Power distribution area energy management method and related device

Abstract

The invention belongs to the field of electric power automation, and discloses a power distribution area energy management method and a related device, and the method comprises the steps: obtaining the type of a power distribution area, and obtaining each optimization objective function coefficient of a multi-objective optimization function of the power distribution area based on a fuzzy controller corresponding to the type of the power distribution area; and based on each optimization objective function coefficient of the multi-objective optimization function of the power distribution area, solving the multi-objective optimization function of the power distribution area to obtain a multi-objective optimization strategy of the power distribution area. According to the method, adaptive weight optimization of the optimization objective function can be carried out by adopting fuzzy control logic according to different scenes, so that the final multi-objective optimization function of the power distribution area better fits the actual situation of the current power distribution area, multi-objective collaborative optimization for different scenes is realized, refining of the power distribution area energy management strategy is completed, and the power distribution area energy management efficiency is improved. The operation efficiency and stability of a power system in a power distribution area are improved, and comprehensive collaborative optimization of various optimization objectives such as energy conservation, emission reduction and economical efficiency is effectively achieved.

Description

Technical Field

[0001] The invention belongs to the field of electric power automation and relates to a distribution station area energy management method and related devices. Background Art

[0002] In modern power systems, with the widespread application of distributed energy and renewable energy, the rapid development of new loads such as distributed photovoltaic power generation, wind power generation and electric vehicle charging piles has significantly increased the volatility and uncertainty of power loads. The complex and diverse energy usage scenarios of low-voltage distribution substations have brought unprecedented challenges to the power system. At the same time, the introduction of energy storage systems has further complicated the energy management of power systems.

[0003] Existing research classifies traditional distribution substations mainly according to the type of load and power source. However, with the addition of more and more new loads and new equipment, the number of various components in modern substations continues to increase. At the same time, the classification of traditional distribution substations is mainly determined by the main load type, large load user type and main power supply source in the substation. With the increasing proportion of distributed renewable energy represented by photovoltaics and wind turbines, and new loads represented by electric vehicle charging piles in various distribution networks, the original substation classification method cannot accurately classify the substation, thus affecting the improvement of substation power quality and substation upgrades, and to a certain extent, affecting the construction of modern power grids. In addition, the existing energy management strategy is relatively extensive and fails to be refined and optimized for different substation scenarios, making it difficult to effectively achieve energy conservation, emission reduction and economic coordinated optimization. Summary of the invention

[0004] The purpose of the present invention is to overcome the above-mentioned shortcomings of the prior art and provide a distribution station area energy management method and related devices.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] According to a first aspect of the present invention, a method for energy management of a distribution substation area is provided, comprising: obtaining the type of the distribution substation area, and obtaining coefficients of each optimization objective function of a multi-objective optimization function of the distribution substation area based on a fuzzy controller corresponding to the type of the distribution substation area; solving the multi-objective optimization function of the distribution substation area based on the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation area, and obtaining a multi-objective optimization strategy for the distribution substation area.

[0007] Optionally, the method of obtaining the type of the distribution station area includes: obtaining classification characteristic index data of the distribution station area; according to the classification characteristic index data of the distribution station area, using an improved K-means pre-clustering algorithm based on split-coupling to obtain each clustering cluster of the distribution station area; obtaining the type of each clustering cluster and using it as the type of each distribution station area in the clustering cluster.

[0008] Optionally, the classification characteristic index data of the distribution station area include: photovoltaic characteristic data, flexible load characteristic data, charging pile characteristic data, seasonal characteristic data, time period characteristic data and climate condition characteristic data; the types of distribution station areas include: areas with photovoltaic output as the main power source, areas with flexible load as the main power source, areas with charging pile load as the main power source and mixed scenario areas.

[0009] Optionally, the fuzzy controller corresponding to the type of the distribution station area is used to obtain the optimization objective function coefficients of the multi-objective optimization function of the distribution station area, including: obtaining the fuzzy control input variables of the distribution station area; wherein the fuzzy control input variables include: station load, distributed power generation, carbon emissions, energy storage status and electricity price; inputting the fuzzy control input variables of the distribution station area into the fuzzy controller corresponding to the type of the distribution station area to obtain the fuzzy control output variables of the distribution station area; and using the fuzzy control output variables of the distribution station area as the optimization objective function coefficients of the multi-objective optimization function of the distribution station area.

[0010] Optionally, the multi-objective optimization function of the distribution station area includes an objective function, constraints and a control object; the objective function F is:

[0011]

[0012] Among them, ω i is the coefficient of the i-th optimization objective function, f i (x) is the i-th optimization objective function, n is the number of optimization objective functions; the constraints include energy balance constraint, energy storage power limit constraint and energy storage state constraint; the control objects include: output regulation of distributed energy, charge state management of energy storage system, charging pile load management and electricity price signal response management.

[0013] Optionally, the optimization objective function includes: energy-saving optimization objective function f1(x):

[0014]

[0015] Where T is the total time step; E loss (t) is the energy loss at the tth moment; E total (t) is the total energy at the tth moment, including charging and discharging energy; emission reduction optimization objective function f2(x):

[0016]

[0017] Among them, P g (t) is the power consumption of the distribution station area at time t; P c (t) and P d (t) are the charge and discharge amounts of the energy storage at time t; ηch (t) and η dis (t) are the charging efficiency and discharging efficiency of energy storage at time t; α g (t) and α e (t) are the carbon emission factor of power supply from the power grid and the carbon emission factor of energy storage charging at time t; the economic optimization objective function f3(x):

[0018]

[0019] Among them, C buy (t) is the electricity purchase cost; M(t) and O(t) are the operation and maintenance cost and energy storage system degradation cost of the distribution station area at time t, respectively; λ ch (t) and λ dis (t) is the electricity purchase price and electricity sales price at time t.

[0020] According to a second aspect of the present invention, there is provided a distribution substation energy management system, comprising: a coefficient adaptation module, for obtaining the type of the distribution substation, and obtaining coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation based on a fuzzy controller corresponding to the type of the distribution substation; and a strategy optimization module, for solving the multi-objective optimization function of the distribution substation based on the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation, and obtaining a multi-objective optimization strategy for the distribution substation.

[0021] Optionally, the method of obtaining the type of the distribution station area includes: obtaining classification characteristic index data of the distribution station area; according to the classification characteristic index data of the distribution station area, using an improved K-means pre-clustering algorithm based on split-coupling to obtain each clustering cluster of the distribution station area; obtaining the type of each clustering cluster and using it as the type of each distribution station area in the clustering cluster.

[0022] According to a third aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned distribution station area energy management method when executing the computer program.

[0023] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned distribution station area energy management method are implemented.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] The energy management method for a distribution substation area of ​​the present invention first obtains the type of the distribution substation area, and then obtains the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation area based on the fuzzy controller corresponding to the type of the distribution substation area. The fuzzy control logic can be used to perform adaptive weight optimization of the optimization objective function according to different scenarios, so that the final multi-objective optimization function of the distribution substation area is more in line with the actual situation of the current distribution substation area, and multi-objective collaborative optimization for different scenarios is achieved. The energy management strategy of the distribution substation area is refined, thereby improving the energy management effect of the distribution substation area, improving the operating efficiency and stability of the power system in the distribution substation area, and effectively realizing the comprehensive collaborative optimization of various optimization objectives such as energy saving, emission reduction and economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 The present invention is a flowchart of a method for energy management of a distribution station area according to an embodiment of the present invention.

[0027] Figure 2 This is a fuzzy logic control principle diagram of an embodiment of the present invention.

[0028] Figure 3 This is a schematic diagram of a method for energy management in a distribution station area according to an embodiment of the present invention.

[0029] Figure 4 It is a structural block diagram of the energy management system of a distribution station area according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0033] See also Figure 1 In one embodiment of the present invention, a distribution substation energy management method is provided to achieve multi-objective optimization of source, grid, load and storage within the distribution substation, refine the energy control strategy, and assist in the construction of a new power system.

[0034] Specifically, the power distribution area energy management method of the present invention includes the following steps:

[0035] S1: Obtain the type of the distribution substation, and based on the fuzzy controller corresponding to the type of the distribution substation, obtain the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation.

[0036] S2: Based on the coefficients of the optimization objective functions of the multi-objective optimization function of the distribution substation area, the multi-objective optimization function of the distribution substation area is solved to obtain the multi-objective optimization strategy of the distribution substation area.

[0037] The energy management method for a distribution substation area of ​​the present invention first obtains the type of the distribution substation area, and then obtains the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation area based on the fuzzy controller corresponding to the type of the distribution substation area. The fuzzy control logic can be used to perform adaptive weight optimization of the optimization objective function according to different scenarios, so that the final multi-objective optimization function of the distribution substation area is more in line with the actual situation of the current distribution substation area, and multi-objective collaborative optimization for different scenarios is achieved. The energy management strategy of the distribution substation area is refined, thereby improving the energy management effect of the distribution substation area, improving the operating efficiency and stability of the power system in the distribution substation area, and effectively realizing the comprehensive collaborative optimization of various optimization objectives such as energy saving, emission reduction and economy.

[0038] In one possible implementation, the method of obtaining the type of the distribution station area includes: obtaining classification characteristic index data of the distribution station area; according to the classification characteristic index data of the distribution station area, using an improved K-means pre-clustering algorithm based on split-coupling to obtain each clustering cluster of the distribution station area; obtaining the type of each clustering cluster and using it as the type of each distribution station area in the clustering cluster.

[0039] Specifically, we first analyze the differences in energy structure between new distribution substations and traditional distribution substations, including the impact of the introduction of distributed power sources and energy storage systems on the energy sources of distribution substations; at the same time, we examine the differences in power network architecture between new distribution substations and traditional distribution substations, such as the impact of flexible load access and substation energy storage systems on the regulation capacity of grid load distribution; on this basis, we explore the operating characteristics of new distribution substations and traditional distribution substations in terms of energy scheduling, supply and demand matching, etc., such as the impact of the volatility of renewable energy generation on the power balance of distribution substations. There are many differences between new distribution substations and traditional distribution substations, mainly including:

[0040] 1. Diversification of energy sources: New distribution substations are more inclined to introduce distributed energy and energy storage systems, such as solar photovoltaic, wind power generation and battery energy storage, to achieve diversification of energy sources and the use of renewable energy. Traditional distribution substations mainly rely on centralized power plants, such as thermal power generation and nuclear power generation, with a relatively single energy source.

[0041] 2. Energy efficiency: By introducing distributed energy and energy storage systems, new distribution substations can more flexibly utilize renewable energy and produce, store and consume electricity locally, thereby improving energy efficiency. Traditional distribution substations may have problems such as imbalance in energy supply and demand and large energy transmission losses, and low energy efficiency.

[0042] 3. Power network architecture: New distribution substations are usually more flexible in terms of power network architecture, with more flexible load access and energy storage system regulation capabilities, and can better adapt to the volatility of renewable energy and changes in power demand. However, the power network architecture of traditional distribution substations is relatively fixed, lacks support for flexible loads and energy storage systems, and has weak grid load regulation capabilities.

[0043] 4. Power supply reliability: The new distribution substation can improve power supply reliability, reduce dependence on traditional power grids, and reduce the risk of power outages by introducing distributed energy and energy storage systems. The power supply reliability of traditional distribution substations is limited by the stability and capacity of centralized power plants and traditional power grids, and there is a high risk of power outages.

[0044] 5. Changes in load characteristics: New distribution substations often have more flexible loads, that is, the ability to flexibly adjust and control power demand. At the same time, the introduction of energy storage systems also enables new distribution substations to better cope with load fluctuations and peak-valley differences, thereby improving energy efficiency and power supply quality.

[0045] 6. Differences in energy management and operation modes: New distribution substations usually adopt more intelligent and automated modes in energy management and operation. Through data analysis, artificial intelligence and Internet of Things technologies, new distribution substations can accurately monitor, predict and control energy, thereby improving energy efficiency and reducing operating costs.

[0046] 7. Emphasis on environment and sustainable development: New distribution substations pay more attention to environmental protection and sustainable development. By adopting clean energy and low-carbon technologies, as well as optimizing energy utilization and management, new distribution substations can reduce carbon emissions and environmental pollution, and promote sustainable utilization and development of energy.

[0047] Then, according to the differences in characteristics between the new distribution substation and the traditional distribution substation, the key factors that may affect the operation of the distribution substation are determined, and an index system that comprehensively considers the operation status of the substation is designed. The index system is shown in Table 1:

[0048] Table 1

[0049]

[0050] In view of the characteristics of the new distribution area, it is necessary to adjust the relevant influencing factors to adapt to its characteristics. The following are the influencing factors adapted to the characteristics of the new distribution area:

[0051] 1. Factors affecting distributed energy access: including the type, capacity and volatility of distributed energy. New distribution substations may use a large number of distributed energy, so it is necessary to consider the impact of their access on grid operation and stability.

[0052] 2. Influencing factors of flexible load regulation: The characteristics and regulation capacity of flexible loads have an important impact on the operation of the substation. Therefore, factors such as the access ratio, response speed and regulation range of flexible loads need to be considered.

[0053] 3. Factors affecting the application of energy storage systems: The capacity, charge and discharge rate, and dispatch strategy of energy storage systems have a significant impact on the operation of new distribution substations. The application scenarios and operation modes of energy storage systems need to be considered.

[0054] 4. Intelligent dispatching and control influencing factors: Intelligent dispatching and control technology is crucial to the operation of new distribution substations. Factors such as the access ratio of intelligent devices and the optimization of control algorithms need to be considered.

[0055] 5. Grid interconnection and coordination factors: The interconnection and coordination between the new distribution substation and the grid has an impact on the safe and stable operation of the power system. It is necessary to consider factors such as the interconnection method between the substation and the grid and the coordination and dispatching mechanism.

[0056] 6. Environmentally friendly factors: New distribution substations should focus on being environmentally friendly, so factors such as the proportion of renewable energy and the application of emission reduction technologies need to be considered.

[0057] 7. Operation management and maintenance factors: The operation management and maintenance of new distribution substations also need to be adjusted, including factors such as equipment status monitoring and fault diagnosis and processing.

[0058] Based on the above analysis, according to indicators such as the proportion of distributed energy installed capacity and power generation, in this implementation, the distribution stations are divided into the following categories:

[0059] 1. Areas dominated by photovoltaic power output: If the proportion of distributed photovoltaic installed capacity is high, and photovoltaic power generation accounts for a large proportion of the overall power generation, the distribution area can be classified as an area dominated by photovoltaic power output. This type of distribution area mainly relies on solar photovoltaic power generation and has obvious photovoltaic characteristics.

[0060] 2. Flexible load-dominated distribution area: If the proportion of flexible load access is high, while the proportion of distributed energy installed capacity is low, and the load fluctuation range is large and the load regulation capability is strong, then the distribution area can be classified as a flexible load-dominated distribution area. This type of distribution area has strong load-side characteristics.

[0061] 3. Areas with charging pile load as the main load: If the installed capacity of charging piles accounts for a high proportion, and the charging pile load accounts for a large proportion of the overall load, the distribution area can be classified as an area with charging pile load as the main load. This type of distribution area is mainly used for electric vehicle charging and has obvious characteristics of electric vehicle charging piles.

[0062] 4. Hybrid scenario substation: Some substations may have a mix of various sources, loads, and storage, including distributed energy such as photovoltaic and wind power, flexible loads, charging piles and other load types, and may also be equipped with energy storage systems. This type of distribution substation has a complex energy structure and load characteristics, and is classified by comprehensively considering multiple factors.

[0063] At the same time, in order to build a more comprehensive and refined classification standard, in this implementation, the following dimensions are added for consideration:

[0064] 1. Seasonality. Spring: Wind power output is high, photovoltaic output gradually increases, and the load is relatively stable. Summer: Photovoltaic output is the highest, load peaks are obvious (such as air conditioning load), and there is a large demand for flexible load regulation. Autumn: Photovoltaic and wind power outputs are relatively balanced, and the load is relatively stable. Winter: Wind power output is high, photovoltaic output decreases, load peaks (such as heating load), and there is a large demand for energy storage regulation.

[0065] 2. Time period. Daytime: The photovoltaic output is the highest, the electric vehicle charging load is low, and the load regulation demand is small. Nighttime: The photovoltaic output is zero, the wind power output fluctuates greatly, the electric vehicle charging load is high, and the energy storage regulation demand is large.

[0066] 3. Climate conditions. Sunny day: PV output is high, wind power output is less affected. Cloudy day: PV output is low, load-side power demand increases. High wind speed: wind power output is high, energy storage system needs to adjust wind power fluctuations. Low wind speed: wind power output is low, need to rely on PV and energy storage system.

[0067] The above classification standards are integrated, and by inviting experts in distribution network operation, maintenance and management to discuss and evaluate, further optimize and adjust, and construct a comprehensive and detailed distribution station area classification standard, namely a multi-dimensional scenario classification standard:

[0068] 1. Areas dominated by photovoltaic power output. Classification characteristics: high proportion of photovoltaic installed capacity, high photovoltaic power generation. Feature description: Consider seasonal and climatic conditions, such as the maximum photovoltaic output on sunny days in summer, with strong adaptability. Seasonal influence: The output is highest in summer and lower in winter, requiring energy storage adjustment. Time period influence: high output during the day and low output at night. Climate condition influence: high output on sunny days and low output on cloudy days. Optimization standard: In areas with high photovoltaic output, further refine the fluctuation characteristics of photovoltaic output and optimize it in combination with the regulation capability of the energy storage system.

[0069] 2. Substations dominated by flexible loads. Classification characteristics: high flexible load ratio, low distributed energy installed capacity, and large load fluctuations. Feature description: Consider time periods and seasonality. For example, in summer, the demand for flexible load regulation is large and the regulation capacity is strong during the day. Seasonal impact: The regulation demand is high in summer and relatively low in winter. Time period impact: The regulation demand is high during the day and low at night. Impact of climate conditions: The load demand increases on cloudy days. Optimization criteria: Increase consideration of load regulation response time to ensure rapid response and high efficiency of load regulation in substations with high flexible load access.

[0070] 3. Areas dominated by charging pile loads. Classification characteristics: high proportion of installed capacity of charging piles, high load of charging piles. Feature description: Consider the time period, such as high charging load at night and uneven load distribution during the day and night. Seasonal influence: high demand for electric vehicle charging in winter and summer. Time period influence: peak charging at night and low during the day. Impact of climatic conditions: charging demand may change in bad weather. Optimization criteria: Combined with the analysis of electric vehicle charging behavior by experts, the time period distribution characteristics of charging pile loads are further refined to facilitate more accurate prediction of charging peaks and lows.

[0071] 4. Mixed scenario substation. Classification characteristics: A mixture of multiple distributed energy sources and load types, equipped with energy storage systems. Feature description: Consider seasonality, time period and climate conditions, such as the coordinated regulation of wind power and energy storage systems in winter, which is highly complex. Seasonal influence: High wind power and energy storage output in winter, high photovoltaic output in summer. Time period influence: Photovoltaic peak during the day, energy storage regulation at night. Climate condition influence: High photovoltaic power on sunny days, high wind power at high wind speeds. Optimization criteria: Increase consideration of the coordinated dispatching capabilities of multiple energy sources and loads, and optimize in combination with dispatching strategies under different seasons and climate conditions.

[0072] These classification standards can better reflect the diverse characteristics and operational requirements of distribution substations, and provide a scientific basis for subsequent distribution substation clustering and multi-objective energy management.

[0073] Optionally, before clustering, it is necessary to collect and preprocess various types of classified characteristic indicator data of the distribution station area. The classified characteristic indicator data include, but are not limited to: photovoltaic characteristic data, flexible load characteristic data, charging pile characteristic data, seasonal characteristic data, time period characteristic data, and climate condition characteristic data. Among them, photovoltaic characteristic data include the proportion of photovoltaic installed capacity, the proportion of photovoltaic power generation, etc., flexible load characteristic data include flexible load proportion, load fluctuation range, load regulation capability, etc., charging pile characteristic data include charging pile installed capacity proportion, charging pile load proportion, etc., seasonal characteristic data, time period characteristic data, and climate condition characteristic data can be seasonal influences, time period influences, and climate condition influences on the distribution station area. These data are standardized to make them comparable and convenient for clustering algorithm processing.

[0074] In this implementation, an improved K-means pre-clustering algorithm based on split-coupling is used to obtain the clusters of the distribution station area. The improved K-means pre-clustering algorithm based on split-coupling is a split-coupling algorithm, which uses the CHI (Chi-Square Statistic) index as the effectiveness evaluation index, and uses binary K-means as the splitting algorithm to select clusters or cluster pairs that can increase the effectiveness index for splitting and coupling operations, until the split-coupling operations on all clusters or cluster pairs cannot increase the effectiveness index, indicating that the algorithm converges, and outputs the number of clusters at this time. The specific steps are as follows:

[0075] 1. Set the data sample set size to N, the split flag B=0, and the coupling flag E=0.

[0076] 2. Enter the split loop, split flag B = 0.

[0077] 3. Select the cluster that can increase the effectiveness index and use binary K-means to perform a split operation B=B+1.

[0078] 4. Repeat step 3 until all clusters cannot be split and the validity index cannot be increased.

[0079] 5. If the split flag bit B=0 and the coupling flag bit E=0, go to step 10; otherwise, go to step 6.

[0080] 6. Enter the coupling cycle, coupling flag E=0.

[0081] 7. Select the cluster pair that can increase the effectiveness index for coupling operation and update the cluster, E = E + 1.

[0082] 8. Repeat step 7 until all cluster pairs are coupled and the validity index cannot be increased.

[0083] 9. If the split flag bit B=0 and the coupling flag bit E=0, go to step 10; otherwise, go to step 2.

[0084] 10. The algorithm ends, the current cluster and the number of clusters are determined, and the clustering results are output.

[0085] The clustering results of the distribution substations are obtained by the improved K-means pre-clustering algorithm based on split-coupling. Combined with the above-mentioned multi-dimensional scene classification standards, the types of each cluster cluster are explained and defined according to the classification characteristic indicator data of each distribution substation in each cluster cluster in the clustering results, and used as the types of each distribution substation in the cluster cluster, such as the substation dominated by photovoltaic output, the substation dominated by flexible load, etc. Optionally, it is also possible to evaluate in combination with expert experience, and optimize and adjust the classification results in combination with the multi-dimensional scene classification standards to ensure the scientificity and accuracy of the classification. In addition, the classification results can be applied in actual distribution substations, the effectiveness of the classification can be verified through actual data, and the multi-dimensional scene classification standards and clustering methods can be further optimized based on feedback.

[0086] To further illustrate the accuracy of the classification method of the present invention, the classification accuracy of the classification method of the present invention is compared with that of the traditional single-index classification model. In order to verify the classification accuracy in detail, 100 actual known types of distribution station data are taken as an example, including photovoltaic output, flexible load, charging pile load, seasonal factors, time period factors and climate conditions. The accuracy indicators are recall rate and precision rate, and the calculation formula is as follows:

[0087]

[0088] Among them, R and P are recall rate and precision rate respectively; N T 、N S 、N Y They are the number of correctly classified areas, the total number of actual category areas, and the total number of predicted category areas.

[0089] The comparison of the classification results obtained by the two methods is shown in Table 2:

[0090] Table 2

[0091]

[0092]

[0093] By comparing and analyzing the data, it can be seen that the method of the present invention is superior to the traditional model in terms of classification accuracy, recall rate and precision. Taking 100 distribution substations as an example, the total number of correct classifications of the method of the present invention is 92, while that of the traditional model is 78. In the four categories of photovoltaic output-dominated substations, flexible load-dominated substations, charging pile load-dominated substations, and mixed scenario substations, the recall rates of the method of the present invention are 92.00%, 93.33%, 90.00% and 92.00%, respectively, which are higher than the 80.00%, 80.00%, 70.00% and 80.00% of the traditional model. In addition, the precision of the method of the present invention is also significantly higher than that of the traditional model in each category, which are 95.83%, 96.55%, 94.74% and 92.00%, respectively, while the precision of the traditional model is 66.67%, 75.00%, 77.78% and 86.96%, respectively. This shows that the method of the present invention is more accurate in identifying and predicting various types of distribution substation areas, and can better adapt to scene classification under various load conditions, thereby supporting its application in distribution substation area classification.

[0094] In a possible implementation, the fuzzy controller corresponding to the type of the distribution station area obtains the optimization objective function coefficients of the multi-objective optimization function of the distribution station area, including: obtaining the fuzzy control input variables of the distribution station area; wherein the fuzzy control input variables include: station load, distributed power generation, carbon emissions, energy storage status and electricity price; inputting the fuzzy control input variables of the distribution station area into the fuzzy controller corresponding to the type of the distribution station area to obtain the fuzzy control output variables of the distribution station area; and using the fuzzy control output variables of the distribution station area as the optimization objective function coefficients of the multi-objective optimization function of the distribution station area.

[0095] Specifically, through the detailed classification of distribution substations, different types of distribution substations can formulate appropriate energy management strategies in a targeted manner to achieve the refinement and intelligence of distribution substation operation. Scenario classification provides a clear direction and priority for the optimization strategy, and the energy management strategy flexibly adjusts the optimization target according to the classification results, making the connection between the two more natural and smooth. In this way, not only the stability and economy of the distribution substation operation are improved, but also the adaptability of the distribution substation to the changing environment is enhanced, thus providing strong support for achieving the energy conservation, emission reduction and sustainable development goals of the new distribution substation.

[0096] Therefore, based on the scene classification, in this implementation, a more refined multi-objective energy management strategy is adopted, that is, different optimization objectives are emphasized for different scenes, and the weights of these objectives also change accordingly. In order to effectively combine scene classification with the multi-objective energy management strategy, in this implementation, fuzzy logic control is used to select the size of the optimization objective function coefficient. This method can adaptively adjust the weights of each optimization objective function according to the specific scene, thereby achieving multi-objective optimization.

[0097] The principle block diagram of the fuzzy logic control system is as follows Figure 2 As shown, the core part of the fuzzy logic control system is the fuzzy controller, which includes fuzzification, fuzzy reasoning, defuzzification process and fuzzy rule base.

[0098] Generally, a fuzzy logic controller is designed through MATLAB, which includes the following four steps:

[0099] 1. Fuzzification: Convert input variables (such as load, power generation and carbon emissions) into fuzzy sets. Suppose the input variables are u = [u1, u2, ..., u m ], each input variable is represented by a membership function μ i (u i ) is converted into a fuzzy set.

[0100] 2. Fuzzy rule base: Define a fuzzy rule base, which contains a set of IF-THEN rules to describe the relationship between input variables and output variables (weights). The typical fuzzy rule form is:

[0101] IF u1 is A1 AND u2 is A2 THENωis B

[0102] Among them, A i (i=1,2,…,n) is the input fuzzy language quantity; B is the output fuzzy language quantity.

[0103] Different input variables and fuzzy rule bases can be set for different types of distribution substations to achieve different fuzzy controllers corresponding to different types of distribution substations.

[0104] 3. Fuzzy reasoning: Perform fuzzy reasoning based on the fuzzy rule base and the fuzzy set of input variables to obtain the fuzzy set of output variables.

[0105] 4. Defuzzification: Convert the fuzzy set of output variables into precise values ​​to obtain the coefficients of the optimized objective function.

[0106] In a possible implementation manner, the multi-objective optimization function of the distribution station area includes an objective function, constraints and a control object; the objective function F is:

[0107]

[0108] Among them, ω i is the coefficient of the i-th optimization objective function, f i (x) is the i-th optimization objective function, and n is the number of optimization objective functions.

[0109] The constraints include energy balance constraints, energy storage power limit constraints, and energy storage state constraints.

[0110] The control objects include: output regulation of distributed energy, charge state management of energy storage system, charging pile load management and electricity price signal response management.

[0111] Specifically, there is a close and interdependent relationship between the multi-dimensional scenario classification and multi-objective energy management strategy of the new distribution substation. Scenario classification identifies and distinguishes types of distribution substations with different characteristics by deeply analyzing the energy structure, load characteristics and external operating environment of the substation. These characteristics not only describe the current operating status of the distribution substation, but also provide a scientific basis for formulating effective energy management strategies. For example:

[0112] 1. PV-dominated areas: Due to the high proportion of distributed PV installed capacity and significant PV power generation, energy management strategies need to pay special attention to the volatility of PV output and its impact on the power balance in the area. In such a scenario, the strategy can focus on how to optimize the utilization rate of PV power generation, alleviate the instability caused by the intermittent nature of PV power generation through the intelligent scheduling of energy storage systems, and ensure power supply reliability.

[0113] 2. Flexible load-dominated areas: Due to the high access ratio of flexible loads and significant load fluctuation characteristics, energy management strategies should focus more on the flexible adjustment capabilities of the load side. By enhancing the response speed and adjustment range of the load, the strategy can respond quickly during peak demand periods, thereby reducing the pressure on the power grid and improving the overall energy efficiency.

[0114] 3. Areas dominated by charging pile loads: The high proportion of charging pile installed capacity and the time-varying changes in charging loads have become the main operating characteristics. The energy management strategy should target the day and night fluctuations in charging pile loads, especially during the peak charging period at night, to avoid grid overload, optimize grid operation stability, and reduce power supply costs through reasonable scheduling and load transfer.

[0115] 4. Hybrid scenario substation: Hybrid scenario substations are more complex. Due to the coexistence of multiple distributed energy sources, flexible loads, charging piles and energy storage systems, this type of distribution substation shows a high degree of heterogeneity and complex energy interaction patterns. In this scenario, the energy management strategy needs to comprehensively consider the synergy between various energy types and load characteristics to ensure the stability and economy of the operation of the distribution substation. For example, by intelligently scheduling different types of distributed energy and energy storage systems, balancing the supply and demand relationship between various types of energy, and dynamically adjusting the weights of various optimization objectives under different seasons, time periods and climatic conditions, multi-objective optimization can be finally achieved.

[0116] The optimization objectives of the adaptive multi-objective energy management strategy include three aspects: energy saving (energy efficiency), emission reduction (carbon emission minimization) and economy (cost minimization). These three aspects promote and restrict each other to a certain extent in the operation of the distribution network. While reducing emissions, it can reduce wind and solar power abandonment and improve energy utilization efficiency to a certain extent. However, the power quality and instability of renewable energy will improve the economic efficiency of operation; similarly, if energy efficiency is improved, that is, the energy storage and charging piles in the distribution station area have more regular charging and discharging time, and flexible loads are required to provide some margin, it will lead to increased carbon emissions and reduced economic efficiency of operation; if the best economy is pursued, the status of renewable energy in the distribution network operation model will be greatly reduced, resulting in increased total carbon emissions, increased wind and solar power abandonment, and the utilization rate of energy storage and flexible loads will also be reduced to a certain extent. Therefore, the relationship between these three in different scenarios is difficult to balance, and an algorithm to achieve multi-objective optimization is very important. The optimization functions of these three objectives can be comprehensively optimized by weight weighting method.

[0117] In this embodiment, the optimization objective function includes: an energy-saving optimization objective function f1(x), an emission reduction optimization objective function f2(x) and an economic optimization objective function f3(x).

[0118] Energy-saving optimization objective function f1(x):

[0119]

[0120] Where T is the total time step; E loss (t) is the energy loss at the tth moment; E total (t) is the total energy at moment t, including charging and discharging energy.

[0121] Emission reduction optimization objective function f2(x):

[0122]

[0123] Among them, P g (t) is the power consumption of the distribution station area at time t; P c(t) and P d (t) are the charge and discharge amounts of the energy storage at time t; η ch (t) and η dis (t) are the charging efficiency and discharging efficiency of energy storage at time t; α g (t) and α e (t) are the carbon emission factor of power supply from the power grid and the carbon emission factor of energy storage charging at time t respectively.

[0124] Economic optimization objective function f3(x):

[0125]

[0126] Among them, C buy (t) is the electricity purchase cost, which is affected by electricity price fluctuations. M(t) and O(t) are the operation and maintenance cost and energy storage system degradation cost of the distribution station area at time t, respectively; λ ch (t) and λ dis (t) is the electricity purchase price and electricity sales price at time t.

[0127] In the multi-objective energy management strategy of the new distribution substation, the optimization objectives cover energy saving (energy efficiency), emission reduction (minimization of carbon emissions) and economy (minimization of costs). These three aspects influence and restrict each other in the operation of the distribution network. For example, although optimizing carbon emissions can reduce wind and solar power abandonment and improve energy utilization efficiency, it may lead to a decline in power quality and economy. Similarly, improving energy efficiency usually requires more regular energy storage and charging pile operations, but may increase carbon emissions and operating costs. The pursuit of optimal economy may reduce the use of renewable energy, thereby increasing carbon emissions and reducing the utilization of energy storage and flexible loads. Due to the complex relationship between these objectives, the balance under different scenarios becomes particularly difficult, so the method of achieving multi-objective optimization is crucial.

[0128] In order to comprehensively optimize these objectives, a multi-objective optimization function can be formed through a weighted method. Specifically, the energy-saving optimization objective function mainly improves energy utilization efficiency by optimizing the charging and discharging strategies; the emission reduction optimization objective function reduces carbon emissions by optimizing the operation of the energy storage system; the economic optimization objective function focuses on minimizing the overall cost, including electricity purchase cost, operation and maintenance cost, and degradation cost of the energy storage system. In order to achieve adaptive multi-objective optimization, fuzzy logic control is used to adjust the coefficients of each optimization objective function, so as to adaptively adjust the optimization focus under different operating scenarios. This weight-adjusted optimization method can combine energy-saving, emission reduction and economic objectives into a comprehensive objective function, and achieve the balance of objectives in different scenarios through dynamic weight optimization. The optimization objective functions are combined to obtain the multi-objective optimization function F:

[0129]

[0130] Among them, ω i is the coefficient of the i-th optimization objective function, with a value range of [0, 1], which is used to balance different optimization objectives. i (x) is the i-th optimization objective function, and n is the number of optimization objective functions.

[0131] The constraints of the multi-objective optimization function of the distribution station area include: energy balance constraints, energy storage power limit constraints and energy storage state constraints.

[0132] 1. Energy balance constraint: P g (t)≤P d (t)+P v (t)+P grid (t), where P v (t) is the photovoltaic power generation at time t; P grid (t) is the power supply of the power grid at time t.

[0133] 2. Energy storage power limit constraints: Among them, P max is the maximum power of charge and discharge.

[0134] 3. Energy storage state constraint: SOC min ≤SOC(t)≤SOC max , where SOC(t) is the state of charge of the energy storage at time t; SOC min and SOC max are the minimum and maximum states of charge for energy storage, respectively.

[0135] In the adaptive multi-objective energy management strategy, the design of the control object fully considers various scenarios and system operation requirements to achieve comprehensive optimization of energy saving, emission reduction and economy. The control objects of the multi-objective optimization function of the distribution station area include: output regulation of distributed energy, charge state management of energy storage system, charging pile load management and electricity price signal response management.

[0136] 1. Output regulation of distributed energy: According to the real-time load demand and grid operation status, the output of distributed photovoltaic or wind power generation can be flexibly adjusted to ensure the quality of power while reducing the phenomenon of wind and solar power abandonment and optimizing energy utilization efficiency.

[0137] 2. SOC (state of charge) management of energy storage systems: By precisely controlling the SOC level of the energy storage system, over-charging and discharging of the energy storage can be avoided, thereby extending its service life, reducing degradation costs, and ensuring that the system can provide sufficient backup power at critical moments.

[0138] 3. Charging pile load management: Prioritize charging during the low electricity price period, or reduce the pressure on the power grid by reducing the charging power during the high load period of the power grid. Dynamically adjust the charging plan according to vehicle demand and power grid conditions to improve the charging efficiency of electric vehicles and reduce the peak load of the distribution network.

[0139] 4. Response to electricity price signals: Adjust load and energy storage strategies according to real-time electricity price signals, select the best time to purchase and sell electricity, and maximize economic benefits. Especially under time-of-use electricity prices, reasonable arrangement of the time distribution of energy storage and load can effectively reduce operating costs. In combination with specific scenarios, in areas dominated by photovoltaic output, electricity price signals are particularly important for the control of energy storage systems, while in areas dominated by charging pile loads, the joint scheduling of flexible loads and charging piles is the key point. These control objects coordinate with each other, and dynamically adjust the weights of each target through fuzzy logic control, so that the energy management strategy is more adapted to the actual needs in different scenarios.

[0140] In a possible implementation, solving the multi-objective optimization function of the power distribution station area includes: using an improved particle swarm optimization algorithm IPSO to solve the multi-objective optimization function of the power distribution station area.

[0141] Specifically, the main improvements of IPSO include:

[0142] 1. Combination of individual and global optimality: Based on the standard particle swarm algorithm, the combination mechanism of individual and global optimality is added to improve the convergence speed and stability of the algorithm. 2. Dynamic adjustment of inertia weight: The method of dynamically adjusting inertia weight is adopted to adjust the particle speed update strategy according to the current number of iterations.

[0143] The basic formula of particle swarm optimization algorithm is:

[0144] v i (t+1)=ωv i (t)+c1r1(p i -x i (t))+c2r2(gx i (t))

[0145] x i (t+1)=x i (t)+v i (t+1)

[0146] Among them, v i is the velocity of particle i; x i is the position of particle i; ω is the inertia weight; c1 and c2 are acceleration constants; r1 and r2 are random numbers; p i is the individual optimal position of particle i; g is the global optimal position.

[0147] In a possible implementation, the energy consumption reduction and the impact on energy saving effect of the traditional strategy and the multi-objective optimization strategy obtained by the method of the present invention are compared, and the average values ​​of all types of substations are used for comparison. The data comparison is shown in Table 3:

[0148] Table 3

[0149]

[0150] Through the analysis of Table 3, it can be seen that by implementing the energy management strategy of the present invention, the energy efficiency of the low-voltage distribution station area is significantly improved, and the energy efficiency of the distribution station areas in different scenarios is improved by more than 4%. Because the energy efficiencies of the traditional strategy and the strategy of the present invention are relatively high and the difference is not large, the energy efficiency improvement is not so obvious; at the same time, the energy consumption reduction rate of the distribution station areas in different scenarios after adopting the strategy of the present invention is more than 22%, compared with the traditional strategy The energy consumption reduction rate is about 14%, the energy consumption reduction rate is more than 64%, and the energy-saving effect is significantly improved.

[0151] See also Figure 3 The energy management method for distribution substations of the present invention, when constructing the classification standard for new distribution substations, selects the indicators that are difficult to directly observe and are relatively important in actual projects based on the actual operating characteristics of the new distribution substations and the impact on the distribution network, and constructs a new distribution substation evaluation method system. On the basis of the original classification standard, it adds considerations of dimensions such as seasonality, time period and climate conditions, and provides a more comprehensive and detailed classification standard. It also makes improvements in the algorithm, and uses an improved K-means pre-clustering algorithm based on split-coupling to complete the classification of distribution substations. Compared with traditional classification methods and other existing classification methods, it can better adapt to local conditions and increase the accuracy of classification. At the same time, while completing the classification of new distribution substations, the source, network, load and storage components in the distribution substation are comprehensively considered, and fuzzy control logic can be used for weight optimization according to different scenarios, and a more detailed multi-objective energy management strategy is proposed to achieve multi-objective adaptive energy management.

[0152] The following are device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0153] See also Figure 4 In another embodiment of the present invention, a distribution station area energy management system is provided, which can be used to implement the above-mentioned distribution station area energy management method. Specifically, the distribution station area energy management system includes a coefficient adaptive module and a strategy optimization module.

[0154] Among them, the coefficient adaptive module is used to obtain the type of the distribution substation, and based on the fuzzy controller corresponding to the type of the distribution substation, obtain the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation; the strategy optimization module is used to solve the multi-objective optimization function of the distribution substation based on the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation, and obtain the multi-objective optimization strategy of the distribution substation.

[0155] In one possible implementation, the method of obtaining the type of the distribution station area includes: obtaining classification characteristic index data of the distribution station area; according to the classification characteristic index data of the distribution station area, using an improved K-means pre-clustering algorithm based on split-coupling to obtain each clustering cluster of the distribution station area; obtaining the type of each clustering cluster and using it as the type of each distribution station area in the clustering cluster.

[0156] All relevant contents of each step involved in the aforementioned embodiment of the power distribution station area energy management method can be referred to the functional description of the functional modules corresponding to the power distribution station area energy management system in the embodiment of the present invention, and will not be repeated here.

[0157] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into one processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0158] In another embodiment of the present invention, a computer device is provided, the computer device including a processor and a memory, the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in a computer storage medium to implement a corresponding method flow or a corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the distribution station area energy management method.

[0159] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It can be understood that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the energy management method for the distribution station area in the above embodiment.

[0160] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0161] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0162] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0163] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for energy management of a distribution station area, characterized in that: include: Obtain the type of the power distribution substation, and based on the fuzzy controller corresponding to the type of the power distribution substation, obtain the coefficients of each optimization objective function of the multi-objective optimization function of the power distribution substation; Based on the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation area, the multi-objective optimization function of the distribution substation area is solved to obtain the multi-objective optimization strategy of the distribution substation area.

2. The method for energy management of a distribution station area according to claim 1, characterized in that: The type of obtaining the distribution station area includes: Obtain classification characteristic index data of distribution station areas; According to the classification characteristic index data of the distribution station area, the improved K-means pre-clustering algorithm based on split-coupling is used to obtain the clusters of the distribution station area; The type of each cluster is obtained and used as the type of each distribution station area within the cluster.

3. The method for energy management of a distribution station area according to claim 2, characterized in that: The classification characteristic index data of the distribution station area includes: photovoltaic characteristic data, flexible load characteristic data, charging pile characteristic data, seasonal characteristic data, time period characteristic data and climate condition characteristic data; The types of distribution station areas include: areas dominated by photovoltaic output, areas dominated by flexible loads, areas dominated by charging pile loads, and mixed scenario areas.

4. The method for energy management of a distribution station area according to claim 1, characterized in that: The fuzzy controller corresponding to the type of the distribution station area obtains the coefficients of each optimization objective function of the multi-objective optimization function of the distribution station area, including: Obtaining fuzzy control input variables of the distribution station area; wherein the fuzzy control input variables include: station area load, distributed generation, carbon emissions, energy storage status and electricity price; The fuzzy control input variables of the distribution station area are input into the fuzzy controller corresponding to the type of the distribution station area to obtain the fuzzy control output variables of the distribution station area; and the fuzzy control output variables of the distribution station area are used as the optimization objective function coefficients of the multi-objective optimization function of the distribution station area.

5. The method for energy management of a distribution station area according to claim 1, characterized in that: The multi-objective optimization function of the distribution station area includes an objective function, constraint conditions and a control object; The objective function F is: Among them, ω i is the coefficient of the i-th optimization objective function, f i (x) is the i-th optimization objective function, and n is the number of optimization objective functions; The constraints include energy balance constraints, energy storage power limit constraints, and energy storage status constraints; The control objects include: output regulation of distributed energy, charge state management of energy storage system, charging pile load management and electricity price signal response management.

6. The method for energy management of a distribution station area according to claim 5, characterized in that: The optimization objective function includes: Energy-saving optimization objective function f1(x): Where T is the total time step; E loss (t) is the energy loss at the tth moment; E total (t) is the total energy at time t, including charging and discharging energy; Emission reduction optimization objective function f2(x): Among them, P g (t) is the power consumption of the distribution station area at time t; P c (t) and P d (t) are the charge and discharge amounts of the energy storage at time t; η ch (t) and η dis (t) are the charging efficiency and discharging efficiency of energy storage at time t; α g (t) and α e (t) are the carbon emission factor of power supply from the power grid and the carbon emission factor of energy storage charging at time t; Economic optimization objective function f3(x): Among them, C buy (t) is the electricity purchase cost; M(t) and O(t) are the operation and maintenance cost and energy storage system degradation cost of the distribution station area at time t, respectively; λ ch (t) and λ dis (t) is the electricity purchase price and electricity sales price at time t.

7. A distribution station area energy management system, characterized in that: include: A coefficient adaptive module is used to obtain the type of the distribution substation area and obtain the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation area based on the fuzzy controller corresponding to the type of the distribution substation area; The strategy optimization module is used to solve the multi-objective optimization function of the distribution substation area based on the coefficients of each optimization objective function of the multi-objective optimization function of the distribution substation area, and obtain the multi-objective optimization strategy of the distribution substation area.

8. The power distribution area energy management system according to claim 7, characterized in that: The type of obtaining the distribution station area includes: Obtain classification characteristic index data of distribution station areas; According to the classification characteristic index data of the distribution station area, the improved K-means pre-clustering algorithm based on split-coupling is used to obtain the clusters of the distribution station area; The type of each cluster is obtained and used as the type of each distribution station area within the cluster.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the power distribution area energy management method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the power distribution area energy management method according to any one of claims 1 to 7 are implemented.

Images