Intelligent power plant prediction and scheduling system and method based on big data technology

Abstract

The invention relates to the technical field of power consumption management, in particular to an intelligent power plant prediction and scheduling system and method based on the big data technology, and the system comprises a prediction analysis module which combines an analysis result in a reported data fluctuation feature analysis module to construct a data reporting interval duration adaptive model, and obtaining a prediction result corresponding to the load report prediction information submitted last time based on the current time in combination with historical electrical load data of the to-be-tested enterprise. According to the method, the fluctuation change of the electrical load of the enterprise to be measured at different times in the time period and the influence of the fluctuation intensity on the subsequent prediction result are considered, and the self-adaptive adjustment of the load data reporting time is realized according to the fluctuation degree of the electrical load data, so that the precision of the dynamic load prediction result is ensured, and the accuracy of the dynamic load prediction result is improved. The electric energy storage of the power plant is accurately controlled.

Description

Technical Field

[0001] The present invention relates to the field of electricity management technology, and specifically to a smart power plant prediction and scheduling system and method based on big data technology. Background Art

[0002] With the development of the social economy and the improvement of people's living standards, people's demand for electricity is becoming stronger and stronger. Whether it is production or life, it is inseparable from the use of electricity. However, the current storage of electric energy is relatively difficult. Therefore, during the power production process, it is necessary to estimate the user's electricity demand (load) in advance, so as to adjust the generated power and distribute the generated power. Generally speaking, electricity consumption is divided into two types: residential electricity consumption and enterprise electricity consumption. For residential electricity consumption, it maintains regularity; however, for enterprise electricity consumption, the electricity demand in each cycle varies. Currently, power plants often reserve electricity by receiving electricity demand regularly reported by enterprises and residents. However, due to the irregular electricity demand of enterprises, and relying solely on the electricity demand regularly reported by enterprises to reserve electricity, it is passive and cannot actively predict the electricity demand of enterprises to be tested. As a result, the power reserve of power plants does not match the electricity demand. Therefore, how to predict the power reserve of power plants has become an urgent problem to be solved in today's society. Summary of the Invention

[0003] The purpose of the present invention is to provide a smart power plant prediction and scheduling system and method based on big data technology to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solution: a smart power plant prediction and scheduling method based on big data technology, the method comprising the following steps: S1. Receive electricity demand forecast information reported by the power consumption area covered by the power plant, obtain historical electricity load data of the enterprise to be tested, and extract the load forecast information submitted by the enterprise to be tested each time from the historical data; S2. Obtain the actual order deviation rate corresponding to two consecutive load forecast reports submitted by the enterprise under test, analyze the relationship between the data deviation amount within the time period corresponding to each load forecast report submitted by the enterprise under test and the data fluctuation characteristics of the actual power load information within the time period corresponding to the previous load forecast report submitted, and obtain the report fluctuation characteristic function of the enterprise under test under the corresponding order deviation rate; S3. Based on the analysis results in S2, a data reporting interval adaptive model is constructed, and combined with the historical electricity load data of the enterprise to be tested, a prediction result corresponding to the load reporting prediction information submitted most recently based on the current time is obtained; S4. Based on the prediction results obtained in S3, the electricity consumption information of the enterprise to be tested in the corresponding time period is managed, and an early warning is issued for abnormal electricity consumption status.

[0005] Furthermore, the historical power load data in S1 includes predicted power load and actual power load corresponding to different time points; The load reporting forecast information includes the forecast duration and the average power load within the corresponding forecast duration.

[0006] Furthermore, when obtaining the actual order deviation rate corresponding to two adjacent load forecast reports of the enterprise under test in S2, the actual order deviation rate is recorded as A, where A=A1-A2, and the obtained actual order deviation rate is bound to the latter load forecast report information of the two adjacent load forecast reports. A1 represents the ratio of the total amount of uncompleted electricity load orders of the enterprise under test to the remaining order duration when the previous load report forecast information is submitted between two consecutive load report forecast information. A2 represents the ratio of the total amount of uncompleted electricity load orders of the enterprise under test to the remaining order duration when submitting the latter load forecast information of two consecutive load forecast reports; When the corresponding order deviation rate is obtained in S2, the method for reporting the fluctuation characteristic function of the enterprise to be tested includes the following steps: S21. Obtain the load report forecast information of each load with the same bound actual order deviation rate, and obtain the feature association information data pair corresponding to each load report forecast information under the corresponding actual order deviation rate, recorded as (B1, C1). C1 represents the data deviation amount within the time period corresponding to the corresponding load report forecast information, and B1 represents the data fluctuation characteristics of the actual power load information within the time period corresponding to the previous load report forecast information of the corresponding load report forecast information; S22. For the plurality of feature association information data pairs under the same actual order deviation rate, determine the coordinate point corresponding to each feature association information data pair in a plane rectangular coordinate system, where the plane rectangular coordinate system is a coordinate system for data fluctuation characteristics and data deviation amounts; S23, based on the function model y=p1×(x-p2) in the database 2 +P3, and P1, P2, and P3 are all coefficients of the function model. Fit the coordinate points in the plane rectangular coordinate system in S22, and use the function corresponding to the fitting result as the reporting fluctuation characteristic function of the enterprise under test when the corresponding order deviation rate is M. When the order deviation rate is M, the reporting fluctuation characteristic function of the enterprise under test is recorded as GM (x), and the average value of the distance from each obtained coordinate point in the plane rectangular coordinate system to GM (x) before fitting is obtained, recorded as LGM; The method for obtaining B1 comprises the following steps: S201, obtaining the prediction time t1 corresponding to the corresponding load reporting prediction information and the average power load E within the corresponding prediction time; S202, obtaining the actual power load corresponding to different time points in the time period corresponding to the corresponding load report forecast information, and recording the actual power load corresponding to the time period of the forecast duration t1 at the time t as Et; S203, obtain B1, B1=1 / t1×(∫ t=0 t1 Etdt-E×t1); The method for obtaining C1 comprises the following steps: S211, obtaining the actual power load corresponding to different time points in the time period corresponding to the previous load report forecast information of the corresponding load report forecast information, recording the actual power load corresponding to the time point with a time interval t2 of the minimum time point in the obtained time period as ESt2, and recording the maximum time interval in the obtained time period as t3; S212, obtain C1, wherein C1=F[1 / t3×∫ t2=0 t3 ESt2dt2, EP, {ESt2|0≤t2≤t3}] / t3, Among them, EP represents the load error tolerance value preset in the database, {ESt2|0≤t2≤t3} represents the set of ESt2 corresponding to different values of t2 when 0≤t2≤t3. F[1 / t3×∫ t2=0 t3 ESt2dt2, EP, {ESt2|0≤t2≤t3}] means {ESt2|0≤t2≤t3} does not belong to [1 / t3×∫ t2=0 t3 ESt2dt2-EP,1 / t3×∫ t2=0 t3 The length of the time interval composed of the time points corresponding to all elements of [ESt2dt2+EP].

[0007] The present invention analyzes the reporting fluctuation characteristic function GM(x) of the enterprise to be tested when the order deviation rate is M, in order to obtain the influence of the fluctuation of the actual power load data corresponding to the previous load reporting forecast information on the deviation corresponding to the next load reporting forecast information in two adjacent load reporting forecast information, and provides data support for the screening of the mark points to be analyzed in the process of constructing the data reporting interval adaptive model in the subsequent step.

[0008] Furthermore, the method for constructing a data reporting interval adaptive model in S3 includes the following steps: S301, obtaining the reported fluctuation characteristic function GM(x) and LGM of the enterprise under test when the order deviation rate is M; S302, when the order deviation rate is M, all feature association information data pairs corresponding to the tested enterprise whose distance GM(x) is less than or equal to β×LGM are obtained, and the corresponding coordinate points of the obtained feature association information data pairs in the plane rectangular coordinate system are marked, where β is a constant preset in the database; The setting of β in the present invention takes into account the different reference values of each coordinate point for the subsequent analysis steps during the curve fitting process. During the fitting process, the greater the distance between the coordinate point and GM (x), the greater the deviation between the coordinate point and the fitting result (theoretical analysis result), and the greater the error caused by incorporating the coordinate point into the analysis object in the subsequent steps. β limits the screening range of coordinate points to a certain extent, and thus ensures the accuracy of the subsequent analysis results to a certain extent. When the number of coordinate points is sufficient, the smaller the β value, the greater the analysis accuracy.

[0009] S303: Using W as a reference point, obtain all the marking points obtained in S302 whose absolute value of the difference between the first value and W is less than or equal to a first preset value h. When the number of obtained marking points is less than the second preset value k, the first preset value h is adaptively adjusted, and the first preset value h is added with the adjustment step h1 to obtain a new first preset value, and S303 is executed again, where h1 is a constant preset in the database. When the number of obtained marking points is greater than or equal to the second preset value k, jump to S304; The present invention adaptively adjusts the first preset value to ensure that the number of analyzed marking points is sufficient (the number of samples is sufficient), thereby ensuring the accuracy of the analysis result.

[0010] S304. Obtain the adaptive adjustment feature of the data reporting interval corresponding to the reference point W, denoted as RW, where RW={RW1, RW2}, where RW1 represents the average value of the adaptive adjustment coefficients of the data reporting interval corresponding to each mark point W, and RW2 represents the adaptive adjustment upper limit of the data reporting interval corresponding to W. The adaptive adjustment coefficient of the data reporting interval corresponding to each mark point is equal to the ratio of the predicted duration of the load reporting prediction information corresponding to the second data in the corresponding mark point divided by the maximum interval duration of the actual power load information corresponding to the load reporting prediction information corresponding to the first data in the mark point. When obtaining RW2, first obtain each mark point corresponding to W, and calculate the difference between the predicted duration of the load reporting prediction information corresponding to the second data in each mark point and the maximum interval duration of the actual power load information corresponding to the load reporting prediction information corresponding to the first data in the mark point. RW2 is equal to the average value of the corresponding differences of each mark point corresponding to W; S305. Obtain the predicted duration corresponding to the load reporting prediction information corresponding to W in the data reporting interval adaptive model, recorded as TW, TW=min{RW1×T, RW2+T}, where T represents the predicted duration in the load reporting prediction information submitted last time before the load reporting prediction information corresponding to W, and min{RW1×T, RW2+T} represents the minimum value between RW1×T and RW2+T.

[0011] Furthermore, when the prediction result corresponding to the load forecast information submitted most recently at the current time is obtained in S3, the actual order deviation rate before and after the load forecast information submitted most recently at the current time is calculated, and the corresponding report fluctuation characteristic function of the enterprise to be tested is obtained according to the obtained actual order deviation rate. The load forecast information submitted most recently based on the current time is recorded as U, the forecast duration in the forecast result corresponding to U is recorded as TZ, and the average power load within the forecast duration corresponding to U is recorded as Q, where Q represents the average value of the actual power load in the time period corresponding to the load forecast information submitted by U last time. Obtain the maximum interval duration of the time period corresponding to the load forecast information submitted by U last time, recorded as TU1, obtain the data fluctuation characteristics of the actual power load information in the time period corresponding to the load forecast information submitted by U last time, recorded as W1, and combine the constructed data reporting interval adaptive model to obtain the prediction duration TZ corresponding to the load reporting forecast information when W is W1 in the data reporting interval adaptive model. When TZ is greater than or equal to the preset value in the database, keep the value corresponding to TZ unchanged. When TZ is less than the preset value in the database, the value corresponding to TZ is changed to the preset value to obtain a new TZ.

[0012] Furthermore, when the electricity consumption information of the enterprise to be tested within the corresponding time period is managed in S4, the abnormal electricity consumption state indicates that the data deviation of the corresponding load reporting forecast information within the corresponding time period is greater than the preset value of the database. The corresponding forecast duration in the next submitted load reporting forecast information after sending the early warning information is manually set by the user.

[0013] In the present invention, the corresponding prediction duration in the next load reporting prediction information submitted after sending the early warning information is manually set by the user. This is because when an early warning occurs, it means that there is a certain degree of deviation in the prediction duration currently obtained by the data reporting interval duration adaptive model. In this state, if no human intervention (manual adjustment) is performed, the adaptive adjustment results of the data reporting interval duration adaptively generated in the subsequent steps will have large errors, affecting the user management of the user to be tested in the subsequent process.

[0014] A smart power plant prediction and dispatching system based on big data technology, comprising the following modules: An electricity consumption data acquisition module, which acquires historical electricity load data of the enterprise to be tested and extracts load report forecast information submitted by the enterprise to be tested each time from the historical data; A reporting data fluctuation characteristic analysis module, wherein the reporting data fluctuation characteristic analysis module obtains the actual order deviation rate corresponding to two adjacent load reporting forecast information of the enterprise under test, analyzes the relationship between the data deviation amount within the time period corresponding to the load reporting forecast information submitted by the enterprise under test each time and the data fluctuation characteristics of the actual power load information within the time period corresponding to the previous load reporting forecast information when the actual order deviation rate is the same, and obtains the reporting fluctuation characteristic function of the enterprise under test when the corresponding order deviation rate is obtained; A prediction analysis module, which combines the analysis results of the reported data fluctuation characteristic analysis module to build a data reporting interval adaptive model, and combines the historical electricity load data of the enterprise to be tested to obtain the prediction result corresponding to the load reporting prediction information submitted most recently at the current time; The power consumption early warning management module manages the power consumption information of the enterprise to be tested within the corresponding time period based on the prediction results obtained in the prediction analysis module, and issues early warnings for abnormal power consumption status.

[0015] Furthermore, the reported data fluctuation feature analysis module includes an order deviation acquisition module and a fluctuation feature analysis module. The order deviation acquisition module is used to obtain the actual order deviation rate corresponding to two consecutive load forecast report information of the enterprise under test; The fluctuation characteristic analysis module analyzes the relationship between the data deviation amount in the time period corresponding to the load reporting forecast information submitted by the enterprise to be tested each time and the data fluctuation characteristics of the actual power load information in the time period corresponding to the previous load reporting forecast information when the actual order deviation rate is the same, and obtains the reporting fluctuation characteristic function of the enterprise to be tested when the corresponding order deviation rate is obtained.

[0016] Compared with the existing technology, the beneficial effects achieved by the present invention are: the present invention takes into account the fluctuation of the electricity load of the enterprise to be tested at different times within the time period, and the impact of the severity of the fluctuation on the subsequent prediction results, and realizes adaptive adjustment of the load data reporting time according to the fluctuation degree of the electricity load data, thereby ensuring the accuracy of the dynamic load forecast results and realizing precise control of the power plant's energy reserves. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 This is a flow chart of the smart power plant prediction and scheduling method based on big data technology of the present invention; Figure 2 It is a structural diagram of the smart power plant prediction and scheduling system based on big data technology of the present invention. DETAILED DESCRIPTION

[0018] 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.

[0019] See also Figure 1 The present invention provides a technical solution: a smart power plant prediction and scheduling method based on big data technology, the method comprising the following steps: S1. Receive electricity demand forecast information reported by the power consumption area covered by the power plant, obtain historical electricity load data of the enterprise to be tested, and extract the load forecast information submitted by the enterprise to be tested each time from the historical data; The historical power load data in S1 includes the predicted power load and the actual power load corresponding to different time points; The load reporting forecast information includes the forecast duration and the average power load within the corresponding forecast duration.

[0020] S2. Obtain the actual order deviation rate corresponding to two consecutive load forecast reports submitted by the enterprise under test, analyze the relationship between the data deviation amount within the time period corresponding to each load forecast report submitted by the enterprise under test and the data fluctuation characteristics of the actual power load information within the time period corresponding to the previous load forecast report submitted, and obtain the report fluctuation characteristic function of the enterprise under test under the corresponding order deviation rate; When obtaining the actual order deviation rate corresponding to two adjacent load forecast reports of the enterprise under test in S2, the actual order deviation rate is recorded as A, where A=A1-A2, and the obtained actual order deviation rate is bound to the latter load forecast report information of the two adjacent load forecast reports. A1 represents the ratio of the total amount of uncompleted electricity load orders of the enterprise under test to the remaining order duration when the previous load report forecast information is submitted between two consecutive load report forecast information. A2 represents the ratio of the total amount of uncompleted electricity load orders of the enterprise under test to the remaining order duration when submitting the latter load forecast information of two consecutive load forecast reports; In this embodiment, if two adjacent load forecast reports are recorded as A and B respectively, If A is submitted, the unfinished order quantity of the enterprise under test is e1 and the remaining order duration is te1, If B is submitted, the unfinished order quantity of the enterprise under test is e2 and the remaining order duration is te2, Then the actual order deviation rate of B is e1 / te1-e2 / te2. At this point, e1 / te1 reflects, to a certain extent, the degree of pressure on the company under test to complete order A, and e2 / te2 reflects, to a certain extent, the degree of pressure on the company under test to complete order B. The difference between e1 / te1 and e2 / te2 reflects, to a certain extent, the change in the company's order completion pressure. If the change is different, the subsequent analysis of data fluctuation characteristics and data deviation will also be different. When the corresponding order deviation rate is obtained in S2, the method for reporting the fluctuation characteristic function of the enterprise to be tested includes the following steps: S21. Obtain the load report forecast information of each load with the same bound actual order deviation rate, and obtain the feature association information data pair corresponding to each load report forecast information under the corresponding actual order deviation rate, recorded as (B1, C1). C1 represents the data deviation amount within the time period corresponding to the corresponding load report forecast information, and B1 represents the data fluctuation characteristics of the actual power load information within the time period corresponding to the previous load report forecast information of the corresponding load report forecast information; S22. For the plurality of feature association information data pairs under the same actual order deviation rate, determine the coordinate point corresponding to each feature association information data pair in a plane rectangular coordinate system, where the plane rectangular coordinate system is a coordinate system for data fluctuation characteristics and data deviation amounts; S23, based on the function model y=p1×(x-p2) in the database 2+P3, and P1, P2, and P3 are all coefficients of the function model. Fit the coordinate points in the plane rectangular coordinate system in S22, and use the function corresponding to the fitting result as the reporting fluctuation characteristic function of the enterprise under test when the corresponding order deviation rate is M. When the order deviation rate is M, the reporting fluctuation characteristic function of the enterprise under test is recorded as GM (x), and the average value of the distance from each obtained coordinate point in the plane rectangular coordinate system to GM (x) before fitting is obtained, recorded as LGM; The method for obtaining B1 comprises the following steps: S201, obtaining the prediction time t1 corresponding to the corresponding load reporting prediction information and the average power load E within the corresponding prediction time; S202, obtaining the actual power load corresponding to different time points in the time period corresponding to the corresponding load report forecast information, and recording the actual power load corresponding to the time period of the forecast duration t1 at the time t as Et; S203, obtain B1, B1=1 / t1×(∫ t=0 t1 Etdt-E×t1); The method for obtaining C1 comprises the following steps: S211, obtaining the actual power load corresponding to different time points in the time period corresponding to the previous load report forecast information of the corresponding load report forecast information, recording the actual power load corresponding to the time point with a time interval t2 of the minimum time point in the obtained time period as ESt2, and recording the maximum time interval in the obtained time period as t3; S212, obtain C1, wherein C1=F[1 / t3×∫ t2=0 t3 ESt2dt2, EP, {ESt2|0≤t2≤t3}] / t3, Among them, EP represents the load error tolerance value preset in the database, {ESt2|0≤t2≤t3} represents the set of ESt2 corresponding to different values of t2 when 0≤t2≤t3. F[1 / t3×∫ t2=0 t3 ESt2dt2, EP, {ESt2|0≤t2≤t3}] means {ESt2|0≤t2≤t3} does not belong to [1 / t3×∫ t2=0 t3 ESt2dt2-EP,1 / t3×∫ t2=0 t3 The length of the time interval composed of the time points corresponding to all elements of ESt2dt2+EP], In this embodiment, {ESt2|0≤t2≤t3} does not belong to [1 / t3×∫ t2=0t3 ESt2dt2-EP,1 / t3×∫ t2= 0 t3 The time interval composed of the time points corresponding to all elements of ESt2dt2+EP] may be the union of multiple different time intervals. In this case, F[1 / t3×∫ t2=0 t3 ESt2dt2, EP, {ESt2|0≤t2≤t3}] is equal to the sum of the interval lengths of the time intervals corresponding to each component in the obtained union.

[0021] S3. Based on the analysis results in S2, a data reporting interval adaptive model is constructed, and combined with the historical electricity load data of the enterprise to be tested, a prediction result corresponding to the load reporting prediction information submitted most recently based on the current time is obtained; The method for constructing a data reporting interval adaptive model in S3 includes the following steps: S301, obtaining the reported fluctuation characteristic function GM(x) and LGM of the enterprise under test when the order deviation rate is M; S302, when the order deviation rate is M, all feature association information data pairs corresponding to the tested enterprise whose distance GM(x) is less than or equal to β×LGM are obtained, and the corresponding coordinate points of the obtained feature association information data pairs in the plane rectangular coordinate system are marked, where β is a constant preset in the database; S303: Using W as a reference point, obtain all the marking points obtained in S302 whose absolute value of the difference between the first value and W is less than or equal to a first preset value h. When the number of obtained marking points is less than the second preset value k, the first preset value h is adaptively adjusted, and the first preset value h is added with the adjustment step h1 to obtain a new first preset value, and S303 is executed again, where h1 is a constant preset in the database. When the number of obtained marking points is greater than or equal to the second preset value k, jump to S304; S304. Obtain the adaptive adjustment feature of the data reporting interval corresponding to the reference point W, denoted as RW, where RW={RW1, RW2}, where RW1 represents the average value of the adaptive adjustment coefficients of the data reporting interval corresponding to each mark point W, and RW2 represents the adaptive adjustment upper limit of the data reporting interval corresponding to W. The adaptive adjustment coefficient of the data reporting interval corresponding to each mark point is equal to the ratio of the predicted duration of the load reporting prediction information corresponding to the second data in the corresponding mark point divided by the maximum interval duration of the actual power load information corresponding to the load reporting prediction information corresponding to the first data in the mark point. When obtaining RW2, first obtain each mark point corresponding to W, and calculate the difference between the predicted duration of the load reporting prediction information corresponding to the second data in each mark point and the maximum interval duration of the actual power load information corresponding to the load reporting prediction information corresponding to the first data in the mark point. RW2 is equal to the average value of the corresponding differences of each mark point corresponding to W; S305. Obtain the predicted duration corresponding to the load reporting prediction information corresponding to W in the data reporting interval adaptive model, recorded as TW, TW=min{RW1×T, RW2+T}, where T represents the predicted duration in the load reporting prediction information submitted last time before the load reporting prediction information corresponding to W, and min{RW1×T, RW2+T} represents the minimum value between RW1×T and RW2+T.

[0022] When the prediction result corresponding to the load forecast information submitted most recently at the current time is obtained in S3, the actual order deviation rate before and after the load forecast information submitted most recently at the current time is calculated, and the report fluctuation characteristic function of the corresponding enterprise to be tested is obtained according to the obtained actual order deviation rate. The load forecast information submitted most recently based on the current time is recorded as U, the forecast duration in the forecast result corresponding to U is recorded as TZ, and the average power load within the forecast duration corresponding to U is recorded as Q, where Q represents the average value of the actual power load in the time period corresponding to the load forecast information submitted by U last time. Obtain the maximum interval duration of the time period corresponding to the load forecast information submitted by U last time, recorded as TU1, obtain the data fluctuation characteristics of the actual power load information in the time period corresponding to the load forecast information submitted by U last time, recorded as W1, and combine the constructed data reporting interval adaptive model to obtain the prediction duration TZ corresponding to the load reporting forecast information when W is W1 in the data reporting interval adaptive model. When TZ is greater than or equal to the preset value in the database, keep the value corresponding to TZ unchanged. When TZ is less than the preset value in the database, the value corresponding to TZ is changed to the preset value to obtain a new TZ.

[0023] S4. Based on the prediction results obtained in S3, manage the electricity consumption information of the enterprise under test in the corresponding time period and issue early warnings for abnormal electricity consumption status; When managing the electricity consumption information of the enterprise to be tested within the corresponding time period in S4, the abnormal electricity consumption status indicates that the data deviation of the corresponding load reporting forecast information within the corresponding time period is greater than the preset value of the database. The corresponding forecast duration in the next submitted load reporting forecast information after sending the early warning information is manually set by the user.

[0024] like Figure 2 As shown in the figure, a smart power plant prediction and dispatching system based on big data technology includes the following modules: An electricity consumption data acquisition module, which acquires historical electricity load data of the enterprise to be tested and extracts load report forecast information submitted by the enterprise to be tested each time from the historical data; A reporting data fluctuation characteristic analysis module, wherein the reporting data fluctuation characteristic analysis module obtains the actual order deviation rate corresponding to two adjacent load reporting forecast information of the enterprise under test, analyzes the relationship between the data deviation amount within the time period corresponding to the load reporting forecast information submitted by the enterprise under test each time and the data fluctuation characteristics of the actual power load information within the time period corresponding to the previous load reporting forecast information when the actual order deviation rate is the same, and obtains the reporting fluctuation characteristic function of the enterprise under test when the corresponding order deviation rate is obtained; A prediction analysis module, which combines the analysis results of the reported data fluctuation characteristic analysis module to build a data reporting interval adaptive model, and combines the historical electricity load data of the enterprise to be tested to obtain the prediction result corresponding to the load reporting prediction information submitted most recently at the current time; The power consumption early warning management module manages the power consumption information of the enterprise to be tested within the corresponding time period based on the prediction results obtained in the prediction analysis module, and issues early warnings for abnormal power consumption status.

[0025] The reported data fluctuation feature analysis module includes an order deviation acquisition module and a fluctuation feature analysis module. The order deviation acquisition module is used to obtain the actual order deviation rate corresponding to two consecutive load forecast report information of the enterprise under test; The fluctuation characteristic analysis module analyzes the relationship between the data deviation amount in the time period corresponding to the load reporting forecast information submitted by the enterprise to be tested each time and the data fluctuation characteristics of the actual power load information in the time period corresponding to the previous load reporting forecast information when the actual order deviation rate is the same, and obtains the reporting fluctuation characteristic function of the enterprise to be tested when the corresponding order deviation rate is obtained.

[0026] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0027] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A smart power plant prediction and scheduling method based on big data technology is characterized by: The method comprises the following steps: S1. Receive electricity demand forecast information reported by the power consumption area covered by the power plant, obtain historical electricity load data of the enterprise to be tested, and extract the load forecast information submitted by the enterprise to be tested each time from the historical data; S2. Obtain the actual order deviation rate corresponding to two consecutive load forecast reports submitted by the enterprise under test, analyze the relationship between the data deviation amount within the time period corresponding to each load forecast report submitted by the enterprise under test and the data fluctuation characteristics of the actual power load information within the time period corresponding to the previous load forecast report submitted, and obtain the report fluctuation characteristic function of the enterprise under test under the corresponding order deviation rate; S3. Based on the analysis results in S2, a data reporting interval adaptive model is constructed, and combined with the historical electricity load data of the enterprise to be tested, a prediction result corresponding to the load reporting prediction information submitted most recently based on the current time is obtained; S4. Based on the prediction results obtained in S3, the electricity consumption information of the enterprise to be tested in the corresponding time period is managed, and an early warning is issued for abnormal electricity consumption status.

2. The smart power plant prediction and scheduling method based on big data technology according to claim 1 is characterized by: The historical power load data in S1 includes the predicted power load and the actual power load corresponding to different time points; The load reporting forecast information includes the forecast duration and the average power load within the corresponding forecast duration.

3. The smart power plant prediction and scheduling method based on big data technology according to claim 2 is characterized by: When obtaining the actual order deviation rate corresponding to two adjacent load forecast reports of the enterprise under test in S2, the actual order deviation rate is recorded as A, where A=A1-A2, and the obtained actual order deviation rate is bound to the latter load forecast report information of the two adjacent load forecast reports. A1 represents the ratio of the total amount of uncompleted electricity load orders of the enterprise under test to the remaining order duration when the previous load report forecast information is submitted between two consecutive load report forecast information. A2 represents the ratio of the total amount of uncompleted electricity load orders of the enterprise under test to the remaining order duration when submitting the latter load forecast information of two consecutive load forecast reports; When the corresponding order deviation rate is obtained in S2, the method for reporting the fluctuation characteristic function of the enterprise to be tested includes the following steps: S21. Obtain the load report forecast information of each load with the same bound actual order deviation rate, and obtain the feature association information data pair corresponding to each load report forecast information under the corresponding actual order deviation rate, recorded as (B1, C1). C1 represents the data deviation amount within the time period corresponding to the corresponding load report forecast information, and B1 represents the data fluctuation characteristics of the actual power load information within the time period corresponding to the previous load report forecast information of the corresponding load report forecast information; S22. For the plurality of feature association information data pairs under the same actual order deviation rate, determine the coordinate point corresponding to each feature association information data pair in a plane rectangular coordinate system, where the plane rectangular coordinate system is a coordinate system for data fluctuation characteristics and data deviation amounts; S23, based on the function model y=p1×(x-p2) in the database 2 +P3, and P1, P2, and P3 are all coefficients of the function model. Fit the coordinate points in the plane rectangular coordinate system in S22, and use the function corresponding to the fitting result as the reporting fluctuation characteristic function of the enterprise under test when the corresponding order deviation rate is M. When the order deviation rate is M, the reporting fluctuation characteristic function of the enterprise under test is recorded as GM (x), and the average value of the distance from each obtained coordinate point in the plane rectangular coordinate system to GM (x) before fitting is obtained, recorded as LGM; The method for obtaining B1 comprises the following steps: S201, obtaining the prediction time t1 corresponding to the corresponding load reporting prediction information and the average power load E within the corresponding prediction time; S202, obtaining the actual power load corresponding to different time points in the time period corresponding to the corresponding load report forecast information, and recording the actual power load corresponding to the time period of the forecast duration t1 at the time t as Et; S203, obtain B1, B1=1 / t1×(∫ t=0 t1 Etdt-E×t1); The method for obtaining C1 comprises the following steps: S211, obtaining the actual power load corresponding to different time points in the time period corresponding to the previous load report forecast information of the corresponding load report forecast information, recording the actual power load corresponding to the time point with a time interval t2 of the minimum time point in the obtained time period as ESt2, and recording the maximum time interval in the obtained time period as t3; S212, obtain C1, wherein C1=F[1 / t3×∫ t2=0 t3 ESt2dt2, EP, {ESt2|0≤t2≤t3}] / t3, Among them, EP represents the load error tolerance value preset in the database, {ESt2|0≤t2≤t3} represents the set of ESt2 corresponding to different values of t2 when 0≤t2≤t3. F[1 / t3×∫ t2=0 t3 ESt2dt2, EP, {ESt2|0≤t2≤t3}] means {ESt2|0≤t2≤t3} does not belong to [1 / t3×∫ t2=0 t3 ESt2dt2-EP,1 / t3×∫ t2=0 t3 The length of the time interval composed of the time points corresponding to all elements of [ESt2dt2+EP].

4. The smart power plant prediction and scheduling method based on big data technology according to claim 3 is characterized by: The method for constructing a data reporting interval adaptive model in S3 includes the following steps: S301, obtaining the reported fluctuation characteristic function GM(x) and LGM of the enterprise under test when the order deviation rate is M; S302, when the order deviation rate is M, all feature association information data pairs corresponding to the tested enterprise whose distance GM(x) is less than or equal to β×LGM are obtained, and the corresponding coordinate points of the obtained feature association information data pairs in the plane rectangular coordinate system are marked, where β is a constant preset in the database; S303: Using W as a reference point, obtain all the marking points obtained in S302 whose absolute value of the difference between the first value and W is less than or equal to a first preset value h. When the number of obtained marking points is less than the second preset value k, the first preset value h is adaptively adjusted, and the first preset value h is added with the adjustment step h1 to obtain a new first preset value, and S303 is executed again, where h1 is a constant preset in the database. When the number of obtained marking points is greater than or equal to the second preset value k, jump to S304; S304. Obtain the adaptive adjustment feature of the data reporting interval corresponding to the reference point W, denoted as RW, where RW={RW1, RW2}, where RW1 represents the average value of the adaptive adjustment coefficients of the data reporting interval corresponding to each mark point W, and RW2 represents the adaptive adjustment upper limit of the data reporting interval corresponding to W. The adaptive adjustment coefficient of the data reporting interval corresponding to each mark point is equal to the ratio of the predicted duration of the load reporting prediction information corresponding to the second data in the corresponding mark point divided by the maximum interval duration of the actual power load information corresponding to the load reporting prediction information corresponding to the first data in the mark point. When obtaining RW2, first obtain each mark point corresponding to W, and calculate the difference between the predicted duration of the load reporting prediction information corresponding to the second data in each mark point and the maximum interval duration of the actual power load information corresponding to the load reporting prediction information corresponding to the first data in the mark point. RW2 is equal to the average value of the corresponding differences of each mark point corresponding to W; S305. Obtain the predicted duration corresponding to the load reporting prediction information corresponding to W in the data reporting interval adaptive model, recorded as TW, TW=min{RW1×T, RW2+T}, where T represents the predicted duration in the load reporting prediction information submitted last time before the load reporting prediction information corresponding to W, and min{RW1×T, RW2+T} represents the minimum value between RW1×T and RW2+T.

5. The smart power plant prediction and scheduling method based on big data technology according to claim 4 is characterized by: When the prediction result corresponding to the load forecast information submitted most recently at the current time is obtained in S3, the actual order deviation rate before and after the load forecast information submitted most recently at the current time is calculated, and the report fluctuation characteristic function of the corresponding enterprise to be tested is obtained according to the obtained actual order deviation rate. The load forecast information submitted most recently based on the current time is recorded as U, the forecast duration in the forecast result corresponding to U is recorded as TZ, and the average power load within the forecast duration corresponding to U is recorded as Q, where Q represents the average value of the actual power load in the time period corresponding to the load forecast information submitted by U last time. Obtain the maximum interval duration of the time period corresponding to the load forecast information submitted by U last time, recorded as TU1, obtain the data fluctuation characteristics of the actual power load information in the time period corresponding to the load forecast information submitted by U last time, recorded as W1, and combine the constructed data reporting interval adaptive model to obtain the prediction duration TZ corresponding to the load reporting forecast information when W is W1 in the data reporting interval adaptive model. When TZ is greater than or equal to the preset value in the database, keep the value corresponding to TZ unchanged. When TZ is less than the preset value in the database, the value corresponding to TZ is changed to the preset value to obtain a new TZ.

6. The smart power plant prediction and scheduling method based on big data technology according to claim 1 is characterized by: When managing the electricity consumption information of the enterprise to be tested within the corresponding time period in S4, the abnormal electricity consumption status indicates that the data deviation of the corresponding load reporting forecast information within the corresponding time period is greater than the preset value of the database. The corresponding forecast duration in the next submitted load reporting forecast information after sending the early warning information is manually set by the user.

7. A smart power plant prediction and scheduling system based on big data technology using the smart power plant prediction and scheduling method based on big data technology according to any one of claims 1 to 6, characterized in that: The system includes the following modules: An electricity consumption data acquisition module, which acquires historical electricity load data of the enterprise to be tested and extracts load report forecast information submitted by the enterprise to be tested each time from the historical data; A reporting data fluctuation characteristic analysis module, wherein the reporting data fluctuation characteristic analysis module obtains the actual order deviation rate corresponding to two adjacent load reporting forecast information of the enterprise under test, analyzes the relationship between the data deviation amount within the time period corresponding to the load reporting forecast information submitted by the enterprise under test each time and the data fluctuation characteristics of the actual power load information within the time period corresponding to the previous load reporting forecast information when the actual order deviation rate is the same, and obtains the reporting fluctuation characteristic function of the enterprise under test when the corresponding order deviation rate is obtained; A prediction analysis module, which combines the analysis results of the reported data fluctuation characteristic analysis module to build a data reporting interval adaptive model, and combines the historical electricity load data of the enterprise to be tested to obtain the prediction result corresponding to the load reporting prediction information submitted most recently at the current time; The power consumption early warning management module manages the power consumption information of the enterprise to be tested within the corresponding time period based on the prediction results obtained in the prediction analysis module, and issues early warnings for abnormal power consumption status.

8. The smart power plant prediction and dispatching system based on big data technology according to claim 7 is characterized by: The reported data fluctuation feature analysis module includes an order deviation acquisition module and a fluctuation feature analysis module. The order deviation acquisition module is used to obtain the actual order deviation rate corresponding to two consecutive load forecast report information of the enterprise under test; The fluctuation characteristic analysis module analyzes the relationship between the data deviation amount in the time period corresponding to the load reporting forecast information submitted by the enterprise to be tested each time and the data fluctuation characteristics of the actual power load information in the time period corresponding to the previous load reporting forecast information when the actual order deviation rate is the same, and obtains the reporting fluctuation characteristic function of the enterprise to be tested when the corresponding order deviation rate is obtained.

Images