Method and system for comprehensively evaluating effect of participating in demand response of battery swap station

Abstract

The invention discloses a comprehensive evaluation method and system for a demand response participation effect of a battery swap station. The method comprises the steps of establishing an effect multi-dimensional evaluation index system based on the demand response participation effect of the battery swap station according to historical data information generated when the battery swap station participates in the demand response; establishing a first variable-weight matter-element extension model in combination with an effect multi-dimensional evaluation index system based on the participation of the battery swap station in the demand response, performing missing value compensation based on deep learning, and improving the first variable-weight matter-element extension model to obtain a second variable-weight matter-element extension model; and according to the second variable weight matter element extension model, evaluating the effect multi-dimensional evaluation index system based on the participation of the battery swap station in the demand response. According to the comprehensive evaluation method and system for the effect of participating in the demand response of the battery swap station, an accurate and comprehensive evaluation result can be provided, good application prospects and popularization value are achieved, and the method and system have great significance in promoting efficient operation of the battery swap station and stable operation of a power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of comprehensive evaluation of the effect of battery swap stations participating in demand response, and in particular to a method and system for comprehensive evaluation of the effect of battery swap stations participating in demand response. Background Art

[0002] As global climate change and environmental degradation become increasingly severe, electric vehicles are gradually becoming the main choice for future transportation with their environmental protection and energy-saving characteristics. At the same time, the development of smart grid technology also provides the possibility for efficient use and optimal configuration of energy. In this context, with the characteristics of flexible energy storage and elastic charging of electric vehicles, electric vehicles participating in grid demand response are gradually being promoted and applied. Due to the characteristics of battery storage energy storage, battery swap stations not only provide efficient and convenient energy supply for electric vehicles, but also serve as important nodes for vehicle-grid interaction. By participating in demand response, battery swap stations can reduce charging loads and reduce grid pressure during peak grid loads; increase charging loads and improve grid equipment utilization during low grid loads. This not only helps to balance grid loads and optimize energy configuration, but also helps to improve the economic benefits of battery swap stations.

[0003] However, despite the increasing importance of electric vehicles participating in demand response, there is still a lack of research on its effectiveness evaluation. Existing evaluation methods mostly focus on the evaluation of the effectiveness of charging stations as a link between the power grid and electric vehicles in demand response. However, due to the differences in operation mode, functional positioning, technical implementation and data availability of battery swap stations, it is necessary to study a set of methods for evaluating the effectiveness of battery swap stations participating in demand response for the scenario of battery swap stations.

[0004] Therefore, there is an urgent need for a scientific, systematic and comprehensive evaluation index system and method for the effectiveness of battery swap stations in demand response, so as to accurately reflect the actual effect of battery swap stations in demand response and provide strong support for policy formulation, operation optimization and user demand satisfaction. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the present invention provides a method and system for comprehensively evaluating the effect of battery swap stations participating in demand response, which can solve the problems mentioned in the background technology.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a method for comprehensively evaluating the effect of a battery swap station participating in demand response, comprising:

[0010] Based on the historical data information generated by the battery swap stations participating in demand response, a multi-dimensional evaluation index system based on the effect of the battery swap stations participating in demand response is established;

[0011] A first variable-weighted matter-element extension model is established in combination with the multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response, and missing values ​​are supplemented based on deep learning, and the first variable-weighted matter-element extension model is improved to obtain a second variable-weighted matter-element extension model;

[0012] According to the second variable-weight matter-element extension model, a multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response is evaluated.

[0013] As a preferred solution of the comprehensive evaluation method of the effect of battery swap stations participating in demand response according to the present invention, the establishment of a multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response includes:

[0014] The multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response is a system composed of indicators arbitrarily selected by users, and the selected indicators include response flexibility indicators, response performance indicators, response quality indicators and response benefit indicators;

[0015] The response flexibility index at least includes an index calculated by a climbing rate per minute and a descending rate per minute;

[0016] The response performance index at least includes an index calculated by response time and continuous response duration;

[0017] The response quality index at least includes an index calculated by response capacity and control deviation rate;

[0018] The response benefit index includes at least an index calculated by direct response benefit and cost reduction benefit.

[0019] As a preferred solution of the comprehensive evaluation method of the effect of battery swap stations participating in demand response according to the present invention, the first variable weight matter-element extension model established in combination with the multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response includes:

[0020] According to the multi-dimensional evaluation index system of the effect of battery swap stations participating in demand response, the classic domain, node domain and matter-element to be evaluated of the first variable weight matter-element extension model are determined;

[0021] The demand response effect of the battery swap station is divided into j levels, and any level interval is P j There are n indicators that affect the effectiveness of demand response of battery swap stations, namely c1, c2, c n There are n different features, n is at least 8, and the characteristic value range of each eigenvalue is V nj ∈ nj ,b nj >, then the demand response effectiveness first variable weight matter-element extension model classic domain matrix R j It is expressed as follows:

[0022]

[0023] Among them, a nj , b nj are the maximum and minimum values ​​of the characteristic index respectively.

[0024] As a preferred solution of the comprehensive evaluation method of the effect of battery swap stations participating in demand response according to the present invention, wherein: the establishment of the first variable-weighted matter-element extension model in combination with the multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response also includes:

[0025] The node domain matter-element matrix is ​​expressed as follows:

[0026]

[0027] Among them, R p is the node domain matter-element matrix, P represents the overall evaluation level of demand response effectiveness of battery swap stations, c n is n different characteristic indicators, V pn is the value range of the evaluation level of the demand response effectiveness of the battery swap station, They are the lower and upper limits of the value range corresponding to each evaluation level;

[0028] The object element to be evaluated is the measured value of the indicators of each evaluation dimension of the demand response effect of the battery swap station, which is expressed as:

[0029]

[0030] Among them, R0 represents all the elements to be evaluated, c n is n different characteristic indicators, v n The measured values ​​of each indicator.

[0031] As a preferred scheme of the comprehensive evaluation method of the effect of battery swap stations participating in demand response described in the present invention, wherein: the missing value compensation based on deep learning is performed, the first variable-weighted matter-element extension model is improved to obtain the second variable-weighted matter-element extension model, including: using a generative adversarial network to compensate for the missing values.

[0032] ​As a preferred solution of the comprehensive evaluation method of the effect of battery swap stations participating in demand response according to the present invention, wherein: the missing value compensation based on deep learning, the improvement of the first variable weight matter-element extension model, and the second variable weight matter-element extension model also include:

[0033] When the measured data of the evaluation index exceeds the range of the node domain, the classical domain matter-element and the matter-element to be evaluated are normalized and expressed as:

[0034]

[0035] Among them, R′ j is the normalized classical domain matter element, c n is n evaluation indicators, a nj 、b nj are the maximum and minimum values ​​of the characteristic index, respectively. is the upper limit of the value range of the evaluation index corresponding to each evaluation level, R′0 is the normalized object element to be evaluated, and v n The measured values ​​of each indicator.

[0036] As a preferred solution of the comprehensive evaluation method of the effect of battery swap stations participating in demand response according to the present invention, wherein: the missing value compensation based on deep learning, the improvement of the first variable weight matter-element extension model, and the second variable weight matter-element extension model also include:

[0037] The weights are determined by combining a decision tree algorithm, and the first variable weight matter-element extension model is improved;

[0038] Assign the largest weight to the feature with the strongest correlation with the target variable, and then apply variable weight theory to make corrections;

[0039] The demand response effectiveness score of the battery swap station is calculated based on the determined indicator weights, and then the proximity criterion is used to determine the evaluation level of the demand response effectiveness of the battery swap station;

[0040] The evaluation results of the demand response effectiveness of the battery swap station are quantified to determine the degree of closeness between each evaluation level, thereby achieving quantitative determination of the evaluation level of the demand response effectiveness of the battery swap station.

[0041] In a second aspect, the present invention provides a comprehensive evaluation system for the effect of battery swap stations participating in demand response, including:

[0042] A system establishment module is used to establish a multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response based on the historical data information generated by the battery swap stations participating in demand response;

[0043] A model updating module, used to establish a first variable-weighted matter-element extension model in combination with the multi-dimensional evaluation index system based on the effect of the battery swap station participating in the demand response, and to improve the first variable-weighted matter-element extension model based on deep learning to make up for missing values, so as to obtain a second variable-weighted matter-element extension model;

[0044] An evaluation module is used to evaluate the multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response according to the second variable-weight matter-element extension model.

[0045] In a third aspect, the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method when executing the computer program.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method described above when executed by a processor.

[0047] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention proposes a comprehensive evaluation method and system for the effect of battery swap stations participating in demand response, and establishes a multidimensional evaluation index system based on the effect of battery swap stations participating in demand response according to the historical data information generated by the battery swap stations participating in demand response; a first variable weight matter-element extension model is established in combination with the multidimensional evaluation index system based on the effect of battery swap stations participating in demand response, and the first variable weight matter-element extension model is improved based on deep learning to make up for missing values, and a second variable weight matter-element extension model is obtained; according to the second variable weight matter-element extension model, the multidimensional evaluation index system based on the effect of battery swap stations participating in demand response is evaluated. The present invention can comprehensively consider all aspects of battery swap stations participating in demand response, including but not limited to response speed, response capability, economy, environmental impact, etc., so as to provide a comprehensive evaluation result. By using deep learning technology to make up for data missing, the present invention can effectively deal with the problem of missing values ​​in historical data and improve the accuracy and reliability of the evaluation model. Through the improvement of the variable weight matter-element extension model, the present invention can dynamically adjust the weights of each evaluation index according to actual conditions, so that the evaluation results are more in line with the dynamic changes of the actual demand response effect. Combined with the decision tree algorithm to determine the weights, the present invention can reasonably allocate weights according to the correlation between the features and the target variables, further improving the accuracy of the evaluation results. Using the proximity criterion to judge the evaluation level, the present invention can quantify the degree of closeness between the effectiveness of the battery swap station's demand response and each evaluation level, and provide decision makers with intuitive evaluation results. The evaluation system of the present invention has good scalability, and can flexibly adjust the evaluation index system and evaluation model according to the new situation and new needs of the battery swap station's participation in demand response, so as to adapt to the ever-changing evaluation needs. The evaluation method and system of the present invention have a high degree of automation, can reduce manual intervention, improve evaluation efficiency, and reduce evaluation costs.

[0048] To sum up, the comprehensive evaluation method and system for the effect of battery swap stations participating in demand response proposed in the present invention can not only provide accurate and comprehensive evaluation results, but also have good application prospects and promotion value, which is of great significance for promoting the efficient operation of battery swap stations and the stable operation of power grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0050] Figure 1 A method flow chart of a comprehensive evaluation method and system for the effect of a battery swap station participating in demand response provided by an embodiment of the present invention;

[0051] Figure 2 An internal structural diagram of a computer device of a method and system for comprehensively evaluating the effect of a battery swap station participating in demand response provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0053] Example 1

[0054] Reference Figure 1-Figure 2 , which is the first embodiment of the present invention, and provides a method and system for comprehensively evaluating the effect of a battery swap station participating in demand response, including:

[0055] Before describing the embodiments of the present application in detail, some related concepts are first explained for the sake of clarity.

[0056] Variable-weight matter-element extension model: The variable-weight matter-element extension model is a method for dealing with multi-criteria decision-making problems. It combines matter-element theory, extensions and variable-weight ideas. Matter-element theory is a mathematical tool used to describe the attributes and values ​​of things. A matter-element consists of three elements: object (N), feature (C) and value (V), expressed as (N, C, V). For example, for a battery swap station, the object N can be a specific battery swap station, the feature C can be the response time, and the value V is the actual value of the response time of the battery swap station. Extensions is a theoretical framework for studying uncertainty and fuzziness. In extensions, two important concepts are usually defined: Normal Set: represents the valid value range of a feature, such as the valid range of response time may be set to 1 to 10 minutes. Node Set: refers to a wider range of values ​​than the normal domain, used to describe uncertainty and fuzziness, such as the response time may be between 0 and 15 minutes. In multi-criteria decision-making problems, the importance of different features (or evaluation indicators) may change with the situation. The variable weight idea allows the weights of different features to be adjusted according to specific circumstances, thereby more accurately reflecting the preferences of decision makers and changes in the actual environment.

[0057] In the related art, there are some methods for evaluating the effectiveness of battery swap stations in participating in demand response, but these methods often have limitations, such as being unable to fully consider all relevant factors or being insufficiently flexible in dealing with missing data.

[0058] This application provides a method that can effectively solve the above-mentioned problems. Next, a comprehensive evaluation method of the effect of the battery swap station participating in demand response will be described in detail in combination with multiple embodiments.

[0059] Figure 1 A method flow chart of a comprehensive evaluation method and system for the effect of battery swap stations participating in demand response is shown, including:

[0060] S101, based on historical data information generated by the battery swap station participating in demand response, establish a multi-dimensional evaluation index system based on the effect of the battery swap station participating in demand response;

[0061] In the embodiment of the present application, a multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response is established, including:

[0062] The multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response is a system composed of indicators arbitrarily selected by users, and the selected indicators include response flexibility index, response performance index, response quality index and response benefit index;

[0063] The response flexibility index at least includes an index calculated by the ramp-up rate per minute and the ramp-down rate per minute;

[0064] The response performance index at least includes an index calculated by response time and continuous response duration;

[0065] Response quality indicators include at least indicators calculated by response capacity and control deviation rate;

[0066] The response benefit index at least includes an index calculated by direct response benefit and cost reduction benefit.

[0067] Exemplarily, a response flexibility index is constructed. The flexibility of the battery swap station in participating in demand response is an important aspect to ensure the response effect. Higher response flexibility can participate in demand response more efficiently. The present invention uses two indicators, climbing rate per minute and descending rate per minute, to measure the response flexibility of the battery swap station in participating in demand response.

[0068] ① Ramp rate per minute: refers to the average load increase per minute when the battery swap station participates in demand response. The expression is as follows:

[0069] P ramp =P incr / T dur

[0070] Among them, P incr is the load increase when the battery swap station participates in demand response, T dur The duration of the battery swap station’s participation in demand response.

[0071] ② Downhill rate per minute: refers to the average load reduction per minute when the battery swap station participates in demand response. The expression is as follows:

[0072] P dwn =P rdc / Tdur

[0073] Among them, P rdc It is the load reduction when the battery swap station participates in demand response.

[0074] Furthermore, in terms of response performance, the response time and continuous response time are used to measure the response performance of the battery swap station in demand response.

[0075] ① Response time: The time from when the battery swap station receives the adjustment signal to when it actually changes the load output, in seconds.

[0076] ② Continuous response time: the length of time that the battery swap station can continuously respond after receiving the dispatch instruction, in minutes;

[0077] Furthermore, the response quality refers to the gap between the actual response level of the battery swap station when participating in demand response and the response target. The present invention uses the response capacity and the control deviation rate to measure the response quality of the battery swap station participating in demand response.

[0078] ① Response capacity: The actual response capacity of the battery swap station is determined by the difference between the baseline load and the actual measured average load during the response time period. The expression is as follows:

[0079] L cap =L bas -L act

[0080] Among them, L bas is the baseline load, L act is the actual measured average load.

[0081] ② Control deviation rate: reflects the difference between the actual response capacity of the battery swap station and the target response capacity. Its expression is as follows:

[0082] L dev =((L act -L aim ) / L aim )*100%

[0083] Among them, L act is the actual response capacity, L aim is the target response capacity, L act and L aim The unit is MW.

[0084] Furthermore, in terms of response benefits, the response benefits of a single participation of a battery swap station in demand response are measured by two indicators: direct response benefits and cost reduction.

[0085] ① Direct response benefits: Determined based on the actual response capacity and the subsidy standard for participating in demand response, and its expression is as follows:

[0086] Y dir =L cap *S coef *S pr

[0087] Among them, S coef is the subsidy coefficient, S pr To declare the subsidy price.

[0088] ② Cost reduction: At present, the electricity price of the battery swap station basically implements the peak-valley time-of-use electricity price. Under the premise of ensuring the normal operation of the battery swap station, the electricity cost of the battery swap station can be reduced by responding to the peak load of the power grid. The reduction in electricity cost is an additional benefit of the normal operation of the battery swap station, so the benefits obtained from participating in demand response are higher than the benefits of normal operation. Its expression is as follows:

[0089] Y don =L cap *△P ep

[0090] Among them, L cap is the actual response amount of the battery swap station in a single demand response event, △P ep It is the price difference of electricity purchase unit during the electricity transfer period when participating in demand response.

[0091] In an optional embodiment, the multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response is a system composed of indicators arbitrarily selected by users. The selected indicators may also include response sustainability indicators, response safety indicators, and response environmental impact indicators.

[0092] Exemplarily, the response sustainability index includes at least an index calculated by response frequency and response duration. This index reflects the long-term stability and sustainability of the battery swap station's participation in demand response, ensuring that the battery swap station can maintain efficient response capabilities over a long period of time.

[0093] ① Response frequency: refers to the number of times the battery swap station participates in demand response within a specific time period, and its expression is as follows:

[0094] F resp =N resp / T dur

[0095] Among them, N resp is the number of times the battery swap station participates in demand response, T dur is the length of the time period considered.

[0096] Furthermore, the response safety index at least includes an index calculated by the failure rate and the recovery time. This index ensures the safety of the battery swap station when participating in the demand response and avoids additional losses caused by failures.

[0097] ① Failure rate: refers to the frequency of failures of the battery swap station during the demand response process, and its expression is as follows:

[0098] R fail =N fail / N resp

[0099] Among them, N fail is the number of failures that occur in the battery swap station during the demand response process, N resp The total number of times the battery swap station participated in demand response.

[0100] Furthermore, the response environmental impact index at least includes an index calculated by carbon emissions and energy consumption. This index reflects the impact of the battery swap station's participation in demand response on the environment, and promotes the use of green energy and environmental protection.

[0101] ① Carbon emissions: refers to the carbon dioxide emissions generated by the battery swap station during the demand response process, and its expression is as follows:

[0102] E carb =E gen *F resp *E fact

[0103] Among them, E gen is the power generation of the battery swap station, F resp is the response frequency, E fact is the carbon dioxide emission factor per unit of electricity generated.

[0104] ②Energy consumption: refers to the total amount of energy consumed by the battery swap station in the process of participating in demand response. Its expression is as follows:

[0105] E cons =E gen / E eff

[0106] Among them, E gen is the power generation of the battery swap station, E eff The energy conversion efficiency of the battery swap station.

[0107] It should be noted that by comprehensively considering these indicators, the effect of battery swap stations participating in demand response can be more comprehensively evaluated, providing a more accurate reference for decision makers. In practical applications, the indicator system can be adjusted according to specific needs and environments to adapt to different application scenarios and goals.

[0108] S102, establishing a first variable-weighted matter-element extension model based on a multi-dimensional evaluation index system of the effect of battery swap stations participating in demand response, and improving the first variable-weighted matter-element extension model based on deep learning to compensate for missing values, thereby obtaining a second variable-weighted matter-element extension model;

[0109] It should be noted that the variable-weighted matter-element extension model introduces the concept of attribute weights on the basis of the matter-element extension model. By introducing attribute weights, the variable-weighted matter-element extension model can more accurately measure the similarities and differences between elements and perform classification and evaluation. The consideration of attribute weights enables the model to better reflect the actual situation and improves the accuracy and reliability of classification and evaluation results.

[0110] The present invention is based on the variable-weighted matter-element extension model and a multi-dimensional evaluation index system for the effect of battery swap stations participating in demand response. It uses machine learning to process missing data and data mining to improve weight distribution, thereby improving the variable-weighted matter-element extension model and using this improved model to effectively evaluate the effect of battery swap stations participating in demand response.

[0111] In the embodiment of the present application, the first variable weight matter-element extension model is established in combination with the multi-dimensional evaluation index system based on the effect of the battery swap station participating in the demand response, and further includes:

[0112] The node domain matter-element matrix is ​​expressed as follows:

[0113]

[0114] Among them, R p is the node domain matter-element matrix, P represents the overall evaluation level of demand response effectiveness of battery swap stations, c n is n different characteristic indicators, V pn is the value range of the evaluation level of the demand response effectiveness of the battery swap station, They are the lower and upper limits of the value range corresponding to each evaluation level;

[0115] It should be noted that the node-domain matter-element matrix of the present invention is composed of four evaluation levels of demand response effectiveness of battery swap stations, eight evaluation indicators and value ranges of the eight evaluation indicators.

[0116] The object element to be evaluated is the measured value of the indicators of each evaluation dimension of the demand response effect of the battery swap station, which is expressed as:

[0117]

[0118] Among them, R0 represents all the elements to be evaluated, c n is n different characteristic indicators, v n The measured values ​​of each indicator.

[0119] Based on deep learning, missing values ​​are compensated, and the first variable-weight matter-element extension model is improved to obtain the second variable-weight matter-element extension model, which includes: using a generative adversarial network to compensate for missing values.

[0120] In an embodiment of the present application, the present invention applies a generative adversarial network (GAN) to compensate for missing values ​​and improve the accuracy of subsequent evaluations. A generative adversarial network is a deep learning model consisting of two neural networks: a generator and a discriminator. The generator is responsible for generating data, such as images, sounds, or text, from random noise. The goal of the generator is to deceive the discriminator into believing that the generated data is real data. The discriminator is responsible for distinguishing between real data and generated data. The goal of the discriminator is to identify the generated data as accurately as possible. The generator and the discriminator compete with each other to improve performance together. As training proceeds, the generator will generate more and more realistic data, and the discriminator will become more and more adept at identifying the generated data. By applying a generative adversarial network (GAN), the missing data of the battery swap station participating in demand response can be compensated, and the accuracy of the effect evaluation can be improved.

[0121] Based on deep learning, missing values ​​are supplemented and the first variable weight matter-element extension model is improved to obtain the second variable weight matter-element extension model, which also includes:

[0122] When the measured data of the evaluation index exceeds the range of the node domain, the value of its correlation function cannot be measured (that is, the denominator is zero), and the model cannot be used to evaluate the power quality. Therefore, it is necessary to improve the matter-element extension model by normalizing the classical domain matter-element and the matter-element to be evaluated, which can be expressed as:

[0123]

[0124] Among them, R′ j is the normalized classical domain matter element, c n is n evaluation indicators, a nj 、b nj are the maximum and minimum values ​​of the characteristic index, respectively. is the upper limit of the value range of the evaluation index corresponding to each evaluation level, R′0 is the normalized object element to be evaluated, and v n The measured values ​​of each indicator.

[0125] Based on deep learning, missing values ​​are supplemented and the first variable weight matter-element extension model is improved to obtain the second variable weight matter-element extension model, which also includes:

[0126] The decision tree algorithm is combined to determine the weights, and the first variable weight matter-element extension model is improved;

[0127] Assign the largest weight to the feature with the strongest correlation with the target variable, and then apply variable weight theory to make corrections;

[0128] The demand response effectiveness score of the battery swap station is calculated based on the determined indicator weights, and then the proximity criterion is used to determine the evaluation level of the demand response effectiveness of the battery swap station;

[0129] The evaluation results of the demand response effectiveness of the battery swap station are quantified to determine the degree of closeness between each evaluation level, thereby achieving quantitative determination of the evaluation level of the demand response effectiveness of the battery swap station.

[0130] In the embodiment of the present application, the weight allocation method of the present invention is to allocate the largest weight to the feature with the strongest correlation (positive correlation or negative correlation) with the target variable. Then, the variable weight theory is applied for correction:

[0131]

[0132] in, The minimum and maximum values ​​of the indicator, V i is the actual value of the evaluation index, d imin ,d imax They are the minimum and maximum distances between each indicator and the indicator boundary value, respectively. α is a variable weight factor. When α>0, it means that the response effectiveness needs to highlight individual evaluation dimensions, and the balance requirements between indicators are relatively low; when α=0, it indicates a fixed weight model; when α<0, it indicates that the indicators of each evaluation dimension of the response effectiveness are relatively balanced. In the present invention, each indicator of the effectiveness of the battery swap station participating in the demand response is relatively important, so α is -1.

[0133] Furthermore, the demand response effectiveness score of the battery swap station is calculated based on the determined indicator weights, and then the proximity criterion is used to determine the evaluation level of the demand response effectiveness of the battery swap station. The calculation method of the proximity criterion is as follows:

[0134]

[0135] Among them, N j (P0) is the degree of closeness to the performance evaluation level, D j (v i ) is the distance between the object element R0 to be evaluated and the normalized classical domain, w i (X) is the optimal weight of the indicator, v i is the actual value of the indicator, a ij , b ij The minimum and maximum values ​​of each level indicator. The final evaluation level can be determined based on the maximum value of the closeness between the evaluation object and each level; where j ranges from (1 to 5).

[0136] Furthermore, by N j′ (p0) = max{N j (p0)}, the object-element to be evaluated belongs to level j′. Order:

[0137]

[0138] The calculation method of the evaluation level j* of the demand response effectiveness of the battery swap station is:

[0139]

[0140] Among them, N j (P0) is the degree of closeness of the evaluation level of demand response effectiveness of the battery swap station, j is the classification level of the evaluation level of demand response effectiveness of the battery swap station (the value is 4 in the present invention), j * It is a level characteristic variable, which is used to characterize the closeness between the object-element to be evaluated and each level.

[0141] Furthermore, according to j * The calculation results can quantify the degree of closeness between the evaluation results of the demand response effectiveness of the battery swap station and each evaluation level, thereby realizing the quantitative determination of the evaluation level of the demand response effectiveness of the battery swap station.

[0142] S103, evaluating a multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response according to the second variable-weight matter-element extension model.

[0143] In the embodiment of the present application, the effectiveness evaluation level is divided into four levels, namely level one, level two, level three and level four. Different levels correspond to different level characteristic variable values. This part can be designed by the user or operator. Level one indicates that the effect of the battery swap station participating in the demand response is very good, level two indicates good effect, level three indicates average effect, and level four indicates poor effect. Through the evaluation of the second variable weight matter-element extension model, the specific level of the demand response effectiveness of the battery swap station can be obtained.

[0144] In an optional embodiment, a corresponding optimization strategy can also be formulated based on the evaluation results. For the first and second level battery swap stations, it is possible to consider further expanding the scale of their participation in demand response and improving their role in the power system. For the third level battery swap stations, it is necessary to analyze their existing problems and make targeted improvements to improve the effect of their participation in demand response. For the fourth level battery swap stations, it is necessary to conduct in-depth investigations and studies to find out the reasons for their poor participation in demand response and formulate corresponding improvement measures.

[0145] In an optional embodiment, an optimization strategy may be implemented and the optimization effect may be tracked and evaluated. By implementing the optimization strategy, the effect of the battery swap station participating in the demand response may be improved, thereby better balancing the supply and demand relationship of the power system and improving the stability and reliability of the power system.

[0146] In an optional embodiment, the optimization strategy can also be continuously adjusted according to the tracking and evaluation results. In the process of implementing the optimization strategy, new problems and challenges may arise, so it is necessary to continuously adjust the optimization strategy according to the tracking and evaluation results to ensure that the effect of the battery swap station participating in demand response continues to improve.

[0147] In summary, the present invention proposes a comprehensive evaluation method and system for the effect of battery swap stations participating in demand response. According to the historical data information generated by the battery swap stations participating in demand response, a multidimensional evaluation index system based on the effect of battery swap stations participating in demand response is established; a first variable weight matter-element extension model is established in combination with the multidimensional evaluation index system based on the effect of battery swap stations participating in demand response, and the first variable weight matter-element extension model is improved based on deep learning to make up for missing values, and a second variable weight matter-element extension model is obtained; according to the second variable weight matter-element extension model, the multidimensional evaluation index system based on the effect of battery swap stations participating in demand response is evaluated. The present invention can comprehensively consider all aspects of battery swap stations participating in demand response, including but not limited to response speed, response capability, economy, environmental impact, etc., so as to provide a comprehensive evaluation result. By using deep learning technology to make up for data missing, the present invention can effectively deal with the problem of missing values ​​in historical data and improve the accuracy and reliability of the evaluation model. Through the improvement of the variable weight matter-element extension model, the present invention can dynamically adjust the weights of each evaluation index according to actual conditions, so that the evaluation result is more in line with the dynamic changes of the actual demand response effect. Combined with the decision tree algorithm to determine the weights, the present invention can reasonably allocate weights according to the correlation between the features and the target variables, further improving the accuracy of the evaluation results. Using the proximity criterion to judge the evaluation level, the present invention can quantify the degree of closeness between the effectiveness of the battery swap station's demand response and each evaluation level, and provide decision makers with intuitive evaluation results. The evaluation system of the present invention has good scalability, and can flexibly adjust the evaluation index system and evaluation model according to the new situation and new needs of the battery swap station's participation in demand response, so as to adapt to the ever-changing evaluation needs. The evaluation method and system of the present invention have a high degree of automation, can reduce manual intervention, improve evaluation efficiency, and reduce evaluation costs.

[0148] The comprehensive evaluation method and system for the effect of battery swap stations participating in demand response proposed in the present invention can not only provide accurate and comprehensive evaluation results, but also have good application prospects and promotion value, which is of great significance for promoting the efficient operation of battery swap stations and the stable operation of power grids.

[0149] This embodiment also provides a comprehensive evaluation system for the effect of battery swap stations participating in demand response, including:

[0150] A system establishment module is used to establish a multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response based on the historical data information generated by the battery swap stations participating in demand response;

[0151] A model updating module is used to establish a first variable-weighted matter-element extension model based on a multi-dimensional evaluation index system of the effect of battery swap stations participating in demand response, and to improve the first variable-weighted matter-element extension model based on deep learning to make up for missing values, thereby obtaining a second variable-weighted matter-element extension model;

[0152] The evaluation module is used to evaluate the multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response according to the second variable weight matter-element extension model.

[0153] The above-mentioned unit modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above-mentioned modules.

[0154] This embodiment also provides a computer device, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 2 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a comprehensive evaluation method for the effect of a battery swap station participating in demand response is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0155] This embodiment further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0156] Based on the historical data information generated by the battery swap stations participating in demand response, a multi-dimensional evaluation index system based on the effect of the battery swap stations participating in demand response is established;

[0157] The first variable-weighted matter-element extension model is established by combining the multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response, and the missing values ​​are supplemented based on deep learning. The first variable-weighted matter-element extension model is improved to obtain the second variable-weighted matter-element extension model.

[0158] According to the second variable weight matter-element extension model, a multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response is evaluated.

[0159] Example 2

[0160] Reference Figure 1-Figure 2 , which is an embodiment of the present invention, provides a comprehensive evaluation method and system for the effect of battery swap stations participating in demand response. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through experiments.

[0161] Assume that a battery swap station participates in a demand response program that requires the station to reduce its load by 20% within 10 minutes. The actual response of the battery swap station is as follows:

[0162] Table 1 Evaluation index values ​​after normalization of the first variable weight matter-element extension model

[0163]

[0164] (1) Determine indicator weights

[0165] Based on the second variable weight matter-element extension model, the weights of each indicator are determined as follows:

[0166] Table 2 Comprehensive weights of evaluation indicators

[0167]

[0168] (2) Calculation of indicator scores

[0169] The second variable weight matter-element extension model is used to calculate the scores of each indicator:

[0170] Table 3 Evaluation index score calculation

[0171]

[0172] (3) Comprehensive evaluation score

[0173] The weighted score for each indicator is calculated:

[0174] Table 4 Evaluation index weighted score calculation

[0175]

[0176] From this, the comprehensive evaluation score can be calculated:

[0177] Comprehensive evaluation score = 0.2 + 0.1 + 0.075 + 0.135 + 0.2 + 0.095 + 0.1 + 0.05 = 0.955

[0178] (3) Example conclusion

[0179] According to the results of the case analysis, the battery swap station has a good effect in participating in demand response and has a high comprehensive evaluation score. Specifically, the response flexibility and response quality of the battery swap station are the most outstanding, especially the climbing rate and the descending rate.

[0180] In addition, the analysis of this example shows that the evaluation method of the present invention can effectively evaluate the effect of battery swap stations participating in demand response.

[0181] 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 preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0182] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the present application can adopt 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.) that contain computer-usable program code. The scheme in the embodiments of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0183] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 generate 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.

[0184] 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 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0185] 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.

[0186] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0187] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A comprehensive evaluation method for the effect of battery swap stations participating in demand response, characterized in that: include: Based on the historical data information generated by the battery swap stations participating in demand response, a multi-dimensional evaluation index system based on the effect of the battery swap stations participating in demand response is established; A first variable-weighted matter-element extension model is established in combination with the multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response, and missing values ​​are supplemented based on deep learning, and the first variable-weighted matter-element extension model is improved to obtain a second variable-weighted matter-element extension model; According to the second variable-weight matter-element extension model, a multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response is evaluated.

2. The comprehensive evaluation method for the effect of battery swap stations participating in demand response according to claim 1, characterized in that: The multi-dimensional evaluation index system for the effect of battery swap stations participating in demand response is established, including: The multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response is a system composed of indicators arbitrarily selected by users, and the selected indicators include response flexibility indicators, response performance indicators, response quality indicators and response benefit indicators; The response flexibility index at least includes an index calculated by a climbing rate per minute and a descending rate per minute; The response performance index at least includes an index calculated by response time and continuous response duration; The response quality index at least includes an index calculated by response capacity and control deviation rate; The response benefit index includes at least an index calculated by direct response benefit and cost reduction benefit.

3. The comprehensive evaluation method for the effect of battery swap stations participating in demand response according to claim 2 is characterized in that: The first variable-weighted matter-element extension model established in combination with the multi-dimensional evaluation index system based on the effect of the battery swap station participating in the demand response includes: According to the multi-dimensional evaluation index system of the effect of battery swap stations participating in demand response, the classic domain, node domain and matter-element to be evaluated of the first variable weight matter-element extension model are determined; The demand response effect of the battery swap station is divided into j levels, and any level interval is P j There are n indicators that affect the effectiveness of demand response of battery swap stations, namely c1, c2, c n There are n different features, n is at least 8, and the characteristic value range of each eigenvalue is V nj ∈ nj ,b nj >, then the demand response effectiveness first variable weight matter-element extension model classic domain matrix R j It is expressed as follows:​ Among them, a nj 、b nj are the maximum and minimum values ​​of the characteristic index respectively.

4. The comprehensive evaluation method for the effect of battery swap stations participating in demand response according to claim 3 is characterized in that: The establishing of the first variable weight matter-element extension model in combination with the multi-dimensional evaluation index system based on the effect of the battery swap station participating in the demand response also includes: The node domain matter-element matrix is ​​expressed as follows: Among them, R p is the node domain matter-element matrix, P represents the overall evaluation level of demand response effectiveness of battery swap stations, c n is n different characteristic indicators, V pn is the value range of the evaluation level of the demand response effectiveness of the battery swap station, They are the lower and upper limits of the value range corresponding to each evaluation level; The object element to be evaluated is the measured value of the indicators of each evaluation dimension of the demand response effect of the battery swap station, which is expressed as: Among them, R0 represents all the elements to be evaluated, c n is n different characteristic indicators, v n The measured values ​​of each indicator.

5. The comprehensive evaluation method for the effect of battery swap stations participating in demand response according to claim 4 is characterized in that: The missing value compensation based on deep learning and the improvement of the first variable-weight matter-element extension model to obtain the second variable-weight matter-element extension model include: using a generative adversarial network to compensate for the missing values.

6. The comprehensive evaluation method for the effect of battery swap stations participating in demand response according to claim 5, characterized in that: The missing value compensation based on deep learning is performed to improve the first variable weight matter-element extension model to obtain the second variable weight matter-element extension model, and further includes: When the measured data of the evaluation index exceeds the range of the node domain, the classical domain matter-element and the matter-element to be evaluated are normalized and expressed as: Among them, R′ j is the normalized classical domain matter element, c n is n evaluation indicators, a nj 、b nj are the maximum and minimum values ​​of the characteristic index, respectively. is the upper limit of the value range of the evaluation index corresponding to each evaluation level, R′0 is the normalized object element to be evaluated, and v n The measured values ​​of each indicator.

7. The comprehensive evaluation method for the effect of battery swap stations participating in demand response according to claim 6, characterized in that: The missing value compensation based on deep learning is performed to improve the first variable weight matter-element extension model to obtain the second variable weight matter-element extension model, and further includes: The weights are determined by combining a decision tree algorithm, and the first variable weight matter-element extension model is improved; Assign the largest weight to the feature with the strongest correlation with the target variable, and then apply variable weight theory to make corrections; The demand response effectiveness score of the battery swap station is calculated based on the determined indicator weights, and then the proximity criterion is used to determine the evaluation level of the demand response effectiveness of the battery swap station; The evaluation results of the demand response effectiveness of the battery swap station are quantified to determine the degree of closeness between each evaluation level, thereby achieving quantitative determination of the evaluation level of the demand response effectiveness of the battery swap station.

8. A comprehensive evaluation system for the effect of battery swap stations participating in demand response, characterized in that: include: A system establishment module is used to establish a multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response based on the historical data information generated by the battery swap stations participating in demand response; A model updating module, used to establish a first variable-weighted matter-element extension model in combination with the multi-dimensional evaluation index system based on the effect of the battery swap station participating in the demand response, and to improve the first variable-weighted matter-element extension model based on deep learning to make up for missing values, so as to obtain a second variable-weighted matter-element extension model; An evaluation module is used to evaluate the multi-dimensional evaluation index system based on the effect of battery swap stations participating in demand response according to the second variable-weight matter-element extension model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images