A resource allocation method and system based on a virtual power plant

Abstract

The present invention relates to a resource allocation method and system based on a virtual power plant, belonging to the field of power technology. The method includes: respectively obtaining the power basic data corresponding to different historical time periods in the area covered by the virtual power plant; analyzing the power basic data to obtain the power analysis data corresponding to the power basic data in different historical time periods; constructing an initial power prediction model according to the power analysis data; obtaining the fluctuation coefficient corresponding to the power prediction model to correct the initial power prediction model and obtain a target power prediction model; performing supply-demand balance prediction based on the target power prediction model and the power data corresponding to the current time period, and allocating power resources according to the prediction result. The present invention can further effectively schedule and allocate power resources.

Description

Technical Field

[0001] The present invention relates to the technical field of electric power, and particularly to a resource allocation method and system based on a virtual power plant. Background Art

[0002] With the large-scale growth of various virtual power plant business data, due to the lack of large-scale data processing capabilities, traditional business routing and network resource allocation methods are less efficient in solving the scheduling of massive data resources. Moreover, a large number of user-side distributed adjustable flexible resources are connected to the distribution network side of the virtual power plant, such as distributed photovoltaic power generation, decentralized wind power generation, electric vehicle charging piles, and commercial building loads. Currently, the general method for unified regulation of distributed flexible resources is simulation regulation, and the adopted method is: through the power generation curves of each flexible resource (distributed photovoltaic power generation, decentralized wind power generation, electric vehicle charging piles, and commercial building loads) for simulation. However, when using the above method, there is usually a problem that corresponding power resource models are not established for different flexible resources, resulting in inaccurate simulated power information and being unfavorable for the scheduling of power resources.

[0003] Therefore, there is an urgent need to propose a resource allocation method and system based on a virtual power plant that can effectively schedule power resources. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a resource allocation method and system based on a virtual power plant that can effectively schedule power resources.

[0005] In a first aspect, a resource allocation method based on a virtual power plant is provided. The method includes: respectively obtaining power basic data corresponding to different historical time periods in the area covered by the virtual power plant, where the power basic data at least includes power demand data and power supply data; analyzing the power basic data to obtain power analysis data corresponding to the power basic data in different historical time periods; constructing an initial power prediction model according to the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model; obtaining fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; and performing supply-demand balance prediction based on the target power prediction model and the power data corresponding to the current time period, and allocating power resources according to the prediction result.

[0006] Optionally, analyzing the power basic data to obtain power analysis data corresponding to the power basic data in different historical time periods includes: performing data cleaning on the power basic data, where the data cleaning process at least includes handling missing values, outlier detection, and consistency checking of the power basic data; performing normalization processing on the data after data cleaning to obtain the power basic data after normalization processing; and analyzing the power basic data after normalization processing to obtain power analysis data corresponding to the power basic data in different historical time periods.

[0007] Optionally, analyzing the power basic data after normalization processing to obtain power analysis data corresponding to the power basic data in different historical time periods includes: respectively calculating and determining target values corresponding to the power demand data and power supply data after normalization processing based on an objective function, where the objective function includes:

[0008] ;

[0009] where, represents the target value, represents the number of data elements, represents the th weight coefficient of the data element, represents the th normalized value of the data element, represents the constant coefficient; defining the target value corresponding to the power demand data greater than a first preset value as the first target value, and defining the target value corresponding to the power supply data greater than a second preset value as the second target value; respectively performing a first marking on the historical time periods corresponding to the first target value and the second target value; in response to detecting that both the first target value and the second target value exist simultaneously in the target historical time period marked once, performing a second marking on the target historical time period; respectively selecting correlation indicators corresponding to the power demand data and power supply data in the target historical time period, and calculating a correlation value based on the correlation indicators, where the calculation formula of the correlation value includes:

[0010] ;

[0011] ;

[0012] where, represents the correlation value, represents the correlation indicator 、 's correlation coefficient, represents time, represents the time coefficient corresponding to the target historical time period, represents the correlation indicator Rate of change represents the associated indicator Rate of change; in response to detecting that the associated value is greater than the third preset value, the target historical time period is marked three times, and the target historical time period after the three marks, as well as the associated value and target value corresponding to the target historical time period, are mapped to generate the power analysis data and saved.

[0013] Optionally, constructing an initial power prediction model based on the power analysis data includes: constructing a first power demand prediction model and a first power supply prediction model; dividing the power analysis data into a training set and a validation set, and training and validating the first power demand prediction model and the first power supply prediction model respectively; when it is detected that the verification result reaches the preset standard, outputting a second power demand prediction model and a second power supply prediction model, and defining the second power demand prediction model and the second power supply prediction model as the initial power prediction model.

[0014] Optionally, the expression of the second power demand prediction model includes:

[0015] ;

[0016] where represents the demand prediction value, represents the number of time periods within a time cycle, represents the time period probability of increased demand, represents the ratio of the associated value to the target value of the power demand data, represents the correction function of the power demand prediction model.

[0017] Optionally, the expression of the second power supply prediction model includes:

[0018] ;

[0019] where represents the supply prediction value, represents the time period probability of increased supply, represents the ratio of the associated value to the target value of the power supply data, represents the correction function of the power supply prediction model.

[0020] Optionally, obtaining the fluctuation coefficient corresponding to the power prediction model to correct the initial power prediction model to obtain the target power prediction model includes: obtaining the relevant parameters of the renewable energy power generation stations in the area covered by the virtual power plant, and determining the fluctuation coefficient of the second power supply prediction model based on the relevant parameters of the renewable energy power generation stations; determining the correction function of the power supply prediction model based on the fluctuation coefficient of the second power supply prediction model to correct the second power supply prediction model, where the correction function of the power supply prediction model includes:

[0021] ;

[0022] where, represents the number of renewable energy power generation stations, represents the th probability of generating a power generation error for a renewable energy power generation station, represents the weight coefficient, represents the correction coefficient; obtaining the power consumption parameters of the user side in different time periods in the area covered by the virtual power plant, and determining the fluctuation coefficient of the second power demand prediction model based on the power consumption parameters of the user side in different time periods; determining the correction function of the power demand prediction model based on the fluctuation coefficient of the second power demand prediction model to correct the second power demand prediction model, where the correction function of the power demand prediction model includes:

[0023] ;

[0024] where, represents the season attribute, represents the th probability of generating a power consumption deviation in a season, represents the weight coefficient, represents the correction coefficient; defining the corrected second power demand prediction model and the second power supply prediction model as the target power prediction model.

[0025] Optionally, based on the target power prediction model and the power data corresponding to the current time period, performing supply-demand balance prediction and allocating power resources according to the prediction result includes: obtaining the power data of the current time period and inputting the power data into the target power prediction model to obtain a demand prediction value and a supply prediction value; in response to detecting that the difference between the demand prediction value and the supply prediction value is greater than the fourth preset value, determining that the current supply and demand are unbalanced and supplying power based on the stored power resources; in response to detecting that the difference between the demand prediction value and the supply prediction value is less than the fourth preset value, determining that the current supply and demand are unbalanced and storing the power resources.

[0026] In a second aspect, a resource allocation system based on a virtual power plant is provided. The device includes: a data acquisition module configured to respectively obtain power basic data corresponding to different historical time periods in the area covered by the virtual power plant, where the power basic data at least includes power demand data and power supply data; a data analysis module configured to analyze the power basic data to obtain power analysis data corresponding to the power basic data in different historical time periods; a model construction module configured to construct an initial power prediction model according to the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model; a model correction module configured to obtain a fluctuation coefficient corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficient respectively includes a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; and a resource allocation module configured to perform a supply-demand balance prediction based on the target power prediction model and the power data corresponding to the current time period, and allocate power resources according to the prediction result.

[0027] Optionally, analyzing the normalized power basic data to obtain power analysis data corresponding to the power basic data in different historical time periods includes: respectively calculating and determining target values corresponding to the normalized power demand data and power supply data based on an objective function, where the objective function includes:

[0028] ;

[0029] where, represents the target value, represents the number of data elements, represents the weight coefficient of the th data element, represents the th data element's normalized value, represents a constant coefficient; defining the target value corresponding to the power demand data greater than a first preset value as a first target value, and defining the target value corresponding to the power supply data greater than a second preset value as a second target value; respectively performing a first marking on the historical time periods corresponding to the first target value and the second target value; in response to detecting that both the first target value and the second target value exist simultaneously in the target historical time period marked once, performing a second marking on the target historical time period; respectively selecting correlation indicators corresponding to the power demand data and the power supply data in the target historical time period, and calculating a correlation value based on the correlation indicators, where the calculation formula of the correlation value includes:

[0030] ;

[0031] ;

[0032] Among them, represents the associated value, represents the associated index and the correlation coefficient of represents time, represents the time coefficient corresponding to the target historical time period, represents the associated index the change rate of represents the associated index the change rate of; in response to detecting that the associated value is greater than a third preset value, the target historical time period is marked three times, and the target historical time period after three markings, as well as the associated value and the target value corresponding to the target historical time period, are mapped to generate the power analysis data and saved.

[0033] In a third aspect, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: respectively obtain the power basic data corresponding to different historical time periods in the area covered by the virtual power plant, where the power basic data at least includes power demand data and power supply data; analyze the power basic data to obtain the power analysis data corresponding to the power basic data in different historical time periods; construct an initial power prediction model according to the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model; obtain the fluctuation coefficient corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficient respectively includes a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; perform a supply-demand balance prediction based on the target power prediction model and the power data corresponding to the current time period, and allocate power resources according to the prediction result.

[0034] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: respectively obtain the power basic data corresponding to different historical time periods in the area covered by the virtual power plant, where the power basic data at least includes power demand data and power supply data; analyze the power basic data to obtain the power analysis data corresponding to the power basic data in different historical time periods; construct an initial power prediction model according to the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model; obtain the fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; perform a supply-demand balance prediction based on the target power prediction model and the power data corresponding to the current time period, and allocate power resources according to the prediction result.

[0035] Fifthly, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the following steps are implemented: respectively obtain the power basic data corresponding to different historical time periods in the area covered by the virtual power plant, where the power basic data at least includes power demand data and power supply data; analyze the power basic data to obtain the power analysis data corresponding to the power basic data in different historical time periods; construct an initial power prediction model according to the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model; obtain the fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; perform a supply-demand balance prediction based on the target power prediction model and the power data corresponding to the current time period, and allocate power resources according to the prediction result.

[0036] The above-mentioned resource allocation method and system based on a virtual power plant, the method comprising: respectively obtaining power basic data corresponding to different historical time periods in the area covered by the virtual power plant, the power basic data at least including power demand data and power supply data; analyzing the power basic data to obtain power analysis data corresponding to the power basic data in different historical time periods; constructing an initial power prediction model according to the power analysis data, wherein the power prediction model at least includes a power demand prediction model and a power supply prediction model; obtaining fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, wherein the fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; performing supply-demand balance prediction based on the target power prediction model and the power data corresponding to the current time period, and performing power resource allocation according to the prediction result. The present invention can improve the power data processing efficiency and the accuracy of supply-demand balance prediction based on constructing a relevant power resource model, and thus can effectively schedule and allocate power resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 FIG. is an application environment diagram of a resource allocation method based on a virtual power plant in an embodiment;

[0038] Figure 2 FIG. is a flowchart of a resource allocation method based on a virtual power plant in an embodiment;

[0039] Figure 3 FIG. is a structural block diagram of a resource allocation system based on a virtual power plant in an embodiment;

[0040] Figure 4 FIG. is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0041] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] It should be understood that in the description of the present invention, unless otherwise clearly required by the context, the words such as "including" and "comprising" throughout the specification should be interpreted in an inclusive sense rather than an exclusive or exhaustive sense; that is, it is the meaning of "including but not limited to".

[0043] It should also be understood that the terms "first", "second", etc. are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more.

[0044] It should be noted that the terms "S1", "S2", etc. are used only for the purpose of describing steps, and do not specifically refer to the order or sequence. Nor are they used to limit the present invention. They are merely for the convenience of describing the method of the present invention and should not be construed as indicating the order of steps. Additionally, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0045] The resource allocation method based on a virtual power plant provided by the present invention can be applied to, for example Figure 1 the application environment shown. Among them, the terminal 102 communicates with the data processing platform set on the server 104 through the network. Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices, and the server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0046] In one embodiment, as Figure 2 shown, a resource allocation method based on a virtual power plant is provided. Taking the terminal in Figure 1 as an example for illustration, it includes the following steps:

[0047] S1: Obtain the corresponding power basic data of the area covered by the virtual power plant in different historical time periods respectively. The power basic data at least includes power demand data and power supply data.

[0048] It should be noted that different historical time periods can be different time periods within a historical time cycle. The historical time cycle can be one year, half a year, or one month. The time period can be one day or one week in a year, etc., which can be selected according to actual needs. A virtual power plant refers to a power coordination management system that aggregates and coordinately optimizes distributed energy resources (DERs) such as energy storage systems, controllable loads, and electric vehicles through information and communication technologies and software systems to participate in the power market and grid operation as a special power plant. The basic power data mainly includes: 1. Data of power generation equipment, such as parameters of the unit's power, voltage, current, frequency, etc., as well as the number and attributes of power generation equipment. The attributes include wind power generation, solar power generation, coal power generation, etc.; 2. Energy market environment data, such as the market electricity price and load forecast on the same day; 3. Weather and meteorological data, such as parameters of temperature, humidity, wind speed, and wind direction; 4. User load data, such as user electricity consumption and electricity usage time. The present invention mainly uses user load data related to power demand data and power generation equipment related data related to power supply data. The above data is mainly obtained from the historical database.

[0049] S2: Analyze the basic power data to obtain power analysis data corresponding to the basic power data in different historical time periods.

[0050] It should be noted that analyzing the basic power data includes performing dimensionless processing on the data and calculating the corresponding target values and correlation values to improve the robustness of subsequent model training.

[0051] In some specific embodiments, analyzing the basic power data to obtain power analysis data corresponding to the basic power data in different historical time periods includes: performing data cleaning on the basic power data. The data cleaning process at least includes processing missing values, outlier detection, and consistency checking of the basic power data. This cleaning process is a common method and will not be elaborated here; performing normalization processing on the data after data cleaning to obtain the normalized basic power data. Among them, the normalization processing process is a common method and will not be elaborated here; analyzing the normalized basic power data to obtain power analysis data corresponding to the basic power data in different historical time periods, including: based on the objective function, respectively calculating and determining the target values corresponding to the normalized power demand data and power supply data. The objective function includes:

[0052] ;

[0053] Among them, represents the target value, represents the number of data elements, represents the th weight coefficient of the data element, represents the normalized value of the th data element, represents the constant coefficient.

[0054] Define the target value corresponding to the power demand data greater than the first preset value as the first target value, and define the target value corresponding to the power supply data greater than the second preset value as the second target value. Among them, the objective function can be used to calculate the target values corresponding to the power demand data and the power supply data respectively. This operation can be executed through two threads. The first preset value and the second preset value can both be set according to actual needs; Mark the historical time periods corresponding to the first target value and the second target value once respectively, and store them classified. Among them, the marker can be set according to actual needs, such as "1 - First target value - time period", "1 - Second target value - time period", etc.; In response to detecting that both the first target value and the second target value exist simultaneously within the target historical time period marked once, perform a secondary mark on the target historical time period, that is, if the historical time periods corresponding to the first target value and the second target value are both marked and their historical time periods belong to the same time period, then perform a secondary mark on this time period; Select the correlation indicators corresponding to the power demand data and the power supply data within the target historical time period respectively. Based on the correlation indicators, calculate the correlation value. Among them, the correlation indicators can be the power generation of the unit, the electricity consumption of users, etc., and the corresponding correlation indicators can be selected according to actual needs. The calculation formula of the correlation value includes:

[0055] ;

[0056] ;

[0057] Among them, represents the correlation value, represents the correlation indicator , the correlation coefficient of represents time, represents the time coefficient corresponding to the target historical time period, represents the correlation indicator the change rate of represents the correlation indicator the change rate of ; In response to detecting that the correlation value is greater than the third preset value, perform a third mark on the target historical time period. Map the target historical time period after the third mark, as well as the correlation value and the target value corresponding to the target historical time period, to generate the power analysis data, and save it. Among them, the third preset value can be set according to actual needs.

[0058] S3: Construct an initial power prediction model based on the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model.

[0059] It should be noted that the initial models corresponding to the power demand prediction model and the power supply prediction model are the second power demand prediction model and the second power supply prediction model respectively.

[0060] In some specific embodiments, constructing an initial power prediction model based on the power analysis data includes: constructing a first power demand prediction model and a first power supply prediction model; dividing the power analysis data into a training set and a validation set, and training and validating the first power demand prediction model and the first power supply prediction model respectively, where the division ratio of the validation set to the training set can be 7:3; when it is detected that the validation result reaches a preset standard, output the second power demand prediction model and the second power supply prediction model, and define the second power demand prediction model and the second power supply prediction model as the initial power prediction model, where the preset standard can be that the prediction accuracy reaches a set value, or the number of training times reaches a set value, etc.

[0061] Specifically, the expression of the second power demand prediction model includes:

[0062] ;

[0063] where, represents the demand prediction value, represents the number of time periods within a time cycle, represents the time period the probability of demand increase occurring, represents the ratio of the associated value of the power demand data to the target value, represents the correction function of the power demand prediction model.

[0064] And, the expression of the second power supply prediction model includes:

[0065] ;

[0066] where, represents the supply prediction value, represents the time period the probability of supply increase occurring, represents the ratio of the associated value of the power supply data to the target value, represents the correction function of the power supply prediction model.

[0067] Among them, during the initial training, the values corresponding to the above correction functions are all constant values set according to past data.

[0068] S4: Obtain the fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient.

[0069] It should be noted that there may be peak-valley or seasonal changes on the power demand side, thus generating corresponding fluctuation coefficients. On the power supply side, corresponding fluctuation coefficients may be generated due to characteristics such as intermittency or randomness of some renewable energy power generation stations (such as wind power stations and photovoltaic power stations, etc.), resulting in prediction errors. Based on this, using the fluctuation coefficients to correct the model can improve the model prediction accuracy.

[0070] In some specific embodiments, obtaining the fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model includes: obtaining the relevant parameters of the renewable energy power generation stations in the area covered by the virtual power plant, and determining the fluctuation coefficients of the second power supply prediction model based on the relevant parameters of the renewable energy power generation stations, where the relevant parameters may include the number of power generation stations, the probability of generating power generation errors for each power generation station, etc., and defining the relevant parameters as the corresponding fluctuation coefficients; based on the fluctuation coefficients of the second power supply prediction model, determining the correction function of the power supply prediction model to correct the second power supply prediction model, where the correction function of the power supply prediction model includes:

[0071] ;

[0072] where represents the number of renewable energy power generation stations, represents the th probability of generating power generation errors for the renewable energy power generation station, represents the weight coefficient, represents the correction coefficient.

[0073] Obtain the power consumption parameters of the user side in different time periods in the area covered by the virtual power plant, and determine the fluctuation coefficients of the second power demand prediction model based on the power consumption parameters of the user side in different time periods, where the power consumption parameters may include the season (such as spring, etc.) when the power consumption data is collected, the probability of generating power consumption deviations for each season, etc., and defining the power consumption parameters as the corresponding fluctuation coefficients; based on the fluctuation coefficients of the second power demand prediction model, determining the correction function of the power demand prediction model to correct the second power demand prediction model, where the correction function of the power demand prediction model includes:

[0074] ;

[0075] Among them, represents the seasonal attribute, represents the probability of power consumption deviation generated in the [n]th season, represents the weight coefficient, represents the correction coefficient; the corrected second power demand prediction model and the second power supply prediction model are defined as the target power prediction model.

[0076] S5: Based on the target power prediction model and the power data corresponding to the current time period, perform a supply-demand balance prediction, and allocate power resources according to the prediction result.

[0077] It should be noted that the power data corresponding to the current time period can be the same type of data as the above-mentioned basic power data, and it is obtained in real time through acquisition devices such as sensors.

[0078] In some specific embodiments, based on the target power prediction model and the power data corresponding to the current time period, performing a supply-demand balance prediction and allocating power resources according to the prediction result includes: obtaining the power data of the current time period, and inputting the power data into the target power prediction model to obtain a demand prediction value and a supply prediction value; in response to detecting that the difference between the demand prediction value and the supply prediction value is greater than a fourth preset value, determining that the current supply and demand is unbalanced, and supplying power based on the stored power resources; in response to detecting that the difference between the demand prediction value and the supply prediction value is less than the fourth preset value, determining that the current supply and demand is unbalanced, and storing the power resources.

[0079] Among them, the difference between the demand prediction value and the supply prediction value refers to the difference obtained by subtracting the supply prediction value from the demand prediction value. The fourth preset value can be set according to actual needs. When the difference is greater than the fourth preset value, it can be determined that the current real-time power generation is insufficient to meet the user-side demand, and it is necessary to supply power to the user-side based on the electric energy pre-stored in the energy storage power station. When the difference is less than the fourth preset value, it can be determined that the current user-side demand is less than the real-time power generation. At this time, the excess electric energy (such as electric energy generated by new energy sources such as photovoltaics) is stored in the energy storage power station for subsequent use.

[0080] In the above resource allocation method based on a virtual power plant, the method includes: respectively obtaining the power basic data corresponding to different historical time periods in the area covered by the virtual power plant, where the power basic data at least includes power demand data and power supply data; analyzing the power basic data to obtain the power analysis data corresponding to the power basic data in different historical time periods; constructing an initial power prediction model according to the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model; obtaining the fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; based on the target power prediction model and the power data corresponding to the current time period, performing a supply-demand balance prediction, and allocating power resources according to the prediction result. The present invention can improve the power data processing efficiency and the supply-demand balance prediction accuracy based on constructing a relevant power resource model, and thus can effectively schedule and allocate power resources.

[0081] It should be understood that although Figure 2 each step in the flowchart of Figure 2 is shown in sequence according to the indication of the arrow, these steps do not necessarily have to be executed in the order indicated by the arrow. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover,

[0082] In one embodiment, as Figure 3As shown in the figure, a resource allocation system based on a virtual power plant is provided, including: a data acquisition module, a data analysis module, a model construction module, a model correction module, and a resource allocation module, where: The data acquisition module is used to respectively obtain the power basic data corresponding to different historical time periods in the area covered by the virtual power plant, and the power basic data at least includes power demand data and power supply data; The data analysis module is used to analyze the power basic data to obtain the power analysis data corresponding to the power basic data in different historical time periods; The model construction module is used to construct an initial power prediction model according to the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model; The model correction module is used to obtain the fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; The resource allocation module is used to perform a supply-demand balance prediction based on the target power prediction model and the power data corresponding to the current time period, and allocate power resources according to the prediction result.

[0083] As a preferred implementation manner, in the embodiment of the present invention, the data analysis module is specifically used for: performing data cleaning on the power basic data, and the data cleaning process at least includes processing missing values, outlier detection, and consistency checking of the power basic data; performing normalization processing on the data after data cleaning to obtain the power basic data after normalization processing; analyzing the power basic data after normalization processing to obtain the power analysis data corresponding to the power basic data in different historical time periods.

[0084] As a preferred implementation manner, in the embodiment of the present invention, the data analysis module is specifically further used for: respectively calculating and determining the target values corresponding to the normalized power demand data and power supply data based on the objective function, and the objective function includes:

[0085] ;

[0086] Wherein, represents the target value, represents the number of data elements, represents the th weight coefficient of the data element, represents the th normalized value of the data element, represents a constant coefficient; define the target value corresponding to the power demand data greater than the first preset value as the first target value, and define the target value corresponding to the power supply data greater than the second preset value as the second target value; perform a first marking on the historical time periods corresponding to the first target value and the second target value respectively; in response to detecting that both the first target value and the second target value exist simultaneously in the target historical time period marked once, perform a second marking on the target historical time period; respectively select the correlation indicators corresponding to the power demand data and the power supply data within the target historical time period, and based on the correlation indicators, calculate the correlation value, and the calculation formula of the correlation value includes:

[0087] ;

[0088] ;

[0089] wherein, represents the correlation value, represents the correlation indicator 、 is the correlation coefficient of, represents time, represents the time coefficient corresponding to the target historical time period, represents the correlation indicator is the change rate of, represents the correlation indicator is the change rate of; in response to detecting that the correlation value is greater than the third preset value, perform a third marking on the target historical time period, map the target historical time period after the third marking, as well as the correlation value and the target value corresponding to the target historical time period, to generate the power analysis data, and save it.

[0090] As a preferred implementation manner, in the embodiment of the present invention, the model construction module is specifically used for: constructing a first power demand prediction model and a first power supply prediction model; dividing the power analysis data into a training set and a validation set, and respectively training and validating the first power demand prediction model and the first power supply prediction model; in response to detecting that the verification result reaches the preset standard, output a second power demand prediction model and a second power supply prediction model, and define the second power demand prediction model and the second power supply prediction model as the initial power prediction model, wherein the expression of the second power demand prediction model includes:

[0091] ;

[0092] wherein, represents the demand prediction value, represents the number of time periods within a time cycle, represents the time period The probability of an increase in demand represents the ratio of the associated value corresponding to the power demand data to the target value represents the correction function of the power supply prediction model; the expression of the second power supply prediction model includes:

[0093] ;

[0094] Among them, represents the supply prediction value represents the time period The probability of an increase in supply represents the ratio of the associated value corresponding to the power supply data to the target value represents the correction function of the power supply prediction model

[0095] As a preferred implementation manner, in the embodiment of the present invention, the model correction module is specifically configured to: obtain the relevant parameters of the renewable energy power generation stations in the area covered by the virtual power plant, and determine the fluctuation coefficient of the second power supply prediction model based on the relevant parameters of the renewable energy power generation stations; based on the fluctuation coefficient of the second power supply prediction model, determine the correction function of the power supply prediction model to correct the second power supply prediction model, where the correction function of the power supply prediction model includes:

[0096] ;

[0097] Among them, represents the number of renewable energy power generation stations represents the th probability of generating a power generation error of the renewable energy power generation station represents the weight coefficient represents the correction coefficient; obtain the power consumption parameters of the user side in different time periods in the area covered by the virtual power plant, and determine the fluctuation coefficient of the second power demand prediction model based on the power consumption parameters of the user side in different time periods; based on the fluctuation coefficient of the second power demand prediction model, determine the correction function of the power demand prediction model to correct the second power demand prediction model, where the correction function of the power demand prediction model includes:

[0098] ;

[0099] Among them, represents the season attribute represents the th probability of generating a power consumption deviation in a season represents the weight coefficient It represents a correction coefficient; the corrected second power demand prediction model and the second power supply prediction model are defined as the target power prediction model.

[0100] As a preferred implementation manner, in the embodiment of the present invention, the resource allocation module is specifically configured to: obtain power data of the current time period, and input the power data into the target power prediction model to obtain a demand prediction value and a supply prediction value; in response to detecting that the difference between the demand prediction value and the supply prediction value is greater than a fourth preset value, determine that the current supply and demand are unbalanced, and supply based on the stored power resources; in response to detecting that the difference between the demand prediction value and the supply prediction value is less than the fourth preset value, determine that the current supply and demand are unbalanced, and store the power resources.

[0101] For the specific limitations of the resource allocation system based on the virtual power plant, reference can be made to the limitations of the resource allocation method based on the virtual power plant in the above text, which will not be elaborated here. Each module in the above resource allocation system based on the virtual power plant can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in the form of hardware or independent of it, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0102] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes a resource allocation method based on a virtual power plant. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0103] Those skilled in the art can understand that Figure 4 the structure shown in is only a block diagram of some structures related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0104] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S1: Obtain the power basic data corresponding to different historical time periods in the area covered by the virtual power plant respectively, where the power basic data at least includes power demand data and power supply data; S2: Analyze the power basic data to obtain the power analysis data corresponding to the power basic data in different historical time periods; S3: Construct an initial power prediction model according to the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model; S4: Obtain the fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; S5: Based on the target power prediction model and the power data corresponding to the current time period, perform a supply-demand balance prediction, and allocate power resources according to the prediction result.

[0105] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: S1: Obtain the power basic data corresponding to different historical time periods in the area covered by the virtual power plant respectively, where the power basic data at least includes power demand data and power supply data; S2: Analyze the power basic data to obtain the power analysis data corresponding to the power basic data in different historical time periods; S3: Construct an initial power prediction model according to the power analysis data, where the power prediction model at least includes a power demand prediction model and a power supply prediction model; S4: Obtain the fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model to obtain a target power prediction model, where the fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; S5: Based on the target power prediction model and the power data corresponding to the current time period, perform a supply-demand balance prediction, and allocate power resources according to the prediction result.

[0106] In one embodiment, a computer program product is provided. The computer program product includes a computer program which, when executed by a processor, implements the following steps: S1: Obtain the power basic data corresponding to different historical time periods in the area covered by the virtual power plant respectively. The power basic data at least includes power demand data and power supply data; S2: Analyze the power basic data to obtain the power analysis data corresponding to the power basic data in different historical time periods; S3: Construct an initial power prediction model according to the power analysis data. The power prediction model at least includes a power demand prediction model and a power supply prediction model; S4: Obtain the fluctuation coefficients corresponding to the power prediction model to correct the initial power prediction model and obtain a target power prediction model. The fluctuation coefficients respectively include a power demand side fluctuation coefficient and a power supply side fluctuation coefficient; S5: Based on the target power prediction model and the power data corresponding to the current time period, perform a supply-demand balance prediction, and allocate power resources according to the prediction result.

[0107] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database or other medium used in the various embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0108] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0109] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention.

Claims

1. A resource allocation method based on a virtual power plant, characterized in that: The method comprises: Respectively obtain basic power data corresponding to different historical time periods in the areas covered by the virtual power plant, wherein the basic power data at least includes power demand data and power supply data; Analyze the basic power data to obtain power analysis data corresponding to the basic power data in different historical time periods, including: normalize the basic power data, and calculate and determine the target values ​​corresponding to the normalized basic power data based on the objective function; define the target value corresponding to the power demand data greater than the first preset value as the first target value, and define the target value corresponding to the power supply data greater than the second preset value as the second target value; mark the historical time periods corresponding to the first target value and the second target value once; in response to detecting that the first target value and the second target value exist simultaneously in the target historical time period marked once, mark the target historical time period twice; select the correlation indicators corresponding to the power demand data and the power supply data in the target historical time period respectively, and calculate the correlation value based on the correlation indicator; in response to detecting that the correlation value is greater than the third preset value, mark the target historical time period three times, and map the target historical time period marked three times, and the correlation value and the target value corresponding to the target historical time period to generate the power analysis data; According to the power analysis data, construct an initial power forecasting model, wherein the power forecasting model at least includes a power demand forecasting model and a power supply forecasting model; Obtaining the fluctuation coefficient corresponding to the power forecast model to correct the initial power forecast model to obtain a target power forecast model, wherein the fluctuation coefficients include the fluctuation coefficient of the power demand side and the fluctuation coefficient of the power supply side, including: determining a correction function corresponding to the initial power forecast model based on the fluctuation coefficient, and correcting it to obtain a target power forecast model; Perform supply and demand balance forecast based on the target power forecast model and power data corresponding to the current time period, and allocate power resources according to the forecast results; The normalized power basic data is analyzed to obtain power analysis data corresponding to the power basic data in different historical time periods, including: Based on the objective function, the target values ​​corresponding to the normalized power demand data and power supply data are calculated and determined respectively, and the objective function includes: ； in, represents the target value, Indicates the number of data elements. Indicates The weight coefficient of each data element, Indicates The normalized value of the data element, represents a constant coefficient; The target value corresponding to the power demand data greater than the first preset value is defined as a first target value, and the target value corresponding to the power supply data greater than the second preset value is defined as a second target value; Marking the historical time periods corresponding to the first target value and the second target value respectively; In response to detecting that a first target value and a second target value exist simultaneously within a target historical time period marked once, marking the target historical time period twice; Select the correlation indicators corresponding to the power demand data and the power supply data in the target historical time period respectively, and calculate the correlation value based on the correlation indicators. The calculation formula of the correlation value includes: ； ； in, Represents the associated value, Represents the associated index , The correlation coefficient, Indicates time, Indicates the time coefficient corresponding to the target historical time period, Represents the associated index The rate of change, Represents the associated index The rate of change of In response to detecting that the associated value is greater than a third preset value, marking the target historical time period three times, mapping the target historical time period after the three markings, and the associated value and the target value corresponding to the target historical time period to generate the power analysis data, and save the data; Obtaining the fluctuation coefficient corresponding to the power forecast model to correct the initial power forecast model, and obtaining the target power forecast model includes: Acquire relevant parameters of renewable energy power stations in the area covered by the virtual power plant, and determine the fluctuation coefficient of the second power supply prediction model based on the relevant parameters of the renewable energy power stations; Based on the fluctuation coefficient of the second power supply prediction model, a correction function of the power supply prediction model is determined to correct the second power supply prediction model, wherein the correction function of the power supply prediction model includes: ； in, represents the number of renewable energy power stations, Indicates The probability of a renewable energy power station generating a power generation error, represents the weight coefficient, represents the correction factor; Obtaining power consumption parameters of the user side in different time periods in the area covered by the virtual power plant, and determining the fluctuation coefficient of the second power demand prediction model based on the power consumption parameters of the user side in different time periods; Based on the fluctuation coefficient of the second power demand forecasting model, a correction function of the power demand forecasting model is determined to correct the second power demand forecasting model, wherein the correction function of the power demand forecasting model includes: ； in, Represents the seasonal attribute. Indicates The probability of electricity consumption deviation in each season, represents the weight coefficient, represents the correction factor; The modified second power demand forecasting model and the second power supply forecasting model are defined as the target power forecasting model.

2. The resource allocation method based on a virtual power plant according to claim 1, characterized in that: The power basic data is analyzed to obtain power analysis data corresponding to the power basic data in different historical time periods, including: Performing data cleaning on the basic power data, wherein the data cleaning process at least includes processing missing values, detecting abnormal values, and performing consistency checks on the basic power data; Normalize the cleaned data to obtain normalized basic power data; The normalized power basic data is analyzed to obtain power analysis data corresponding to the power basic data in different historical time periods.

3. The resource allocation method based on virtual power plant according to claim 2, characterized in that: According to the power analysis data, constructing an initial power prediction model includes: Constructing a first power demand forecasting model and a first power supply forecasting model; Dividing the power analysis data into a training set and a validation set, and respectively training and validating the first power demand prediction model and the first power supply prediction model; In response to detecting that the verification result reaches a preset standard, a second power demand forecasting model and a second power supply forecasting model are output, and the second power demand forecasting model and the second power supply forecasting model are defined as the initial power forecasting model.

4. The resource allocation method based on virtual power plant according to claim 3 is characterized in that: The expression of the second power demand prediction model includes: ； in, represents the demand forecast value, Indicates the number of time periods in a time period, Indicates time period The probability of demand increasing. Indicates the ratio of the associated value corresponding to the power demand data to the target value, Represents the correction function of the power demand forecasting model.

5. The resource allocation method based on virtual power plant according to claim 4, characterized in that: The expression of the second power supply prediction model includes: ； in, represents the supply forecast value, Indicates time period The probability of a supply increase occurring, Indicates the ratio of the associated value corresponding to the power supply data to the target value, Represents the correction function of the power supply prediction model.

6. The resource allocation method based on virtual power plant according to claim 5, characterized in that: Providing supply and demand balance prediction based on the target power prediction model and power data corresponding to the current time period, and allocating power resources according to the prediction results includes: Acquire power data for the current time period, and input the power data into the target power forecasting model to obtain a demand forecast value and a supply forecast value; In response to detecting that the difference between the demand prediction value and the supply prediction value is greater than a fourth preset value, determining that the current supply and demand are unbalanced, and supplying based on the stored power resources; In response to detecting that the difference between the demand prediction value and the supply prediction value is less than a fourth preset value, it is determined that the current supply and demand are unbalanced, and the power resources are stored.

7. A resource allocation system based on a virtual power plant for implementing the resource allocation method based on a virtual power plant as claimed in any one of claims 1 to 6, characterized in that: The system comprises: A data acquisition module is used to respectively obtain the basic power data corresponding to the area covered by the virtual power plant in different historical time periods, wherein the basic power data at least includes power demand data and power supply data; A data analysis module, used to analyze the basic power data to obtain power analysis data corresponding to the basic power data in different historical time periods; A model building module, used to build an initial power forecasting model according to the power analysis data, wherein the power forecasting model at least includes a power demand forecasting model and a power supply forecasting model; A model correction module, used to obtain the fluctuation coefficient corresponding to the power forecasting model, so as to correct the initial power forecasting model and obtain a target power forecasting model, wherein the fluctuation coefficients include the fluctuation coefficient of the power demand side and the fluctuation coefficient of the power supply side respectively; The resource allocation module is used to make supply and demand balance prediction based on the target power prediction model and the power data corresponding to the current time period, and to allocate power resources according to the prediction results.

8. The resource allocation system based on virtual power plant according to claim 7, characterized in that: The normalized basic power data is analyzed to obtain power analysis data corresponding to the basic power data in different historical time periods, including: Based on the objective function, the target values ​​corresponding to the normalized power demand data and power supply data are calculated and determined respectively, and the objective function includes: ； in, represents the target value, Indicates the number of data elements. Indicates The weight coefficient of each data element, Indicates The normalized value of the data element, represents a constant coefficient; The target value corresponding to the power demand data greater than the first preset value is defined as a first target value, and the target value corresponding to the power supply data greater than the second preset value is defined as a second target value; Marking the historical time periods corresponding to the first target value and the second target value respectively; In response to detecting that a first target value and a second target value exist simultaneously within a target historical time period marked once, marking the target historical time period twice; Select the correlation indicators corresponding to the power demand data and the power supply data in the target historical time period respectively, and calculate the correlation value based on the correlation indicators. The calculation formula of the correlation value includes: ； ； in, Represents the associated value, Represents the associated index , The correlation coefficient, Indicates time, Indicates the time coefficient corresponding to the target historical time period, Represents the associated index The rate of change, Represents the associated index The rate of change of In response to detecting that the associated value is greater than a third preset value, the target historical time period is marked three times, and the target historical time period after the three markings, as well as the associated value and target value corresponding to the target historical time period are mapped to generate the power analysis data and save it.

Images