A method and system for optimal scheduling of a combined heat and power system based on dynamic game

Abstract

The application discloses a kind of based on dynamic game's combined heat and power system optimization scheduling method and system, it is related to combined heat and power dispatching technical field, including obtaining combined heat and power system information, according to combined heat and power system information, obtains combined heat and power historical data, obtains user information and user basic data, with combined heat and power historical data as foundation, according to user basic data, user is classified, obtains user classification information.The application obtains the corresponding electricity characteristic day of each user by user basic data set, accurately analyzes the heat and power demand characteristics of user by electricity characteristic day, carries out data clustering to user by strategy characteristic vector, in-depth analyzes user characteristics and behavior mode, provides data basis for subsequent system scheduling, accurately evaluates the heat and power demand corresponding to each type of user by user classification information, ensures the accuracy and timeliness of combined heat and power system scheduling.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of combined heat and power scheduling, in particular to a combined heat and power system optimization scheduling method and system based on dynamic game. BACKGROUND

[0002] As an important carrier for realizing energy efficient utilization, combined heat and power systems are facing the key demand for transformation from traditional centralized to digital, intelligent and interactive. Combined heat and power systems improve energy utilization rate by simultaneously producing electricity and heat, and are the core link of building comprehensive energy systems. However, with the large-scale access of distributed energy, energy storage devices and multi-user terminals, the complexity of the system increases exponentially, and the diversity of user behavior and the asymmetry of information interaction become the main bottleneck restricting system optimization. The rapid development of digital technology provides a new path for the upgrading of combined heat and power systems. By collecting and analyzing real-time power and heat data, the operation of combined heat and power systems is optimized by means of dynamic game theory, and the intelligent and efficient level of energy systems is improved.

[0003] Currently, the optimization scheduling of combined heat and power systems cannot accurately analyze user data, cannot accurately evaluate user heat and power demand according to user data, and cannot timely and accurately schedule the heat and power system, reducing the stability and reliability of the heat and power system. In the prior art, all user data is often directly analyzed to evaluate user demand, but in actual process, the heat and power demand of different users often differs, and the presence of only one abnormal user can greatly affect the data analysis of the entire group, making it impossible to accurately evaluate user data. If each user is analyzed separately, not only is the data processing amount large, but also the data processing efficiency is low, reducing the scheduling efficiency of the combined heat and power system and affecting the timeliness and accuracy of the combined heat and power system scheduling. SUMMARY

[0004] To solve the above technical problems, a combined heat and power system optimization scheduling method and system based on dynamic game are provided. The present technical solution solves the problem of being unable to accurately analyze user data, being unable to accurately evaluate user heat and power demand according to user data, being unable to timely and accurately schedule the heat and power system, reducing the stability and reliability of the heat and power system, and the problem of being unable to accurately evaluate user data in the prior art, in which all user data is often directly analyzed to evaluate user demand. In actual process, the heat and power demand of different users often differs, and the presence of only one abnormal user can greatly affect the data analysis of the entire group. If each user is analyzed separately, not only is the data processing amount large, but also the data processing efficiency is low, reducing the scheduling efficiency of the combined heat and power system and affecting the timeliness and accuracy of the combined heat and power system scheduling.

[0005] To achieve the above object, the technical scheme adopted by the present application is:

[0006] A method for optimizing scheduling of a combined heat and power system based on dynamic game, comprising:

[0007] Obtaining combined heat and power system information, the combined heat and power system information including combined heat and power system function information and combined heat and power system performance parameter information;

[0008] According to the combined heat and power system information, obtaining combined heat and power historical data, the combined heat and power historical data including historical power supply data and historical heat supply data;

[0009] Obtaining user information and user basic data, the user basic data including historical power consumption data, historical heat consumption data and demand response data corresponding to each user;

[0010] Based on the combined heat and power historical data, classifying users according to the user basic data to obtain user classification information, the user classification information including main group user information and island user information;

[0011] Obtaining user real-time load data, the user real-time load data including user real-time power consumption load data and user real-time heat supply load data;

[0012] According to the user classification information, taking the sum of user real-time power consumption load corresponding to the main group users as the reference power supply load, and taking the sum of user real-time heat supply load corresponding to the main group users as the reference heat supply load;

[0013] Training an existing model according to the user basic data corresponding to the main group users to obtain a group demand prediction model;

[0014] Based on the reference power supply load and the reference heat supply load, obtaining reference power supply prediction load and reference heat supply prediction load based on the group demand prediction model;

[0015] According to the user basic data corresponding to the island users, obtaining power supply demand deviation coefficients and heat supply demand deviation coefficients corresponding to each island user, the power supply demand deviation coefficient representing the ratio of average daily power consumption of the island user to the maximum daily power consumption, and the heat supply demand deviation coefficient representing the ratio of average daily heat supply of the island user to the maximum daily heat supply;

[0016] Taking the sum of user real-time power consumption load corresponding to the island users as the characteristic power supply load, and taking the sum of user real-time heat supply load corresponding to the island users as the characteristic heat supply load;

[0017] The product of the characteristic power supply load and the power supply demand deviation coefficient is taken as a second power supply predicted load, and the product of the characteristic heat supply load and the heat supply demand deviation coefficient is taken as a second heat supply predicted load;

[0018] The reference power supply predicted load and the second power supply predicted load are taken as a total power supply demand load, and the reference heat supply predicted load and the second heat supply predicted load are taken as a total heat supply demand load;

[0019] The combined heat and power system is dispatched according to the total power supply demand load and the total heat supply demand load.

[0020] Preferably, the user is classified according to the user basic data based on the combined heat and power historical data, and user classification information is obtained, and specifically includes:

[0021] The user basic data corresponding to the same user is divided into the same data set according to the combined heat and power historical data and the user basic data, and the user basic data set is obtained;

[0022] The power consumption characteristic day corresponding to each user is obtained according to the user basic data set;

[0023] The average daily power consumption, the peak-valley power consumption ratio and the power consumption fluctuation coefficient in the power consumption characteristic day of the user are obtained according to the user basic data set, the peak-valley power consumption ratio is the ratio of the total peak power consumption to the total valley power consumption, and the power consumption fluctuation coefficient is the ratio of the difference between the maximum daily power consumption and the minimum daily power consumption to the average daily power consumption;

[0024] The average daily heat supply, the temperature regulation frequency and the heat loss coefficient in the power consumption characteristic day of the user are obtained according to the user basic data set and the power consumption characteristic day, the temperature regulation frequency is the number of daily temperature setting value changes of the user, and the heat loss coefficient is the ratio of the difference between the heat supply and the actual indoor heat absorption to the heat supply;

[0025] The response participation rate, the response intensity and the response delay time are obtained based on the power consumption characteristic day according to the user demand response data and the combined heat and power historical data, the response participation rate is the ratio of the actual response times to the response invitation times, the response intensity is the ratio of the average load reduction amount of each response to the reference load, and the response delay time represents the average time length from the response invitation to the start of response;

[0026] The user basic data is normalized with the average daily power consumption, the peak-valley power consumption ratio, the power consumption fluctuation coefficient, the average daily heat supply, the temperature regulation frequency, the heat loss coefficient, the response participation rate, the response intensity and the response delay time as the characteristic dimensions, and a strategy feature vector corresponding to each user is obtained;

[0027] The policy feature vectors corresponding to the same user are divided into the same data set, and policy feature vector data set information is obtained;

[0028] According to the policy feature vector data set information, a data clustering matching algorithm is obtained based on data clustering feature analysis;

[0029] Based on the data clustering matching algorithm, data clustering is performed on the policy feature vectors, and data clustering information is obtained;

[0030] Based on the data clustering information, the users are classified, and user classification information is obtained.

[0031] Preferably, the user basis data set is used to obtain the electricity consumption characteristic day corresponding to each user, specifically including:

[0032] According to the user basis data set, historical electricity consumption data in each user basis data set is obtained, including daily peak-valley period electricity consumption and daily total electricity consumption of the user;

[0033] According to the user daily peak-valley period electricity consumption, user daily peak-valley period information and electricity consumption information corresponding to each peak-valley period are obtained;

[0034] Based on the electricity consumption corresponding to any user peak period in the user daily peak-valley period, the ratio of the valley period electricity consumption to the electricity consumption corresponding to the user peak period in the user daily peak-valley period is taken as the user electricity consumption deviation coefficient;

[0035] The ratio of the minimum value of the user electricity consumption deviation coefficient corresponding to the user daily peak-valley period electricity consumption to the maximum value of the user electricity consumption deviation coefficient is taken as the user electricity consumption stable difference coefficient corresponding to the user daily peak-valley period;

[0036] According to the electricity consumption stable difference coefficient and the user basis data set, the electricity consumption characteristic coefficient corresponding to each user is obtained;

[0037] The electricity consumption characteristic coefficient is adjusted until the maximum value is reached, and the electricity consumption characteristic day corresponding to each user is obtained;

[0038] The electricity consumption characteristic coefficient is specifically:

[0039] ;

[0040] In the formula, is the electricity consumption characteristic coefficient, represents the maximum value of the electricity consumption stable difference coefficient in h days, represents the minimum value of the electricity consumption stable difference coefficient in h days, and h is the electricity consumption characteristic day.

[0041] Preferably, the strategy feature vector dataset information is used to obtain a data clustering matching algorithm based on data clustering feature analysis, specifically including:

[0042] According to the strategy feature vector dataset information, whether each feature dimension in the strategy feature vector dataset conforms to a normal distribution is determined based on a KS test method, and the feature dimension conforming to the normal distribution is taken as a reference feature dimension;

[0043] According to the reference feature dimension, a strategy feature vector corresponding to the reference feature dimension is taken as a reference feature vector, and a strategy feature vector that is not the reference feature vector is taken as a secondary feature vector;

[0044] According to the reference feature vector, any two reference feature vectors are taken as a reference feature group;

[0045] The sum of the Euclidean distances between the reference feature vector and all secondary feature vectors is taken as a feature divergence coefficient of the reference feature vector;

[0046] The reference feature vector corresponding to the larger value of the feature divergence coefficient in the reference feature group is taken as a first feature vector, and the reference feature vector corresponding to the smaller value of the feature divergence coefficient is taken as a second feature vector;

[0047] According to the reference feature group, a Pearson correlation coefficient between the two reference feature vectors in the reference feature group is obtained;

[0048] The reference feature vectors in the reference feature group are screened according to the Pearson correlation coefficient to obtain a calibration feature vector;

[0049] If the absolute value of the Pearson correlation coefficient is less than 0.3, the reference feature vector in the reference feature group is a non-redundant feature, and if the absolute value of the Pearson correlation coefficient is not less than 0.3, the reference feature vector in the reference feature group is a redundant feature, and the second feature vector in the reference feature group is removed. The ratio of the number of calibration feature vectors to the total number of strategy feature vectors is taken as a normal distribution coefficient;

[0050] According to the normal distribution coefficient, a data clustering matching algorithm is obtained;

[0051] If the normal distribution coefficient is greater than 0.8, the K-means algorithm is taken as the data clustering matching algorithm, and if the normal distribution coefficient is not greater than 0.8, the DBSCAN algorithm is taken as the data clustering matching algorithm.

[0052] Preferably, the strategy feature vector is subjected to data clustering based on the data clustering matching algorithm, specifically including:

[0053] According to the data clustering matching algorithm, corresponding data clustering parameters are obtained;

[0054] If the data clustering matching algorithm is the K-means algorithm, then the initial number of clusters is obtained based on the policy feature vector dataset information and the elbow method.

[0055] Based on the data clustering requirements of the K-means algorithm, K-means iteration parameters are set, including the maximum number of iterations, the cluster center convergence threshold, and the initial cluster center selection method. If the data clustering matching algorithm is the DBSCAN algorithm, the neighborhood radius is obtained based on the elbow method according to the information of the policy feature vector dataset, and the minimum number of samples is set. Based on the data clustering parameters, the stability of the data clustering matching algorithm is verified. Based on stratified sampling, 70% of the data samples are extracted from the policy feature vector dataset as data samples and the clustering is repeated 5 times. The adjusted Rand index of each clustering result and the original result is calculated.

[0056] Based on the adjusted Rand index, it is determined whether the data clustering matching algorithm meets the data clustering requirements. If the adjusted Rand index is greater than 0.8, the data clustering is considered stable; if the adjusted Rand index is not greater than 0.8, the data clustering is considered unstable, and the data clustering parameters are adjusted accordingly. Specifically, if the data clustering matching algorithm is a K-means algorithm, the number of iterations is increased or the initial center selection method is adjusted; if the data clustering matching algorithm is a K-means algorithm, the radius is decreased or the minimum number of samples is reduced.

[0057] Based on the data clustering matching algorithm and data clustering parameters, the policy feature vectors are clustered to obtain data clustering information, which includes data cluster information, the central policy feature vector information corresponding to each data cluster, and the number of users within the cluster.

[0058] Preferably, the step of classifying users based on data clustering information to obtain user classification information specifically includes:

[0059] Based on the data clustering information, obtain the central strategy feature vector information corresponding to each data cluster;

[0060] The Euclidean distance between the central policy feature vectors of any two data clusters is taken as the policy difference between the two data clusters.

[0061] Based on data clustering information and strategy dissimilarity, construct the dissimilarity matrix D:

[0062] ;

[0063] In the formula, QUOTE For the QUOTE The data cluster and the QUOTE a strategy difference degree of each data cluster; according to the difference matrix, an average value and a standard deviation of all elements in the difference matrix are obtained;

[0064] According to the average value and the standard deviation, a difference threshold is obtained;

[0065] According to the user base data set, a data interaction frequency corresponding to each data cluster is obtained, the data interaction frequency representing a number of times of consistent adjustment directions of the users in the cluster and other cluster users in the same period; according to the data interaction frequency corresponding to each data cluster, 1 / 3 of the average value of the data interaction frequency corresponding to the data cluster is taken as a data interaction threshold;

[0066] According to the difference threshold and the data interaction threshold, a strategy isolation index corresponding to each data cluster is obtained;

[0067] Based on a preset strategy isolation index threshold and the strategy isolation index corresponding to each data cluster, it is judged whether the data cluster is an isolated data cluster, and user classification information is obtained;

[0068] The difference threshold is specifically:

[0069] ;

[0070] In the formula, QUOTE is the difference threshold, is the average value of the difference matrix, is the standard deviation of the difference matrix;

[0071] The strategy isolation index is specifically:

[0072] ;

[0073] In the formula, is the strategy isolation index of the xth data cluster, is the maximum value of the strategy difference degree of the xth data cluster and other data clusters, represents the data interaction frequency of the xth data cluster, is the data interaction threshold, and is a weight coefficient, wherein .

[0074] Further, a dynamic game-based combined heat and power system optimization scheduling system is proposed, which is used to realize the optimization scheduling method as described above, and includes:

[0075] The main control module is used for obtaining corresponding data clustering parameters according to a data clustering matching algorithm, verifying the stability of the data clustering matching algorithm according to the data clustering parameters, performing data clustering on a strategy feature vector according to the data clustering matching algorithm and the data clustering parameters, obtaining data clustering information, classifying users on the basis of the data clustering information, obtaining user classification information, training an existing model according to user basic data corresponding to a main group of users, obtaining a group demand prediction model, obtaining a benchmark power supply prediction load and a benchmark heating prediction load on the basis of the group demand prediction model, taking the benchmark power supply prediction load and a second power supply prediction load as a total power supply demand load, taking the benchmark heating prediction load and a second heating prediction load as a total heating demand load, and dispatching a combined heat and power system according to the total power supply demand load and the total heating demand load.

[0076] The information acquisition module is used for acquiring combined heat and power system information, the combined heat and power system information including combined heat and power system function information and combined heat and power system performance parameter information, acquiring combined heat and power historical data according to the combined heat and power system information, the combined heat and power historical data including historical power supply data and historical heating data, acquiring user information and user basic data, the user basic data including historical power consumption data, historical heating data and demand response data of each user, and acquiring user real-time load data, the user real-time load data including user real-time power consumption load data and user real-time heating load data.

[0077] The evaluation module is used for dividing user basic data of a same user into a same data set according to the combined heat and power historical data and the user basic data, acquiring user basic data sets, acquiring power consumption characteristic days corresponding to each user according to the user basic data sets, judging whether each characteristic dimension in a strategy feature vector data set conforms to a normal distribution based on KS test method according to strategy feature vector data set information, taking a characteristic dimension conforming to the normal distribution as a benchmark characteristic dimension, and acquiring a data clustering matching algorithm based on data clustering characteristic analysis based on the strategy feature vector data set information.

[0078] The display module interacts with the main control module and is used for outputting and displaying user classification information, user real-time load data, a benchmark power supply prediction load, a benchmark heating prediction load, a second power supply prediction load, a second heating prediction load, a total power supply demand load and a total heating demand load.

[0079] Optionally, the main control module specifically includes:

[0080] The control unit is used for classifying users based on data clustering information, obtaining user classification information, training an existing model according to user basic data corresponding to a main group of users, obtaining a group demand prediction model, obtaining a benchmark power supply prediction load and a benchmark heating prediction load based on the benchmark power supply load and the benchmark heating load, obtaining a benchmark power supply prediction load and a second power supply prediction load as a total power supply demand load, obtaining a benchmark heating prediction load and a second heating prediction load as a total heating demand load, and dispatching a combined heat and power system according to the total power supply demand load and the total heating demand load.

[0081] The information receiving unit is used for receiving data and transmitting the data to the data processing unit.

[0082] The data processing unit is used for obtaining corresponding data clustering parameters according to the data clustering matching algorithm, verifying the stability of the data clustering matching algorithm according to the data clustering parameters, performing data clustering on a strategy feature vector according to the data clustering matching algorithm and the data clustering parameters, and obtaining data clustering information.

[0083] Optionally, the information obtaining module specifically comprises:

[0084] The first obtaining unit is used for obtaining combined heat and power system information, the combined heat and power system information including combined heat and power system function information and combined heat and power system performance parameter information, and obtaining combined heat and power historical data including historical power supply data and historical heating data according to the combined heat and power system information.

[0085] The second obtaining unit is used for obtaining user information and user basic data, the user basic data including historical power consumption data, historical heating data and demand response data of each user, and obtaining real-time load data including real-time power consumption load data and real-time heating load data of the user.

[0086] Optionally, the evaluation module specifically comprises:

[0087] The first evaluation unit is used for dividing user basic data corresponding to a same user into a same data set according to the combined heat and power historical data and the user basic data, obtaining user basic data sets, and obtaining power consumption characteristic days corresponding to each user according to the user basic data sets.

[0088] A second evaluation unit judges whether each feature dimension in the strategy feature vector dataset conforms to a normal distribution based on a KS test method according to strategy feature vector dataset information, takes the feature dimension conforming to the normal distribution as a reference feature dimension, and obtains a data clustering matching algorithm based on data clustering feature analysis based on the strategy feature vector dataset information.

[0089] Compared with the prior art, the present application has the beneficial effects that:

[0090] The present application proposes a method and system for optimizing scheduling of a combined heat and power system based on dynamic game, obtains the corresponding power consumption characteristic days of each user through user basic dataset, accurately analyzes the heat and power demand characteristics of the user through the power consumption characteristic days, performs data clustering on the user through a strategy feature vector, deeply analyzes the characteristics and behavior patterns of the user, and provides a data basis for subsequent system scheduling, accurately evaluates the corresponding heat and power demand of each type of user through user classification information, and ensures the accuracy and timeliness of the scheduling of the combined heat and power system. BRIEF DESCRIPTION OF DRAWINGS

[0091] Figure 1 A flowchart of the method for optimizing scheduling of a combined heat and power system based on dynamic game is proposed in the present application.

[0092] Figure 2 A flowchart of the method for obtaining user classification information is proposed in the present application.

[0093] Figure 3 A flowchart of the method for obtaining power consumption characteristic days is proposed in the present application.

[0094] Figure 4 A flowchart of the method for obtaining a data clustering matching algorithm is proposed in the present application.

[0095] Figure 5 A block diagram of the system structure of the system for optimizing scheduling of a combined heat and power system based on dynamic game is proposed in the present application. DETAILED DESCRIPTION

[0096] The following description is used to disclose the present application so that those skilled in the art can implement the present application. The preferred embodiments in the following description are only used as examples, and other obvious variants can be thought of by those skilled in the art.

[0097] REFERENCE Figure 1 - Figure 4 As shown in the figure, the method for optimizing scheduling of a combined heat and power system based on dynamic game in the embodiment of the present application comprises:

[0098] Obtaining combined heat and power system information, the combined heat and power system information comprising combined heat and power system function information and combined heat and power system performance parameter information;

[0099] According to the cogeneration system information, obtain cogeneration historical data, the cogeneration historical data including historical power supply data and historical heat supply data;

[0100] Obtain user information and user basic data, the user basic data including historical power consumption data, user historical heat consumption data and user demand response data corresponding to each user;

[0101] On the basis of the cogeneration historical data, classify users according to the user basic data, and obtain user classification information, the user classification information including main group user information and island user information;

[0102] Specifically, on the basis of the cogeneration historical data, classify users according to the user basic data, and obtain user classification information, specifically including:

[0103] According to the cogeneration historical data and the user basic data, divide the user basic data corresponding to the same user into the same data set, and obtain the user basic data set;

[0104] According to the user basic data set, obtain the power consumption characteristic day corresponding to each user;

[0105] According to the user basic data set, obtain the average daily power consumption, the peak-valley power consumption ratio and the power consumption fluctuation coefficient within the power consumption characteristic day of the user, the peak-valley power consumption ratio being the ratio of the total peak segment power consumption to the total valley segment power consumption, and the power consumption fluctuation coefficient being the ratio of the difference between the maximum daily power consumption and the minimum daily power consumption to the average daily power consumption;

[0106] According to the user basic data set and the power consumption characteristic day, obtain the average daily heat supply, the temperature adjustment frequency and the heat loss coefficient within the power consumption characteristic day of the user, the temperature adjustment frequency being the number of daily temperature setting value changes of the user, and the heat loss coefficient being the ratio of the difference between the heat supply and the actual indoor heat absorption to the heat supply;

[0107] According to the user demand response data and the cogeneration historical data, and on the basis of the power consumption characteristic day, obtain the response participation rate, the response intensity and the response delay time, the response participation rate being the ratio of the actual response times to the response invitation times, the response intensity being the ratio of the average load reduction amount of each response to the reference load, and the response delay time representing the average time length from the issuance of the response invitation to the start of the response;

[0108] Normalize the user basic data with the average daily power consumption, the peak-valley power consumption ratio, the power consumption fluctuation coefficient, the average daily heat supply, the temperature adjustment frequency, the heat loss coefficient, the response participation rate, the response intensity and the response delay time as characteristic dimensions, and obtain the strategy feature vector corresponding to each user;

[0109] The policy feature vectors corresponding to the same user are divided into the same data set, and policy feature vector data set information is obtained;

[0110] According to the policy feature vector data set information, a data clustering matching algorithm is obtained based on data clustering feature analysis;

[0111] Based on the data clustering matching algorithm, data clustering is performed on the policy feature vectors to obtain data clustering information;

[0112] Based on the data clustering information, the users are classified to obtain user classification information.

[0113] In this scheme, through multi-dimensional feature mining, accurate clustering and dynamic game adaptation, a "precise portrait-strategy coordination" foundation for the optimal dispatch of the combined heat and power system is constructed on the user side. Through multi-dimensional fusion, the energy characteristic differences of each user type are clearly distinguishable (for example, a user cluster is "high electricity fluctuation + short response delay", which is suitable for undertaking emergency peak shaving tasks), solving the pain points of traditional classification "fuzzy behavior description". Through normalization processing, the dimensional differences of feature quantities are eliminated (for example, the units of electricity consumption and temperature regulation frequency are different), and then similar feature vectors are aggregated using clustering matching algorithms (such as K-means and DBSCAN), and user classification is output, providing differentiated targeting for dispatch strategies and avoiding resource waste caused by "one-size-fits-all" dispatch (such as excessive subsidies for high-response users and ineffective incentives for low-response users). Through multi-dimensional feature mining and data clustering, accurate quantification and classification of user-side energy behavior are achieved, providing a clear mapping of "user type-strategy response" for the optimal dispatch of the combined heat and power system.

[0114] Specifically, according to the user basic data set, the electricity consumption feature days corresponding to each user are obtained, specifically including:

[0115] According to the user basic data set, the historical electricity consumption data in the user basic data set is obtained, and the historical electricity consumption data includes daily peak-valley period electricity consumption and daily total electricity consumption of the user;

[0116] According to the user daily peak-valley period electricity consumption, the user daily peak-valley period information and the electricity consumption information corresponding to each peak-valley period are obtained;

[0117] Based on the electricity consumption corresponding to any user peak period in the user daily peak-valley period, the ratio of the valley period electricity consumption to the electricity consumption corresponding to the user peak period in the user daily peak-valley period is taken as the user electricity consumption deviation coefficient;

[0118] The ratio of the minimum value of the user electricity consumption deviation coefficient corresponding to the user daily peak-valley period electricity consumption to the maximum value of the user electricity consumption deviation coefficient is taken as the user electricity consumption stability difference coefficient corresponding to the user daily peak-valley period;

[0119] According to the electricity consumption stability difference coefficient and the user basic data set, the electricity consumption characteristic coefficient corresponding to each user is obtained;

[0120] The electricity consumption characteristic coefficient is adjusted until the maximum value is reached, and the electricity consumption characteristic day corresponding to each user is obtained;

[0121] The electricity consumption characteristic coefficient is specifically:

[0122] ;

[0123] In the formula, is the electricity consumption characteristic coefficient, represents the maximum value of the electricity consumption stability difference coefficient in h days, represents the minimum value of the electricity consumption stability difference coefficient in h days, and h is the electricity consumption characteristic day.

[0124] In the scheme, the user electricity consumption stability and the characteristic day are accurately quantified, key user side data support is provided for cogeneration system optimization scheduling, the electricity consumption deviation coefficient and the stability difference coefficient are calculated from the user peak valley period electricity consumption data, and the electricity consumption characteristic coefficient formula is constructed. Multi-dimensional decomposition of user electricity consumption behavior, accurate identification of electricity consumption stability / fluctuation characteristics (such as large peak valley difference of factory users, characteristic coefficient reflecting fluctuation law), make up for the problem of insufficient description of user electricity consumption characteristics in traditional classification, let the scheduling strategy adapt to the real electricity consumption mode of users, and use the electricity consumption characteristic day as a key index of user characteristics to provide core basis for subsequent clustering. Different characteristic days of users (such as long-term stable electricity consumption of residents and short-term large fluctuation of businesses), in dynamic game scheduling, corresponding to different response cost and benefit, accurate classification can optimize the strategy (such as designing flexible electricity price for users with short characteristic days and large fluctuations), improve the actual adaptability of game equilibrium solution, reduce supply-demand mismatch, and the electricity consumption law of users identified based on characteristic days can predict the load change of different users in extreme weather and peak valley period. When scheduling, reserve standby capacity in advance for high fluctuation users reflected by the characteristic day, optimize energy distribution for stable users, improve the ability of the system to cope with uncertainty, enhance the flexibility and reliability of the cogeneration system, and help achieve dynamic balance between supply and demand.

[0125] Specifically, according to the strategy characteristic vector data set information, based on data clustering feature analysis, a data clustering matching algorithm is obtained, which specifically includes:

[0126] According to the strategy characteristic vector data set information, based on the KS test method, it is judged whether each characteristic dimension in the strategy characteristic vector data set conforms to the normal distribution, and the characteristic dimension conforming to the normal distribution is taken as the reference characteristic dimension;

[0127] According to the benchmark feature dimension, a strategy feature vector corresponding to the benchmark feature dimension is taken as a benchmark feature vector, and a strategy feature vector other than the benchmark feature vector is taken as a secondary feature vector;

[0128] According to the benchmark feature vectors, any two benchmark feature vectors are taken as a benchmark feature group;

[0129] A sum of Euclidean distances between the benchmark feature vectors and all secondary feature vectors is taken as a feature divergence coefficient of the benchmark feature vector;

[0130] A benchmark feature vector corresponding to a larger value of the feature divergence coefficient in the benchmark feature group is taken as a first feature vector, and a benchmark feature vector corresponding to a smaller value of the feature divergence coefficient is taken as a second feature vector;

[0131] According to the benchmark feature group, a Pearson correlation coefficient between two benchmark feature vectors in the benchmark feature group is obtained;

[0132] According to the Pearson correlation coefficient, a benchmark feature vector in the benchmark feature group is screened to obtain a calibration feature vector;

[0133] If the absolute value of the Pearson correlation coefficient is less than 0.3, the benchmark feature vector in the benchmark feature group is a non-redundant feature, and if the absolute value of the Pearson correlation coefficient is not less than 0.3, the benchmark feature vector in the benchmark feature group is a redundant feature, and the second feature vector in the benchmark feature group is removed; a ratio of the number of calibration feature vectors to the total number of strategy feature vectors is taken as a normal distribution coefficient;

[0134] According to the normal distribution coefficient, a data clustering matching algorithm is obtained;

[0135] If the normal distribution coefficient is greater than 0.8, the K-means algorithm is taken as the data clustering matching algorithm, and if the normal distribution coefficient is not greater than 0.8, the DBSCAN algorithm is taken as the data clustering matching algorithm.

[0136] In the scheme, a scientific clustering method is provided for user classification through feature screening and algorithm adaptation. The benchmark feature dimension of normal distribution is identified based on KS test, and the redundant features (e.g., the strong correlation between "average daily electricity consumption" and "peak-valley electricity consumption ratio") are removed in combination with Pearson correlation coefficient (threshold value 0.3), and the non-redundant calibration feature vector is reserved. This screening reduces the interference of noise features on clustering (e.g., removing the strong correlation features of heat loss coefficient and temperature regulation frequency), makes the strategy feature vector more focused on the core differences (e.g., demand response strength and electricity fluctuation coefficient), improves the accuracy of subsequent clustering, and lays a high-quality data foundation for user classification. Based on the normal distribution coefficient (calibration feature vector proportion), the adaptive algorithm is automatically selected: when the normal distribution feature proportion is more than 80%, K-means is used (suitable for spherical clusters and uniformly distributed data), otherwise DBSCAN is used (good at non-convex, uneven density clustering). For example, the electricity consumption features of residential users are normally distributed (suitable for K-means), while the complex load features of industrial parks are more suitable for DBSCAN. This "data-driven" algorithm selection avoids the classification bias caused by fixed algorithms, making the user clustering results more consistent with the actual energy consumption patterns. The user classification output by the optimized clustering algorithm can more accurately reflect the demand response potential and energy consumption characteristics of different users.

[0137] Specifically, based on the data clustering matching algorithm, the strategy feature vector is data clustered, specifically including:

[0138] According to the data clustering matching algorithm, the corresponding data clustering parameters are obtained;

[0139] If the data clustering matching algorithm is a K-means algorithm, the initial cluster number is obtained based on the elbow method according to the strategy feature vector dataset information;

[0140] Based on the K-means algorithm data clustering requirement, the K-means iteration parameters are set, including the maximum iteration number, the cluster center convergence threshold and the initial cluster center selection method; if the data clustering matching algorithm is a DBSCAN algorithm, the field radius is obtained based on the elbow method according to the strategy feature vector dataset information, and the minimum sample number is set; according to the data clustering parameters, the stability of the data clustering matching algorithm is verified, 70% of the strategy feature vector dataset is extracted based on stratified sampling as data samples, and the adjusted Rand index of each clustering result and the original result is calculated by repeating clustering 5 times;

[0141] According to the adjusted Rand index, it is judged whether the data clustering matching algorithm meets the data clustering demand, if the adjusted Rand index is greater than 0.8, it is determined that the data clustering is stable, if the adjusted Rand index is not greater than 0.8, it is determined that the data clustering is unstable, and the data clustering parameters are adjusted, wherein, if the data clustering matching algorithm is K-means algorithm, the number of iterations is increased or the initial center selection method is adjusted, if the data clustering matching algorithm is K-means algorithm, the radius is reduced or the minimum sample number is reduced;

[0142] According to the data clustering matching algorithm and the data clustering parameters, the strategy feature vector is data clustered to obtain data clustering information, the data clustering information includes data cluster information, center strategy feature vector information corresponding to each data cluster and cluster user number information.

[0143] In the scheme, through accurate parameter configuration, stability verification and clustering optimization, reliable clustering results are provided for user grouping, and customized parameter configuration is made according to the characteristic differences of K-means and DBSCAN algorithms, so that the algorithm adapts to the distribution characteristics of the strategy feature vector (such as the dense or sparse distribution of user electricity / heat features). For example, for the resident user group in the electricity feature set, the initial cluster number setting of K-means can accurately capture the subdivision types such as "stable electricity" and "peak-valley fluctuation"; for the industrial park users with scattered electricity features, the field radius adjustment of DBSCAN can avoid misclassification of high / low load users into the same cluster. This parameter adaptation solves the clustering deviation caused by "one-size-fits-all" parameters, makes the data cluster more consistent with the actual energy consumption law of users, verifies the stability by hierarchical sampling and calculating the adjusted Rand index (ARI), and dynamically adjusts the parameters to form a closed loop of "parameter setting→ verification→ optimization". This mechanism effectively avoids clustering distortion caused by accidental factors (such as sample fluctuation), and ensures the consistency of the clustering results. Stable clustering results are the basis for formulating long-term scheduling strategies - avoiding repeated adjustment of strategies due to user grouping fluctuations, reducing scheduling costs, and through parameter adaptation, stability verification and result optimization, the strategy feature vector is converted into stable, accurate and interpretable user grouping information, providing a clear mapping of "user group characteristics→ scheduling strategy" for dynamic game scheduling.

[0144] It should be noted that in the embodiment, the maximum number of iterations in the K-means iteration parameter is 100, the clustering center convergence threshold is 0.001, that is, the iteration is stopped when the center distance of two iterations is less than 0.001, and the initial clustering center selection method adopts the k-means++ algorithm to avoid random deviation

[0145] Specifically, based on the data clustering information, the user is classified to obtain user classification information, specifically including:

[0146] According to the data clustering information, center strategy feature vector information corresponding to each data cluster is obtained;

[0147] The Euclidean distance of the center strategy feature vectors corresponding to any two data clusters is taken as the strategy difference degree of the two data clusters;

[0148] According to the data clustering information and the strategy difference degree, a difference matrix D is constructed:

[0149] ;

[0150] In the formula, QUOTE is the strategy difference degree of the first QUOTE data cluster and the first QUOTE data cluster; according to the difference matrix, the mean and the standard deviation of all elements in the difference matrix are obtained;

[0151] According to the mean and the standard deviation, a difference threshold is obtained;

[0152] According to the user basic data set, data interaction frequency corresponding to each data cluster is obtained, and the data interaction frequency represents the number of times that the users in the cluster and the users in other clusters have consistent load adjustment directions in the same period; according to the data interaction frequency corresponding to each data cluster, 1 / 3 of the average value of the data interaction frequency corresponding to the data cluster is taken as a data interaction threshold;

[0153] According to the difference threshold and the data interaction threshold, a strategy isolation index corresponding to each data cluster is obtained;

[0154] Based on the preset strategy isolation index threshold and the strategy isolation index corresponding to each data cluster, it is judged whether the data cluster is an isolated data cluster, and user classification information is obtained;

[0155] The difference threshold is specifically:

[0156] ;

[0157] In the formula, is the difference threshold, is the mean of the difference matrix, is the standard deviation of the difference matrix;

[0158] The strategy isolation index is specifically:

[0159] ;

[0160] In the formula, is the strategy isolation index of the first x data cluster, a maximum strategy difference value of the xth data cluster and other data clusters, a data interaction frequency of the xth data cluster, a data interaction threshold value, a weight coefficient, wherein .

[0161] In the scheme, by constructing a quantitative model of strategy difference and interaction, the "island effect" of user groups is accurately identified, key support is provided for cogeneration scheduling, the Euclidean distance of the strategy feature vector of the data cluster center is calculated, and a difference matrix is constructed. The difference threshold value is determined by the mean and standard deviation, the strategy difference of different user groups (such as the difference between "peak-valley power consumption type" and "stable power consumption type" groups) is quantified, the user group boundary is clearly divided, the relationship between different groups is more clear, and scheduling inefficiency caused by confusion is avoided. The data interaction frequency (intra-cluster and other cluster user load adjustment consistency) is introduced, and the strategy isolation index is calculated in combination with the difference threshold value. The "island data cluster" (such as a user group with large strategy difference and less interaction) is identified, which provides a basis for subsequent cogeneration system scheduling and improves the scheduling efficiency and accuracy.

[0162] It can be understood that in the scheduling of the cogeneration system, the system is often scheduled according to the load demand of the users. However, in the scheduling process, if the entire user group is directly taken as the basis for scheduling the system, the scheduling result obtained is often an equilibrium result. However, in the actual process, only a few abnormal users in the similar behavior user group will cause a great change in the scheduling result. If each user is analyzed separately, not only the data processing amount is large, but also there is a time delay, which cannot ensure the timeliness of the cogeneration system.

[0163] It should be noted that in the embodiment, the strategy isolation index values of all clusters are sorted, the top 20% quantile value is taken as the strategy isolation index threshold value, the candidate island clusters with a strategy isolation index exceeding the threshold value are screened out, and the information interaction records of the users in the clusters (such as whether participating in the strategy discussion of the public information platform) are further checked. If more than 90% of the users have no cross-cluster information interaction, the potential island cluster is marked. The potential island cluster that simultaneously satisfies "there are at least three other clusters with a strategy difference exceeding the difference threshold value" and "the interaction frequency is lower than the data interaction threshold value" is determined as the island user group in combination with the difference and interaction between the clusters.

[0164] Obtaining real-time load data of users, the real-time load data of users including real-time power load data of users and real-time heating load data of users;

[0165] According to the user classification information, the sum of the real-time power load of the users corresponding to the main group of users is taken as the reference power load, and the sum of the real-time heating load of the users corresponding to the main group of users is taken as the reference heating load;

[0166] According to the user basic data corresponding to the main group user, the existing model is trained to obtain a group demand prediction model;

[0167] Based on the benchmark power supply load and the benchmark heating load, the benchmark power supply prediction load and the benchmark heating prediction load are obtained based on the group demand prediction model;

[0168] According to the user basic data corresponding to the island user, the power supply demand deviation coefficient and the heating demand deviation coefficient corresponding to each island user are obtained, the power supply demand deviation coefficient represents the ratio of the average daily power consumption of the island user to the maximum daily power consumption, and the heating demand deviation coefficient represents the ratio of the average daily heating amount of the island user to the maximum daily heating amount;

[0169] The sum of the user real-time power consumption load corresponding to the island user is taken as the characteristic power supply load, and the sum of the user real-time heating load corresponding to the island user is taken as the characteristic heating load;

[0170] The product of the characteristic power supply load and the power supply demand deviation coefficient is taken as the second power supply prediction load, and the product of the characteristic heating load and the heating demand deviation coefficient is taken as the second heating prediction load;

[0171] The benchmark power supply prediction load and the second power supply prediction load are taken as the total power supply demand load, and the benchmark heating prediction load and the second heating prediction load are taken as the total heating demand load;

[0172] According to the total power supply demand load and the total heating demand load, the combined heat and power system is dispatched.

[0173] It should be noted that based on the neural network model, the real-time demand of the user is predicted through the historical data, which is a common technical means known to those skilled in the art, so in this embodiment, it is not further expanded, and optionally, according to the user classification information, the behavior characteristic information corresponding to the main group user and the island user is obtained, and based on the existing dynamic game model, the combined heat and power system scheduling strategy is formulated.

[0174] Referring to Figure 5 Further, in combination with the above-mentioned one kind of combined heat and power system optimization scheduling method based on dynamic game, a combined heat and power system optimization scheduling system based on dynamic game is proposed, which comprises:

[0175] The main control module is used for obtaining corresponding data clustering parameters according to a data clustering matching algorithm, verifying the stability of the data clustering matching algorithm according to the data clustering parameters, performing data clustering on a strategy feature vector according to the data clustering matching algorithm and the data clustering parameters, obtaining data clustering information, classifying users on the basis of the data clustering information, obtaining user classification information, training an existing model according to user basic data corresponding to a main group of users, obtaining a group demand prediction model, obtaining a benchmark power supply prediction load and a benchmark heating prediction load on the basis of the group demand prediction model, taking the benchmark power supply prediction load and a second power supply prediction load as a total power supply demand load, taking the benchmark heating prediction load and a second heating prediction load as a total heating demand load, and dispatching a combined heat and power system according to the total power supply demand load and the total heating demand load.

[0176] The information acquisition module is used for acquiring combined heat and power system information, the combined heat and power system information including combined heat and power system function information and combined heat and power system performance parameter information, acquiring combined heat and power historical data according to the combined heat and power system information, the combined heat and power historical data including historical power supply data and historical heating data, acquiring user information and user basic data, the user basic data including historical power consumption data, historical heating data and demand response data of each user, and acquiring user real-time load data, the user real-time load data including user real-time power consumption load data and user real-time heating load data.

[0177] The evaluation module is used for dividing user basic data of a same user into a same data set according to the combined heat and power historical data and the user basic data, acquiring user basic data sets, acquiring power consumption characteristic days of each user according to the user basic data sets, judging whether each characteristic dimension in the strategy feature vector data set conforms to a normal distribution based on the KS test method according to the strategy feature vector data set information, taking a characteristic dimension conforming to the normal distribution as a benchmark characteristic dimension, and acquiring the data clustering matching algorithm based on data clustering feature analysis based on the strategy feature vector data set information.

[0178] The display module interacts with the main control module and is used for outputting and displaying user classification information, user real-time load data, a benchmark power supply prediction load, a benchmark heating prediction load, a second power supply prediction load, a second heating prediction load, a total power supply demand load and a total heating demand load.

[0179] The main control module specifically includes:

[0180] The control unit is used for classifying users based on data clustering information, obtaining user classification information, training an existing model according to user basic data corresponding to a main group of users, obtaining a group demand prediction model, obtaining a benchmark power supply prediction load and a benchmark heating prediction load based on the benchmark power supply load and the benchmark heating load, obtaining a benchmark power supply prediction load and a second power supply prediction load as a total power supply demand load, obtaining a benchmark heating prediction load and a second heating prediction load as a total heating demand load, and dispatching a combined heat and power system according to the total power supply demand load and the total heating demand load.

[0181] The information receiving unit is used for receiving data and transmitting the data to the data processing unit.

[0182] The data processing unit is used for obtaining corresponding data clustering parameters according to the data clustering matching algorithm, verifying the stability of the data clustering matching algorithm according to the data clustering parameters, performing data clustering on a strategy feature vector according to the data clustering matching algorithm and the data clustering parameters, and obtaining data clustering information.

[0183] The information acquisition module specifically includes:

[0184] The first acquisition unit is used for obtaining combined heat and power system information, the combined heat and power system information including combined heat and power system function information and combined heat and power system performance parameter information, and obtaining combined heat and power historical data including historical power supply data and historical heating data according to the combined heat and power system information.

[0185] The second acquisition unit is used for obtaining user information and user basic data, the user basic data including historical power consumption data, historical heating data and demand response data of each user, and obtaining real-time load data including real-time power consumption load data and real-time heating load data of the user.

[0186] The evaluation module specifically includes:

[0187] The first evaluation unit is used for dividing user basic data corresponding to the same user into the same data set according to the combined heat and power historical data and the user basic data, obtaining user basic data sets, and obtaining power consumption characteristic days corresponding to each user according to the user basic data sets.

[0188] A second evaluation unit judges whether each feature dimension in the strategy feature vector dataset conforms to a normal distribution based on a KS test method according to strategy feature vector dataset information, takes the feature dimension conforming to the normal distribution as a reference feature dimension, and obtains a data clustering matching algorithm based on data clustering feature analysis based on the strategy feature vector dataset information.

[0189] In summary, the application has the advantages that: the user basic dataset is used to obtain the corresponding power consumption feature day of each user, the power consumption feature day is used to accurately analyze the thermal power demand characteristics of the user, the strategy feature vector is used to perform data clustering on the user, the characteristics and behavior patterns of the user are deeply analyzed, a data basis is provided for subsequent system scheduling, the classification information of the user is used to accurately evaluate the corresponding thermal power demand of each type of user, and the accuracy and timeliness of the combined heat and power system scheduling are ensured.

[0190] The basic principle, main features and advantages of the application are shown and described above. It should be understood by those skilled in the art that the application is not limited by the above examples, and the above examples and descriptions in the specification are only the principles of the application. Without departing from the spirit and scope of the application, various changes and improvements can be made to the application, and these changes and improvements all fall within the scope of the claimed application. The scope of protection claimed by the application is defined by the appended claims and their equivalents.

Claims

1. A method for optimal scheduling of a combined heat and power system based on dynamic game, characterized in that, The method comprises the following steps: acquiring combined heat and power system information, wherein the combined heat and power system information comprises combined heat and power system function information and combined heat and power system performance parameter information; acquiring combined heat and power historical data according to the combined heat and power system information, wherein the combined heat and power historical data comprises historical power supply data and historical heat supply data; acquiring user information and user basic data, wherein the user basic data comprises historical power consumption data, historical heat consumption data and demand response data of each user; classifying users according to the user basic data based on the combined heat and power historical data to acquire user classification information, wherein the user classification information comprises main group user information and island user information; acquiring user real-time load data, wherein the user real-time load data comprises user real-time power consumption load data and user real-time heat supply load data; taking the sum of user real-time power consumption loads of the main group users as a reference power supply load and taking the sum of user real-time heat supply loads of the main group users as a reference heat supply load according to the user classification information; training an existing model according to the user basic data of the main group users to acquire a group demand prediction model; acquiring reference power supply prediction load and reference heat supply prediction load based on the group demand prediction model based on the reference power supply load and the reference heat supply load; acquiring power supply demand deviation coefficients and heat supply demand deviation coefficients of each island user according to the user basic data of the island users, wherein the power supply demand deviation coefficient represents a ratio of an average daily power consumption of the island user to a maximum daily power consumption, and the heat supply demand deviation coefficient represents a ratio of an average daily heat supply of the island user to a maximum daily heat supply; taking the sum of user real-time power consumption loads of the island users as a characteristic power supply load and taking the sum of user real-time heat supply loads of the island users as a characteristic heat supply load; taking a product of the characteristic power supply load and the power supply demand deviation coefficient as a second power supply prediction load and taking a product of the characteristic heat supply load and the heat supply demand deviation coefficient as a second heat supply prediction load; taking the reference power supply prediction load and the second power supply prediction load as a total power supply demand load and taking the reference heat supply prediction load and the second heat supply prediction load as a total heat supply demand load; scheduling the combined heat and power system according to the total power supply demand load and the total heat supply demand load.

2. The method of claim 1, wherein, The method further comprises the following steps: dividing user basic data corresponding to the same user into the same data set according to the combined heat and power historical data and the user basic data to acquire user basic data sets; acquiring power consumption characteristic days of each user according to the user basic data sets; acquiring an average daily power consumption, a peak-valley power consumption ratio and a power consumption fluctuation coefficient within the power consumption characteristic days of the user according to the user basic data sets, wherein the peak-valley power consumption ratio is a ratio of a total peak power consumption to a total valley power consumption, and the power consumption fluctuation coefficient is a ratio of a maximum daily power consumption to a minimum daily power consumption to the average daily power consumption. According to the user basic data set and the electricity characteristic day, the average daily heat supply, the temperature regulation frequency and the heat loss coefficient in the electricity characteristic day of the user are obtained, the temperature regulation frequency is the number of daily temperature setting value changes of the user, and the heat loss coefficient is the ratio of the difference between the heat supply and the actual indoor heat absorption to the heat supply; According to the user demand response data and the combined heat and power generation historical data, the response participation rate, the response intensity and the response delay time are obtained based on the electricity characteristic day, the response participation rate is the ratio of the actual response times to the response invitation times, the response intensity is the ratio of the average load reduction amount of each response to the reference load, and the response delay time represents the average time length from the response invitation to the start of the response; The average daily electricity consumption, the peak-valley electricity consumption ratio, the electricity fluctuation coefficient, the average daily heat supply, the temperature regulation frequency, the heat loss coefficient, the response participation rate, the response intensity and the response delay time are taken as the characteristic dimensions for the normalization processing of the user basic data, and the corresponding strategy feature vector of each user is obtained; The strategy feature vectors corresponding to the same user are divided into the same data set, and the strategy feature vector data set information is obtained; According to the strategy feature vector data set information, the data clustering matching algorithm is obtained based on the data clustering feature analysis; Based on the data clustering matching algorithm, the data clustering of the strategy feature vector is performed, and the data clustering information is obtained; Based on the data clustering information, the users are classified, and the user classification information is obtained.

3. The method of claim 2, wherein, According to the user basic data set, the electricity characteristic day corresponding to each user is obtained, specifically including: According to the user basic data set, the historical electricity consumption data in each user basic data set is obtained, and the historical electricity consumption data includes the daily peak-valley period electricity consumption and the daily total electricity consumption of the user; According to the daily peak-valley period electricity consumption of the user, the daily peak-valley period information and the electricity consumption information corresponding to each peak-valley period are obtained; Based on the electricity consumption corresponding to any user peak period in the daily peak-valley period of the user, the ratio of the valley period electricity consumption to the electricity consumption corresponding to the user peak period in the daily peak-valley period of the user is taken as the user electricity deviation coefficient; The ratio of the minimum value of the user electricity deviation coefficient corresponding to the daily peak-valley period electricity consumption of the user to the maximum value of the user electricity deviation coefficient is taken as the electricity stable difference coefficient corresponding to the daily user; According to the electricity stable difference coefficient and the user basic data set, the electricity characteristic coefficient corresponding to each user is obtained; The electricity characteristic coefficient is adjusted until the maximum value is reached, and the electricity characteristic day corresponding to each user is obtained; The electricity characteristic coefficient is adjusted until the maximum value is reached, and the electricity characteristic day corresponding to each user is obtained; In the formula, is the electricity use characteristic coefficient represents the maximum value of the electricity use stability difference coefficient within h days, represents the minimum value of the electricity use stability difference coefficient within h days, and h is the electricity use characteristic day number.

4. The method of claim 3, wherein, According to the strategy feature vector data set information, the data clustering matching algorithm is obtained based on the data clustering feature analysis, specifically including: According to the strategy feature vector data set information, whether each characteristic dimension in the strategy feature vector data set conforms to the normal distribution is judged based on the KS test method, and the characteristic dimension conforming to the normal distribution is taken as the reference characteristic dimension; According to the reference characteristic dimension, the strategy feature vector corresponding to the reference characteristic dimension is taken as the reference feature vector, and the strategy feature vector that is not the reference feature vector is taken as the secondary feature vector; According to the benchmark feature vectors, taking any two benchmark feature vectors as a benchmark feature group; Taking the sum of the Euclidean distances between the benchmark feature vector and all secondary feature vectors as the feature divergence coefficient of the benchmark feature vector; Taking the benchmark feature vector corresponding to the larger value of the feature divergence coefficient in the benchmark feature group as the first feature vector, and taking the benchmark feature vector corresponding to the smaller value of the feature divergence coefficient as the second feature vector; According to the benchmark feature group, the Pearson correlation coefficient between the two benchmark feature vectors in the benchmark feature group is obtained; According to the Pearson correlation coefficient, the benchmark feature vectors in the benchmark feature group are screened to obtain a calibration feature vector; If the absolute value of the Pearson correlation coefficient is less than 0.3, the benchmark feature vector in the benchmark feature group is a non-redundant feature, and if the absolute value of the Pearson correlation coefficient is not less than 0.3, the benchmark feature vector in the benchmark feature group is a redundant feature, and the second feature vector in the benchmark feature group is removed; Taking the ratio of the number of calibration feature vectors to the total number of strategy feature vectors as a normal distribution coefficient; According to the normal distribution coefficient, a data clustering matching algorithm is obtained; If the normal distribution coefficient is greater than 0.8, the K-means algorithm is taken as the data clustering matching algorithm, and if the normal distribution coefficient is not greater than 0.8, the DBSCAN algorithm is taken as the data clustering matching algorithm.

5. The method of claim 4, wherein, The data clustering matching algorithm is used to perform data clustering on the strategy feature vectors, specifically including: According to the data clustering matching algorithm, corresponding data clustering parameters are obtained; If the data clustering matching algorithm is the K-means algorithm, the elbow method is used to obtain the initial cluster number based on the strategy feature vector dataset information; The K-means iteration parameters are set based on the K-means algorithm data clustering requirements, including the maximum iteration number, the cluster center convergence threshold, and the initial cluster center selection method; if the data clustering matching algorithm is the DBSCAN algorithm, the elbow method is used to obtain the radius based on the strategy feature vector dataset information, and the minimum sample number is set; the data clustering matching algorithm is verified for stability based on the data clustering parameters, 70% of the strategy feature vector dataset is extracted as data samples based on stratified sampling, and the adjusted Rand index of each clustering result and the original result is calculated after repeating clustering for 5 times; According to the adjusted Rand index, it is judged whether the data clustering matching algorithm meets the data clustering requirements, if the adjusted Rand index is greater than 0.8, it is determined that the data clustering is stable, and if the adjusted Rand index is not greater than 0.8, it is determined that the data clustering is unstable, and the data clustering parameters are adjusted; if the data clustering matching algorithm is the K-means algorithm, the iteration number is increased or the initial center selection method is adjusted; if the data clustering matching algorithm is the K-means algorithm, the radius is reduced or the minimum sample number is reduced; According to the data clustering matching algorithm and the data clustering parameters, the strategy feature vectors are data clustered to obtain data clustering information, including data cluster information, center strategy feature vector information corresponding to each data cluster, and cluster user number information.

6. The method of claim 5, wherein, The data clustering information is used to classify the users and obtain user classification information, which specifically includes: According to the data clustering information, the center strategy feature vector information corresponding to each data cluster is obtained; The Euclidean distance of the center strategy feature vectors of any two data clusters is taken as the strategy difference degree of the two data clusters; According to the data clustering information and the strategy difference degree, a difference matrix D is constructed: ； In the formula, For the first The data cluster and the first The strategy variance of each data cluster; based on the variance matrix, obtain the mean and standard deviation of all elements in the variance matrix; According to the mean and the standard deviation, a difference threshold is obtained; According to the user basic data set, the data interaction frequency corresponding to each data cluster is obtained, which represents the number of times that the users in the cluster and the users in other clusters have consistent load adjustment directions at the same time; 1 / 3 of the average value of the data interaction frequency corresponding to each data cluster is taken as the data interaction threshold according to the data interaction frequency corresponding to each data cluster; According to the difference threshold and the data interaction threshold, the strategy isolation index corresponding to each data cluster is obtained; Based on the preset strategy isolation index threshold and the strategy isolation index corresponding to each data cluster, it is judged whether the data cluster is an isolated data cluster, and the user classification information is obtained; The difference threshold is specifically: wherein is the difference threshold, is the difference matrix mean, is the difference matrix standard deviation; The strategy isolation index is specifically: wherein is the strategy isolation index of the xth data cluster, is the maximum strategy difference of the xth data cluster from other data clusters, represents the data interaction frequency of the xth data cluster, is the data interaction threshold, is the weight coefficient, wherein .

7. A dynamic game based optimal scheduling system for combined heat and power system, for implementing the optimal scheduling method of any one of claims 1-6, characterized in that, It includes: The main control module is used to obtain the corresponding data clustering parameters according to the data clustering matching algorithm, verify the stability of the data clustering matching algorithm according to the data clustering parameters, perform data clustering on the strategy feature vector according to the data clustering matching algorithm and the data clustering parameters, obtain the data clustering information, classify the users based on the data clustering information, obtain the user classification information, train the existing model according to the user basic data corresponding to the main group of users, obtain the group demand prediction model, obtain the benchmark power supply prediction load and the benchmark heating prediction load based on the group demand prediction model, take the benchmark power supply prediction load and the second power supply prediction load as the total power supply demand load, take the benchmark heating prediction load and the second heating prediction load as the total heating demand load, and dispatch the combined heat and power system according to the total power supply demand load and the total heating demand load; The information acquisition module is used to obtain the combined heat and power system information, which includes the combined heat and power system function information and the combined heat and power system performance parameter information, obtain the combined heat and power historical data including the historical power supply data and the historical heating data according to the combined heat and power system information, obtain the user information and the user basic data including the historical electricity data, the historical heating data and the demand response data of each user, and obtain the user real-time load data including the user real-time electricity load data and the user real-time heating load data. An evaluation module is configured to divide user basic data corresponding to the same user into the same data set according to the cogeneration historical data and the user basic data, obtain a user basic data set, obtain a power consumption characteristic day corresponding to each user according to the user basic data set, determine whether each characteristic dimension in the strategy characteristic vector data set conforms to a normal distribution based on the KS test method according to the strategy characteristic vector data set information, take the characteristic dimension conforming to the normal distribution as a reference characteristic dimension, and obtain a data clustering matching algorithm based on data clustering characteristic analysis based on the strategy characteristic vector data set information. A display module is interactive with the main control module and is configured to output and display user classification information, user real-time load data, reference power supply prediction load, reference heating supply prediction load, second power supply prediction load, second heating supply prediction load, total power supply demand load, and total heating supply demand load.

8. The system according to claim 7, wherein, The main control module specifically includes: A control unit is configured to classify users based on data clustering information, obtain user classification information, train an existing model according to user basic data corresponding to a main group of users, obtain a group demand prediction model, obtain reference power supply prediction load and reference heating supply prediction load based on the group demand prediction model based on reference power supply load and reference heating supply load, take the reference power supply prediction load and the second power supply prediction load as the total power supply demand load, take the reference heating supply prediction load and the second heating supply prediction load as the total heating supply demand load, and dispatch the cogeneration system according to the total power supply demand load and the total heating supply demand load; An information receiving unit is interactive with the information obtaining module and the evaluation module and is configured to receive data and transmit the data to a data processing unit; The data processing unit is configured to obtain corresponding data clustering parameters according to the data clustering matching algorithm, verify the stability of the data clustering matching algorithm according to the data clustering parameters, and perform data clustering on the strategy characteristic vector according to the data clustering matching algorithm and the data clustering parameters to obtain data clustering information. 9.The system of claim 7, wherein, The information obtaining module specifically includes: A first obtaining unit is configured to obtain cogeneration system information, the cogeneration system information including cogeneration system function information and cogeneration system performance parameter information, and obtain cogeneration historical data according to the cogeneration system information, the cogeneration historical data including historical power supply data and historical heating supply data; A second obtaining unit is configured to obtain user information and user basic data, the user basic data including historical power consumption data, user historical heating data, and user demand response data corresponding to each user, and obtain user real-time load data, the user real-time load data including user real-time power consumption load data and user real-time heating supply load data.

10. The system of claim 7, wherein, The evaluation module specifically includes: The first evaluation unit is used for dividing the user basic data corresponding to the same user into the same data set according to the combined heat and power historical data and the user basic data, obtaining the user basic data set, and obtaining the power consumption characteristic days corresponding to each user according to the user basic data set. The second evaluation unit is used for judging whether each characteristic dimension in the strategy characteristic vector data set conforms to the normal distribution based on the KS test method according to the strategy characteristic vector data set information, taking the characteristic dimension conforming to the normal distribution as a reference characteristic dimension, and obtaining a data clustering matching algorithm based on data clustering characteristic analysis based on the strategy characteristic vector data set information.

Images