Method and device for evaluating energy storage configuration scheme of power distribution network

Abstract

The invention discloses a power distribution network energy storage configuration scheme evaluation method and device. The method comprises the following steps: constructing an evaluation index system of a to-be-evaluated power distribution network energy storage configuration scheme; dynamically distributing the weight of each evaluation index in the normalized evaluation index system; visualizing the dynamic weight distribution of each evaluation index by adopting a thermodynamic diagram; and analyzing the relevance among the evaluation indexes by using a Pearson's correlation coefficient. According to the technical scheme provided by the embodiment of the invention, the problems that in an existing power distribution network energy storage configuration scheme evaluation method, fixed weight distribution is difficult to adapt to dynamic operation requirements, complex relevance among indexes cannot be comprehensively considered, and a complex multi-index evaluation result is difficult to visually display are solved. According to the technical scheme provided by the embodiment of the invention, the evaluation flexibility and accuracy are improved, the evaluation result is more comprehensive and scientific, a decision maker is helped to quickly understand complex data, and the decision making efficiency and the optimization effect are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution networks, and particularly to an evaluation method and device for a distribution network energy storage configuration scheme. Background Art

[0002] With the rapid development of new energy technologies, the application of energy storage systems in distribution networks has become increasingly widespread. During the optimization and configuration process of energy storage systems, evaluating the advantages and disadvantages of energy storage schemes has become an important link in improving the operation efficiency of distribution networks, reducing costs, and enhancing the new energy consumption capacity. However, there are some significant problems in the existing evaluation methods during practical applications.

[0003] Firstly, many traditional evaluation methods are based on fixed weight allocation strategies and lack adaptability to changes in actual operating conditions. In distribution networks, the output of new energy is highly volatile and the load demand changes frequently. These dynamic factors are difficult to effectively evaluate through fixed weights. This results in the inability of existing evaluation methods to reflect the changes in actual operation when dealing with real-time data, thereby affecting the accuracy and effectiveness of energy storage configuration schemes.

[0004] Secondly, existing methods usually cannot comprehensively consider the complex correlations between various indicators. Traditional evaluation methods often analyze each indicator in isolation, ignoring the possible mutual influences and linkage effects between different indicators. For example, indicators such as peak shaving and valley filling rate, wind curtailment rate, and new energy utilization rate may have strong correlations under different operating conditions. Simple evaluation indicators may not be able to reflect these mutual relationships, resulting in deviations in the design of energy storage system optimization schemes.

[0005] Finally, the visualization means of existing methods are relatively simple and it is difficult to intuitively display the complex multi-index evaluation results. Although some methods use graphical means to display evaluation results, most still mainly rely on tables and texts, lacking effective display of results such as weight changes and correlation analysis. The lack of intuitive and clear visualization makes it easy for decision-makers to miss key information when analyzing complex data, affecting the efficiency of optimization decisions.

[0006] Therefore, the existing energy storage configuration evaluation methods urgently need to be improved, especially in terms of dynamic adaptability, multi-dimensional correlation analysis, and intuitive visualization display, to better support the optimization design and decision-making process of energy storage systems. Summary of the Invention

[0007] The present invention provides an evaluation method for a distribution network energy storage configuration scheme to solve the problems existing in the existing evaluation methods for distribution network energy storage configuration schemes, such as the fixed weight allocation being difficult to adapt to dynamic operation requirements, the inability to comprehensively consider the complex correlations between various indicators, and the difficulty in intuitively displaying complex multi-index evaluation results.

[0008] According to one aspect of the present invention, there is provided an evaluation method for a distribution network energy storage configuration scheme, including:

[0009] Construct an evaluation index system for the distribution network energy storage configuration scheme to be evaluated;

[0010] Dynamically allocate the weights of each evaluation index in the normalized evaluation index system;

[0011] Use a heat map to visualize the dynamic weight distribution of each evaluation index;

[0012] Use the Pearson correlation coefficient to analyze the correlation between each evaluation index.

[0013] Optionally, the construction of the evaluation index system for the distribution network energy storage configuration scheme to be evaluated includes:

[0014] Establish economic evaluation indexes, energy utilization rate evaluation indexes, voltage quality evaluation indexes, reliability evaluation indexes, and flexibility evaluation indexes; wherein, the economic evaluation indexes include energy storage investment cost and energy storage operation and maintenance cost; the energy utilization rate evaluation indexes include wind and light abandonment rate, new energy utilization rate, energy storage peak shaving and valley filling rate, and average line loss; the voltage quality evaluation indexes include voltage deviation index and voltage qualification rate; the reliability evaluation indexes include probability of insufficient power supply and expected value of insufficient power supply; the flexibility evaluation indexes include maximum line load rate and net load volatility.

[0015] Optionally, the energy storage investment cost should satisfy the following relationship:

[0016] In the formula, C inv is the energy storage investment cost; E ess,i and P ess,i are respectively the rated capacity and rated power of the i-th energy storage planned; S ess is the set of energy storage installation nodes; r is the discount rate; y ess is the operating life of the energy storage; c e , c p are respectively the investment costs per unit capacity and per unit power of the energy storage;

[0017] The energy storage operation and maintenance cost should satisfy the following relationship:

[0018] In the formula, C OM is the energy storage operation and maintenance cost; c ess is the operating cost per unit power of the energy storage device; is the charging and discharging power of the energy storage device at node i at time t;

[0019] The wind and light abandonment rate should satisfy the following relationship:

[0020] Wherein, CR is the curtailment rate of wind and solar power; N DG is the set of distributed PV / wind power installation nodes; is the available power generation of distributed PV / wind power at node n in the distribution network at time t; is the actual power generation of distributed PV / wind power at node n in the distribution network at time t;

[0021] The new energy utilization rate should satisfy the following relationship:

[0022] Wherein, NER is the new energy utilization rate;

[0023] The energy storage peak shaving and valley filling rate should satisfy the following relationship:

[0024] Wherein, f p is the energy storage peak shaving and valley filling rate; P ld is the load deficit of the system; P l ′ d is the load deficit of the system after adding energy storage;

[0025] The average line loss should satisfy the following relationship:

[0026] Wherein, ALR is the average line loss; P loss,t is the total network loss in the distribution network at time t; L is the total number of branches;

[0027] The voltage deviation index should satisfy the following relationship:

[0028] Wherein, VOI is the voltage deviation index; N is the total number of nodes in the distribution network; U n,t is the actual value of the voltage at node n in the distribution network at time t; U n,rated is the rated value of the voltage at node n in the distribution network at time t;

[0029] The voltage qualification rate should satisfy the following relationship:

[0030] Wherein, RQV is the voltage qualification rate; N RQV,t is the number of nodes with qualified voltage in the distribution network at time t;

[0031] The probability of insufficient power supply should satisfy the following relationship:

[0032] Wherein, PLC is the probability of insufficient power supply; T is the total simulation time; d i is the duration of the state lasting; n is the total number of states within time T; The test function corresponding to the probability of insufficient power supply PLC in state is as follows:

[0033]

[0034] The expected value of insufficient power supply should satisfy the following relationship:

[0035] In the formula, EENS is the expected value of insufficient power supply; F EENS is the test function of the expected value of insufficient power supply EENS; represents the total load shedding amount of the system in state ;

[0036] The maximum line load rate should satisfy the following relationship:

[0037] In the formula, MLR is the maximum line load rate; P l,t is the actual active power transmitted by line l; P l,max is the maximum transmissible active power of line l;

[0038] The net load volatility should satisfy the following relationship:

[0039] In the formula, FRNL is the net load volatility; P t NL and are the net load values of the distribution network at time t and the previous time t - 1 respectively.

[0040] Optionally, the weights of the evaluation indicators in the normalized evaluation index system for dynamic allocation include:

[0041] Taking the mean value of each evaluation indicator as the reference value of evaluation indicator j;

[0042] Calculating the deviation value between the current value of evaluation indicator j and the reference value;

[0043] Calculating the dynamic weight of evaluation indicator j based on the absolute value of the deviation value;

[0044] Weighted summing each evaluation indicator according to the dynamic weight to calculate the comprehensive score of the energy storage configuration scheme.

[0045] Optionally, the reference value of evaluation indicator j should satisfy the following relationship:

[0046] In the formula, B j is the reference value of evaluation indicator j; X j(t) represents the value of evaluation index j at time t; T is the length of the time period;

[0047] The deviation value is calculated using the following formula:

[0048] In the formula, Δ j (t) represents the deviation value of evaluation index j at time t;

[0049] The dynamic weight is calculated using the following formula:

[0050] In the formula, w j (t) represents the dynamic weight of evaluation index j at time t;

[0051] The comprehensive score of the energy storage configuration scheme is calculated using the following formula:

[0052] In the formula, s(t) is the comprehensive score of the energy storage configuration scheme; V j (t) represents the normalized value of index j at time t.

[0053] Optionally, visualizing the dynamic weight distribution of each evaluation index using a heatmap includes:

[0054] Setting the cells of the heatmap to display specific weight values;

[0055] Showing the dynamic weight distribution through the shade of color to identify key time points;

[0056] Determining the change time period of the dynamic weight of each evaluation index according to the change of each evaluation index at different time points;

[0057] Judging the correlation of each evaluation index according to the dynamic weight distribution of different evaluation indexes at the same time point.

[0058] Optionally, analyzing the correlation between each evaluation index using the Pearson correlation coefficient includes:

[0059] Calculating the Pearson correlation coefficient of any two evaluation indexes;

[0060] Calculating the Pearson correlation coefficient for pairwise combinations of all evaluation indexes and generating a symmetric linear correlation matrix;

[0061] Generating a heatmap according to the symmetric linear correlation matrix, where the horizontal axis and vertical axis of the heatmap are each evaluation index, and the color of the cells in the heatmap represents the magnitude of the Pearson correlation coefficient: the shade of color represents the strength of the correlation between evaluation indexes;

[0062] Analyzing the correlation between each evaluation index according to the Pearson correlation coefficient.

[0063] Optionally, the Pearson correlation coefficient is calculated using the following formula:

[0064] In the formula: and are the mean values of evaluation index A and evaluation index B respectively, A i and B i are the i-th sample values of evaluation index A and evaluation index B;

[0065] The symmetric linear correlation matrix satisfies the following form:

[0066] where r i,j represents the Pearson correlation coefficient between evaluation index i and evaluation index j;

[0067] Analyzing the correlation between the evaluation indexes according to the Pearson correlation coefficient includes:

[0068] When the Pearson correlation coefficient is greater than a preset threshold, the two evaluation indexes are positively correlated;

[0069] When the Pearson correlation coefficient is less than a preset threshold, the two evaluation indexes are negatively correlated;

[0070] When the Pearson correlation coefficient is equal to a preset threshold, the two evaluation indexes are not correlated.

[0071] Optionally, before dynamically allocating the weights of the evaluation indexes in the normalized evaluation index system, it further includes:

[0072] Normalizing each evaluation index in the evaluation index system.

[0073] According to another aspect of the present invention, there is provided an evaluation device for a distribution network energy storage configuration scheme, including:

[0074] A construction module for constructing an evaluation index system for the distribution network energy storage configuration scheme to be evaluated;

[0075] An allocation module for dynamically allocating the weights of the evaluation indexes in the normalized evaluation index system;

[0076] A visualization module for visualizing the dynamic weight distribution of each evaluation index using a heat map;

[0077] An analysis module for analyzing the correlation between the evaluation indexes using the Pearson correlation coefficient.

[0078] An embodiment of the present invention provides a method and device for evaluating a distribution network energy storage configuration scheme. The method includes: constructing an evaluation index system for the distribution network energy storage configuration scheme to be evaluated; dynamically allocating the weights of each evaluation index in the evaluation index system after normalization processing; visualizing the dynamic weight distribution of each evaluation index by using a heat map; and analyzing the correlation between each evaluation index by using the Pearson correlation coefficient. The technical solution provided by the embodiment of the present invention, by dynamically allocating the weights of each evaluation index in the evaluation index system after normalization processing, enables the weights of each evaluation index to be adjusted in real time and dynamically, solves the problem that fixed weights cannot adapt to the fluctuations of new energy and load changes, and improves the flexibility and accuracy of evaluation; analyzes the correlation between each evaluation index by using the Pearson correlation coefficient, realizes the correlation analysis of each evaluation index, deeply excavates the mutual relationship between each evaluation index, avoids the defect that traditional methods ignore the correlation between indexes, and makes the evaluation result more comprehensive and scientific; and visualizes the dynamic weight distribution of each evaluation index by using a heat map, intuitively displays the dynamic weights and index correlations, solves the problem of insufficient visualization of existing methods, helps decision-makers quickly understand complex data, and improves the decision-making efficiency and optimization effect.

[0079] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0081] Figure 1 It is a flowchart of a method for evaluating a distribution network energy storage configuration scheme provided by an embodiment of the present invention;

[0082] Figure 2 It is a flowchart of another method for evaluating a distribution network energy storage configuration scheme provided by an embodiment of the present invention;

[0083] Figure 3 It is a schematic structural diagram of a device for evaluating a distribution network energy storage configuration scheme provided by an embodiment of the present invention;

[0084] Figure 4 It is a schematic structural diagram of an electronic device for a method for evaluating a distribution network energy storage configuration scheme provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0085] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0086] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0087] Figure 1 FIG. is a flowchart of an evaluation method for a distribution network energy storage configuration scheme provided by an embodiment of the present invention. This embodiment is applicable to the situation where it is difficult for fixed weight allocation to meet dynamic operation requirements. This method can be executed by a distribution network energy storage configuration scheme evaluation device, which can be implemented in the form of hardware and / or software, and can be configured in any electronic device with communication functions. Refer to Figure 1 , the evaluation method for the distribution network energy storage configuration scheme includes:

[0088] S110. Construct an evaluation index system for the distribution network energy storage configuration scheme to be evaluated.

[0089] Among them, the distribution network is an important link in the power system responsible for distributing electric energy to each user terminal. The energy storage configuration scheme is a series of related arrangements for the distribution network, planning and determining at which locations, what capacity to configure, and what type of energy storage device to use, etc., aiming to utilize the functions of the energy storage system such as storing electric energy and releasing electric energy when needed to improve the operation status of the distribution network, such as enhancing power supply reliability and regulating power quality. In the context of the distribution network energy storage configuration scheme, it is necessary to establish multiple indicators in different dimensions that can be quantitatively or qualitatively described to comprehensively evaluate whether the given energy storage configuration scheme is reasonable and whether it can achieve the expected effect. The evaluation index system can include economic evaluation indicators, reliability evaluation indicators, energy utilization rate evaluation indicators, voltage quality evaluation indicators, and flexibility evaluation indicators, etc.

[0090] Specifically, according to the target performance requirements of the distribution network, an evaluation index system for the energy storage configuration plan of the distribution network to be evaluated is constructed. The purpose of constructing this evaluation index system is to comprehensively, scientifically and objectively measure the advantages and disadvantages of the distribution network energy storage configuration plan, assist in decision-making, and select the configuration plan that best meets the actual needs and can bring good comprehensive benefits, such as improving the operation stability of the distribution network, reducing costs, and improving energy utilization efficiency.

[0091] S120. Dynamically allocate the weights of each evaluation index in the normalized evaluation index system.

[0092] Specifically, after constructing the evaluation index system, different indicators often have different dimensions, magnitudes and value ranges. For example, some indicators may have values between 0 and 100 (such as the charge and discharge efficiency of the energy storage system expressed as a percentage), while some indicators may have values of several thousand yuan or even tens of thousands of yuan (such as the initial investment cost of the energy storage configuration plan). Normalization is to use specific mathematical methods to uniformly transform these indicator values of different types and ranges into a specific standard range that is convenient for comparison and subsequent calculations, usually the interval from 0 to 1. The advantage of doing this is to eliminate the influence brought by differences such as dimensions, so that each indicator can be considered under the same "scale" in subsequent operations such as weight allocation, making the entire evaluation process more scientific and fair. The weight represents the relative importance degree of each evaluation index in the entire evaluation system. For example, for the distribution network energy storage configuration plan, the overall weight of the indicators from the perspective of reliability may be relatively high, which means that when comprehensively evaluating whether the plan is good or not, the reliability-related indicators have a greater impact on the final result. Weight allocation is to determine how much "weight" each indicator specifically accounts for, and its sum is generally 1 or 100%. Dynamically allocating weights means that the weights are not fixed, but will change flexibly according to different situations, conditions, time stages and other factors. For example, in the initial stage of the development of the distribution network, more attention may be paid to the weight of the economic indicators of the energy storage configuration plan because of the need to control costs and achieve rapid construction; while as the distribution network has higher and higher requirements for power supply reliability, in the subsequent stage, the weight of the reliability-related indicators may be appropriately increased, and the weights of other indicators are adjusted accordingly. That is to say, dynamically allocating weights can adjust the importance of each evaluation index in real time according to the actual application scenarios, different development needs, etc., so that the entire evaluation index system can better adapt to changes and always maintain a reasonable and accurate evaluation ability for the evaluation object.

[0093] S130. Use a heat map to visualize the dynamic weight distribution of each evaluation index.

[0094] Specifically, a heat map is a commonly used data visualization method that mainly presents the differences and distributions of data intuitively through the depth of color, the change of hue, etc. In a heat map, different data values are usually mapped to corresponding color intervals. The higher the value, the darker or more vivid the corresponding color; the lower the value, the lighter and duller the color. In this way, viewers can immediately see the size and height comparison of data in different dimensions and quickly grasp the overall trend and characteristics of the data. Using this intuitive visualization tool of the heat map, the dynamic weight distribution of each evaluation index is displayed. Specifically, each evaluation index is used as a different dimension (such as rows or columns) of the heat map, and then according to the weight values corresponding to each index in different situations, it is converted into corresponding colors and displayed in the heat map. For example, if an index has a high weight in a certain stage, the color of the corresponding cell in the heat map will be relatively dark and very eye-catching; while the color of the cell corresponding to an index with a low weight is relatively light. In this way, by observing the heat map, users can clearly and intuitively see information such as the change trend of the weights of different evaluation indexes in different situations and which index is more important in which stages, without having to look at complex digital tables, and can more efficiently grasp the distribution characteristics of the dynamic weights of each evaluation index as a whole to assist in related analysis, decision-making and other work.

[0095] S140. Analyze the correlation between each evaluation index by using the Pearson correlation coefficient.

[0096] Specifically, it is crucial to understand the correlation between various evaluation indicators because there may be mutual influence and correlation among them. Some indicators may show a trend of co-variation, that is, when one indicator value increases, the other indicator value also increases; while some indicators may show an inverse variation, when one indicator value rises, the other indicator value decreases instead. Analyzing this correlation helps to more deeply understand the internal logic of the entire evaluation indicator system, avoid duplication and redundancy among indicators, and can more scientifically and reasonably consider these relationships when performing subsequent comprehensive evaluation, weight allocation, etc. The Pearson correlation coefficient is used to measure the strength of the linear correlation between two variables. Regarding each evaluation indicator as a different variable, the Pearson correlation coefficient between pairwise evaluation indicators is calculated using mathematical methods. For example, calculate the Pearson correlation coefficient between the charge-discharge efficiency indicator and the initial investment cost indicator of the energy storage system, and judge the strength of the linear correlation and the specific correlation direction (positive correlation or negative correlation) between them through the obtained specific value. For example, if the Pearson correlation coefficient is greater than 0, it indicates a linear positive correlation between the two indicators; if the Pearson correlation coefficient is less than 0, it indicates a linear negative correlation between the two indicators; if the Pearson correlation coefficient is equal to 0, it indicates that there is no linear correlation between the two indicators. After calculating and analyzing all pairwise evaluation indicators in this way, the linear correlation situation among the indicators in the entire evaluation indicator system can be clearly sorted out. Then, based on these analysis results, the indicator system can be optimized, such as removing some indicators with overly strong correlation (high positive correlation or high negative correlation) that cause information duplication, or fully considering this correlation impact among indicators when performing subsequent comprehensive evaluation and other tasks, making the entire evaluation process more scientific and accurate.

[0097] The technical solution provided by the embodiment of the present invention dynamically allocates the weights of each evaluation indicator in the normalized evaluation indicator system, enabling the weights of each evaluation indicator to be adjusted in real time dynamically, solving the problem that fixed weights cannot adapt to new energy fluctuations and load changes, and improving the flexibility and accuracy of evaluation; using the Pearson correlation coefficient to analyze the correlation between each evaluation indicator, realizing the correlation analysis of each evaluation indicator, deeply exploring the mutual relationship between each evaluation indicator, avoiding the defect of ignoring the correlation between indicators in the traditional method, and making the evaluation result more comprehensive and scientific; and visualizing the dynamic weight distribution of each evaluation indicator by using a heat map, intuitively displaying the dynamic weights and indicator correlations, solving the problem of insufficient visualization in the existing method, helping decision-makers quickly understand complex data, and improving the decision-making efficiency and optimization effect.

[0098] In some embodiments, optionally, step S110 includes:

[0099] Establish economic evaluation indicators, energy utilization rate evaluation indicators, voltage quality evaluation indicators, reliability evaluation indicators, and flexibility evaluation indicators; among them, the economic evaluation indicators include energy storage investment cost and energy storage operation and maintenance cost; the energy utilization rate evaluation indicators include the wind and light abandonment rate, new energy utilization rate, energy storage peak shaving and valley filling rate, and average line loss; the voltage quality evaluation indicators include voltage deviation index and voltage qualification rate; the reliability evaluation indicators include the probability of insufficient power supply and the expected value of insufficient power supply; the flexibility evaluation indicators include the maximum line load rate and the net load volatility.

[0100] Optionally, the energy storage investment cost should satisfy the following relationship:

[0101] In the formula, C inv is the energy storage investment cost; E ess,i and P ess,i are the rated capacity and rated power of the i-th energy storage planned respectively; S ess is the set of energy storage installation nodes; r is the discount rate; y ess is the operating life of the energy storage; c e and c p are the investment costs per unit capacity and per unit power of the energy storage respectively;

[0102] The energy storage operation and maintenance cost should satisfy the following relationship:

[0103] In the formula, C OM is the energy storage operation and maintenance cost; c ess is the operating cost of the energy storage device per unit power; is the charging and discharging power of the energy storage device at node i at time t;

[0104] The wind and light abandonment rate should satisfy the following relationship:

[0105] In the formula, CR is the wind and light abandonment rate; N DG is the set of distributed photovoltaic / wind power installation nodes; is the available power generation of distributed photovoltaic / wind power at node n in the distribution network at time t; is the actual power generation of distributed photovoltaic / wind power at node n in the distribution network at time t;

[0106] The new energy utilization rate should satisfy the following relationship:

[0107] In the formula, NER is the new energy utilization rate;

[0108] The energy storage peak shaving and valley filling rate should satisfy the following relationship:

[0109] In the formula, fp is the energy storage peak shaving and valley filling rate; P ld is the load deficit of the system; P l ′ d is the load deficit of the system after adding energy storage;

[0110] The average line loss should satisfy the following relationship:

[0111] In the formula, ALR is the average line loss; P loss,t is the total line loss at time t in the distribution network; L is the total number of branches;

[0112] The voltage deviation index should satisfy the following relationship:

[0113] In the formula, VOI is the voltage deviation index; N is the total number of nodes in the distribution network; U n,t is the actual value of the voltage at node n at time t in the distribution network; U n,rated is the rated value of the voltage at node n at time t in the distribution network;

[0114] The voltage qualification rate should satisfy the following relationship:

[0115] In the formula, RQV is the voltage qualification rate; N RQV,t is the number of nodes with qualified voltage at time t in the distribution network;

[0116] The probability of insufficient power supply should satisfy the following relationship:

[0117] In the formula, PLC is the probability of insufficient power supply; T is the total simulation time; d i is the state duration; n is the total number of states within time T; is the test function corresponding to the probability of insufficient power supply PLC in the state ;

[0118]

[0119] The expected value of insufficient power supply should satisfy the following relationship:

[0120] In the formula, EENS is the expected value of insufficient power supply; F EENS is the test function of the expected value of insufficient power supply EENS; represents the total load shedding amount of the system in the state ;

[0121] The maximum line load rate should satisfy the following relationship:

[0122] Wherein, MLR is the maximum line load rate; P l,t is the actual active power transmitted by line l; P l,max is the maximum transmissible active power of line l;

[0123] The net load volatility should satisfy the following relationship:

[0124] Wherein, FRNL is the net load volatility; P t NL and are the net load values of the distribution network at time t and the previous time t-1, respectively.

[0125] In some embodiments, optionally, step S120 includes:

[0126] S121. Take the mean value of each evaluation index as the reference value of evaluation index j.

[0127] Optionally, the reference value of evaluation index j should satisfy the following relationship:

[0128] Wherein, B j is the reference value of evaluation index j; X j (t) represents the value of evaluation index j at time t; T is the length of time.

[0129] S122. Calculate the deviation value between the current value and the reference value of evaluation index j.

[0130] Specifically, the deviation value is calculated using the following formula:

[0131] Wherein, Δ j (t) represents the deviation value of evaluation index j at time t.

[0132] S123. Calculate the dynamic weight of evaluation index j based on the absolute value of the deviation value.

[0133] Specifically, the dynamic weight is calculated using the following formula:

[0134] Wherein, w j (t) represents the dynamic weight of evaluation index j at time t.

[0135] S124. Perform weighted summation on each evaluation index according to the dynamic weight, and calculate the comprehensive score of the energy storage configuration scheme.

[0136] Specifically, the comprehensive score of the energy storage configuration scheme is calculated using the following formula:

[0137] where s(t) is the comprehensive score of the energy storage configuration plan; V j (t) represents the normalized value of index j at time t.

[0138] In some embodiments, optionally, step S130 includes:

[0139] S131. Set the specific weight value to be displayed in the cell of the heat map.

[0140] Specifically, generally, only through the original color mapping of the heat map, people can only generally understand the relative high and low of the weight values, that is, intuitively judge which index has a high weight and which index has a low weight through the color depth, but cannot exactly know what the specific value is. And setting the specific weight value to be displayed in the cell of the heat map is to take certain operation means to make each cell representing the index not only show the corresponding color change, but also directly display the actual weight value corresponding to the index, which is convenient for direct observation and comparison. For example, the heat map can be generated by using the Seaborn library in Python or by operating in Excel, etc., and the specific weight value is set to be displayed in the cell of the heat map.

[0141] S132. Display the dynamic weight distribution through the color depth and identify the key time points.

[0142] Specifically, the color depth is used to represent the weight size; the weight greater than 0 and less than 0.3 is a low-weight item, the weight greater than 0.3 and less than 0.7 is a medium-weight item, and the weight greater than 0.7 and less than 1 is a high-weight item. The low-weight items are represented by light colors and the high-weight items are represented by dark colors, and a color scheme with a gradual change of warm and cold colors is adopted. With the help of visualization means, such as using charts such as heat maps, different weight values are mapped to the corresponding colors. Generally, the higher the weight value, the darker the corresponding color, and the lower the weight value, the lighter the color. The dark area indicates that the index is more important at this time point, and the light area indicates that the index is less important at this time point. In this way, by observing the change of colors, it can be intuitively seen how the weights of each index change during the whole time period, which indexes increase in weight in some stages, which indexes decrease in weight in some stages, and the relative high and low comparison between the weights of different indexes, etc., and overall grasp the dynamic trend of the weight distribution. In the process of dynamic weight change, there are some special time nodes. At these moments, the distribution of weights has changed significantly, which may mean that the system, project, etc. have entered a new stage, or there have been major changes in the external environment, which have an important impact on the overall evaluation, decision-making, etc. When the dynamic weight distribution is displayed by colors, the time positions where the colors change suddenly (suddenly become darker or lighter) and the obvious changes in the color comparison of different indexes are often the key time points worthy of attention.

[0143] S133. Determine the change time period of the dynamic weight of each evaluation index according to the changes of each evaluation index at different time points.

[0144] Specifically, first observe the changes of a single evaluation index at different time points, then determine the change time period of the dynamic weight of each evaluation index, and finally analyze which factors actually lead to the change of the dynamic weight of this evaluation index.

[0145] S134. Judge the correlation of each evaluation index according to the dynamic weight distribution of different evaluation indexes at the same time point.

[0146] Specifically, when focusing on the same time point, each evaluation index has its corresponding weight value, and these weight values together constitute the dynamic weight distribution at this time point. By observing the dynamic weight distribution of different evaluation indexes at the same time point, their correlation can be analyzed.

[0147] In some embodiments, optionally, step S140 includes:

[0148] S141. Calculate the Pearson correlation coefficient of any two evaluation indexes.

[0149] Optionally, the Pearson correlation coefficient is calculated using the following formula:

[0150] In the formula, and are the mean values of evaluation index A and evaluation index B respectively, A i and B i are the i-th sample values of evaluation index A and evaluation index B;

[0151] S142. Calculate the Pearson correlation coefficient for pairwise combination of all evaluation indexes and generate a symmetric linear correlation matrix.

[0152] Among them, the symmetric linear correlation matrix satisfies the following form:

[0153] Among them, r i,j represents the Pearson correlation coefficient of evaluation index i and evaluation j.

[0154] Specifically, regard each index in the evaluation system as a different variable, then form each pair of two indexes, and calculate the Pearson correlation coefficient between them respectively. After completing the calculation of the Pearson correlation coefficient for pairwise combination of all evaluation indexes, these coefficients will be sorted into the form of a matrix, and this matrix is the symmetric linear correlation matrix.

[0155] S143. Generate a heat map according to the symmetric linear correlation matrix.

[0156] Among them, the horizontal and vertical axes of the heat map are the evaluation indicators. The color of the cells in the heat map indicates the size of the Pearson correlation coefficient: the depth of the color indicates the strength of the correlation between the evaluation indicators; the symmetric linear correlation matrix is ​​a data presentation form obtained by calculating the Pearson correlation coefficient for all evaluation indicators in pairs. It is a square matrix with the same number of rows and columns as the number of evaluation indicators. The elements on the main diagonal are all 1, which means that each indicator is completely positively correlated with itself; the elements in other positions are the Pearson correlation coefficients between different evaluation indicators, which reflect the degree and direction of the linear correlation between the indicators (positive correlation, negative correlation or no correlation, etc.). Moreover, since the correlation coefficient between indicator A and indicator B is the same as the correlation coefficient between indicator B and indicator A, the matrix presents a symmetrical characteristic.

[0157] Specifically, the data in the symmetric linear correlation matrix is ​​used as input, and the relevant visualization software or programming tools (such as the Seaborn library in Python, Tableau, etc.) are used to map the Pearson correlation coefficient value of each position in the matrix into the corresponding color according to certain rules, thereby generating a heat map. Specific operation: First, the evaluation indicators corresponding to the rows and columns in the symmetric linear correlation matrix are used as the horizontal and vertical axes of the heat map, respectively, so that each cell in the heat map represents the correlation between the two evaluation indicators. Then, the color of the cell is determined according to the correlation coefficient value corresponding to the cell. For example, if the Pearson correlation coefficient is greater than 0 (indicating a strong positive correlation), it can be represented by a darker red series, and the darker the color, the stronger the positive correlation; if the Pearson correlation coefficient is less than 0 (indicating a strong negative correlation), it can be represented by a darker blue series, and the darker the color means the stronger the negative correlation; and when the Pearson correlation coefficient is equal to 0 (indicating no correlation), the corresponding cell color will be lighter, and white or light gray can be used. Through the heat map generated in this way, users can very intuitively see the strength and direction of the correlation between different indicators in the entire evaluation index system. At a glance, you can quickly identify which indicators are highly correlated (dark areas) and which are less correlated (light areas), which helps to more deeply understand the logical relationship within the evaluation index system and assist in subsequent analysis and decision-making, such as determining whether there are duplicate indicators that need to be streamlined, and which indicators need to focus on the impact of each other in the comprehensive evaluation.

[0158] S144. Analyze the correlation between each evaluation index based on the Pearson correlation coefficient.

[0159] Specifically, when the Pearson correlation coefficient is greater than a preset threshold, the two evaluation indicators are positively correlated; when the Pearson correlation coefficient is less than the preset threshold, the two evaluation indicators are negatively correlated; when the Pearson correlation coefficient is equal to the preset threshold, the two evaluation indicators are not correlated.

[0160] Among them, the preset threshold can be set in advance.

[0161] Specifically, if the Pearson correlation coefficient is greater than 0, it indicates that the two evaluation indicators are strongly positively correlated; if the Pearson correlation coefficient is less than 0, it indicates that the two evaluation indicators are strongly negatively correlated; and when the Pearson correlation coefficient is equal to 0, it indicates that the two evaluation indicators are not correlated. Find the Pearson correlation coefficient |r i,j | greater than 0.3 and less than 1 for the index pairs, indicating that their correlation is strong, and analyze their synergy effect; for example, if the peak shaving and valley filling rate and the new energy utilization rate have a Pearson correlation coefficient r i,j = 0.85, it shows that improving the peak shaving and valley filling rate helps to improve the new energy utilization efficiency; find the Pearson correlation coefficient |r i,j | greater than 0 and less than 0.3 for the index pairs, indicating that there is no correlation between them and their independence is strong; for example, if the investment cost and the curtailment rate of wind power have a correlation coefficient r i,j = 0.05, changing either of them will have no impact on the other index; find the Pearson correlation coefficient r i,j < -0.3 and greater than -1 for the index pairs, indicating that their correlation is weak, and analyze their competition relationship; for example, if the curtailment rate of wind power and the new energy utilization rate have a correlation coefficient r i,j = -0.75, it shows that increasing the new energy utilization rate will significantly reduce the curtailment rate of wind power. In this way, taking a certain evaluation index as the target index, the association relationship between other indexes and the target index can be obtained; if the relationship between the two is strong, it means that both can be improved simultaneously, and if the relationship between the two is weak, it means that they cannot be improved simultaneously; combining the correlation results helps decision-makers formulate multi-objective scheduling strategies and balance the synergy effect and competition relationship.

[0162] Figure 2 It is a flowchart of another evaluation method for the distribution network energy storage configuration scheme provided by the embodiments of the present invention. The embodiments of the present invention further refine the foregoing embodiments on the basis of the above-mentioned embodiments. Refer to Figure 2 and this evaluation method for the distribution network energy storage configuration scheme includes:

[0163] S210. Construct an evaluation index system for the distribution network energy storage configuration scheme to be evaluated.

[0164] S220. Perform normalization processing on each evaluation index in the evaluation index system.

[0165] Specifically, due to the large differences in the numerical ranges and dimensions of different evaluation indicators, it is necessary to normalize the data to ensure the comparability of each indicator during subsequent analysis. The Min-Max normalization is used to transform the data into the range [0, 1]. If the evaluation indicator is a positive indicator, that is, the larger the indicator, the better, the calculation formula is:

[0166]

[0167] where X is the actual value of the indicator, X min and X max are the minimum and maximum values of the indicator respectively. If the evaluation indicator is a negative indicator, that is, the smaller the indicator, the better, the calculation formula is:

[0168]

[0169] Organize all the normalized evaluation indicators into a two-dimensional matrix X, where each column is an indicator and each row is a sample.

[0170]

[0171] where X i,j represents the value of the j-th evaluation indicator at the i-th moment.

[0172] S230. Dynamically allocate the weights of each evaluation indicator in the normalized evaluation indicator system.

[0173] S240. Visualize the dynamic weight distribution of each evaluation indicator using a heat map.

[0174] S250. Analyze the correlation between each evaluation indicator using the Pearson correlation coefficient.

[0175] The technical solution provided by the embodiment of the present invention, by constructing a comprehensive evaluation indicator system covering five dimensions of economy, energy utilization rate, voltage quality, flexibility, and reliability, and adopting a dynamic weight allocation method to adjust the weights of each indicator according to real-time operation data, makes the evaluation result more in line with the actual operation conditions. At the same time, by methods such as linear correlation analysis, the correlation between multiple indicators is mined, the synergistic or competitive relationship of energy storage configuration on the performance of the distribution network is revealed, and the linkage effect and weight distribution between indicators are intuitively displayed using heat map technology, providing a scientific basis for optimizing the energy storage configuration scheme and improving the operation efficiency of the distribution network.

[0176] Figure 3 is a schematic structural diagram of an evaluation device for a distribution network energy storage configuration scheme provided by an embodiment of the present invention. Refer to Figure 3 The evaluation device for the distribution network energy storage configuration scheme includes a construction module 310, an allocation module 320, a visualization module 330, and an analysis module 340.

[0177] The construction module 310 is used to construct an evaluation index system for the energy storage configuration scheme of the distribution network to be evaluated;

[0178] The allocation module 320 is used to dynamically allocate the weights of the evaluation indexes in the evaluation index system after normalization processing;

[0179] The visualization module 330 is used to visualize the dynamic weight distribution of each evaluation index by using a heat map;

[0180] The analysis module 340 is used to analyze the correlation between the evaluation indexes by using the Pearson correlation coefficient.

[0181] The evaluation device for the energy storage configuration scheme of the distribution network provided by the embodiment of the present invention can execute the evaluation method for the energy storage configuration scheme of the distribution network provided by any embodiment of the present invention, and has the corresponding function modules and beneficial effects for executing the method.

[0182] Figure 4 It is a schematic structural diagram of an electronic device for an evaluation method of an energy storage configuration scheme of a distribution network provided by an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0183] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by the at least one processor. The processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0184] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0185] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for evaluating a distribution network energy storage configuration scheme.

[0186] In some embodiments, a method for evaluating a distribution network energy storage configuration scheme can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for evaluating a distribution network energy storage configuration scheme described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute a method for evaluating a distribution network energy storage configuration scheme by any other suitable means (e.g., by means of firmware).

[0187] The various embodiments of the systems and technologies described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special or general programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0188] A computer program for implementing the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer program may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on a remote machine or server.

[0189] In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0190] In order to provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, speech input, or tactile input).

[0191] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend, middleware, or frontend components. The components of the system can be interconnected to each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0192] A computing system can include a client and a server. The client and the server are generally far from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0193] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0194] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for evaluating a distribution network energy storage configuration scheme, characterized in that: include: Construct an evaluation index system for the energy storage configuration scheme of the distribution network to be evaluated; Dynamically assign the weight of each evaluation index in the normalized evaluation index system; A heat map is used to visualize the dynamic weight distribution of each evaluation index; The Pearson correlation coefficient was used to analyze the correlation between the evaluation indicators.

2. The method for evaluating the energy storage configuration scheme of a distribution network according to claim 1, characterized in that: The evaluation index system for constructing the distribution network energy storage configuration scheme to be evaluated includes: Establish economic evaluation indicators, energy utilization evaluation indicators, voltage quality evaluation indicators, reliability evaluation indicators and flexibility evaluation indicators; wherein the economic evaluation indicators include energy storage investment cost and energy storage operation and maintenance cost; the energy utilization evaluation indicators include wind and solar power abandonment rate, new energy utilization rate, energy storage peak shaving and valley filling rate and average line loss; the voltage quality evaluation indicators include voltage deviation index and voltage qualification rate; the reliability evaluation indicators include power supply shortage probability and power supply shortage expectation; the flexibility evaluation indicators include line maximum load rate and net load fluctuation rate.

3. The method for evaluating the energy storage configuration scheme of the distribution network according to claim 2, characterized in that: The energy storage investment cost should satisfy the following relationship: In the formula, C inv is the energy storage investment cost; E ess,i and P ess,i are the rated capacity and rated power of the planned i-th energy storage respectively; S ess is the energy storage installation node set; r is the discount rate; y ess is the operating life of energy storage; c e 、c p are the investment costs per unit capacity and per unit power of energy storage respectively; The energy storage operation and maintenance cost should satisfy the following relationship: In the formula, C OM is the energy storage operation and maintenance cost; c ess is the operating cost of the energy storage device per unit power; is the charging and discharging power of the energy storage device at node i during period t; The wind and solar power abandonment rate should satisfy the following relationship: Where CR is the wind and solar power abandonment rate; N DG Install node collection for distributed photovoltaic / wind power; is the available power generation of distributed photovoltaic / wind power at node n at time t in the distribution network; is the actual power generation of distributed photovoltaic / wind power at node n in the distribution network at time t; The new energy utilization rate should satisfy the following relationship: In the formula, NER is the utilization rate of new energy; The energy storage peak shaving and valley filling rate should satisfy the following relationship: In the formula, f p P is the peak-shaving and valley-filling rate of energy storage; ld is the load deficit of the system; P′ ld The load shortfall of the system after adding energy storage; The average line loss should satisfy the following relationship: Where ALR is the average line loss; P loss,t is the total network loss at time t in the distribution network; L is the total number of branches; The voltage offset index should satisfy the following relationship: Where VOI is the voltage deviation index; N is the total number of nodes in the distribution network; U n,t is the actual value of the voltage at node n in the distribution network at time t; U n,rated is the rated value of the voltage at node n in the distribution network at time t; The voltage qualification rate should satisfy the following relationship: Where, RQV is the voltage qualification rate; N RQV,t is the number of nodes with qualified voltage at time t in the distribution network; The probability of insufficient power supply should satisfy the following relationship: Where PLC is the probability of insufficient power supply; T is the total simulation time; d i Status Duration; n is the total number of states within T time; For the status The following is the experimental function corresponding to the power supply shortage probability PLC: The power supply shortage expectation should satisfy the following relationship: Where EENS is the expected electricity supply shortage; F EENS The experimental function of the expected EENS for insufficient power supply; Indicates that the system is in state The total load reduction; The maximum load rate of the line should satisfy the following relationship: Where, MLR is the maximum load rate of the line; P l,t is the actual active power transmitted by line l; P l,max is the maximum transmittable active power of line l; The net load fluctuation rate should satisfy the following relationship: Where FRNL is the net load fluctuation rate; P t NL and are the net load values ​​of the distribution network at time t and the previous time t-1 respectively.

4. The method for evaluating the energy storage configuration scheme of a distribution network according to claim 1, characterized in that: The weights of the evaluation indicators in the evaluation indicator system after the dynamic allocation and normalization processing include: The mean of each evaluation index is taken as the benchmark value of evaluation index j; Calculating a deviation between the current value of the evaluation index j and the reference value; Calculating the dynamic weight of the evaluation index j based on the absolute value of the deviation value; The evaluation indicators are weighted and summed according to the dynamic weights to calculate the comprehensive score of the energy storage configuration scheme.

5. The method for evaluating the energy storage configuration scheme of the distribution network according to claim 4, characterized in that: The reference value of the evaluation index j should satisfy the following relationship: In the formula, B j is the benchmark value of evaluation index j; X j (t) represents the value of evaluation index j at time t; T is the length of the time; The deviation value is calculated using the following formula: In the formula, Δ j (t) represents the deviation value of evaluation index j at time t; The dynamic weight is calculated using the following formula: In the formula, w j (t) represents the dynamic weight of evaluation index j at time t; The comprehensive score of the energy storage configuration scheme is calculated using the following formula: Where s(t) is the comprehensive score of the energy storage configuration scheme; V j (t) represents the normalized value of index j at time t.

6. The method for evaluating the energy storage configuration scheme of a distribution network according to claim 1, characterized in that: The use of a heat map to visualize the dynamic weight distribution of each evaluation index includes: Set the cells of the heat map to display specific weight values; Display dynamic weight distribution through color depth to identify key time points; Determine a change time period of the dynamic weight of each evaluation indicator according to the change of each evaluation indicator at different time points; According to the dynamic weight distribution of different evaluation indicators at the same time point, the correlation of each evaluation indicator is judged.

7. The method for evaluating distribution network energy storage configuration scheme according to claim 1, characterized in that: The use of the Pearson correlation coefficient to analyze the correlation between the evaluation indicators includes: Calculate the Pearson correlation coefficient between any two evaluation indicators; The Pearson correlation coefficient is calculated for all evaluation indicators in pairs, and a symmetric linear correlation matrix is ​​generated; Generate a heat map according to the symmetric linear correlation matrix, wherein the horizontal axis and the vertical axis of the heat map are the evaluation indicators, and the color of the cells in the heat map indicates the size of the Pearson correlation coefficient: the color depth indicates the strength of the correlation between the evaluation indicators; The correlation between the evaluation indicators is analyzed according to the Pearson correlation coefficient.

8. The method for evaluating the energy storage configuration scheme of the distribution network according to claim 7, characterized in that: The Pearson correlation coefficient is calculated using the following formula: In the formula, and are the means of evaluation index A and evaluation index B, A i and B i is the i-th sample value of evaluation index A and evaluation index B; The symmetric linear correlation matrix satisfies the following form: Among them, r i,j represents the Pearson correlation coefficient between evaluation index i and evaluation j; Analyzing the correlation between the evaluation indicators according to the Pearson correlation coefficient includes: When the Pearson correlation coefficient is greater than a preset threshold, the two evaluation indicators are positively correlated; When the Pearson correlation coefficient is less than a preset threshold, the two evaluation indicators are negatively correlated; When the Pearson correlation coefficient is equal to the preset threshold, the two evaluation indicators are unrelated.

9. The method for evaluating energy storage configuration schemes of distribution networks according to claim 1, characterized in that: Before dynamically allocating the weights of the evaluation indicators in the evaluation indicator system after normalization, the method further includes: Each evaluation index in the evaluation index system is normalized.

10. A distribution network energy storage configuration scheme evaluation device, characterized in that: include: A construction module, wherein the construction module is used to construct an evaluation index system for the distribution network energy storage configuration scheme to be evaluated; An allocation module, which is used to dynamically allocate the weight of each evaluation index in the evaluation index system after normalization; A visualization module, wherein the visualization module is used to visualize the dynamic weight distribution of each evaluation index using a heat map; The analysis module is used to analyze the correlation between the evaluation indicators using the Pearson correlation coefficient.

Images