Electrical Integrity Research Articles

Reduced order modelling method for electromagnetic analysis of electrical machines

AbstractThis paper presents a workflow to create a reduced order model for the electromagnetic analysis of electrical machines over its operating range so that the stator forces can be exported for mechanical analysis. A permanent magnet synchronous motor developed within the EDISON (Electric Drivetrain Integration by Simulation and OptimizatioN) project is used as a model to validate the workflow. The response surface model approximation method is used to generate the reduced order model, which is then validated by comparing with the results from finite element analyses.

CNSC-45. EXTRINSIC ELECTRICAL MODULATION IMPACTS GLIOBLASTOMA TUMOR GROWTH BY DISRUPTING ITS INTERCELLULAR COMMUNICATION

Abstract Glioblastoma (GBM) is an incurable primary malignant neoplasm of the central nervous system. GBM as an electrically active neoplasm diffusely colonizes healthy brain tissues, disrupting the neurotransmission balance and causing glioma-related epilepsy (GRE) in up to 50% of patients. Interestingly, GRE is an independent favorable prognostic factor for survival in GBM. The therapeutic induction of seizure may have a previously unexplored oncologic value in GBM. We have previously reported in CT-2A-bearing mice subjected to daily extrinsic electrical modulation (EEM) diminished tumor progression and increased overall survival relative to sham-treated mice, but the mechanism by which EEM produces its anti-tumor effect remains uncertain. Therefore, GBM-bearing mice (CT-2A cells xenografted into 5-7 weeks old C57BL/6 female mice, n=5/group) received either a single EEM of 2.0 millicoulombs (mC) or sham treatment. The mice were terminated at 3 hours, 24 hours, 4, 7, and 10 days post-EEM, and tumors and contralateral brain cortex were analyzed using bulk RNA-sequencing and Sequential immunofluorescence (SeqIFTM). SeqIFTM revealed how EEM activates neuronal activity via cFOS expression and induces tumor-specific cell damage through cleaved caspase-3 expression, without affecting healthy brain tissue. Furthermore, RNA-seq performed post-EEM revealed gene expression changes of not only synapse organization markers but also of several tumor-tumor and tumor-neuron connectivity key markers, such as growth-associated protein 43 (GAP43), neuroligin-3 (NLGN3), and glutamate receptors such as GRIA4 and GRIN1 between others. However, the expression of these markers diminished significantly 96h after-EEM, indicating a reduction in intercellular electrical communication by the inhibition of the neoplasm cells electrical integration with neuronal circuits by downregulating glutamatergic receptor expression, blocking the synapse-forming protein NLGN3, and the network-connecting protein GAP43. Taken together, our findings reveal how by the disruption of these critical interactions within the tumor microenvironment though EEM impacts on GBM growth making it more susceptible to therapeutic interventions.

Enhancing distribution system performance by optimizing electric vehicle charging station integration in smart grids using the honey badger algorithm

The global surge in electric vehicle (EV) adoption has driven significant research into electric vehicle charging stations (EVCS) due to their environmentally friendly attributes, including low CO₂ emissions. However, integrating EVCS into existing distribution grids presents challenges such as power losses and voltage instability, especially with the increasing incorporation of renewable distributed generation (RDG) sources and battery energy storage systems (BESS). This study introduces a novel honey badger optimization algorithm (HBOA), designed to enhance solution convergence and optimize multi-objective criteria efficiently. HBOA strategically places EVCS while considering vehicle-to-grid (V2G) capabilities and user driving behaviors over a full 24-hour cycle, effectively addressing uncertainties and dynamic conditions. Simulations on modified IEEE 69-bus and Indian 28-bus radial distribution systems (RDS) demonstrate significant results: in the IEEE 69-bus system, power loss is reduced by 62.0%, the voltage stability index (VSI) increases from 0.7139 to 0.8311, and CO₂ emissions decrease by 66.0%. In the Indian 28-bus system, power loss decreases by 55.5%, with VSI improving from 0.7394 to 0.9964, leading to a 50.0% reduction in CO₂ emissions. The proposed smart microgrid (MG) structure incorporates interconnected MGs for residential, commercial, and industrial sectors, emphasizing the efficacy of RDGs in mitigating the impact of EVCS on RDS. The advantages of the HBOA method lie in its superior optimization capabilities, which enhance system performance, reduce operational costs, and promote sustainability, highlighting the proposed methodology’s potential for future integration of EVCS in distribution networks.

Optimization of emission scheduling in microgrids with electric vehicle integration

In the context of the continuous development of new energy vehicles, an increasing number of electric vehicles (EVs) are being integrated into microgrids, which impacts the operation of microgrids. It is necessary to analyze the emission scheduling of microgrids connected with EVs to ensure the smooth and reliable operation of microgrids with EV integration. This paper aims to realize optimal microgrid scheduling. This article took the case of EV connection with microgrids through orderly charging and discharging. Firstly, mathematical models for each output unit in the microgrid were established. Then, aiming to minimize both the operational cost and pollution emission treatment cost of the microgrid, an emission dispatch optimization model was developed. The whale optimization algorithm (WOA) was chosen as the solving algorithm, and an improved WOA (IWOA) was obtained by optimizing the original WOA in terms of population initialization and position updating parameters. An example analysis revealed that the IWOA demonstrated superior optimization performance compared to other optimization algorithms. In the scenario of orderly charging and discharging, the EVs discharged during peak hours and charged during off-peak hours to balance the microgrid load. The operating cost obtained through the IWOA was 967.25 yuan, and the pollution emission treatment cost was 241.52 yuan, resulting in a total cost of 1208.77 yuan. These results confirm the reliability of the proposed IWOA in solving the model and its applicability in optimizing microgrids with EV integration.

Optimizing Electric Vehicle Integration in Virtual Power Plants: A Stochastic Optimization Framework With MDNN Integration

Optimizing Electric Vehicle Integration in Virtual Power Plants: A Stochastic Optimization Framework With MDNN Integration

Probing structural and electrochemical properties of a 2D CoMoO4@hBN nanocomposite as pseudocapacitive electrode for high-performance supercapacitors

The effectiveness of energy storage is largely determined by the electrode material's performance in critical areas. Enhancements in ion transport, cyclic stability, rate capability, and specific capacitance directly boost the supercapacitors' overall performance and broaden their application potential. This study aims to enhance these properties by incorporating hexagonal boron nitride (hBN) into cobalt molybdate (CoMoO4) material in a 1:1 stoichiometric ratio. The CoMoO₄@hBN nanocomposite was synthesized using a hydrothermal method followed by ball milling. The X-ray diffraction (XRD) analysis confirmed the formation of a single-phase CoMoO4@hBN composite, with a significant increase in crystallite size from 18.21 nm in pure CoMoO₄ to 25.6 nm, along with a slight shift in diffraction peaks, indicating enhanced crystallinity and structural defects due to the substitution of oxygen with boron atoms. Raman spectroscopy revealed that the composite retains the characteristic peaks of both CoMoO₄ and hBN, with stable sharp peaks at 936 cm−1 (Mo=O bond) and 1367 cm−1 (E2g peak of hBN) even after 20 depth measurements, confirming successful conjugation and consistent vibrational properties. The X-ray photoelectron spectroscopy (XPS) showed a slight shift in Co 2p and Mo 3d binding energies to higher values, suggesting improved electronic interactions between CoMoO4 and hBN, which could enhance the composite's conductivity. The electrochemical analysis demonstrated that incorporating h-BN significantly boosts the electrode's performance compared to pristine CoMoO4, with about 37 % increase in specific capacitance at 1 A g−1, reduced charge transfer resistance (0.11 Ω), and superior cyclic stability with 96 % capacitance retention after 5000 cycles. These findings indicate that hBN enhances both the electrical conductivity and structural integrity of CoMoO4, positioning the CoMoO4@hBN composite as a promising material for high-performance supercapacitors.

Electrical liquid crystal integration with VCSEL arrays for tunable orthogonal polarization laser

Vertical-cavity surface-emitting laser (VCSEL) arrays that can emit orthogonally polarized light have shown broad application potential and market demand in the fields of optical communication, optical sensors, and biomedicine. Two kinds of polarization-switching VCSEL arrays based on anti-parallel (AP) oriented liquid crystal (LC) external cavities and twisted nematic (TN) oriented LC external cavities are proposed in this paper. The light is independently guided by the LC electrically, achieving uniform lasing of linearly polarized light with mutually orthogonal polarization modes and equal power. The uniformity and polarization tunable ability of the lasing orthogonally polarized light power is guaranteed by the integration of the LC external cavity and the VCSEL array.

Green light for bidirectional charging? Unveiling grid repercussions and life cycle impacts

Bidirectional charging, such as Vehicle-to-Grid, is increasingly seen as a way to integrate the growing number of battery electric vehicles into the energy system. The electrical storage capacity in the system can be enhanced by using electric vehicles as flexible storage units. However, large-scale applications of Vehicle-to-Grid may require significant expansion of distribution grids. Previous studies lack a comprehensive environmental assessment of related impacts. Contributing to this research gap, this article combines techno-economic grid simulations with scenario-based Life Cycle Assessments. The case study focuses on rural distribution grids in Southern Germany, projecting the repercussions of different charging scenarios by 2040. Besides a Vehicle-to-Grid scenario, a mixed scenario of Vehicle-to-Home, Vehicle-to-Grid, and direct charging is investigated. Results indicate that Vehicle-to-Grid charging increases grid impacts due to higher charging simultaneities and power losses, especially when following spot market prices. Despite these challenges, the secondary use of battery electric vehicles as storage units can offset adverse environmental effects. Bidirectional charging allows for higher use of volatile renewable energies and can accelerate their integration into the power system. When considering these diverse environmental effects, bidirectional charging scenarios show overall lower impacts on climate change per battery electric vehicle compared to direct charging. The insights provided are valuable for researchers, industry, utilities, and policymakers to understand the potential positive and negative impacts of large-scale battery electric vehicle integration. The article highlights the most influential parameters that should be considered before large-scale penetration.

Self‐Powered Wearable Pressure Sensors for Detection and Separation of Signals for Various Human Movements

A detailed study on the dynamic response of mountable pressure sensors is presented, with a focus on foot pressure sensors integrated with carbon nanotube (CNT)‐coated cotton fibers. The research explores the sensor's sensitivity to pressure changes, repeatability, hysteresis, and durability through rigorous modeling and experimental validation. Computational simulations using Python and experimental data demonstrate the sensor's nonlinear conductance response to applied force, attributed to the varying contact area and number of contact points among the fibers. Long‐term outdoor exposure tests confirm the material's resilience, maintaining electrical conductivity and structural integrity. The study also demonstrates the sensor's ability to monitor human activities like walking, running, stair climbing, and jumping, as well as detecting muscle movements during swallowing, coughing, and speech, highlighting potential applications in health monitoring and artificial voice synthesis. The MRMR algorithm is used for feature selection to distinguish activities, demonstrating the sensor's potential for activity recognition. Additionally, a piezoelectric sensor on the pressure sensors estimates harvested electric power to power wearable devices. This work contributes to the advancement of self‐powered wearable pressure sensors to monitor real‐time human activity, with implications for healthcare, sports performance, and assistive technologies.

Comparison of Effects of Partial Discharge Echo in Various High-Voltage Insulation Systems

In this article, an extension of a conventional partial discharge (PD) approach called partial discharge echo (PDE), which is applied to different classes of electrical insulation systems of power devices, is presented. Currently, high-voltage (HV) electrical insulation is attributed not only to transmission and distribution grids but also to the industrial environment and emerging segments such as transportation electrification, i.e., electric vehicles, more-electric aircraft, and propulsion in maritime vehicles. This novel PDE methodology extends the conventional and established PD-based assessment, which is perceived to be one of the crucial indicators of HV electrical insulation integrity. PD echo may provide additional insight into the surface conditions and charge transport phenomena in a non-invasive way. It offers new diagnostic attributes that expand the evaluation of insulation conditions that are not possible by conventional PD measurements. The effects of partial discharge echo in various segments of insulation systems (such as cross-linked polyethylene [XLPE] power cable sections that contain defects and a twisted-pair helical coil that represents motor-winding insulation) are shown in this paper. The aim is to demonstrate the echo response on representative electrical insulating materials; for example, polyethylene, insulating paper, and Nomex. Comparisons of the PD echo decay times among various insulation systems are depicted, reflecting dielectric surface phenomena. The presented approach offers extended quantitative assessments of the conditions of HV electrical insulation, including its detection, measurement methodology, and interpretation.

Electrification of Transportation: Policy Framework, Technical Aspects and Challenges in Pakistan - A Case Study

Pakistan faces severe air pollution and high dependency on imported fossil fuels for transportation, urgently needing solutions. Electrification of transportation could address these issues, but Pakistan lacks a clear roadmap for adopting electric vehicles. This paper examines the electrification of transportation in Pakistan, focusing on policies, technical aspects, and standards. It looks at best practices from developed countries and discusses incentives offered by the Pakistani government to boost electric vehicle adoption. The study also explores challenges and opportunities in adopting electric vehicles within existing power systems. A SWOT analysis is included, highlighting strengths, weaknesses, opportunities, and threats related to electric vehicle policies and market integration in Pakistan. By reviewing these factors, the paper provides insights into the obstacles and potential benefits of electric vehicle adoption. It also suggests ways for developing nations like Pakistan to encourage widespread use of electric vehicles, aiming to reduce fossil fuel dependency and meet environmental goals.

Optimal operation of a residential energy hub participating in electricity and heat markets

The integration of electricity and heat networks provides significant benefits by enhancing system flexibility and improving overall energy efficiency. Energy hubs play an important role in these interconnected systems, facilitating the production, conversion, and storage of energy across different forms. Potential flexible loads that may exist in an energy hub can further optimize its resource utilization and operational stability. In this respect, this paper addresses the day-ahead energy management of a residential complex modeled as an energy hub, incorporating medium-scale generation and storage units, as well as must-run and flexible loads. We also consider energy hub operator’s energy transactions in power distribution system and district heating and aim to obtain the optimal bidding strategy of this profit-driven agent. The negotiations among the energy hub operator, distribution system operator, and district heat network operator are modeled as a single-leader multi-follower Stackelberg game. A Nash Equilibrium of this game can be obtained by modeling the interactions among players as a bi-level optimization problem. The lower-level problems account for multi-period optimal power flow, modeled as an exact AC optimal power flow, and multi-period optimal thermal flow. The upper-level problem models the energy management of the energy hub. Replacing the lower-level problems with their optimality conditions, the optimal bidding of the energy hub operator can be obtained by solving the resulted mixed-integer linear programming problem as a mathematical program with equilibrium constraints. Finally, we numerically evaluate the proposed framework in a case study for a large residential complex participating in a power distribution and a heat network.

A Novel Method for Online Diagnostic Analysis of Partial Discharge in Instrument Transformers and Surge Arresters from the Correlation of HFCT and IEC Methods

In this work, a new methodology is proposed for the online and non-invasive extraction of partial discharge (PD) pulses from raw measurement data obtained using a simplified setup. This method enables the creation of sub-windows with optimized size, each containing a single candidate PD pulse. The proposed approach integrates mathematical morphological filtering (MMF) with kurtosis, a first-order Savitzky-Golay smoothing filter, the Otsu method for thresholding, and a specific technique to associate each sub-window with the phase angle of the applied voltage waveform, enabling the construction of phase-resolved PD (PRPD) patterns. The methodology was validated against a commercial PD detection device adhering to the IEC (International Electrotechnical Commission) standard. Experimental results demonstrated that the proposed method, utilizing an off-the-shelf 8-bit resolution data acquisition system and a low-cost high-frequency current transformer (HFCT) sensor, effectively diagnoses and characterizes PD activity in high-voltage equipment, such as surge arresters and instrument transformers, even in noisy environments. It was able to characterize PD activity using only a few cycles of the applied voltage waveform and identify low amplitude PD pulses with low signal-to-noise ratio signals. Other contribution of this work is the diagnosis and fault signature obtained from a real surge arrester (SA) with a nominal voltage of 192 kV, corroborated by destructive disassembly and internal inspection of the tested equipment. This work provides a cost-effective and accurate tool for real-time PD monitoring, which can be embedded in hardware for continuous evaluation of electrical equipment integrity.

Incorporation of SnSe2/SnO2 heterostructures in carbon nanotubes for excellent lithium storage performance

As a new type of negative electrode material, tin-based material exhibits a high theoretical capacity. However, tin-based anode materials always undergo severe volume change upon alloying reaction during lithium insertion and extraction, which leads to the pulverization of the active materials and poor electrochemical performance, seriously hampering its practical application. In this work, oxygen-containing group functionalized carbon nanotubes (FCNTs) were facilely obtained, and the three-dimensional crosslinked SnSe2-SnO2@FCNTs multiphase materials were prepared by solvothermal and high-temperature heat treatment. The formation of Sn-O-C bonds from oxygen-containing functional groups of FCNTs combined with Sn can promote the electric connection and integrity of the composites. The implanted defects in FCNTs can not only be beneficial to anchoring SnO2 and SnSe2 nanoparticles, but also helpful to the penetration of Li+ ions into the electrodes from electrolyte. In addition, the large Fermi energy difference between SnSe2 and SnO2 nanoparticles results in the formation of a built-in electric field at the interface of the multiphase materials, accelerating the diffusion of ions. The smaller size of the multiphase materials leads to significant pseudocapacitive behavior, which facilitates the highly reversible surface/interface adsorption. Under the multiple effects of FCNTs, SnSe2, and SnO2, the SnSe2-SnO2@FCNTs multiphase materials exhibited excellent electrochemical performance. At a current density of 0.1A·g-1, a discharge specific capacity of 898.0mAh·g-1 was achieved. When the current density was increased to 2A·g-1, it still exhibited a discharge specific capacity of 443.9mAh·g-1. After a long charge/discharge cycling at 1A·g-1 over 450 cycles, it still showed a specific capacity of ~ 400mAh·g-1. This work significantly demonstrated the enhanced Li-storage performance of SnSe2-SnO2 heterostructures incorporated in the functionalized multi-walled CNTs. This opens a new way to synthesize advanced tin-based materials as high-performance anodes for high-energy density lithium-ion batteries.

Electric Vehicle Integration in Coupled Power Distribution and Transportation Networks: A Review

Integrating electric vehicles (EVs) into the coupled power distribution network (PDN) and transportation network (TN) presents substantial challenges. This paper explores three key areas in EV integration: charging/discharging scheduling, charging navigation, and charging station planning. First, the paper discusses the features and importance of EV integrated traffic–power networks. Then, it examines key factors influencing EV strategy, such as user behavior, charging preferences, and battery performance. Next, the study establishes an EV charging and discharging model, with particular emphasis on the complexities introduced by factors such as pricing mechanisms and integration approaches. Furthermore, the charging navigation model and the role of real-time traffic information are discussed. Additionally, the paper highlights the importance of multi-type charging stations and the impact of uncertainty on charging station planning. The paper concludes by identifying significant challenges and potential opportunities for EV integration. Future research should focus on enhancing coupled network modeling, refining user behavior models, developing incentive pricing mechanisms, and advancing autonomous driving and automated charging technologies. Such efforts will be essential for achieving a sustainable and efficient EV ecosystem.

Strategic integration of residential electricity: An optimisation model for solar energy utilisation and carbon reduction

The Solar Combined Cooling, Heating, and Power (S-CCHP) system, distinct from traditional centralised generation, provides clean energy solutions by installing user-side renewable energy capture facilities like solar panels to address the energy crisis and mitigate global warming. Previous research on the design of S-CCHP for buildings has often emphasised self-sufficiency, with less focus on the role of these systems as energy suppliers on the market. However, it is feasible to install scaled-up solar facilities that generate enough power to export to the grid, reducing grid pressure and enhancing the renewable energy mix. This study analyses the optimal design deployment for electricity within the S-CCHP system, based on the Renewable Energy System for Residential Building Heating and Electricity Production (RESHeat) system installed in Limanowa. It aims to optimise owner energy deployment by strategically integrating electricity generation, hybrid storage, and the electricity market to maximise owner benefits. A Life Cycle Assessment is also conducted to explore greenhouse gas emissions across scenarios with different storage facilities and reuse rates. Results show that the optimal deployment of 264 PV panels, each with a rated power of 440 W, generates 105 MWh annually, resulting in the surplus of 90.18 MWh with a selling price of 115 EUR/MWh. Vanadium redox flow batteries offer the highest revenue (4922.01 EUR) with the lowest storage costs, while lithium-ion batteries have the lowest carbon emissions (1.22 t CO2 eq/y). Sensitivity analysis and revenue break-even analysis are further conducted to assess the robustness and financial viability.

High-Resolution Monitored Data Analysis of EV Public Charging Stations for Modelled Grid Impact Validation

As electric vehicle adoption grows, understanding the impact of electric vehicle charging on electricity grids becomes increasingly important. Accurate grid impact modelling requires high-quality charging infrastructure data. This study examined the electric vehicle recharging infrastructure and usage patterns in a region of the Italian Alps over a three-year period from 2021 to 2023. The primary objectives were to analyze the growth and distribution of electric vehicle charging stations, assess energy consumption, and evaluate charging behaviours across various recharging points. The research involved collecting empirical data from 411,800 recharging sessions and simulated data using the emobpy tool to model energy consumption and charging behavior. Key findings reveal a substantial increase in the number of recharging points, from 673 in 2021 to 970 in 2023, with the total energy delivered increasing from 938 MWh in 2021 to 4133 MWh in 2023. The data showed distinct temporal trends: AC points were primarily used during the day, while DC points saw higher usage during morning and late afternoon peaks, aligning with travelling times. The study’s validation of simulation results against empirical data emphasized the importance of high-quality input for accurate grid impact assessments. These findings suggest the necessity for strategic placement of recharging infrastructure and provide practical insights for policymakers, urban planners, and utility companies to support sustainable electric vehicle integration.

Unlocking Grid Flexibility: Leveraging Mobility Patterns for Electric Vehicle Integration in Ancillary Services

The electrification of mobility has introduced considerable challenges to distribution networks due to varying demand patterns in both time and location. This underscores the need for adaptable tools to support strategic investments, grid reinforcement, and infrastructure deployment. In this context, the present study employs real-world datasets to propose a comprehensive spatial–temporal energy model that integrates a traffic model and geo-referenced data to realistically evaluate the flexibility potential embedded in the light-duty transportation sector for a given study region. The methodology involves assessing traffic patterns, evaluating the grid impact of EV charging processes, and extending the analysis to flexibility services, particularly in providing primary and tertiary reserves. The analysis is geographically confined to the Lombardy region in Italy, relying on a national survey of 8.2 million trips on a typical day. Given a target EV penetration equal to 2.5%, corresponding to approximately 200,000 EVs in the region, flexibility bands for both services are calculated and economically evaluated. Within the modeled framework, power-intensive services demonstrated significant economic value, constituting over 80% of the entire potential revenues. Considering European markets, the average marginal benefit for each EV owner is in the order of 10 € per year, but revenues could be higher for sub-classes of users better fitting the network needs.

Integrated planning research of active distribution networks considering electric vehicle integration in the context of dual carbon

Abstract Against the backdrop of the dual carbon strategy, electric vehicles are experiencing rapid growth in popularity due to their environmentally friendly characteristics. However, their load volatility, randomness, and impact also present new challenges to the carrying capacity of the distribution network. Addressing the inadequacies of existing research in tackling these challenges from the perspective of distribution network planning, this paper proposes a method that integrates the optimization planning of distributed energy supply systems, flexible DC systems, and charging piles in the active distribution network by analyzing the spatiotemporal characteristics of electric vehicle charging loads and ensuring the basic charging needs of electric vehicles, utilizing flexible regulation resources such as V2G, flexible DC systems, and energy storage, and comprehensively considering system carrying capacity, green and low-carbon level, and economic factors through the analytic hierarchy process. Typical case studies demonstrate that through this method, the planning system can effectively enhance the carrying capacity of the distribution network, improve the self-consistency of green energy, and reduce the overall life-cycle energy costs in the region during operation.

Physical model-assisted deep reinforcement learning for energy management optimization of industrial electric-hydrogen coupling system with hybrid energy storage

Utilizing renewable energy sources (RESs), such as wind and solar, to convert electrical energy into hydrogen energy for industrial users with different types of energy storage can enhance the integration of green electricity, thereby replacing fossil fuels like natural gas. In the energy management optimization of industrial electric‑hydrogen coupling system (EHCS) with high RESs integration, the traditional optimization methods cannot effectively address the nonlinear characteristics of equipment and stochastic RES generation, while the model-free reinforcement learning methods struggle to improve the training efficiency and may lead to constraint violation. To address this challenge, this paper proposes a short time scale energy management approach for EHCS based on physical models assisted deep reinforcement learning (DRL). Firstly, the energy management optimization model of the EHCS is developed based on the operation characteristics of the equipment within the system. Secondly, the energy management model of EHCS is formulated as a DRL framework. The DRL agent is efficiently trained with the assistance of the action transformation which takes into account the physical characteristics of the equipment during operation. Finally, a case study is conducted to verify the effectiveness of the proposed model for achieving high-efficiency agent training, reducing decision-making time for equipment scheduling, addressing the stochastic RES generation, and realizing the economic operation of EHCS with good performance based on the equipment characteristics.