Power load intelligent scheduling system and method based on user load portrait

Abstract

The invention relates to the technical field of power dispatching systems, and discloses an intelligent power load dispatching system and method based on a user load portrait, and the system comprises a user load portrait construction module, a user power load prediction module, and a user power load dispatching module. Carrying out historical prediction power dispatching load error ratio change trend numerical statistics of user side power load prediction time by combining numerical processing based on user historical prediction power dispatching load error ratio parameters; and according to the user historical predicted power dispatching load parameter, the user historical actual power dispatching load parameter and the user historical predicted power dispatching load error change weight parameter, intelligent and accurate prediction of a power theoretical actual dispatching load prediction result of user-side power load prediction time is carried out. Scientific statistics of power load dispatching parameters is realized based on a user power dispatching load error change trend, and the precision and reliability of power load dispatching are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power dispatching systems, and specifically to a power load intelligent dispatching system and method based on user load profiling. Background Art

[0002] User load profiles are refined descriptive labels generated based on user electricity data, by analyzing their electricity behavior patterns, load characteristics, and underlying patterns. They help power companies or energy service providers understand user needs, optimize service strategies, and provide data support for demand-side management and market transactions. Based on user load profiles, a new power dispatching system can be constructed, shifting from "load-driven by source" to "load-driven by source," improving the intelligent management of power load dispatch. However, existing power dispatching systems cannot intelligently establish user load profiles or accurately predict user-side power dispatch parameters, reducing the sophistication and reliability of user-side power dispatch.

[0003] A Chinese invention patent with announcement number CN116544934B discloses a power dispatching method and system for power load forecasting, which obtains production characteristic information and temperature characteristic information; obtains predicted power load; obtains idle power sources in a preset time zone; generates M power supply plans; obtains M first fitnesses; obtains M second fitnesses; obtains M third fitnesses; and obtains a recommended power supply plan for power dispatching. The above technical solution cannot correct power load dispatching errors, thereby reducing the reliability of power dispatching. Summary of the Invention

[0004] (1) Technical problems solved In order to solve the problem that the above-mentioned existing power dispatching system cannot intelligently establish user load profile information, cannot accurately predict user-side power dispatching parameters, and reduces the refinement and reliability of user-side power dispatching, the above purpose of scientifically constructing a user load portrait feature library, accurately predicting user-side power load dispatching parameters, and intelligently executing user-side power load dispatching operations is achieved.

[0005] (2) Technical solution The present invention is implemented through the following technical solution: a method for intelligent dispatching of electric loads based on user load profiles, the method comprising the following steps: S1. Collecting historical power load dispatch feature text data of users; S2. Establishing a user-side power load profile feature library based on the user's historical power load dispatch feature text data and the user load profile construction keywords, and generating a user load profile feature library; S3. Collecting user power load forecast time data; S4. Search and process the historical predicted power dispatching load information, historical actual power dispatching load information, and historical predicted power dispatching load error ratio information of the user-side power load forecast time according to the user power load forecast time data and the user load profile feature library, and generate user historical predicted power dispatching load data, user historical actual power dispatching load data, and user historical predicted power dispatching load error ratio data, respectively; S5. Performing numerical analysis of the change trend of the historical predicted power dispatching load error ratio of the user-side power load forecast time based on the user's historical predicted power dispatching load error ratio data, and generating weight data of the change of the user's historical predicted power dispatching load error; S6. Performing metering processing on the power theoretical actual dispatch load prediction result of the user-side power load prediction time based on the user's historical predicted power dispatch load data, the user's historical actual power dispatch load data, and the user's historical predicted power dispatch load error change weight data, and generating the user's power theoretical actual dispatch load prediction data; S7. Construct user power load dispatch prediction result data and execute user power load dispatch operation.

[0006] Preferably, the steps for collecting the user's historical power load dispatch feature text data are as follows: S11. Collect historical power load dispatch feature information of the target user end online through the power management platform, and generate user historical power load dispatch feature text data The user's historical power load dispatch feature text data includes the target user's historical annual single-month power forecast dispatch load information, historical annual single-month power actual dispatch load information, historical annual single-month power forecast dispatch load error ratio and user identity feature information; Preferably, the steps for establishing a user-side power load profile feature library based on the user's historical power load dispatch feature text data and the user load profile construction keywords and generating the user load profile feature library are as follows: S21. Build a user load profile and construct a keyword set , ;in Indicates the Build keywords for user load profiles, Indicates the maximum number of keywords for constructing a user load profile; the keywords for constructing a user load profile include keywords for power forecast and dispatch load for a single month in a historical year, keywords for actual power dispatch load for a single month in a historical year, keywords for error ratio of power forecast and dispatch load for a single month in a historical year, and keywords for user identity feature information; S22, using the KD tree nearest neighbor search algorithm to Construct a keyword set according to the user load profile Keywords for constructing user load profiles Search and classify the historical power load dispatch feature information of the user side, and build a user load profile feature library ,in Indicates the keywords for constructing the user load profile The corresponding user load profile feature data, the user load profile feature data represents the keyword constructed based on the set user load profile The user-specific personal historical power load dispatch classification and collation feature information is constructed.

[0007] Preferably, the steps for collecting user power load forecast time data are as follows: S31, collect the time characteristic information of the current year and specific month of the target user's power load dispatch forecast online through the power management platform, and generate the user's power load forecast time data ,in The unit consists of year and month.

[0008] Preferably, the steps of searching and processing the historical predicted power dispatching load information, the historical actual power dispatching load information, and the historical predicted power dispatching load error ratio information of the user-side power load forecast time according to the user power load forecast time data and the user load portrait feature library, and respectively generating the user historical predicted power dispatching load data, the user historical actual power dispatching load data, and the user historical predicted power dispatching load error ratio data are as follows: S41, the user power load forecast time data and the user load profile feature library User load profile characteristic data described in According to the time feature character matching, the predicted power dispatching load information of the historical year and month corresponding to the user-side power load forecast time, the actual power dispatching load information of the historical year and month, and the predicted power dispatching load error ratio information of the historical year and month are searched, and the user's historical predicted power dispatching load data set is generated respectively after data identification. , User historical actual power dispatch load data collection and the user's historical forecast power dispatch load error ratio data set , execute to generate the user's historical forecast power dispatch load data set , the user's historical actual power dispatch load data set and the user's historical prediction power dispatch load error ratio data set The specific steps are as follows: S411, initialize algorithm parameters, population size N, maximum number of iterations T; S412, initializing the population, calculating the fitness value, and determining the power load dispatch information search pathfinder and the power load dispatch information search follower; S413, according to the position formula In the user load profile feature library Update the power load dispatch information to search for the pathfinder position in the search space of , where t represents the current iteration number of the algorithm; represents the pathfinder for searching power load dispatch information after the tth iteration In the user load profile feature library The position in the search space, Represents the pathfinder for searching power load dispatch information after the t-1th iteration In the user load profile feature library The position in the search space of Represents the pathfinder for searching power load dispatch information after the t+1th iteration In the user load profile feature library The position in the search space, represents the step size factor of the pathfinder movement in the search for power load dispatch information and It obeys uniform distribution in [0,1]; S414, according to the position formula Update the power load dispatch information and search for followers in the user load profile feature database The position in the search space of Represents the power load dispatch information search follower after the tth iteration In the user load profile feature library The position in the search space of Indicates the power load dispatch information search follower after the t+1th iteration In the user load profile feature library The position in the search space of Represents the search followers of other power load dispatch information after the tth iteration In the user load profile feature library The position in the search space of the power load dispatch information search follower Mobile not only with power load dispatch information search pathfinder location Related to and subject to other power load dispatch information search follower location The impact of Represents the power load dispatch information search among followers in the user load profile feature database The position distance parameter in the search space of Indicates that the power load dispatch information search pathfinder and the power load dispatch information search follower are in the user load portrait feature library The position distance parameter in the search space of , ; represents the interaction coefficient between followers searching for power load dispatch information, represents the attraction coefficient of the power load dispatch information search pathfinder to the power load dispatch information search follower, 、 All are uniformly distributed within [1,2]; is the step size factor for the movement of the power load dispatch information search follower and other power load dispatch information search followers, is the step size factor for the power load dispatch information search follower and the power load dispatch information search pathfinder, 、 All are random numbers in the range [0,1]; S415: Calculate the user load profile feature library All the user load profile feature data in the search space Time data related to the user's power load forecast The fitness value and the user load profile feature library Update the search space to search for the user's power load forecast time data The most matching user load profile feature data Global optimal value; S416: When the maximum number of iterations is met, the output of the time data of the user's power load forecast that is searched out in step S415 is output. Matched user load profile feature data The corresponding historical annual single month forecast power dispatch load information, historical annual single month actual power dispatch load information and historical annual single month forecast power dispatch load error ratio information are processed to generate the user's historical forecast power dispatch load data set. , User historical actual power dispatch load data collection and the user's historical forecast power dispatch load error ratio data set ;in , ,in Indicates the search for the user's power load forecast time data The corresponding Historical forecast power dispatch load data of users in the same month of the historical year, Indicates the maximum value of the historical annual quantity; The unit is kilowatt; The larger the number value, the more historical forecast power dispatch load data of the user is collected. The predicted time data of the user's power load The larger the corresponding time interval; ,in Indicates the search for the user's power load forecast time data The corresponding The actual power dispatch load data of users in the same month of the historical year, The unit is kilowatt; ,in Indicates the search for the user's power load forecast time data The corresponding The historical forecast power dispatch load error ratio data of users in the same month of the historical year, ; The values ​​of include positive, negative and zero; A positive value indicates that the user's historical predicted power dispatch load is greater than the user's historical actual power dispatch load. A negative value indicates that the user's historical predicted power dispatch load is less than the user's historical actual power dispatch load. A value of zero indicates that the user's historical predicted power dispatch load is equal to the user's historical actual power dispatch load.

[0009] Preferably, the steps of performing numerical analysis and processing on the change trend of the historical predicted power dispatching load error ratio of the user-side power load forecast time based on the user historical predicted power dispatching load error ratio data and generating the user historical predicted power dispatching load error change weight data are as follows: S51. Obtain the user's historical predicted power dispatch load error ratio data set ; S52, using a linear regression algorithm to calculate the user's historical prediction power dispatch load error ratio data set The user's historical forecast power dispatch load error ratio data to Perform linear regression numerical analysis and measurement processing of the user's historical prediction of power dispatch load error ratio numerical change trend, and generate the user's historical prediction of power dispatch load error change weight data set ,in Indicates the The user's historical forecast power dispatch load error ratio data to Perform linear regression numerical analysis on the trend of the numerical change of the user's historical forecast power dispatch load error ratio and measure the generated weight data of the user's historical forecast power dispatch load error change; Indicates the The user's historical forecast power dispatch load error ratio data to Perform linear regression numerical analysis on the trend of the numerical change of the user's historical forecast power dispatch load error ratio and measure the generated weight data of the user's historical forecast power dispatch load error change; The user's historical prediction power dispatch load error change weight data represents the user's historical prediction power dispatch load error ratio data to Corresponding to Same month in historical year Numerical characteristic parameters of the change trend of the user's historical forecast power load dispatch error during the same month of the historical year; to The value of includes any one of positive, negative and zero; to A positive value indicates Same month in historical year During the same month of the historical year, the error degree of the user's historical forecast power load dispatch operation increased. to Negative values ​​indicate an upward Same month in historical year The error degree of the user's historical forecast power load dispatching operation during the same month of the historical year is reduced. to A value of zero indicates an upper Same month in historical year There is no error in the user's historical forecast power load dispatching operation during the same month of the historical year. to The value of is the same whether it is positive or negative.

[0010] Preferably, the steps of performing metering processing on the power theoretical actual dispatching load forecast result of the user-side power load forecast time based on the user's historical predicted power dispatching load data, the user's historical actual power dispatching load data, and the user's historical predicted power dispatching load error change weight data, and generating the user's power theoretical actual dispatching load forecast data are as follows: S61. Obtain the user's historical predicted power dispatch load data , the user's historical actual power dispatch load data , the user's historical prediction power dispatch load error change weight data , the user's historical prediction power dispatch load error change weight data ; S62, the user's historical prediction power dispatch load error ratio data , the user's historical actual power dispatch load data The weight data of the user's historical prediction of power dispatch load error change are respectively , the user's historical prediction power dispatch load error change weight data Perform numerical measurement processing on the power theoretical actual dispatch load forecast results of the user-side power load forecast time to generate the user power theoretical actual dispatch load forecast data ,in The measurement formula is as follows , wherein the user power theory actual dispatch load forecast data Represents the user's power load forecast time data The theoretical and actual power dispatch load forecast parameters corresponding to the specific month of the current year, Represents the user's power load forecast time data The theoretical forecast power dispatch load analysis parameters corresponding to the specific month of the current year, and All units are in kilowatts.

[0011] Preferably, the steps of constructing the user power load dispatch prediction result data and executing the user power load dispatch operation are as follows: S71, the user power load forecast time data , the user's theoretical actual dispatch load forecast data After data identification, the user power load dispatch prediction result data is constructed ,in ; S72, the power management platform dispatches the user's power load prediction result data The user power load forecast time and the user power dispatch load forecast parameters are used to execute the user power load dispatch operation.

[0012] An electric load intelligent dispatching system based on user load profiles is used to implement the electric load intelligent dispatching method based on user load profiles. The system includes a user load profile building module, a user electric load prediction module, and a user electric load dispatching module; The user load profile construction module includes a unit for collecting user historical power load dispatch feature information, a user load profile construction keyword storage unit, and a user load profile feature library establishment unit; The unit for collecting user historical power load dispatch feature information collects user historical power load dispatch feature text data through the power management platform; the user load portrait construction keyword storage unit is used to store user load portrait construction keywords; the user load portrait feature library establishment unit performs user-side power load portrait feature library establishment processing based on the user historical power load dispatch feature text data and the user load portrait construction keywords, and generates a user load portrait feature library; The user power load prediction module includes a user power load prediction time acquisition unit, a user history prediction power dispatching load information search unit, a user history actual power dispatching load information search unit, a user history prediction power dispatching load error ratio search unit, a user history prediction power dispatching load error change weight parameter measurement unit, and a user power dispatching load prediction unit; The user power load forecast time acquisition unit collects user power load forecast time data through the power management platform; the user historical forecast power dispatching load information search unit performs historical forecast power dispatching load search processing of the user-side power load forecast time according to the user power load forecast time data and the user load portrait feature library, and generates user historical forecast power dispatching load data; the user historical actual power dispatching load information search unit performs historical actual power dispatching load information search processing of the user-side power load forecast time according to the user power load forecast time data and the user load portrait feature library, and generates user historical actual power dispatching load data; the user historical forecast power dispatching load error ratio search unit performs historical forecast power dispatching load error ratio search processing of the user power load forecast time according to the user power load forecast time data and the user load portrait feature library, and generates user historical actual power dispatching load data. The user-end power load forecast time historical forecast power dispatching load error ratio information search and processing, and generate user historical forecast power dispatching load error ratio data; the user historical forecast power dispatching load error change weight parameter metering unit, based on the user historical forecast power dispatching load error ratio data, performs numerical analysis and processing on the change trend of the historical forecast power dispatching load error ratio of the user-end power load forecast time, and generates user historical forecast power dispatching load error change weight data; the user power dispatching load forecasting unit, based on the user historical forecast power dispatching load data, the user historical actual power dispatching load data, and the user historical forecast power dispatching load error change weight data, performs metering processing on the power theoretical actual dispatching load forecast result of the user-end power load forecast time, and generates user power theoretical actual dispatching load forecast data; The user power load scheduling module includes a user power load scheduling prediction result generating unit and a user power load scheduling execution unit; The user power load scheduling prediction result generation unit constructs user power load scheduling prediction result data based on user power load prediction time information and user power theoretical actual scheduling load prediction information; the user power load scheduling execution unit, the power management platform executes the user power load scheduling operation according to the user power load scheduling prediction result data.

[0013] (3) Beneficial effects The present invention provides a system and method for intelligent power load dispatching based on user load profiles. It has the following beneficial effects: 1. Accurately obtain the user's historical power load dispatch information through the power management platform to provide real data support for the refined construction of the user-side power load portrait feature library; based on the user's historical power load dispatch information, combined with intelligent search algorithms and scientifically preset user load portrait construction keywords, the user-side power load portrait feature library is efficiently and intelligently established, realizing intelligent and customized establishment of the user load portrait feature library, and improving the scientific nature of power load dispatch.

[0014] 2. Dynamically collect user power load forecast time information through the power management platform to provide reliable data support for accurate statistics of power load dispatching parameters at the forecast time; accurately classify, search and collect historical forecast power dispatching load information, historical actual power dispatching load information and historical forecast power dispatching load error ratio information of user-side power load forecast time based on user power load forecast time data combined with intelligent recognition algorithm and user load portrait feature library, so as to improve the efficiency and accuracy of power load dispatching; numerically count the change trend of historical forecast power dispatching load error ratio of user-side power load forecast time based on user historical forecast power dispatching load error ratio parameters combined with numerical processing, so as to realize digital and accurate prediction of power load dispatching parameters of user historical forecast power dispatching load error change trend; intelligently and accurately predict the actual power dispatching load forecast results of user-side power load forecast time based on user historical forecast power dispatching load parameters, user historical actual power dispatching load parameters and user historical forecast power dispatching load error change weight parameters, so as to realize scientific statistics of power load dispatching parameters based on user power dispatching load error change trend, and improve the accuracy and reliability of power load dispatching.

[0015] 3. By scientifically constructing the user power load dispatch prediction result parameters based on the user power load forecast time information, the user power theoretical actual dispatch load forecast information and combining data processing, the user power load dispatch prediction results can be collected in a timely and efficient manner; the power management platform can autonomously and accurately execute the user power load dispatch operation based on the user power load dispatch prediction result information, thereby improving the quality and applicability of power load dispatch. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of the modules of the power load intelligent dispatching system based on user load profiling provided by the present invention; Figure 2 This is a flow chart of the method for intelligent power load scheduling based on user load profiling provided by the present invention. DETAILED DESCRIPTION

[0017] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0018] The embodiments of the power load intelligent dispatching system and method based on user load profile are as follows: Example

[0019] See also Figure 1 - Figure 2 , an intelligent power load dispatching method based on user load profile, the method comprises the following steps: S1. Collecting historical power load dispatch feature text data of users; S2. Establishing and processing a user-side power load profile feature library based on the user's historical power load dispatch feature text data and the user load profile construction keywords, and generating a user load profile feature library; S3. Collecting user power load forecast time data; S4. Search and process the historical predicted power dispatching load information, historical actual power dispatching load information, and historical predicted power dispatching load error ratio information of the user-side power load forecast time based on the user power load forecast time data and the user load profile feature library, and generate user historical predicted power dispatching load data, user historical actual power dispatching load data, and user historical predicted power dispatching load error ratio data, respectively; S5. Perform numerical analysis and processing on the change trend of the historical predicted power dispatching load error ratio of the user-side power load forecast time based on the user's historical predicted power dispatching load error ratio data, and generate the user's historical predicted power dispatching load error change weight data; S6. Performing metering processing on the power theoretical actual dispatch load forecast result at the user-side power load forecast time based on the user's historical predicted power dispatch load data, the user's historical actual power dispatch load data, and the user's historical predicted power dispatch load error change weight data, and generating the user's power theoretical actual dispatch load forecast data; S7. Construct user power load dispatch prediction result data and execute user power load dispatch operation.

[0020] For further information, see Figure 1 - Figure 2 The steps for collecting the user's historical power load dispatch feature text data are as follows: S11. Collect historical power load dispatch feature information of the target user end online through the power management platform, and generate user historical power load dispatch feature text data ,The user historical power load dispatching feature text data includes the target user end’s historical annual single month power forecast dispatching load information, historical annual single month power actual dispatching load information, historical annual single month power forecast dispatching load error ratio, and user identity feature information; The steps for establishing and processing the user-side power load profile feature library are as follows: S21. Build a user load profile and construct a keyword set , ;in Indicates the Build keywords for user load profiles, Indicates the maximum number of keywords for constructing user load profiles; keywords for constructing user load profiles include keywords for historical monthly power forecast and dispatch loads, keywords for historical monthly power actual dispatch loads, keywords for historical monthly power forecast and dispatch load error ratios, and keywords for user identity feature information. S22, using the KD tree nearest neighbor search algorithm to convert the user's historical power load scheduling feature text data Build keyword collection based on user load profile Keywords for constructing user load profiles Search and classify the historical power load dispatch feature information of the user side, and build a user load profile feature library ,in Keywords for constructing user load profiles The corresponding user load profile feature data, which represents the keyword constructed based on the set user load profile The user-specific personal historical power load dispatch classification and collation feature information is constructed.

[0021] By collecting the user's historical power load dispatch feature information unit, the power management platform is used to accurately obtain the user's historical power load dispatch information, providing real data support for the refined construction of the user-side power load portrait feature library; the user load portrait feature library establishment unit, based on the user's historical power load dispatch information combined with the intelligent search algorithm and the scientifically preset user load portrait construction keywords, conducts efficient and intelligent establishment of the user-side power load portrait feature library, realizes intelligent and customized establishment of the user load portrait feature library, and improves the scientific nature of power load dispatch.

[0022] For further information, see Figure 1 - Figure 2 ,The steps for collecting user power load forecast time data are as follows: S31, collect the time characteristic information of the current year and specific month of the target user's power load dispatch forecast online through the power management platform, and generate the user's power load forecast time data ,in The unit consists of year and month.

[0023] The steps for searching and processing the historical predicted power dispatching load information, historical actual power dispatching load information, and historical predicted power dispatching load error ratio information of the user-side power load forecast time based on the user power load forecast time data and the user load profile feature library, and respectively generating the user's historical predicted power dispatching load data, the user's historical actual power dispatching load data, and the user's historical predicted power dispatching load error ratio data are as follows: S41, user power load forecast time data and user load profile feature library User load profile feature data According to the time feature character matching, the predicted power dispatching load information of the historical year and month corresponding to the user-side power load forecast time, the actual power dispatching load information of the historical year and month, and the predicted power dispatching load error ratio information of the historical year and month are searched, and the user's historical predicted power dispatching load data set is generated respectively after data identification. , User historical actual power dispatch load data collection and the user's historical forecast power dispatch load error ratio data set , execute to generate user historical forecast power dispatch load data set , User historical actual power dispatch load data collection and the user's historical forecast power dispatch load error ratio data set The specific steps are as follows: S411, initialize algorithm parameters, population size N, maximum number of iterations T; S412, initializing the population, calculating the fitness value, and determining the power load dispatch information search pathfinder and the power load dispatch information search follower; S413, according to the position formula In the user load profile feature library Update the power load dispatch information to search for the pathfinder position in the search space of , where t represents the current iteration number of the algorithm; represents the pathfinder for searching power load dispatch information after the tth iteration In the user load profile feature library The position in the search space of Represents the pathfinder for searching power load dispatch information after the t-1th iteration In the user load profile feature library The position in the search space of Represents the pathfinder for searching power load dispatch information after the t+1th iteration In the user load profile feature library The position in the search space of represents the step size factor of the pathfinder movement in the search for power load dispatch information and It obeys uniform distribution in [0,1]; S414, according to the position formula Update power load dispatch information and search followers in the user load profile feature library The position in the search space of Represents the power load dispatch information search follower after the tth iteration In the user load profile feature library The position in the search space of Indicates the power load dispatch information search follower after the t+1th iteration In the user load profile feature library The position in the search space of Represents the search followers of other power load dispatch information after the tth iteration In the user load profile feature library The position in the search space of the power load dispatch information search follower Mobile not only with power load dispatch information search pathfinder location Related to and subject to other power load dispatch information search follower location The impact of Represents the power load dispatch information search between followers in the user load profile feature database The position distance parameter in the search space of Indicates the relationship between the power load dispatch information search pathfinder and the power load dispatch information search follower in the user load profile feature library The position distance parameter in the search space of , ; represents the interaction coefficient between followers searching for power load dispatch information, represents the attraction coefficient of the power load dispatch information search pathfinder to the power load dispatch information search follower, 、 All are uniformly distributed within [1,2]; is the step size factor for the movement of the power load dispatch information search follower and other power load dispatch information search followers, is the step size factor for the power load dispatch information search follower and the power load dispatch information search pathfinder, 、 All are random numbers in the range [0,1]; S415. Calculate user load profile feature library All user load profile feature data in the search space and user power load forecast time data The fitness value is in the user load profile feature library Update the search space to find the time data related to the user's power load forecast The most matching user load profile feature data Global optimal value; S416: When the maximum number of iterations is met, the output of step S415 is searched out and the user's power load forecast time data is output. Matching user load profile feature data The corresponding historical annual single month forecast power dispatch load information, historical annual single month actual power dispatch load information and historical annual single month forecast power dispatch load error ratio information are processed to generate the user's historical forecast power dispatch load data set. , User historical actual power dispatch load data collection and the user's historical forecast power dispatch load error ratio data set ;in , ,in Represents the searched and user power load forecast time data The corresponding Historical forecast power dispatch load data of users in the same month of the historical year, Indicates the maximum value of the historical annual quantity; The unit is kilowatt; The larger the number value, the more historical forecast power dispatch load data of users is collected. Data on the time distance to user power load forecast The larger the corresponding time interval; ,in Represents the searched and user power load forecast time data The corresponding The actual power dispatch load data of users in the same month of the historical year, The unit is kilowatt; ,in Represents the searched and user power load forecast time data The corresponding The historical forecast power dispatch load error ratio data of users in the same month of the historical year, ; The values ​​of include positive, negative and zero; A positive value indicates that the user's historical predicted power dispatch load is greater than the user's historical actual power dispatch load. A negative value indicates that the user's historical predicted power dispatch load is less than the user's historical actual power dispatch load. A value of zero indicates that the user's historical predicted power dispatch load is equal to the user's historical actual power dispatch load.

[0024] The steps for performing numerical analysis and processing of the change trend of the historical forecast power dispatching load error ratio of the user-side power load forecast time based on the user's historical forecast power dispatching load error ratio data and generating the user's historical forecast power dispatching load error change weight data are as follows: S51. Obtaining a user's historical forecast power dispatch load error ratio data set ; S52, using linear regression algorithm to predict the user's historical power dispatch load error data set Historical forecast power dispatch load error ratio data for medium-sized users to Perform linear regression numerical analysis and measurement processing of the user's historical prediction of power dispatch load error ratio numerical change trend, and generate the user's historical prediction of power dispatch load error change weight data set ,in Indicates the The error ratio data of the user's historical power dispatch load prediction to Perform linear regression numerical analysis on the trend of the numerical change of the user's historical forecast power dispatch load error ratio and measure the generated weight data of the user's historical forecast power dispatch load error change; Indicates the The error ratio data of the user's historical power dispatch load prediction to Perform linear regression numerical analysis on the change trend of the user's historical prediction power dispatch load error ratio and generate the user's historical prediction power dispatch load error change weight data through metering processing; the user's historical prediction power dispatch load error change weight data represents the user's historical prediction power dispatch load error ratio data to The corresponding previous historical year same month to the previous Numerical characteristic parameters of the change trend of the user's historical forecast power load dispatch error during the same month of the historical year; to The value of includes any one of positive, negative and zero; to A positive value indicates Same month in historical year During the same month of the historical year, the error degree of the user's historical forecast power load dispatch operation increased. to Negative values ​​indicate an upward Same month in historical year The error degree of the user's historical forecast power load dispatching operation during the same month of the historical year is reduced. to A value of zero indicates an upper Same month in historical year There is no error in the user's historical forecast power load dispatching operation during the same month of the historical year. to The value of is the same whether it is positive or negative.

[0025] The steps for measuring and processing the power theoretical actual dispatch load forecast results at the user-side power load forecast time based on the user's historical predicted power dispatch load data, the user's historical actual power dispatch load data, and the user's historical predicted power dispatch load error change weight data, and generating the user's power theoretical actual dispatch load forecast data are as follows: S61. Obtaining historical forecasted power dispatch load data of users , User's historical actual power dispatch load data , User historical prediction power dispatch load error change weight data , User historical prediction power dispatch load error change weight data ; S62, the user's historical prediction of power dispatch load error ratio data , users' historical actual power dispatch load data Respectively with the user's historical prediction power dispatch load error change weight data , User historical prediction power dispatch load error change weight data Perform numerical measurement processing on the power theoretical actual dispatch load forecast results of the user-side power load forecast time to generate the user power theoretical actual dispatch load forecast data ,in The measurement formula is as follows , where the user's power theory actual dispatch load forecast data Indicates user power load forecast time data The theoretical and actual power dispatch load forecast parameters corresponding to the specific month of the current year, Indicates user power load forecast time data The theoretical forecast power dispatch load analysis parameters corresponding to the specific month of the current year, and All units are in kilowatts.

[0026] Through the user power load forecast time collection unit, the power management platform is used to dynamically collect user power load forecast time information, providing reliable data support for the accurate statistics of power load dispatching parameters during forecast time; the user historical forecast power dispatching load information search unit, the user historical actual power dispatching load information search unit and the user historical forecast power dispatching load error ratio search unit cooperate with each other, and according to the user power load forecast time data, the intelligent recognition algorithm and the user load portrait feature library are combined to accurately classify and search and collect the historical forecast power dispatching load information, historical actual power dispatching load information and historical forecast power dispatching load error ratio information of the user-end power load forecast time, so as to improve the efficiency and accuracy of power load dispatching; the user historical forecast power dispatching load error ratio is combined with the intelligent recognition algorithm and the user load portrait feature library to accurately classify and search and collect the historical forecast power dispatching load information, historical actual power dispatching load information and historical forecast power dispatching load error ratio information of the user-end power load forecast time, so as to improve the efficiency and accuracy of power load dispatching; The difference change weight parameter metering unit performs numerical statistics of the historical predicted power dispatching load error ratio change trend of the user-side power load forecast time based on the user's historical predicted power dispatching load error ratio parameter combined with numerical processing, so as to realize the digital and accurate prediction of the power load dispatching parameters of the user's historical predicted power dispatching load error change trend; the user power dispatching load prediction unit performs intelligent and accurate prediction of the power theoretical actual dispatching load prediction result of the user-side power load forecast time based on the user's historical predicted power dispatching load parameter, the user's historical actual power dispatching load parameter, and the user's historical predicted power dispatching load error change weight parameter, so as to realize scientific statistics of the power load dispatching parameters based on the user's power dispatching load error change trend, and improve the accuracy and reliability of power load dispatching.

[0027] For further information, see Figure 1 - Figure 2 The steps for constructing the user power load dispatch prediction result data and executing the user power load dispatch operation are as follows: S71, user power load forecast time data , User power theoretical actual dispatch load forecast data After data identification, the user power load dispatch prediction result data is constructed ,in ; S72, the power management platform dispatches the forecast result data based on the user's power load The user power load forecast time and the user power dispatch load forecast parameters are used to execute the user power load dispatch operation.

[0028] Through the user power load dispatch prediction result generation unit, the user power load dispatch prediction result parameters are scientifically constructed based on the user power load prediction time information, the user power theoretical actual dispatch load prediction information and data processing, so as to realize the timely and efficient collection of user power load dispatch prediction results; the user power load dispatch execution unit, the power management platform independently and accurately executes the user power load dispatch operation according to the user power load dispatch prediction result information, thereby improving the quality and applicability of power load dispatch.

[0029] See also Figure 1 - Figure 2 , an electric load intelligent dispatching system based on user load portrait, used to implement an electric load intelligent dispatching method based on user load portrait, the system includes a user load portrait construction module, a user electric load prediction module, and a user electric load dispatching module; The user load profile construction module includes a unit for collecting user historical power load dispatch feature information, a user load profile construction keyword storage unit, and a user load profile feature library establishment unit; A unit for collecting user historical power load dispatch feature information is used to collect user historical power load dispatch feature text data through the power management platform; a user load profile construction keyword storage unit is used to store user load profile construction keywords; a user load profile feature library establishment unit is used to establish and process the user-side power load profile feature library based on the user historical power load dispatch feature text data and the user load profile construction keywords, and generate a user load profile feature library; The user power load prediction module includes a user power load prediction time acquisition unit, a user history prediction power dispatching load information search unit, a user history actual power dispatching load information search unit, a user history prediction power dispatching load error ratio search unit, a user history prediction power dispatching load error change weight parameter measurement unit, and a user power dispatching load prediction unit; The user power load forecast time collection unit collects the user power load forecast time data through the power management platform; the user historical forecast power dispatching load information search unit performs historical forecast power dispatching load search processing of the user-side power load forecast time according to the user power load forecast time data and the user load portrait feature library, and generates the user historical forecast power dispatching load data; the user historical actual power dispatching load information search unit performs historical actual power dispatching load information search processing of the user-side power load forecast time according to the user power load forecast time data and the user load portrait feature library, and generates the user historical actual power dispatching load data; the user historical forecast power dispatching load error ratio search unit performs historical forecast power dispatching load error ratio search processing of the user-side power load forecast time according to the user power load forecast time data and the user load portrait feature library The historical prediction power dispatching load error ratio information of the load forecast time is searched and processed, and the user's historical prediction power dispatching load error ratio data is generated; the user's historical prediction power dispatching load error change weight parameter metering unit performs numerical analysis and processing on the historical prediction power dispatching load error ratio change trend of the user-side power load forecast time based on the user's historical prediction power dispatching load error ratio data, and generates the user's historical prediction power dispatching load error change weight data; the user power dispatching load prediction unit performs metering and processing on the power theoretical actual dispatching load prediction result of the user-side power load forecast time based on the user's historical prediction power dispatching load data, the user's historical actual power dispatching load data, and the user's historical prediction power dispatching load error change weight data, and generates the user's power theoretical actual dispatching load prediction data; The user power load dispatch module includes a user power load dispatch prediction result generating unit and a user power load dispatch executing unit; The user power load dispatching prediction result generation unit constructs the user power load dispatching prediction result data based on the user power load forecast time information and the user power theoretical actual dispatching load forecast information; the user power load dispatching execution unit, the power management platform executes the user power load dispatching operation according to the user power load dispatching prediction result data.

[0030] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. The intelligent dispatching method of power load based on user load profile is characterized by: The method comprises the following steps: S1. Collecting historical power load dispatch feature text data of users; S2. Establishing and processing the user-side power load profile feature library and generating the user load profile feature library; S3. Collecting user power load forecast time data; S4, searching and processing the historical predicted power dispatching load information, the historical actual power dispatching load information, and the historical predicted power dispatching load error ratio information of the user-side power load forecast time, and generating the user's historical predicted power dispatching load data, the user's historical actual power dispatching load data, and the user's historical predicted power dispatching load error ratio data respectively; S5. Perform numerical analysis and processing on the change trend of the historical forecast power dispatching load error ratio of the user-side power load forecast time, and generate weight data of the change of the user's historical forecast power dispatching load error; S6. Perform metering processing on the power theoretical actual dispatch load forecast result at the user-side power load forecast time, and generate user power theoretical actual dispatch load forecast data; S7. Construct user power load dispatch prediction result data and execute user power load dispatch operation.

2. The method for intelligent power load dispatching based on user load profile according to claim 1 is characterized in that: Said S1 comprises the following steps: S11. Collect historical power load dispatch feature information of the target user end online through the power management platform, and generate user historical power load dispatch feature text data .

3. The method for intelligent power load dispatching based on user load profile according to claim 2 is characterized in that: The S2 comprises the following steps: S21. Build a user load profile and construct a keyword set , ;in Indicates the Build keywords for user load profiles, Indicates the maximum number of keywords used to construct the user load profile; S22, using KD tree nearest neighbor search algorithm to As described As stated in Search and classify the historical power load dispatch feature information of the user side, and build a user load profile feature library ,in Indicates the The corresponding user load profile characteristic data, the user load profile characteristic data represents the The user-specific personal historical power load dispatch classification and collation feature information is constructed.

4. The method for intelligent power load dispatching based on user load profile according to claim 3 is characterized by: The S3 includes the following steps: S31, collect the time characteristic information of the current year and specific month of the target user's power load dispatch forecast online through the power management platform, and generate the user's power load forecast time data ,in The unit consists of year and month.

5. The method for intelligent power load dispatching based on user load profile according to claim 4 is characterized in that: The S4 comprises the following steps: S41, the With the As stated in According to the time feature character matching, the predicted power dispatching load information of the historical year and month corresponding to the user-side power load forecast time, the actual power dispatching load information of the historical year and month, and the predicted power dispatching load error ratio information of the historical year and month are searched, and the user's historical predicted power dispatching load data set is generated respectively after data identification. , User historical actual power dispatch load data collection and the user's historical forecast power dispatch load error ratio data set , execute to generate the user's historical forecast power dispatch load data set , the user's historical actual power dispatch load data set and the user's historical prediction power dispatch load error ratio data set The specific steps are as follows: S411, initialize algorithm parameters, population size N, maximum number of iterations T; S412, initializing the population, calculating the fitness value, and determining the power load dispatch information search pathfinder and the power load dispatch information search follower; S413, according to the position formula Update the power load dispatch information in the search space to search for the pathfinder position; S414, update the power load dispatch information according to the position formula and search for followers in the The position in the search space of S415, calculate the All the above in the search space With the The fitness value, and in the Update the search space to find the The best match Global optimal value; S416, when the maximum number of iterations is met, the output step S415 searches for the Matching the The corresponding historical annual single month forecast power dispatch load information, historical annual single month actual power dispatch load information and historical annual single month forecast power dispatch load error ratio information are processed to generate the user's historical forecast power dispatch load data set. , User historical actual power dispatch load data collection and the user's historical forecast power dispatch load error ratio data set ;in , ,in Indicates the search result and the The corresponding Historical forecast power dispatch load data of users in the same month of the historical year, Indicates the maximum value of the historical annual quantity; The unit is kilowatt; The larger the number, the more Distance The larger the corresponding time interval; ,in Indicates the search result and the The corresponding The actual power dispatch load data of users in the same month of the historical year, The unit is kilowatt; ,in Indicates the search for the user's power load forecast time data The corresponding The historical forecast power dispatch load error ratio data of users in the same month of historical years.

6. The method for intelligent power load dispatching based on user load profile according to claim 5 is characterized in that: The S5 comprises the following steps: S51, obtain the ; S52, using linear regression algorithm to As stated in to Perform linear regression numerical analysis and measurement processing of the user's historical prediction of power dispatch load error ratio numerical change trend, and generate the user's historical prediction of power dispatch load error change weight data set ,in Indicates the times the to Perform linear regression numerical analysis on the trend of the numerical change of the user's historical forecast power dispatch load error ratio and measure the generated weight data of the user's historical forecast power dispatch load error change; Indicates the times the to Perform linear regression numerical analysis on the numerical change trend of the user's historical predicted power dispatch load error ratio and measure the generated user's historical predicted power dispatch load error change weight data.

7. The method for intelligent power load dispatching based on user load profile according to claim 6, characterized in that: The S6 comprises the following steps: S61, obtain the 、 、 、 ; S62, the 、 Respectively with the 、 Perform numerical measurement processing on the power theoretical actual dispatch load forecast results of the user-side power load forecast time to generate the user power theoretical actual dispatch load forecast data ,in The measurement formula is as follows , wherein Indicates the The theoretical and actual power dispatch load forecast parameters corresponding to the specific month of the current year, Indicates the The theoretical forecast power dispatch load analysis parameters corresponding to the specific month of the current year, and All units are in kilowatts.

8. The method for intelligent power load dispatching based on user load profile according to claim 7 is characterized in that: The S7 comprises the following steps: S71, the 、 After data identification, the user power load dispatch prediction result data is constructed ; S72, the power management platform is based on The user power load forecast time and the user power dispatch load forecast parameters are used to execute the user power load dispatch operation.

9. An intelligent power load dispatching system based on user load profiles, used to implement the intelligent power load dispatching method based on user load profiles according to any one of claims 1 to 8, characterized in that: The system includes a user load profile building module, a user power load prediction module, and a user power load scheduling module.

Images