A method and system for user-side adjustable resources to participate in peak load auxiliary services

Abstract

The present invention discloses a method and system for user-side adjustable resources to participate in peak-shaving auxiliary services, including: obtaining configuration information, power consumption information and cost information of all adjustable resources of a single user; using a predetermined calculation model to calculate the adjustment cost of each adjustable resource; determining the load forecast value of each adjustable resource on the forecast day based on a clustering algorithm and historical power load data on the user side; and making quantity and price declarations with the goal of maximizing user benefits. Advantages: Combining historical power load data on the user side with a clustering algorithm to perform load prediction for adjustable resources, while analyzing the operating cost of adjustable resources based on the configuration, power consumption and cost information of adjustable resources; based on the load prediction results and cost analysis results of adjustable resources, assisting the user-side adjustable resources to participate in peak-shaving auxiliary services in a declaration manner, which can alleviate peak-valley differences, reduce transaction risks, and improve the utilization rate of power grid assets.

Description

Technical Field

[0001] The present invention relates to the technical field of power auxiliary service peak-shaving technology, and in particular to a method and system for user-side adjustable resources to participate in peak-shaving auxiliary services. Background Art

[0002] In recent years, with the continuous improvement of people's living standards and the continuous transformation of industrial structure, the seasonal difference of electricity demand has become increasingly prominent, the electricity load has increased year by year, and the peak of electricity consumption has become more and more significant. The traditional solution of relying on deep peak-shaving transformation on the power supply side or building new power plants cannot meet the existing demand. Not only is the investment in the power grid large, but there is also a large peak-to-valley difference. Summary of the invention

[0003] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide a method and system for user-side adjustable resources to participate in peak-shaving auxiliary services. On the one hand, it can alleviate the peak-to-valley difference and improve the safe, stable and economical operation capabilities of the power grid. On the other hand, it can improve the utilization rate of power grid assets and delay or reduce power grid investment.

[0004] In order to solve the above technical problems, the present invention provides a method for user-side adjustable resources to participate in peak load auxiliary services, comprising:

[0005] Obtain configuration information, power usage information, and cost information of all adjustable resources of a single user;

[0006] Input configuration information, power consumption information and cost information of all adjustable resources into a predetermined calculation model to calculate the adjustment cost of each adjustable resource;

[0007] Determine the load forecast value of each adjustable resource on the forecast day based on the clustering algorithm and the historical power load data on the user side;

[0008] Based on the adjustment cost of each adjustable resource, the load forecast value of each adjustable resource and the pre-acquired peak-shaving auxiliary service transaction announcement information, quantity and price declarations are made with the goal of maximizing user benefits.

[0009] Furthermore, the calculation model is:

[0010]

[0011] Among them, C iv is the vth adjustable resource adjustment cost of the ith user, i∈{m 1 ,...,m d},v∈{m i，1 ,...,m i,n},{m 1 ,...,m d} indicates a total of d users, {mi，1 ,...,m i,n} means that each user has n adjustable resources, n is a variable, β iv is the adjustment cost weight of the vth adjustable resource of the ith user, α is the subsidy ratio of the aggregator, C si The hardware equipment cost for users, C oi Investing in software system costs for users, C yi is the annual operation and management cost of the system, T is the number of years for project implementation, C xio It is the annual project management fee paid by the user to the aggregator in the oth year.

[0012] Furthermore, the load forecast value of each adjustable resource on the forecast day is determined based on the clustering algorithm and the historical power load data on the user side, including:

[0013] Obtain the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side;

[0014] Identify and correct abnormal data and bad data of the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side;

[0015] Based on the corrected historical 96-point power load data of all adjustable resources on the user side, the K-means clustering algorithm is used to extract the typical curves and cluster centers of each type of adjustable resources;

[0016] Based on the corrected historical 96-point electricity load data of each adjustable resource on the user side, normalization is performed to determine the load curve of each adjustable resource;

[0017] Calculate the distance between the load curve of each adjustable resource and the typical curve of each category of adjustable resources in the cluster center, group the adjustable resources with similar power consumption characteristics to obtain grouped loads, determine the corresponding load forecasting algorithm based on the power consumption pattern of the grouped loads, and perform load forecasting on each adjustable resource on the forecast day to obtain the load forecast value of each adjustable resource on the forecast day.

[0018] Furthermore, the corrected historical 96-point electricity load data of all adjustable resources on the user side is a standard format file including user name, all adjustable resource names, industry attributes, 96-point load curves and rated power fields;

[0019] The corrected historical 96-point electricity load data of each adjustable resource on the user side is a standard format file including user name, single adjustable resource name, industry attribute, 96-point load curve and rated power field.

[0020] Furthermore, the K-means clustering algorithm is used to extract typical curves and cluster centers of each type of adjustable resource based on the corrected historical 96-point power load data of all adjustable resources on the user side, including:

[0021] (7) Determine the number of clusters k;

[0022] (8) Initialize k cluster centers μ1,...,μk;

[0023] (9) Calculate the distance between the sample and each cluster center, and assign each sample to the nearest cluster center, wherein the sample is the historical 96-point load curve data of each adjustable resource on the user side; the sample refers to the historical 96-point power load data;

[0024] (10) Update the cluster center of each cluster based on the samples of each cluster

[0025] (11) Iterate steps (3) to (4) until the similarity measure function of K-means clustering begins to converge;

[0026] The similarity measurement function expression of the K-means clustering is:

[0027]

[0028] Among them, E is the sum of squared errors of all samples, k is the number of clusters, C i is the i-th cluster, p is the sample point in the cluster space, μ i is the cluster center of the i-th cluster;

[0029] (12) Based on the convergence result of step (5), the converged cluster centers and the typical load curves of the adjustable resources based on each cluster center are determined.

[0030] Furthermore, the normalization processing is performed based on the corrected historical 96-point electricity load data of each adjustable resource on the user side to determine the load curve of each adjustable resource, including:

[0031] The 96-point average of the corrected historical load data of each adjustable resource on the user side is taken and normalized to determine the load curve of each adjustable resource.

[0032] Furthermore, the quantity and price declaration is carried out with the goal of maximizing user benefits according to the adjustment cost of each adjustable resource, the load forecast value of each adjustable resource and the pre-acquired peak load auxiliary service transaction announcement information, including:

[0033] Obtain peak load auxiliary service transaction announcement information, send information to users of adjustable resources, and obtain adjustable resource power consumption information and adjustable information fed back by users of adjustable resources;

[0034] Clustering the adjustable resources based on the adjustable resource power consumption information, adjustable information, the adjustment cost of each adjustable resource, and the load forecast value of each adjustable resource;

[0035] According to the clustering results, based on the consideration of maximizing the comprehensive benefits of users and in accordance with the proportional experience method, the quantity and price of adjustable resources participating in the peak load auxiliary service are declared in radical, aggressive, balanced, stable, cautious and conservative ways. The specific quotation methods are as follows:

[0036] P apply =ηP allow_max

[0037] Considering the day-ahead ancillary service quotation, the quotation constraint is:

[0038] C i,all / 365≤P apply

[0039] Among them, P apply Declare a price for a single user adjustable resource, P allow_max is the maximum declared price stipulated in the trading rules, η is the adjustment coefficient, C i,all It is the annual adjustment cost of the adjustable resources of a single user. The adjustment coefficients η of the radical, aggressive, balanced, steady, cautious and conservative types gradually decrease, and 0<η≤1. Based on the user name, industry attributes, names of all adjustable resources, 96-point load curve and rated power, the quantity and price of adjustable resource ancillary service market transactions are declared taking into account the analyzed typical load curve of user-side adjustable resources, adjustment cost and adjustment coefficient.

[0040] A system for user-side adjustable resources to participate in peak load auxiliary services, comprising:

[0041] A first acquisition module is used to acquire configuration information, power usage information and cost information of all adjustable resources of a single user;

[0042] A first calculation module, used for inputting configuration information, power consumption information and cost information of all adjustable resources into a predetermined calculation model to calculate the adjustment cost of each adjustable resource;

[0043] A prediction module, used to determine the load prediction value of each adjustable resource on the prediction day based on a clustering algorithm and historical power load data on the user side;

[0044] The declaration module is used to declare quantity and price based on the regulation cost of each adjustable resource, the load forecast value of each adjustable resource and the pre-acquired peak-shaving auxiliary service transaction announcement information, with the goal of maximizing user benefits.

[0045] Furthermore, the calculation model is:

[0046]

[0047] Among them, C iv is the vth adjustable resource adjustment cost of the ith user, i∈{m 1 ,...,m d},v∈{m i，1 ,...,m i,n},{m 1 ,...,m d} indicates a total of d users, {m i，1 ,...,m i,n} means that each user has n adjustable resources, n is a variable, β iv is the adjustment cost weight of the vth adjustable resource of the ith user, α is the subsidy ratio of the aggregator, C si The hardware equipment cost for users, C oi Investing in software system costs for users, C yi is the annual operation and management cost of the system, T is the number of years for project implementation, C xio It is the annual project management fee paid by the user to the aggregator in the oth year.

[0048] Furthermore, the prediction module includes:

[0049] The second acquisition module is used to acquire the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side;

[0050] A preprocessing module, used to identify and correct abnormal data and bad data of the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side;

[0051] An extraction module is used to extract typical curves and cluster centers of each type of adjustable resources based on the corrected historical 96-point power load data of all adjustable resources on the user side using a K-means clustering algorithm;

[0052] A determination module, used for performing normalization processing based on the corrected historical 96-point electricity load data of each adjustable resource on the user side to determine the load curve of each adjustable resource;

[0053] The second calculation module is used to calculate the distance between the load curve of each adjustable resource and the typical curve of each category of adjustable resources in the cluster center, group the adjustable resources with similar power consumption characteristics to obtain grouped loads, determine the corresponding load forecasting algorithm based on the power consumption rules of the grouped loads, and perform load forecasting on each adjustable resource on the forecast day to obtain the load forecast value of each adjustable resource on the forecast day.

[0054] Furthermore, the corrected historical 96-point electricity load data of all adjustable resources on the user side is a standard format file including user name, all adjustable resource names, industry attributes, 96-point load curves and rated power fields;

[0055] The corrected historical 96-point electricity load data of each adjustable resource on the user side is a standard format file including user name, single adjustable resource name, industry attribute, 96-point load curve and rated power field.

[0056] Furthermore, the extraction module includes a first clustering module, which is used to perform the following process:

[0057] (1) Determine the number of clusters k;

[0058] (2) Initialize k cluster centers μ1,...,μk;

[0059] (3) Calculate the distance between the sample and each cluster center, and assign each sample to the nearest cluster center, where the sample is the historical 96-point load curve data of each adjustable resource on the user side;

[0060] The sample refers to the historical 96-point electricity load data;

[0061] (4) Update the cluster center of each cluster based on the samples of each cluster

[0062] (5) Iterate steps (3) to (4) until the similarity measure function of K-means clustering begins to converge;

[0063] The similarity measurement function expression of the K-means clustering is:

[0064]

[0065] Among them, E is the sum of squared errors of all samples, k is the number of clusters, C i is the i-th cluster, p is the sample point in the cluster space, μ i is the cluster center of the i-th cluster;

[0066] (6) Based on the convergence result of step (5), the converged cluster centers and the typical load curves of the adjustable resources based on each cluster center are determined.

[0067] Furthermore, the determination module is used to take a 96-point average of the corrected historical load data of each adjustable resource on the user side, and perform normalization processing to determine the load curve of each adjustable resource.

[0068] Furthermore, the declaration module includes:

[0069] The third acquisition module is used to obtain the peak load auxiliary service transaction announcement information, send information to the user of the adjustable resource, and obtain the adjustable resource power consumption information and adjustable information fed back by the user of the adjustable resource;

[0070] A second clustering module is used to cluster the adjustable resources based on the adjustable resource power consumption information, the adjustable information, the adjustment cost of each adjustable resource, and the load prediction value of each adjustable resource;

[0071] The processing module is used to declare the quantity and price of adjustable resources participating in the peak load auxiliary service in a radical, aggressive, balanced, prudent, cautious and conservative manner based on the clustering results and the proportional experience method on the basis of considering the maximization of the comprehensive benefits of users. The specific quotation methods are as follows:

[0072] P apply =ηP allow_max

[0073] Considering the day-ahead ancillary service quotation, the quotation constraint is:

[0074] C i,all / 365≤P apply

[0075] Among them, P apply Declare a price for a single user adjustable resource, P allow_max is the maximum declared price stipulated in the trading rules, η is the adjustment coefficient, C i,all It is the annual adjustment cost of the adjustable resources of a single user, and the adjustment coefficient. The adjustment coefficients η of the radical, aggressive, balanced, stable, cautious and conservative types gradually decrease, and 0<η≤1. Based on the user name, industry attributes, names of all adjustable resources, 96-point load curve and rated power, the quantity and price of adjustable resource ancillary service market transactions are declared taking into account the analyzed typical load curve of user-side adjustable resources, the adjustment cost and the adjustment coefficient.

[0076] A computer-readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, cause the computing device to perform any of the methods described.

[0077] A computing device comprising:

[0078] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the methods described.

[0079] The beneficial effects achieved by the present invention are:

[0080] This invention combines historical electricity load data on the user side with a clustering algorithm to perform load forecasting for adjustable resource groups, and analyzes the operating costs of adjustable resources based on adjustable resource configuration, electricity consumption information, and cost information. Based on the adjustable resource load forecast results and cost analysis results, a quantity and price declaration method is used to assist user-side adjustable resources in participating in peak-shaving auxiliary services, which can alleviate peak-to-valley differences. At the same time, quantity and price declarations are made with the goal of maximizing user benefits, which can obtain relatively stable returns for aggregators, reduce transaction risks, and improve the utilization rate of power grid assets. BRIEF DESCRIPTION OF THE DRAWINGS

[0081] Figure 1 It is a schematic diagram of the process of the present invention;

[0082] Figure 2 It is a flowchart of a method for user-side adjustable resources to participate in peak load auxiliary services based on K-means cluster analysis;

[0083] Figure 3 It is a system schematic diagram of the present invention. DETAILED DESCRIPTION

[0084] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0085] like Figure 1 As shown, a method for user-side adjustable resources to participate in peak load auxiliary services is characterized by comprising:

[0086] Obtain configuration information, power usage information, and cost information of all adjustable resources of a single user;

[0087] Input configuration information, power consumption information and cost information of all adjustable resources into a predetermined calculation model to calculate the adjustment cost of each adjustable resource;

[0088] Determine the load forecast value of each adjustable resource on the forecast day based on the clustering algorithm and the historical power load data on the user side;

[0089] Based on the adjustment cost of each adjustable resource, the load forecast value of each adjustable resource and the pre-acquired peak-shaving auxiliary service transaction announcement information, quantity and price declarations are made with the goal of maximizing user benefits.

[0090] like Figure 2 As shown, a method for user-side adjustable resources to participate in peak load auxiliary services based on K-means cluster analysis includes:

[0091] Step S1: Obtain configuration information and real-time information (power consumption information and cost information) of all adjustable resources of a single user; input the configuration information, power consumption information and cost information of all adjustable resources into a predetermined calculation model to calculate the adjustment cost of each adjustable resource;

[0092] S101, obtaining adjustable resource configuration information, power consumption information and cost information, such as the user to whom the resource belongs, unit capacity, rated power, production power consumption plan, etc.;

[0093] S102. Combine the above configuration information and consider the hardware equipment cost and system operation management fee of the adjustable resources, and calculate the cost of the adjustable resources managed by the aggregator as follows: Where: α is the subsidy ratio of the aggregator, C si The hardware equipment cost for users, C oi Investing in software system costs for users, C yi is the annual operation and management cost of the system, T is the number of years for project implementation, C xio is the annual project management fee paid by the user to the aggregator in the oth year. This fee can be determined to be 0 according to the actual situation. Then the adjustment cost of the vth adjustable resource of the ith user is: Where: i = {m 1 ,...,m d},v={m i，1 ,...,m i,n}, β iv is the adjustment cost weight of the vth adjustable resource of the ith user.

[0094] Step S2: Determine the load forecast value of each adjustable resource on the forecast day based on the clustering algorithm and the historical power load data on the user side;

[0095] Specifically include:

[0096] S201, obtaining 96 points of power load data of adjustable resources on the user side for multiple days in history;

[0097] S202, pre-processing is performed based on the historical 96-point load data of the adjustable resource for multiple days, and a standard format file including fields such as user name, resource name, industry attribute, and 96-point load is generated;

[0098] S203, cluster the pre-processed 96-point load data of adjustable resources using the K-means clustering algorithm, extract the typical curve of adjustable resources, and form cluster centers; the specific steps are as follows: (1) determine the number of clusters k; (2) initialize k cluster centers μ1,...,μk; (3) calculate the distance between the sample and the center, and assign each sample to the nearest center; (4) update the center of each cluster according to the samples of each cluster; (5) iterate (3) to (4) steps until the similarity measurement function begins to converge. The similarity measurement function expression of K-means clustering is: Where E is the sum of squared errors of all samples, k is the number of clusters, and C i is the i-th cluster, p is the sample point in the cluster space, μ i is the cluster center of the i-th cluster;

[0099] S204, taking the 96-point average of the historical load data of a single adjustable resource and performing normalization processing;

[0100] S205, calculate the distance between the load curve of a single adjustable resource and the typical curves of each category in the cluster center, and group the adjustable resources with similar power consumption characteristics to obtain grouped loads; this paper assumes that {m 1 ,...,m d There are d proxy users in total, each user has {m i， 1,...,m i,n} adjustable resources, where i = 1, 2...d, n variables, based on the above adjustable resources {m i， 1,...,m i,n ,...m d,1 ,...m d,n}divided into k groups;

[0101] S206, based on the power consumption pattern of grouped loads, select time series method, trend analysis method, seasonal proportion method and other methods to predict the load of adjustable resources. If a prediction method has high accuracy in predicting the load of adjustable resources, then use this method to predict the load of such adjustable resources. The load prediction results of each user's adjustable resources are as follows: i，1，1 ...,m i,1,96},...{m i,n，1 ...,m i,n,96}},...,{{m d，1，1 ...,m d,1,96},...{m d,n，1 ...,m d,n,96}}.

[0102] Step S3: Calculate the individual user and pre-acquired peak load auxiliary service transaction announcement information based on the adjustment cost of each adjustable resource and the load forecast value of each adjustable resource, and declare quantity and price with the goal of maximizing user benefits.

[0103] Specifically include:

[0104] S301, the aggregator sends information to the user of the adjustable resource according to the peak load auxiliary service transaction announcement information, and the user reports the adjustable resource power consumption information and adjustable information;

[0105] S302, the aggregator reports the information comprehensively, and clusters the adjustable resources based on the load forecast and cost analysis of the adjustable resources in S1 and S2. Considering that the current "Jiangsu Power Market User Adjustable Load Participation in Ancillary Service Market Trading Rules (Trial)" is based on the power user account number for information reporting, the adjustable resources of the same power user are mainly clustered and grouped. On the basis of considering the maximization of comprehensive benefits, according to the proportional experience method, the aggressive, aggressive, balanced, stable, cautious and conservative methods are used to declare the quantity and price of adjustable resources participating in the peak load ancillary service. The specific quotation method is as follows: P apply =ηP allow_max , considering the day-ahead ancillary service price, the price constraint is: C i,all / 365≤P apply , where P apply Declare a price for a single user adjustable resource, P allow_max is the maximum declared price stipulated in the trading rules, η is the adjustment coefficient, C i,all The annual adjustment cost of the adjustable resources managed by the aggregator, the adjustment coefficients η of the radical, aggressive, balanced, stable, cautious and conservative types gradually decrease, and 0<η≤1, are as follows:

[0106]

[0107]

[0108] Based on the above basic user information including user name, industry attributes, names of all adjustable resources, 96-point load curve and rated power, and taking into account the analyzed typical load curve of user-side adjustable resources, adjustment cost and adjustment coefficient, the quantity and price declaration of adjustable resource ancillary service market transactions are carried out.

[0109] like Figure 3 As shown, the present invention also provides a system for user-side adjustable resources to participate in peak load auxiliary services, including:

[0110] A first acquisition module is used to acquire configuration information, power usage information and cost information of all adjustable resources of a single user;

[0111] A first calculation module, used for inputting configuration information, power consumption information and cost information of all adjustable resources into a predetermined calculation model to calculate the adjustment cost of each adjustable resource;

[0112] A prediction module, used to determine the load prediction value of each adjustable resource on the prediction day based on a clustering algorithm and historical power load data on the user side;

[0113] The declaration module is used to declare quantity and price based on the regulation cost of each adjustable resource, the load forecast value of each adjustable resource and the pre-acquired peak-shaving auxiliary service transaction announcement information, with the goal of maximizing user benefits.

[0114] Furthermore, the calculation model is:

[0115]

[0116] Among them, C iv is the adjustment cost of the vth adjustable resource of the ith user, i∈{m 1 ,...,m d},v∈{m i，1 ,...,m i,n},{m 1 ,...,m d} indicates a total of d users, {m i，1 ,...,m i,n} means that each user has n adjustable resources, n is a variable, β iv is the adjustment cost weight of the vth adjustable resource of the ith user, α is the subsidy ratio of the aggregator, C si The hardware equipment cost for users, C oi Investing in software system costs for users, C yi is the annual operation and management cost of the system, T is the number of years for project implementation, C xio It is the annual project management fee paid by the user to the aggregator in the oth year.

[0117] Furthermore, the prediction module includes:

[0118] The second acquisition module is used to acquire the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side;

[0119] A preprocessing module, used to identify and correct abnormal data and bad data of the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side;

[0120] An extraction module is used to extract typical curves and cluster centers of each type of adjustable resources based on the corrected historical 96-point power load data of all adjustable resources on the user side using a K-means clustering algorithm;

[0121] A determination module, used for performing normalization processing based on the corrected historical 96-point electricity load data of each adjustable resource on the user side to determine the load curve of each adjustable resource;

[0122] The second calculation module is used to calculate the distance between the load curve of each adjustable resource and the typical curve of each category of adjustable resources in the cluster center, group the adjustable resources with similar power consumption characteristics to obtain grouped loads, determine the corresponding load forecasting algorithm based on the power consumption rules of the grouped loads, and perform load forecasting on each adjustable resource on the forecast day to obtain the load forecast value of each adjustable resource on the forecast day.

[0123] Furthermore, the corrected historical 96-point electricity load data of all adjustable resources on the user side is a standard format file including user name, all adjustable resource names, industry attributes, 96-point load curves and rated power fields;

[0124] The corrected historical 96-point electricity load data of each adjustable resource on the user side is a standard format file including user name, single adjustable resource name, industry attribute, 96-point load curve and rated power field.

[0125] Furthermore, the extraction module includes a first clustering module, which is used to perform the following process:

[0126] (1) Determine the number of clusters k;

[0127] (2) Initialize k cluster centers μ1,...,μk;

[0128] (3) Calculate the distance between the sample and each cluster center, and assign each sample to the nearest cluster center, where the sample is the historical 96-point load curve data of each adjustable resource on the user side;

[0129] The sample refers to the historical 96-point electricity load data;

[0130] (4) Update the cluster center of each cluster based on the samples of each cluster

[0131] (5) Iterate steps (3) to (4) until the similarity measure function of K-means clustering begins to converge;

[0132] The similarity measurement function expression of the K-means clustering is:

[0133]

[0134] Among them, E is the sum of squared errors of all samples, k is the number of clusters, C i is the i-th cluster, p is the sample point in the cluster space, μ i is the cluster center of the i-th cluster;

[0135] (6) Based on the convergence result of step (5), the converged cluster centers and the typical load curves of the adjustable resources based on each cluster center are determined.

[0136] Furthermore, the determination module is used to take a 96-point average of the corrected historical load data of each adjustable resource on the user side, and perform normalization processing to determine the load curve of each adjustable resource.

[0137] Furthermore, the declaration module includes:

[0138] The third acquisition module is used to obtain the peak load auxiliary service transaction announcement information, send information to the user of the adjustable resource, and obtain the adjustable resource power consumption information and adjustable information fed back by the user of the adjustable resource;

[0139] A second clustering module is used to cluster the adjustable resources based on the adjustable resource power consumption information, the adjustable information, the adjustment cost of each adjustable resource, and the load prediction value of each adjustable resource;

[0140] The processing module is used to declare the quantity and price of adjustable resources participating in the peak load auxiliary service in a radical, aggressive, balanced, prudent, cautious and conservative manner based on the clustering results and the proportional experience method on the basis of considering the maximization of the comprehensive benefits of users. The specific quotation methods are as follows:

[0141] P apply =ηP allow_max

[0142] Considering the day-ahead ancillary service quotation, the quotation constraint is:

[0143] C i,all / 365≤P apply

[0144] Among them, P apply Declare a price for a single user adjustable resource, P allow_max is the maximum declared price stipulated in the trading rules, η is the adjustment coefficient, C i,allIt is the annual adjustment cost of the adjustable resources of a single user, and the adjustment coefficient. The adjustment coefficients η of the radical, aggressive, balanced, stable, cautious and conservative types gradually decrease, and 0<η≤1. Based on the user name, industry attributes, names of all adjustable resources, 96-point load curve and rated power, the quantity and price of adjustable resource ancillary service market transactions are declared taking into account the analyzed typical load curve of user-side adjustable resources, the adjustment cost and the adjustment coefficient.

[0145] The present invention also provides a computer-readable storage medium storing one or more programs, wherein the one or more programs include instructions, and when the instructions are executed by a computing device, the computing device performs any of the methods described.

[0146] The present invention also provides a computing device, comprising:

[0147] One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any of the methods described.

[0148] This invention combines historical electricity load data and first uses the K-means clustering algorithm to predict the load of adjustable resource groups. At the same time, it analyzes the operating costs of adjustable resources based on adjustable resource configuration and electricity consumption information, user hardware equipment costs, system operation and management costs, etc. Based on the adjustable resource load prediction results and cost analysis results, the proportional experience method is used to provide users with multiple types of quantity and price declaration methods to assist user-side adjustable resources in participating in peak-shaving auxiliary services, thereby obtaining relatively stable returns for aggregators and reducing transaction risks.

[0149] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0150] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0151] 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.

[0152] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0153] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for user-side adjustable resources to participate in peak load auxiliary services, It is characterized in that include: Obtain configuration information, power usage information, and cost information of all adjustable resources of a single user; Input configuration information, power consumption information and cost information of all adjustable resources into a predetermined calculation model to calculate the adjustment cost of each adjustable resource; Determine the load forecast value of each adjustable resource on the forecast day based on the clustering algorithm and the historical power load data on the user side; According to the adjustment cost of each adjustable resource, the load forecast value of each adjustable resource and the pre-acquired peak load auxiliary service transaction announcement information, the quantity and price declaration is carried out with the goal of maximizing user benefits, including: Obtain peak load auxiliary service transaction announcement information, send information to users of adjustable resources, and obtain adjustable resource power consumption information and adjustable information fed back by users of adjustable resources; Clustering the adjustable resources based on the adjustable resource power consumption information, adjustable information, the adjustment cost of each adjustable resource, and the load forecast value of each adjustable resource; According to the clustering results, based on the consideration of maximizing the comprehensive benefits of users and in accordance with the proportional experience method, the quantity and price of adjustable resources participating in the peak load auxiliary service are declared in radical, aggressive, balanced, stable, cautious and conservative ways. The specific quotation methods are as follows: ； Considering the day-ahead ancillary service quotation, the quotation constraint is: ； in, Declare prices for individual user-adjustable resources, The maximum declared price stipulated in the trading rules. is the adjustment factor, The annual adjustment cost of adjustable resources for a single user, the adjustment coefficients for the radical, aggressive, balanced, stable, cautious and conservative types gradually decreases, and ; Based on the user name, industry attributes, names of all adjustable resources, 96-point load curve and rated power, while considering the analyzed typical load curve of user-side adjustable resources, adjustment cost and adjustment coefficient, the quantity and price declaration of adjustable resource ancillary service market transactions is carried out.

2. The method for user-side adjustable resources to participate in peak load auxiliary services according to claim 1, It is characterized in that The calculation model is: ； in, For the i User's v Adjustable resource adjustment cost, , , Indicates total d Users, Indicates that each user has n adjustable resources, n is a variable, For the i User's v The adjustment cost weight of an adjustable resource, is the subsidy ratio for aggregators, Invest in hardware equipment costs for users, Invest in software system costs for users, is the annual operation and management cost of the system, T The number of years the project has been implemented, For user o Annual project management fees paid to aggregators.

3. The method for user-side adjustable resources to participate in peak load auxiliary services according to claim 1, It is characterized in that The method of determining the load forecast value of each adjustable resource on the forecast day based on the clustering algorithm and the historical power load data on the user side includes: Obtain the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side; Identify and correct abnormal data and bad data of the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side; Based on the corrected historical 96-point electricity load data of all adjustable resources on the user side, the K-means clustering algorithm is used to extract the typical curves and cluster centers of each type of adjustable resources; Based on the corrected historical 96-point electricity load data of each adjustable resource on the user side, normalization is performed to determine the load curve of each adjustable resource; Calculate the distance between the load curve of each adjustable resource and the typical curve of each category of adjustable resources in the cluster center, group the adjustable resources with similar power consumption characteristics to obtain grouped loads, determine the corresponding load forecasting algorithm based on the power consumption pattern of the grouped loads, and perform load forecasting on each adjustable resource on the forecast day to obtain the load forecast value of each adjustable resource on the forecast day.

4. The method for user-side adjustable resources to participate in peak load auxiliary services according to claim 3, It is characterized in that The corrected historical 96-point power load data of all adjustable resources on the user side is a standard format file including user name, all adjustable resource names, industry attributes, 96-point load curves and rated power fields; The corrected historical 96-point electricity load data of each adjustable resource on the user side is a standard format file including user name, single adjustable resource name, industry attribute, 96-point load curve and rated power field.

5. The method for user-side adjustable resources to participate in peak load auxiliary services according to claim 3, It is characterized in that The K-means clustering algorithm is used to extract typical curves and cluster centers of each type of adjustable resource based on the corrected historical 96-point power load data of all adjustable resources on the user side, including: (1) Determine the number of clusters k; (2) Initialize k cluster centers ; (3) Calculate the distance between the sample and each cluster center and assign each sample to the nearest cluster center, where the sample is the historical 96-point load curve data of each adjustable resource on the user side; The sample refers to the historical 96-point electricity load data; (4) Update the cluster center of each cluster based on the samples of each cluster (5) Iterate steps (3) to (4) until the similarity measure function of K-means clustering begins to converge; The similarity measurement function expression of the K-means clustering is: ； in, E is the sum of squared errors of all samples, k is the number of clusters, C i For the i cluster, p is a sample point in the cluster space, μ i It is i The cluster center of the cluster; (6) Based on the convergence result of step (5), the converged cluster centers and the typical load curves of the adjustable resources based on each cluster center are determined.

6. The method for user-side adjustable resources to participate in peak load auxiliary services according to claim 3, It is characterized in that The normalization process is performed based on the corrected historical 96-point electricity load data of each adjustable resource on the user side to determine the load curve of each adjustable resource, including: The 96-point average of the corrected historical load data of each adjustable resource on the user side is taken and normalized to determine the load curve of each adjustable resource.

7. A system for user-side adjustable resources to participate in peak load auxiliary services, It is characterized in that include: A first acquisition module is used to acquire configuration information, power usage information and cost information of all adjustable resources of a single user; A first calculation module, used for inputting configuration information, power consumption information and cost information of all adjustable resources into a predetermined calculation model to calculate the adjustment cost of each adjustable resource; A prediction module, used to determine the load prediction value of each adjustable resource on the prediction day based on a clustering algorithm and historical power load data on the user side; The declaration module is used to declare quantity and price based on the regulation cost of each adjustable resource, the load forecast value of each adjustable resource, and the pre-acquired peak load auxiliary service transaction announcement information with the goal of maximizing user benefits; The declaration module includes: The third acquisition module is used to obtain the peak load auxiliary service transaction announcement information, send information to the user of the adjustable resource, and obtain the adjustable resource power consumption information and adjustable information fed back by the user of the adjustable resource; A second clustering module is used to cluster the adjustable resources based on the adjustable resource power consumption information, the adjustable information, the adjustment cost of each adjustable resource, and the load prediction value of each adjustable resource; The processing module is used to declare the quantity and price of adjustable resources participating in the peak load auxiliary service in a radical, aggressive, balanced, prudent, cautious and conservative manner based on the clustering results and the proportional experience method on the basis of considering the maximization of the comprehensive benefits of users. The specific quotation methods are as follows: ； Considering the day-ahead ancillary service quotation, the quotation constraint is: ； in, Declare prices for individual user-adjustable resources, The maximum declared price stipulated in the trading rules. is the adjustment factor, The annual adjustment cost of adjustable resources for a single user, the adjustment coefficients for the radical, aggressive, balanced, stable, cautious and conservative types gradually decreases, and ; Based on the user name, industry attributes, names of all adjustable resources, 96-point load curve and rated power, while considering the analyzed typical load curve of user-side adjustable resources, adjustment cost and adjustment coefficient, the quantity and price declaration of adjustable resource ancillary service market transactions is carried out.

8. The system for user-side adjustable resources to participate in peak load auxiliary services according to claim 7, It is characterized in that The calculation model is: ； in, For the i User's v Adjustable resource adjustment cost, , , Indicates total d Users, Indicates that each user has n adjustable resources, n is a variable, For the i User's v The adjustment cost weight of an adjustable resource, is the subsidy ratio for aggregators, Invest in hardware equipment costs for users, Invest in software system costs for users, is the annual operation and management cost of the system, T The number of years the project has been implemented, For user o Annual project management fees paid to aggregators.

9. The system for user-side adjustable resources to participate in peak load auxiliary services according to claim 7, It is characterized in that The prediction module comprises: The second acquisition module is used to acquire the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side; A preprocessing module, used to identify and correct abnormal data and bad data of the historical 96-point power load data of all adjustable resources on the user side and the historical 96-point power load data of each adjustable resource on the user side; An extraction module is used to extract typical curves and cluster centers of each type of adjustable resources based on the corrected historical 96-point power load data of all adjustable resources on the user side using a K-means clustering algorithm; A determination module, used for performing normalization processing based on the corrected historical 96-point electricity load data of each adjustable resource on the user side to determine the load curve of each adjustable resource; The second calculation module is used to calculate the distance between the load curve of each adjustable resource and the typical curve of each category of adjustable resources in the cluster center, group the adjustable resources with similar power consumption characteristics to obtain grouped loads, determine the corresponding load forecasting algorithm based on the power consumption rules of the grouped loads, and perform load forecasting on each adjustable resource on the forecast day to obtain the load forecast value of each adjustable resource on the forecast day.

10. The system for user-side adjustable resources to participate in peak load auxiliary services according to claim 9, It is characterized in that The corrected historical 96-point power load data of all adjustable resources on the user side is a standard format file including user name, all adjustable resource names, industry attributes, 96-point load curves and rated power fields; The corrected historical 96-point electricity load data of each adjustable resource on the user side is a standard format file including user name, single adjustable resource name, industry attribute, 96-point load curve and rated power field.

11. The system for user-side adjustable resources to participate in peak load auxiliary services according to claim 9, It is characterized in that The extraction module includes a first clustering module, which is used to perform the following process: (1) Determine the number of clusters k; (2) Initialize k cluster centers ; (3) Calculate the distance between the sample and each cluster center and assign each sample to the nearest cluster center, where the sample is the historical 96-point load curve data of each adjustable resource on the user side; The sample refers to the historical 96-point electricity load data; (4) Update the cluster center of each cluster based on the samples of each cluster (5) Iterate steps (3) to (4) until the similarity measure function of K-means clustering begins to converge; The similarity measurement function expression of the K-means clustering is: ； in, E is the sum of squared errors of all samples, k is the number of clusters, C i For the i cluster, p is a sample point in the cluster space, μ i It is i The cluster center of the cluster; (6) Based on the convergence result of step (5), the converged cluster centers and the typical load curves of the adjustable resources based on each cluster center are determined.

12. The method for user-side adjustable resources to participate in peak load auxiliary services according to claim 9, It is characterized in that The determination module is used to take the 96-point average of the corrected historical load data of each adjustable resource on the user side, perform normalization processing, and determine the load curve of each adjustable resource.

13. A computer-readable storage medium storing one or more programs, It is characterized in that The one or more programs include instructions which, when executed by a computing device, cause the computing device to perform any one of the methods according to claims 1 to 6.

14. A computing device, It is characterized in that include, One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing any one of the methods according to claims 1 to 6.

Images