are crucial in ensuring the efficient operation of HEPS in UAVs, as they involve multiple power and energy sources. While conventional equivalent consumption minimum strategy (ECMS) is effective in distributing engine and battery output power, it struggles to maintain the battery’s state of charge (SOC) within desired levels in case of engine failure. The present study introduced the fuzzy logic control-equivalent consumption minimum strategy (FLC-ECMS), a fuzzy-based composite energy management strategy that incorporates the robustness and adaptability of fuzzy logic control. Through simulation tests under general aviation cruise flight and cargo transport flight scenarios, the results indicated that hybrid UAV equipped with the HEPS can decrease fuel consumption and CO2 emissions by at least 18.6% and NOx emissions by 10.1% in the first profile and by 23.6% and 11.2% in the second profile, compared to conventional oil-powered UAV. The FLC-ECMS method not only reduces fuel consumption and emissions, but also maintains the battery SOC within permitted range and minimizes the difference between front and back SOC. This study provides new insights into the optimal energy management of HEPS for complex profiles in UAVs, highlighting the significance of UAVs in reducing environmental impacts, and has the potential for broader application in other electric propulsion systems.

Online adaptive energy management strategy for fuel cell hybrid vehicles based on improved cluster and regression learner

An effective energy management strategy (EMS) is essential to ensure the safe and efficient operation of the fuel cell hybrid vehicles. In this paper, an online adaptive EMS is proposed for the fuel cell hybrid vehicles to minimize hydrogen consumption and adjust the strategy according to the driving conditions. Driving pattern recognition is realized by the improved k-means cluster approach which combines multiple k-means clusters with specific distances to serve as the classifier. In each driving pattern, separate machine learning (ML) models are trained to obtain the energy management regression learner. Comparison experiments are performed to determine the optimal ML model and input parameters. The effectiveness of the proposed EMS is evaluated using two compound test driving cycles. Results show that the proposed method achieves the lowest fuel consumption compared to the other five algorithms considered. Remarkably, it reduces hydrogen consumption by up to 5.66% when compared to commonly used methods.

Research on an Improved Rule-Based Energy Management Strategy Enlightened by the DP Optimization Results

Plug-in hybrid electric vehicles (PHEVs) have gradually become an important member of new energy vehicles because of the advantages of both electric and hybrid electric vehicles. A fast and effective energy management strategy can significantly improve the fuel-saving performance of vehicles. By observing the dynamic programming (DP) simulation results, it was found that the vehicle is in the charge-depleting mode, the state of charge (SOC) drops to the minimum at the end of the journey, and the SOC decreases linearly with the mileage. As such, this study proposed an improved rule-based (IRB) strategy enlightened by the DP strategy, which is different from previous rule-based (RB) strategies. Introducing the reference SOC curve and SOC adaptive adjustment, the IRB strategy ensures that the SOC decreases linearly with the driving distance, and the SOC drops to the minimum at the end of the journal, similar to the result of the DP strategy. The fuel economy of PHEV in the RB and DP energy management strategies can be considered as their worst-case and best-case scenarios, respectively. The simulation results show that the fuel consumption of the IRB strategy under the China Light-duty Vehicle Test Cycle is 3.16 L/100 km, which is 7.87% less than that of the RB strategy (3.43 L/100 km), and has reached 44.41% of the fuel-saving effect of the DP strategy (2.84 L/100 km).

Construction of Building Energy Consumption Prediction Model Based on Multi-Optimization Model

This study explores the utilization of the Relevance Vector Machine (RVM) model, optimized using the Sparrow Search Algorithm (SSA), Simulate Anneal Arithmetic (SAA), Particle Swarm Optimization (PSO), and Bayesian Optimization Algorithm (BOP), to construct an energy dissipation model for public buildings in Wuhan City. Energy consumption data and influential factors were collected from 100 public buildings, yielding 15 input variables, including building area, personnel density, and supply air temperature. Energy dissipation served as the output scalar indicator. Through correlation analysis between input and output variables, it was found that building area, personnel density, and supply air temperature significantly impact energy dissipation in public buildings. Principal component analysis (PCA) was employed for data dimensionality reduction, selecting seven main influential factors along with energy dissipation values as the dataset for the predictive model. The BOP-RVM model showed superior performance in terms of R2 (0.9523), r (0.9761), and low RMSE (5.3894) and SI (0.056). These findings hold substantial practical value for accurately predicting building energy consumption and formulating effective energy management strategies.

Optimizing fuel economy and durability of hybrid fuel cell electric vehicles using deep reinforcement learning-based energy management systems

An effective energy management strategy (EMS) is crucial for the reliable operation of fuel cell hybrid electric vehicles (FCHEVs). This study proposes a power distribution optimization strategy for FCHEVs that leverages deep reinforcement learning (DRL) and Pontryagin's minimum principle (PMP). The DRL algorithm effectively balances fuel economy, battery durability, and fuel cell durability objectives. The degradation mechanisms of battery and fuel cell under extreme working conditions are considered in the PMP optimization. A comprehensive evaluation framework is established with degradation and energy consumption models to serve as a reward for deep reinforcement learning to balance fuel economy and power sources' lifetime. Simulation results show that the proposed EMS framework reduces FC degradation by 18.4% and battery degradation by 71.1% compared to traditional PMP-based EMS under the NEDC driving condition. Hardware-in-the-loop (HIL) testing demonstrates that the proposed EMS framework has the potential for real-time application, with an average relative error between experiment and simulation of approximately 0.0203. This research highlights the significance of the proposed EMS framework in ensuring the reliable operation of FCHEVs with enhanced performance and reduced cost.

An online learning framework for self-adaptive dynamic thermal modeling of building envelopes

Modeling dynamic thermal behavior plays a crucial role for developing effective energy management strategies of buildings. In this work, we introduce an improved framework for online training of the GP-integrated 3R-2C model for building envelopes using a modified Ensemble Kalman filter (EnKF) algorithm. The framework combines the R-C model for defining physical constraints with Gaussian process (GP) predictor to capture time-varying thermal dynamics. This modified EnKF algorithm is designed based on Bayesian estimation theory and adapted for online learning, which eliminates the need for offline data collection and training. Numerical experiments using varied synthetic datasets were conducted to evaluate the effectiveness of the proposed framework. The results show that this framework significantly outperforms conventional schemes using the augmented EnKF algorithm: its relative deviations from benchmark results are only half of those achieved by the conventional ones. Importantly, this framework can gradually improve itself and be adapted to the incidental variations in heat transfer characteristics of building surfaces. Furthermore, it is highly flexible, which can be extended to deal with various thermal modeling problems through the utilization of different R-C models and configurations of GP predictors or machine learning techniques.

Integrated Energy Management System for Microgrid based on Renewable Energy Sources

An effective energy management strategy is crucial to ensure highest system reliability, stability, operation efficiency and cost-effective operation of renewable energy sources based standalone microgrid. This paper presents an efficient energy management system for microgrid incorporated with Photovoltaic system, PMSG based wind turbine and energy storages including battery, fuel cell-Electrolyzer. Implemented hybrid modified invasive weed optimization with perturbed and observed method for PV systems to harvest maximum energy during partial shading condition. A sliding mode controller is implemented for boost converter to work as maximum power point tracker for wind turbine. Three solar plants and three wind farms are considered in this paper to establish 1 MW microgrid. Each wind farm is established with multiple wind turbines and similarly each solar plant having multiple PV modules. Each wind turbine and solar plant has their own inverter to synchronize at point of common coupling (PCC). Effective controllers are proposed to supply quality power at PCC under linear status and nonlinear status of single and three phase loads. Small size battery is considered to work under transient time and electrolyzer-fuel cell set will be working under steady state condition to reduce the cost of the system. TS-Fuzzy based controllers are designed for all the converters and implemented hardware-in-loop on a Real Time Simulator (RTS) by using OPAL RT technology/modules. The results unveiled that the RTS precisely emulate the dynamics of the microgrid with proposed controllers.

A Novel on Energy Management Strategy with Maximum Exploitation of Renewables and EV Storage in Distribution Networks

Electric vehicles (EVs) are widely recognized for their environmentally friendly attributes and superior performance. They offer considerable potential for managing energy in low-voltage distribution networks through the use of vehicle-to-grid (V2G) and grid-to-vehicle (G2V) technologies. This article provides a detailed investigation into the management of energy in distribution networks using a combination of EVs, solar photovoltaic (PV), and diesel generators (DG). The water filling algorithm (WFA) is utilized to distribute the storage of EVs in each energy zone in an optimal manner, thereby achieving load flattening, minimizing energy costs, and reducing grid reliance. A multiobjective genetic algorithm (MOGA) is employed to solve a formulated multiobjective optimization problem for load flattening and voltage regulation, with optimal power transaction (OPT) serving as the decision variable. An adaptive neuro-fuzzy inference system (ANFIS) based EV ranking technique is employed to prioritize EVs based on their ability to provide the required services and determine optimal energy distribution (OED) for different scenarios. This study investigates the impact of OED in several scenarios and examines the influence of ANFIS prioritization on overall EV power availability and cost of charging (CoC). The findings of this study are crucial for developing effective energy management strategies that minimize energy costs and reduce grid reliance.

Prediction of Energy Consumption of an Administrative Building using Machine Learning and Statistical Methods

Energy management is now essential in light of the current energy issues, particularly in the building industry, which accounts for a sizable amount of global energy use. Predicting energy consumption is of great interest in developing an effective energy management strategy. This study aims to prove the outperformance of machine learning models over SARIMA models in predicting heating energy usage in an administrative building in Chefchaouen City, Morocco. It also highlights the effectiveness of SARIMA models in predicting energy with limited data size in the training phase. The prediction is carried out using machine learning (artificial neural networks, bagging trees, boosting trees, and support vector machines) and statistical methods (14 SARIMA models). To build the models, external temperature, internal temperature, solar radiation, and the factor of time are selected as model inputs. Building energy simulation is conducted in the TRNSYS environment to generate a database for the training and validation of the models. The models' performances are compared based on three statistical indicators: normalized root mean square error (nRMSE), mean average error (MAE), and correlation coefficient (R). The results show that all studied models have good accuracy, with a correlation coefficient of 0.90 < R < 0.97. The artificial neural network outperforms all other models (R=0.97, nRMSE=12.60%, MAE= 0.19 kWh). Although machine learning methods, in general terms, seemingly outperform statistical methods, it is worth noting that SARIMA models reached good prediction accuracy without requiring too much data in the training phase. Doi: 10.28991/CEJ-2023-09-05-01 Full Text: PDF

Predictive Energy Management Strategy for Hybrid Electric Air-Ground Vehicle Considering Battery Thermal Dynamics

Hybrid electric air-ground vehicles (HEAGVs), which can run on the land and fly in the air, are considered a promising future transportation. The operation of HEAGVs, accompanied by high energy consumption, could lead to increasing battery temperature, which may affect the lifespan of the battery. To make the battery last longer and improve energy efficiency, an effective energy management strategy (EMS) is necessary for the operation of HEAGVs. In this regard, this paper proposes a predictive EMS based on model predictive control (MPC). Firstly, speed information is obtained by intelligent network technology to achieve a prediction of power demand, and then the state of charge (SOC) reference trajectory is planned. Secondly, a Pontryagin’s minimum principle-based model predictive control (PMP-MPC) framework is proposed, including battery thermal dynamics. Under the framework, fuel efficiency is improved by reducing the temperature of the battery. Finally, the proposed method is compared to PMP, dynamic programming (DP), and rule-based (RB) methods. The effect of different preview horizon sizes on fuel economy and battery temperature is analyzed. Verification results under two driving cycles indicate that compared with the rule-based method, the proposed method improves fuel economy by 5.14% and 5.2% and decreases the temperature by 5.9% and 4.9%, respectively. The results demonstrate that the proposed PMP-MPC method can effectively improve fuel economy and reduce temperature.

An Energy Management Strategy for Hybrid Energy Storage System Based on Reinforcement Learning

Due to the continuous high traction power impact on the energy storage medium, it is easy to cause many safety risks during the driving process, such as triggering the aging mechanism, causing rapid deterioration of the battery performance during the driving process and even triggering thermal runaway. Hybrid energy storage is an effective way to solve this problem. The ultracapacitor is an energy storage device that has high power density, which can withstand high instantaneous currents and can be charged and discharged quickly. By combining batteries and ultracapacitors in a hybrid energy storage system, energy sources with different characteristics can be combined to take advantage of their respective strengths and increase the efficiency and lifetime of the system. The energy management strategy plays an important role in the performance of hybrid energy storage systems. Traditional optimization algorithms have difficulty improving the flexibility and practicality of applications. In this paper, an energy management strategy based on reinforcement learning is proposed. The results indicate that the proposed reinforcement method can effectively distribute the charging and discharging conditions of the power supply and maintain the SOC of the battery and, at the same time, meet the power demand of working conditions at the cost of less energy loss and effectively realize the goal of optimizing the overall efficiency and effective energy management strategy.

Unleashing the Furr-Recovery Method: Interacting with Pets in Teleworking Replenishes the Self's Regulatory Resources: Evidence from a Daily-Diary Study.

This study is based on the conservation of resources theory and the recovery step model in order to further explore the furr-recovery method-a mechanism through which workers break their routine by taking micro-moments to interact with their "furry co-workers," thus relieving their fatigue and tension or other negative affective states. Based on this, we argue that this method not only serves the purpose of restoring self-regulatory resources but also ameliorates mental health. Accordingly, this study aims to analyze how daily human-animal interactions during teleworking positively influence teleworkers' mental health, via recovering their self-regulatory resources, at the within-person level. Full-time teleworkers completed multiple online surveys for 5 consecutive workdays (N = 211 × 5 = 1055 daily observations). Multilevel path analysis results showed that on days on which employees had more micro-moments to interact with their "furry co-workers" during the day, they experienced a higher self-regulatory capacity and felt better while working. In sum, the findings give support for the theoretical resource perspective of interacting with pets as an effective energy management strategy while at work. This research extends the theoretical understanding of regulatory resources as a cognitive mechanism that links HAIs to employee mental health. Moreover, the findings outlined here offer practical implications by highlighting the furr-recovery method, a method that teleworkers who own pets may use as a strategy during the working day to restore resources needed to be healthier.

WLTC measuring driving cycle (power reserve measurement procedure for hybrids and electric vehicles)

Problem. The most effective energy management strategies for hybrid vehicles and electric vehicles are optimization-based strategies. These strategies require prior knowledge of the driving cycle, which is not easy to predict. Goal. The goal is to combine the Worldwide harmonized light vehicles test cycle (WLTC) with short trips on small sections with real traffic levels to predict the energy and fuel consumption of hybrid vehicles and electric vehicles. Methodology. Research methods are experimental and mathematical. First of all, eight characteristic parameters are extracted from real speed profiles used on urban road sections in the city of Kharkiv under various road conditions, as well as on short WLTC trips. The minimum distance algorithm is used to compare parameters and determine three traffic levels (heavy, medium, and low traffic) for short WLTC trips. Thus, for each route determined using Google Maps, the energy and fuel consumption of hybrid vehicles and electric vehicles are estimated using short trips by the WLTC, adjusted for distances and traffic levels. In addition, a numerical model of the vehicle was implemented. It was used to test the accuracy of predicting fuel and energy consumption in accordance with the proposed methodology. Originality. For the methodology using only GM information is required as input data; no other device or software is required. This aspect makes the methodology extremely economical. Then, the algorithm regulating traffic levels shown by GM is unique and valid in all urban centers. This aspect makes the methodology universal. WLTC takes into account the driving styles of drivers around the world, so the methodology can be applied to any car driver. Prediction accuracy can be increased by taking into account other input information, such as the distribution of traffic light signals or the driver's typical gear shifting style. Results. The results are promising, as the average absolute percentage error between experimental driving cycles and projected ones is 3.89 % for fuel consumption, increasing to 6.80 % for energy consumption. Practical value. The possibility of energy forecasting and fuel consumption for a hybrid vehicle and an electric vehicle makes it possible to develop energy consumption management systems for HEVs that can manage the energy reserve to ensure full travel by electric traction in limited traffic zone (LTZ) or minimize local air pollution; increase the service life of energy reserves (usually batteries) by maintenance costs and disposal problems reducing; optimize the transmission-use efficiency due to fuel consumption and pollutants emissions reduction.

Energy management for hybrid electric vehicles based on imitation reinforcement learning

An effective energy management strategy (EMS) in hybrid electric vehicles (HEVs) is indispensable to promote consumption efficiency due to time-varying load conditions. Currently, learning based algorithms have been widely applied in energy controlling performance of HEVs. However, the enormous computation intensity, massive data training and rigid requirement of prediction of future operation state hinder their substantial exploitation. To mitigate these concerns, an imitation reinforcement learning-based algorithm with optimal guidance is proposed in this paper for energy control of hybrid vehicles to accelerate the solving process and meanwhile achieve preferable control performance. Firstly, offline global optimization is firstly conducted considering various driving conditions to search power allocation trajectories. Then, the battery depletion boundaries with respect to driving distance are introduced to generate a narrowed state space, in which the optimal trajectory is fused into the training process of reinforcement learning to guide the high-efficiency strategy production. The simulation validations reveal that the proposed method provides preferable energy reduction for HEVs in arbitrary driving scenarios, and suggests an efficient solution instruction for similar problems in mechanical and electrical systems with constraints and optimal information.

Overview of Smart Grid Technology as a Renewable Energy Source

A smart grid is an electricity system that uses digital communications technology to detect, respond to, and take appropriate action in response to changes in demand and a variety of other problems. The secret to effective utilization of distributed energy resources is smart grid technology. Opportunities for renewable energy systems to address electricity generation appear to be growing, especially in light of the importance of climate change, the rising cost of petroleum products, and the falling cost of renewable energy power systems. However, an effective energy management strategy of system must be addressed in order to achieve commercialization and widespread use. Electric power networks have recently benefited from the effective application of the smart grid idea. This research work examines the overview of smart grid technology as a renewable energy source. The concept of a smart grid as well as the advantages and disadvantages of a smart grid renewable energy. The success of promoting renewable energy is significantly influenced by pricing. As a result, it is crucial to evaluate the distinctive qualities connected with alternative sources of renewable energy in order to get insight into the pricing of renewable energy. A survey of recent work in renewable smart grid systems shows the exciting future potential of such research traits. Both policymakers and those who create and use renewable energy systems would benefit from this.

Effective energy management strategy based on deep reinforcement learning for fuel cell hybrid vehicle considering multiple performance of integrated energy system

Effective energy management strategy based on deep reinforcement learning for fuel cell hybrid vehicle considering multiple performance of integrated energy system