Abstract:In island mode, microgrids need to operate independently from traditional power systems, efficiently coordinating internal ener?gy to ensure the continuity and efficiency of energy supply. The twin delayed deep deterministic policy gradient algorithm significantly im?proves the processing efficiency and accuracy of complex continuous control tasks through policy delay updates and the introduction of du?al Q networks. Based on this way, an energy optimization allocation strategy is designed for microgrids embedded with fuel cells based onthe TD3 algorithm, to improve the stable power supply capacity and quality of the microgrid system, reduce energy consumption and opera?tion costs, and enhance the system’s economy and reliability. Through comprehensive analysis, the comprehensive performance of the de?signed energy optimization allocation strategy in different scenarios is comprehensively evaluated. The results show that by optimizing thecharging and discharging modes and ratios of fuel cell systems, the energy optimization allocation strategy designed based on TD3 algo?rithm performs better than traditional algorithms in improving energy allocation efficiency, shortening response time, and reducing operat?ing costs. The research results have verified the efficient adaptability of TD3 algorithm in dealing with fluctuations in renewable energygeneration power output and changes in load demand, and it has wide applicability in practical energy management scenarios.

Abstract:The selection of energy station sites and planning of thermal network layout are one of the most crucial aspects in the process ofregional district heating and cooling station planning. Existing algorithms for energy station site selection and thermal network planningmostly adopt a“two-step method”which separates the problem of load allocation from that of network layout, leading to inconsistent deci?sion-making criteria during the decision process. In consequence, the result of load allocation as well as the network layout may not be opti?mal. To address this issue, a multi-site selection and thermal network planning algorithm based on dynamic parallel competition mecha?nism is proposed. This algorithm directly compares the ways in which loads are connected to various energy station networks, synchronous?ly determining the ownership of load points and corresponding optimal network layout schemes. Case studies demonstrate that the pro?posed dynamic parallel competition algorithm ensures consistency between load allocation and network layout decisions, thereby yieldingsuperior planning results compared to the traditional“two-step method”.

Abstract:To address the difficulties in evaluating the priority order of key technologies in the demonstration application of distributionnetworks and quantifying the degree to which demonstration benefits are affected by regional development differences, a technology demon?strate on application optimization evaluation model that took into account the development of key technologies, application value and thedifference of regional indicators guided by“double S”index is proposed. Based on the internal and external matrix to measure the demandof regional power network differentiated development, a fuzzy comprehensive evaluation method is combined to quantify the demonstrationbenefits of key technologies. The continuous interval order weighted average operator improved analytic hierarchy process and entropyweight method are used to optimize CRITIC algorithm to calculate the subjective and objective weights, and the game theory is introducedto construct the subjective and objective combination weighting method. The intuitionistic fuzzy multi-attribute decision-making method isused to construct the technology demonstration optimization evaluation model. The simulation results show that proposed method can quan?tify the priority of key technology demonstration, and can identify the differences of technology demonstration in different regions, whichprovides a reference for the investment decision of key technology demonstration on the distribution network side, and helps to improve theinvestment efficiency and efficiency of distribution network.

Abstract:Reactive power sharing among distributed generators（DG）is a key problem in droop control based microgrid operation. Thecauses of unequal reactive power sharing include feed impedance differences, load differences, and uneven distribution of DG in size andposition. Therefore, a mixed-integer linear programming（MILP）problem for microgrids is presented to achieve proportional reactive powersharing among microgrids. Firstly, the optimum size and position of DG are studied, and various nonlinear terms involved are linearized indetail. Then a one-day advance schedule is generated on these DGs for a given load profile. After that, an actual ZIP load model is used tomodel the load more accurately. Finally, the proposed method is tested on a modified 33-bus network. The experimental results verify theaccuracy of the proposed planning and scheduling methods

Abstract:Considering the influence of electric vehicle load, a capacity optimization configuration method of micro-grid with WT-PV-DEBES considering electric vehicles is proposed. The modeling methods of load, wind power, photovoltaic system, battery energy storage anddiesel power generation in the microgrid are presented. Considering the dynamic characteristics of the test system, the Grey Wolf Optimiz?er is used to opti-mize the capacity of wind turbine, photovoltaic system, battery energy storage and diesel generator with the goal of mini?mizing the total cost of the micro grid system. Taking an actual 17 nodes microgrid as an example, the simulation results show that the loadin the microgrid system is provided by distributed new energy as far as possible, which effectively reduces greenhouse gas emissions, whileminimizing the total cost of the mi-crogrid system. The system can supply load economically and reliably according to the proposed method。

Abstract:At present, the development of distributed photovoltaic in the entire county is progressing in an orderly manner. However, due tothe small and dispersed load volume of the distribution network in remote areas, the large-scale integration of distributed photovoltaic intothe distribution network brings uncertainty to the system operation, and is prone to risks of exceeding limits such as high or low voltage. Aprobabilistic evaluation method for system voltage and branch power flow to quantify the risk of exceeding limits is introduced. At the sametime, a two-layer optimization scheduling model for mobile energy storage in distribution networks considering the risk of exceeding limitswas established, and a dynamic stochastic optimal power flow algorithm was adopted to solve the established model. Taking the IEEE 33node system as an example, the scheduling control strategy of mobile energy storage is analyzed. The calculation results show that usingthe optimization scheduling method described in this article can not only ensure high operational efficiency of mobile energy storage, butalso improve the voltage quality qualification rate of the distribution system, reduce system network losses, and improve system power sup?ply reliability.

Abstract:In recent years, China has been developing rapidly in the field of electric vehicles, but when a large number of electric vehiclesare connected to the power grid, it will pose a challenge to the stability and reliability of the power grid. V2G technology can balance thepeak-to-valley difference of the grid and promote the consumption of new energy, improve the flexibility of the grid, and thus effectively al?leviate the problems caused by the uncontrolled access of a large number of electric vehicles to the grid. Taking the EV-elocity project inthe UK as a case study, the environmental value, battery aging and user feedback of the V2G project are analyzed in depth, which are alsoissues that have received relatively little attention in carrying out the V2G project in China at present. In addition, the implementation ofV2G projects in China is also briefly introduced, and the problems faced by V2G research in China at the level of project development andresearch direction are pointed out. Finally, relevant suggestions are made with respect to environmental value, battery aging, user experi?ence and acceptance, which are aimed at narrowing the gap with developed countries in the field of this technology so as to promote the de?velopment of V2G projects and the application of V2G technology in China.

Abstract:Aiming at a new form that electricity users are increasingly transforming into“power prosumers”, transmission and distributionrates system of California USA is analyzed and summarized. Firstly, basic content of transmission and distribution services for power pro?sumers is analyzed. Then, charging standards of interconnection process fees, interconnection facilities cost fees, and grid usage fees forpower prosumers are introduced. Next, definition, measurement rules, and charging rules for standby rates in detail are introduced indetail. Finally, the transmission and distribution rates between China and California are compared, and some suggestions are put forward.

Abstract:The potential analysis and aggregate control of temperature control loads are generally required, but the existing schedulingmode of direct control of temperature control load affects the user’s privacy. exergy analysis based on exergy power plant peak load poten?tial assessment and regulation strategy is proposed. Firstly, exergy analysis shows that exergy comfort temperature range of human bodycan be accurately evaluated to determine the peak load capacity range of residential TCLs, and then determine the response capability ofresidential TCLs. Then, virtual power plant is considered as the main body for regulating multiple TCLs. Based on the utility function ofthe TCLs user, the price-power bidding curve is obtained, and the response adjustment capability information is submitted. Finally, afterreceiving the bidding curves of multiple users, VPP takes the revenue maximization as the optimization goal and the purchase price as thedecision variable to obtain the optimal scheduling strategy of VPP. Exergy simulation results verify the effectiveness of exergy peak-loadpotential assessment and regulation strategy for a virtual power plant based on exergy analysis.

Abstract:The new power system consists of four major elements such as source, network, load and storage. The distributed“energy stor?age”characteristics of electric vehicles can complement new energy generation, alleviate the impact of intermittent and fluctuation of newenergy output on the power grid, and effectively reduce the capacity of storage allocation in the power grid. However, the disorderly charg?ing behavior of EVs can aggravate the difference between new energy output and load, so it is necessary to control the charging of EVs inan aggregated manner. Firstly, the disordered charging behavior of different types of electric vehicles is simulated using the Monte Carlomethod, and the impact of disordered charging on the balance between source and load is analyzed. Secondly, the improved k-means++clustering algorithm is used to divide the result of disorderly charging and the difference of new energy into four clustering periods, name?ly,“sharp, peak, flat and valley”. Finally, an optimization strategy for charging aggregation control during overlapping clustering periods isproposed, which is verified in combination with the“Lingfeng Zero-Carbon Evolution Park”project in Ningbo, Zhejiang Province, and theresults show that, under the premise of impairing the charging satisfaction of EV owners as less as possible, this strategy can effectively re?duce the imbalance between new energy output and load, and combined with fixed-energy storage configurations, it can achieve a new typeof electric power and load imbalance. Combined with the fixed energy storage configuration, it enables source-load balancing in new powersystems.

Abstract:Existing guidance method of demand-side participating in flexible interaction do not fully consider the influence of social infor?mation such as preferential information on load, resulting in a large deviation between the actual role of the guiding cues and the expectedresults. In view of such situation, the Attention-LSTM model is used to forecast the load adjustment under the effect of social information,such as guiding cues. Coupon guidance method could be determined with this model. Take time of use tariff and coupon as an example,coupon guidance method considering the influence of preferential information is proposed, to guide consumers to change their electricityconsumption behaviors for less cost of purchasing electricity. And on this basis, a decision-making model of purchase-sale strategy consid?ering the influence of preferential information in multi-level electricity market is established, to maximize the revenue of electricity retail?ers and verify the feasibility and effectiveness of the proposed guidance method, which is solved by particle swarm optimization algorithmand CPLEX, to obtain the optimal guidance strategy and purchase strategy of electricity retailers. An example based on Australian datashows that the electricity purchasing and selling optimization model of electricity ratailers base on coupons guiding can effectively guidecustomers to actively participate in the interaction.

Abstract:The frequent occurrence of extreme weather and continuous increase in power load have challenged the balance between powersupply and demand in high-proportion renewable energy power systems. It is imperative to expedite the development of a new power loadmanagement system for effective monitoring and management of load resources. This system encompasses multiple security zones with di?verse businesses possessing distinct communication requirements, thereby lacking an effective communication network architecture. Usingtypical businesses as case studies, the analysis focuses on the characteristics and communication requirements of the service, while com?paring the adaptability of different communication technologies and businesses. It is proposed to adopt 5G communication technology toconstruct a new power load management system communication network. Then, based on the three networking solutions of 5G independentprivate network, 5G hard slicing, and 5G soft slicing, system network architecture and slicing schemes are devised for varying securityzones. Finally, prospective research technology of the new power load management system’s 5G communication network is contemplated.

Abstract:Lithium battery industrial park can make full use of the advantages of resources to achieve scale production of lithium battery,but the energy consumption intensity is large, and brings energy and link problems, so it is necessary to optimize the production processand achieve low-carbon development. At present, there are many researches on the process optimization of lithium battery manufacturingprocess, but there are less researches on the analysis and optimization of system performance at the campus level. The purpose is to studythe characteristics of energy production and consumption in lithium battery industrial park, and put forward the optimization and improve?ment scheme of the system. Firstly, the steady-state model of typical equipment and links in the lithium battery industrial park is estab?lished. Then, the exergic analysis and thermal economic analysis model of exergic analysis and thermal economic analysis of industrialpark based on Sobol method are built. Finally, the feasibility and effectiveness of the proposed method are verified by an example analysis.The calculation results show that hot blast furnace has the lowest exergic efficiency and the highest total exergic cost in the park, and hasthe highest impact on the exergic cost of system products, so it is necessary to focus on improving its performance.

Abstract:Demand response trading not only promotes the balance between electricity supply and demand, but also has the potential to re?duce carbon emissions. The carbon emission reduction potential of ALs participating in DR trading is explored. Therefore, the economicbenefits of ALs’participation in DR trading should be accompanied by carbon emission reduction benefits. Firstly, considering the role ofALs in reducing carbon emissions, a dual incentive type of demand response model based on response volume and carbon emission reduc?tion is proposed. Secondly, based on the proposed dual incentive type of demand response model, a platform-led demand response tradingmodel is proposed to account for carbon trading. Then, the fuzzy decision-making method is used to solve the Pareto optimal solution of theproposed multi-objective model in the solution set space. Finally, the carbon reduction effects of five types of ALs, industrial customers,commercial customers, residential customers, electric vehicle charging zones, and 5G base stations, are investigated on the improved IEEE30-node system to verify the effectiveness of the proposed model.

Abstract:Current electrical load forecasting models are constrained by high data complexity, data scarcity, limited generalization, and in?sufficient adaptability to dynamic socio-economic factors, impeding their utility in sophisticated grid planning. To meet the planning andscheduling requirements of power grids or large-scale wind, solar, thermal, storage, grid, and load energy base projects, an integrated tech?nology has been proposed. Grey forecasting, spatial load density forecasting, variational autoencoders, and deep causal convolutional neu?ral networks are combined for medium to long-term load forecasting. The introduction of an ordered weighted averaging differential opera?tor amalgamates various predictive techniques, thereby refining accuracy. The experimental results demonstrate that the proposed methodexhibits higher accuracy and robustness compared to traditional methods, particularly in the context of long-term electric load forecasting,effectively enhancing the reliability and applicability of the predictions. This technology effectively overcomes issues of data complexity,data scarcity and model generalization inherent in conventional methods, while adjusting to socio-economic dynamics. It provides substan?tial decision-making support for the planning and evolution of power networks and large-scale integrated energy projects.

Abstract:Low-cost inspection scheme based on industrial non-invasive load identification is proposed to address the environmental moni?toring issues of equipment operation on construction sites. Firstly, load characteristics of dust removal equipment that suppresses air pollu?tion and construction equipment such as static pressure machines that generate noise and vibration pollution are analyzed. Then, a multistage event detection and identification method for environmental inspection is proposed, which overcomes the identification difficulty ofdust removal equipment easily submerged by construction equipment loads. Lastly, a real case is used to verify, and experimental resultsshow that the proposed algorithm greatly improves the detection ability and anti-noise interference ability for complex process events, andrealizes synchronous and efficient detection of the start stop process of construction equipment and dust removal equipment.

Abstract:With the continuous improvement of the electrification level of smart fishing grounds, the proportion of environmentally sensi?tive loads in fishing grounds increases. Load forecasting should fully consider the impact of environmental climate change on the operationof fishery electrical equipment. Firstly, the data collected by the fishing ground monitoring platform are analyzed and preprocessed, andthe typical scenes are divided according to the climatic characteristics. Secondly, the least square method is used to decompose the meteo?rological load affected by the climate, and the correlation coefficient method is used to analyze the correlation between the load and the me?teorological index. The principal component analysis method is used to transform multiple single meteorological indicators into a few com?prehensive indicators in SPSS. The comprehensive meteorological indicators and meteorological load data are used to train the BP neuralnetwork, and the load forecasting model of fishery electrical equipment based on BP neural network in typical scenarios is constructed. Fi?nally, an example is verified based on the operation of fishery electrical equipment and climate index data on the target day. The resultsshow that the model reflects the impact of environmental climate change on the load of fishery electrical equipment, and the error accuracymeets the actual engineering needs.

Abstract:To achieve the dual“low-carbon”goals, China is developing new energy sources with great efforts. However, the substantial in?crease in power fluctuation and intermittency of these new energy sources has significantly added to the challenge of maintaining powerbalance. There is an urgent need to establish a power balance mechanism in the electricity market that can adapt to the extremely high pen?etration of new energy sources. Germany’s energy structure shares a high degree of similarity with China. Hence, analyzing Germany’selectricity market and balance mechanism provides valuable insights. Based on the analysis of the German electricity market, Germany’spower balance mechanism is systematically reviewed with the concept of“Balancing Group”at its core. Drawing on Germany’s experienc?es and considering the current state of China’s electricity market, suggestions are offered upon the development of China’s power balancemechanism, from the perspective of reducing balance demand, decentralizing balance responsibilities, accommodating new energy sources,devolving some dispatch rights,and innovation research direction.