Electrothermal conversion rate control method based on balance capability prediction

Abstract

The invention discloses an electrothermal conversion rate control method based on balance capability prediction, and the method comprises the steps: obtaining historical operation logs, analyzing historical operation data and a historical balance capability index in each historical operation log, and determining feature operation data; constructing a balance capability prediction model of the multi-energy system based on the feature operation data and a historical balance capability index, and generating a balance capability prediction index; analyzing the balance capability prediction index and the real-time electrothermal conversion rate according to a preset control analysis model, determining an initial control strategy, setting a test time length, obtaining the actual application degree of the initial control strategy in the test time length, and calculating the actual application degree of the initial control strategy. Whether a correction instruction is generated for the initial control strategy is judged according to the actual balance capability index and the actual application degree, the accuracy of balance capability prediction and the control effect of the control method for the electrothermal conversion rate are improved, and stable operation of the multi-energy system is guaranteed.

Description

Technical Field

[0001] The present application relates to the technical field of balancing capability prediction, and in particular to an electrothermal conversion rate control method based on balancing capability prediction. Background Art

[0002] Multi-energy energy balance capacity prediction refers to analyzing the supply and demand of multiple energy sources and predicting their balance state in the future, thereby providing a scientific basis for energy planning and decision-making, reducing energy waste and ensuring the stable operation of the multi-energy system.

[0003] In the prior art, the accuracy of balancing capacity prediction is low, resulting in poor control effect of the subsequent electrothermal conversion rate control method. Therefore, how to improve the accuracy of balancing capacity prediction and the control effect of the electrothermal conversion rate control method is a technical problem that needs to be solved. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides an electric heat conversion rate control method based on balancing capacity prediction. By analyzing historical operation data and historical balancing capacity index, characteristic operation data is determined, and a balancing capacity prediction model is constructed to obtain the balancing capacity prediction index for future time periods. The balancing capacity prediction index and the real-time electric heat speed rate are analyzed according to a preset control analysis model to determine the initial control strategy. According to the actual balancing capacity index and the actual application degree of the initial control strategy, it is determined whether to generate a correction instruction, thereby improving the accuracy of the balancing capacity prediction and the control effect of the electric heat conversion rate control method, and ensuring the stable operation of the multi-energy system.

[0005] In some embodiments of the present application, a method for controlling an electrothermal conversion rate based on a balance capability prediction is provided, comprising:

[0006] Obtain historical operation logs of the multi-energy system, analyze historical operation data and historical balance capacity index in each historical operation log, and determine characteristic operation data;

[0007] A balancing capacity prediction model for a multi-energy system is constructed based on characteristic operation data and historical balancing capacity indexes, and a balancing capacity prediction index for future periods is generated based on the balancing capacity prediction model;

[0008] Analyze the balancing capacity prediction index and the real-time electric-heat conversion rate according to a preset control analysis model, determine an initial control strategy, and generate a control instruction for the real-time electric-heat conversion rate based on the initial control strategy;

[0009] The inspection time is set, the actual application degree of the initial control strategy within the inspection time is obtained, and whether to generate a correction instruction for the initial control strategy is determined according to the actual balance ability index and the actual application degree.

[0010] In some embodiments of the present application, the historical operation data and the historical balance capability index in each historical operation log are analyzed to determine the characteristic operation data, including:

[0011] Obtain historical operation logs of multiple historical monitoring periods of the multi-energy system, and obtain each historical operation log to determine a historical balance capability index at each acquisition time node based on a preset balance capability index algorithm;

[0012] Taking the historical monitoring duration of each historical monitoring cycle as the time reference line and the preset time interval as the collection time node, the historical operation data and the historical balance capacity index in the historical operation log of the corresponding historical monitoring cycle are obtained according to the collection time node, and mapped to the corresponding time reference line to obtain the impact analysis diagram of each historical monitoring cycle;

[0013] Performing a fluctuation degree analysis on the historical balance capability index of all the collection time nodes in each impact analysis diagram, screening out the collection time nodes whose fluctuation degree of the historical balance capability index is greater than a preset fluctuation degree threshold, setting the screened adjacent collection time nodes as a characteristic fluctuation period, and determining the period to be analyzed for each characteristic fluctuation period;

[0014] Obtain the historical operation data of each time period to be analyzed in the same impact analysis diagram, and determine whether the change degree of each historical operation data of the time period to be analyzed is greater than a preset change degree threshold. If not, remove the corresponding historical operation data; if so, retain the corresponding historical operation data;

[0015] The first fluctuation feature of the retained historical operation data of each time period to be analyzed and the second fluctuation feature of the historical balance capability index of the corresponding characteristic fluctuation period are obtained, and the characteristic operation data are determined based on the first fluctuation feature and the second fluctuation feature.

[0016] In some embodiments of the present application, determining characteristic operation data based on the first fluctuation characteristic and the second fluctuation characteristic includes:

[0017] Determine the initial mutation time node of the retained historical operation data in the characteristic period to be analyzed, and obtain the first fluctuation feature of each retained historical operation data at the initial mutation time node and in the characteristic period to be analyzed, wherein the first fluctuation feature includes the fluctuation value, fluctuation speed and fluctuation trend of the corresponding historical operation data at the initial mutation time node and multiple preset analysis time nodes in the characteristic period to be analyzed;

[0018] Obtaining a second fluctuation feature of the historical balance capacity index of the characteristic fluctuation period corresponding to each characteristic period to be analyzed, wherein the second fluctuation feature includes fluctuation values, fluctuation rates, and fluctuation trends of the historical balance capacity index at a plurality of preset analysis time nodes in the corresponding characteristic fluctuation period;

[0019] Perform similarity analysis on the second fluctuation feature of the historical balance capacity index in the characteristic fluctuation period and the first fluctuation feature of each historical operation data in the period to be analyzed corresponding to the characteristic fluctuation period, screen out the historical operation data with a similarity greater than a preset similarity threshold, and set them as the focus operation data in the corresponding characteristic fluctuation period;

[0020] Presetting a preset balance capability index interval, and determining the preset balance capability index interval in which the historical balance capability indexes of all characteristic fluctuation periods in different impact analysis diagrams are located;

[0021] Comparing the concerned operation data in each characteristic fluctuation period in the same preset balance ability index interval, and obtaining the occurrence frequency of the same concerned operation data in each characteristic fluctuation period in the same preset balance ability index interval;

[0022] If the occurrence frequency is less than the preset occurrence frequency threshold, the corresponding attention operation data is eliminated. If the occurrence frequency is greater than the preset occurrence frequency threshold, the corresponding attention operation data is retained and the retained attention operation data is set as the characteristic operation data.

[0023] In some embodiments of the present application, the fluctuation trend of each historical operation data in the time period to be analyzed at all preset analysis time nodes is compared with the fluctuation trend of the historical balance capacity index in the characteristic fluctuation period at all preset analysis time nodes to obtain the degree of deviation of the fluctuation trend of each historical operation data and the historical balance capacity index;

[0024] Based on the time node comparison principle, each historical operation data in the analysis period is matched with the preset analysis time node of the historical balance capacity index in the characteristic fluctuation period to obtain multiple preset analysis time node groups;

[0025] Obtain the fluctuation values ​​of the first fluctuation feature and the second fluctuation feature of each preset analysis time node group and make a difference to obtain the fluctuation value difference of each preset analysis time node group;

[0026] Obtaining the fluctuation speeds of the first fluctuation feature and the second fluctuation feature of each preset analysis time node group and subtracting them to obtain the fluctuation speed difference value of each preset analysis time node group;

[0027] Generate the similarity between each historical operation data and the corresponding historical balance capability index according to the fluctuation trend deviation degree, the fluctuation value difference of each preset analysis time node group, and the fluctuation speed difference;

[0028] The calculation formula of the similarity is:

[0029]

[0030] Among them, D is the similarity, x1 is the first similarity conversion coefficient, q1 is the weight coefficient of the fluctuation trend, b1 is the degree of deviation of the fluctuation trend, x2 is the second similarity conversion coefficient, q2 is the weight coefficient of the fluctuation value, b2i is the fluctuation value difference of the i-th preset analysis time node group, m is the total number of preset analysis time node groups, x3 is the third similarity conversion coefficient, q3 is the weight coefficient of the fluctuation speed, and b3i is the fluctuation speed difference of the i-th preset analysis time node group.

[0031] In some embodiments of the present application, a balancing capacity prediction model of a multi-energy system is constructed based on characteristic operation data and historical balancing capacity index, including:

[0032] Obtain the second fluctuation characteristics of the historical balance capacity index of all characteristic fluctuation periods and the first fluctuation characteristics of the characteristic operation data of the period to be analyzed corresponding to the characteristic fluctuation period;

[0033] According to the same characteristic operation data of all time periods to be analyzed and the first fluctuation characteristics of the same characteristic operation data, the training input data and the test input data are divided, and the historical balance capability index of the characteristic fluctuation period corresponding to the time period to be analyzed in the training input data and the second fluctuation characteristics of the historical balance capability index are used as training output data to obtain the initial balance capability prediction model of each characteristic operation data and the historical balance capability index;

[0034] Generate the credibility of the corresponding initial balance ability prediction model based on the test input data, and iteratively train the initial balance ability prediction model whose credibility is less than a preset credibility threshold until the credibility is greater than the preset credibility threshold;

[0035] According to the credibility of each initial balance ability prediction model, a fusion coefficient of the corresponding initial balance ability prediction model is set;

[0036] All initial balancing capacity prediction models and corresponding fusion coefficients are fused, and the fused model is set as the balancing capacity prediction model of the multi-energy system.

[0037] In some embodiments of the present application, generating a balance ability prediction index for a future period based on a balance ability prediction model includes:

[0038] Acquire the real-time characteristic operation data of the multi-energy system during the preset monitoring period, analyze the real-time characteristic operation data during the preset monitoring period, and determine the real-time fluctuation characteristics of the real-time characteristic operation data during the preset monitoring period;

[0039] All real-time characteristic operation data and the real-time fluctuation characteristics of the corresponding real-time characteristic operation data are input into the balance capacity prediction model to obtain the balance capacity prediction index for the future period.

[0040] In some embodiments of the present application, the balance capability prediction index and the real-time electric-thermal conversion rate are analyzed according to a preset control analysis model to determine an initial control strategy, including:

[0041] Analyze the current balance ability prediction index based on the preset control analysis model to obtain a preset control strategy library corresponding to the current balance ability prediction index;

[0042] The preset control strategy library includes a plurality of preset electrothermal conversion rate differences of the current balance capability prediction index, and each preset electrothermal conversion rate difference is associated with a specific preset control strategy;

[0043] Acquire the real-time electrothermal conversion rate, and subtract the real-time electrothermal conversion rate from the standard electrothermal conversion rate corresponding to the current balance capacity prediction index to obtain the real-time electrothermal conversion rate difference;

[0044] A similarity analysis is performed between the real-time electrothermal conversion rate difference and several preset electrothermal conversion rate differences in the preset control strategy library, and the preset control strategy corresponding to the preset electrothermal conversion rate difference with the greatest similarity is set as the initial control strategy for the real-time electrothermal conversion rate.

[0045] In some embodiments of the present application, obtaining the actual application degree of the initial control strategy within the inspection time includes:

[0046] Pre-set multiple application evaluation indicators;

[0047] Acquire the real-time operation data within the inspection time, and determine the associated operation data of each application evaluation indicator according to the degree of association between the application evaluation indicator and the real-time operation data;

[0048] Comparing the associated operation data with the standard operation data corresponding to the application evaluation index to obtain a first deviation degree between the associated operation data and the standard operation data, and generating a sub-application degree of the associated operation data according to the first deviation degree;

[0049] Obtaining a second deviation degree between the associated operating data and the standard operating data before the initial control strategy, and generating a change trend and a change rate of the deviation degree from the second deviation degree of the associated operating data to the first deviation degree;

[0050] Generate a first compensation coefficient of the sub-application degree corresponding to the associated operation data according to the change trend; generate a second compensation coefficient of the sub-application degree corresponding to the associated operation data according to the change rate;

[0051] Generate an actual application degree of the initial control strategy according to the sub-application degree of the associated operation data, the first compensation coefficient, the second compensation coefficient, and the weight coefficient of the corresponding application evaluation index;

[0052] The calculation formula of the actual application degree is:

[0053]

[0054] Among them, Y is the actual application degree, f1 is the weight coefficient of the first application evaluation index, n1 is the total number of associated operation data of the first application evaluation index, Z1 s1 is the sub-application degree of the s1th associated running data of the first application evaluation indicator, c11 s1 is the first compensation coefficient of the s1th associated operation data of the first application evaluation index, c21 s1 is the second compensation coefficient of the s1th associated operation data of the first application evaluation index, Zr s1 is the sub-application degree of the srth associated running data of the rth application evaluation indicator, c1r sr is the first compensation coefficient of the srth associated operation data of the rth application evaluation index, c2r sr is the second compensation coefficient of the srth associated operating data of the rth application evaluation indicator, and nr is the total number of associated operating data of the rth application evaluation indicator.

[0055] In some embodiments of the present application, judging whether to generate a correction instruction for the initial control strategy according to the actual balance capability index and the actual application degree includes:

[0056] Pre-set index difference threshold;

[0057] Obtain the index difference between the actual balance capability index and the balance capability prediction index at the same time node. If the index difference is less than the index difference threshold, no correction instruction is sent. If the index difference is greater than the index difference threshold, a first-level correction instruction of the initial control strategy is sent.

[0058] Pre-set application threshold;

[0059] If the actual application degree is greater than the application degree threshold, no correction instruction is sent;

[0060] If the actual application degree is less than the application degree threshold, a secondary correction instruction of the initial control strategy is sent.

[0061] Compared with the prior art, the electrothermal conversion rate control method based on the balance capacity prediction in the embodiment of the present application has the following beneficial effects:

[0062] By analyzing historical operating data and historical balancing capacity index, determining characteristic operating data, and constructing a balancing capacity prediction model, the balancing capacity prediction index for future time periods is obtained. The balancing capacity prediction index and the real-time electric heating speed rate are analyzed according to the preset control analysis model to determine the initial control strategy. Based on the actual balancing capacity index and the actual application of the initial control strategy, it is determined whether to generate correction instructions, thereby improving the accuracy of balancing capacity prediction and the control effect of the electric heating conversion rate control method, and ensuring the stable operation of the multi-energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a flow chart of an electrothermal conversion rate control method based on balance capacity prediction in a preferred embodiment of the present application. DETAILED DESCRIPTION

[0064] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0065] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0066] The terms "first", "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0067] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0068] like Figure 1 As shown, a method for controlling an electrothermal conversion rate based on a balance capability prediction in a preferred embodiment of the present application includes:

[0069] Step S101: Obtain historical operation logs of the multi-energy system, analyze historical operation data and historical balance capacity index in each historical operation log, and determine characteristic operation data;

[0070] Step S102: constructing a balancing capacity prediction model for the multi-energy system according to the characteristic operation data and the historical balancing capacity index, and generating a balancing capacity prediction index for a future period based on the balancing capacity prediction model;

[0071] Step S103: analyzing the balancing capability prediction index and the real-time electrothermal conversion rate according to a preset control analysis model, determining an initial control strategy, and generating a control instruction for the real-time electrothermal conversion rate based on the initial control strategy;

[0072] Step S104: setting the inspection time, obtaining the actual application degree of the initial control strategy within the inspection time, and determining whether to generate a correction instruction for the initial control strategy according to the actual balance capability index and the actual application degree.

[0073] In some embodiments of the present application, the historical operation data and the historical balance capability index in each historical operation log are analyzed to determine the characteristic operation data, including:

[0074] Obtain historical operation logs of multiple historical monitoring periods of the multi-energy system, and obtain each historical operation log to determine a historical balance capability index at each acquisition time node based on a preset balance capability index algorithm;

[0075] Taking the historical monitoring duration of each historical monitoring cycle as the time reference line and the preset time interval as the collection time node, the historical operation data and the historical balance capacity index in the historical operation log of the corresponding historical monitoring cycle are obtained according to the collection time node, and mapped to the corresponding time reference line to obtain the impact analysis diagram of each historical monitoring cycle;

[0076] Performing a fluctuation degree analysis on the historical balance capability index of all the collection time nodes in each impact analysis diagram, screening out the collection time nodes whose fluctuation degree of the historical balance capability index is greater than a preset fluctuation degree threshold, setting the screened adjacent collection time nodes as a characteristic fluctuation period, and determining the period to be analyzed for each characteristic fluctuation period;

[0077] Obtain the historical operation data of each time period to be analyzed in the same impact analysis diagram, and determine whether the change degree of each historical operation data of the time period to be analyzed is greater than a preset change degree threshold. If not, remove the corresponding historical operation data; if so, retain the corresponding historical operation data;

[0078] The first fluctuation feature of the retained historical operation data of each time period to be analyzed and the second fluctuation feature of the historical balance capability index of the corresponding characteristic fluctuation period are obtained, and the characteristic operation data are determined based on the first fluctuation feature and the second fluctuation feature.

[0079] In this embodiment, the preset balance capability index algorithm is determined based on a plurality of methods capable of evaluating the multi-energy balance capability index.

[0080] In this embodiment, the time period to be analyzed refers to a preset time period adjacent to each characteristic fluctuation time period, wherein the preset time period is 30 minutes.

[0081] In this embodiment, it is determined whether the degree of change of the historical operating data within the time period to be analyzed is greater than a preset change degree threshold, so as to first eliminate the operating data that has no effect on the historical balance capacity index, reduce the amount of data processing and analysis, and improve the judgment speed of subsequent characteristic operating data and the accuracy of the balance capacity prediction model.

[0082] In some embodiments of the present application, determining characteristic operation data based on the first fluctuation characteristic and the second fluctuation characteristic includes:

[0083] Determine the initial mutation time node of the retained historical operation data in the characteristic period to be analyzed, and obtain the first fluctuation feature of each retained historical operation data at the initial mutation time node and in the characteristic period to be analyzed, wherein the first fluctuation feature includes the fluctuation value, fluctuation speed and fluctuation trend of the corresponding historical operation data at the initial mutation time node and multiple preset analysis time nodes in the characteristic period to be analyzed;

[0084] Obtaining a second fluctuation feature of the historical balance capacity index of the characteristic fluctuation period corresponding to each characteristic period to be analyzed, wherein the second fluctuation feature includes fluctuation values, fluctuation rates, and fluctuation trends of the historical balance capacity index at a plurality of preset analysis time nodes in the corresponding characteristic fluctuation period;

[0085] Perform similarity analysis on the second fluctuation feature of the historical balance capacity index in the characteristic fluctuation period and the first fluctuation feature of each historical operation data in the period to be analyzed corresponding to the characteristic fluctuation period, screen out the historical operation data with a similarity greater than a preset similarity threshold, and set them as the focus operation data in the corresponding characteristic fluctuation period;

[0086] Presetting a preset balance capability index interval, and determining the preset balance capability index interval in which the historical balance capability indexes of all characteristic fluctuation periods in different impact analysis diagrams are located;

[0087] Comparing the concerned operation data in each characteristic fluctuation period in the same preset balance ability index interval, and obtaining the occurrence frequency of the same concerned operation data in each characteristic fluctuation period in the same preset balance ability index interval;

[0088] If the occurrence frequency is less than the preset occurrence frequency threshold, the corresponding attention operation data is eliminated. If the occurrence frequency is greater than the preset occurrence frequency threshold, the corresponding attention operation data is retained and the retained attention operation data is set as the characteristic operation data.

[0089] In this embodiment, the occurrence frequency=the number of occurrences of the same focused operating data in each characteristic fluctuation period in the same preset balance ability index interval / the number of all characteristic fluctuation periods in the same preset balance ability index interval.

[0090] In this embodiment, the preset analysis time nodes refer to time nodes with the same time intervals set in advance in the time period to be analyzed and the characteristic fluctuation time period, and the preset analysis time nodes in each time period to be analyzed are set according to the initial mutation nodes of each historical operation data, while the preset analysis time nodes in the characteristic fluctuation time period are set from the beginning.

[0091] In this embodiment, the preset balance capability index interval in which the historical balance capability index of the characteristic fluctuation period is located means that the maximum historical balance capability index and the minimum historical balance capability index of the characteristic fluctuation period are both in the corresponding preset balance capability index interval, and the historical balance capability index of the characteristic fluctuation period is divided into the corresponding preset balance capability index interval, and the focus operation data of multiple characteristic fluctuation periods are comprehensively analyzed to improve the accuracy of subsequent characteristic operation data, thereby laying the foundation for the subsequent construction of a balance capability prediction model.

[0092] In this embodiment, by comparing the fluctuation characteristics of the historical balance capability index and each historical operating data at multiple preset analysis time nodes, the change relationship between the historical balance capability index and the historical operating data at the corresponding preset analysis time nodes is obtained, so as to determine the operating data of interest, and compare the operating data of interest in all characteristic fluctuation periods belonging to the same preset balance capability index interval to obtain the frequency of occurrence of the operating data of interest in the corresponding preset balance capability index interval, and eliminate the operating data of interest with a lower frequency of occurrence, retain the remaining operating data of interest and set it as characteristic operating data, so as to improve the accuracy of the characteristic operating data.

[0093] In this embodiment, the characteristic operation data refers to data that causes large fluctuations in the balance capacity index. The accuracy of the characteristic operation data is improved, and a balance capacity prediction model is constructed based on the fluctuation characteristics of the characteristic operation data and the historical balance capacity index. The accuracy of the balance capacity prediction model is improved to determine the control efficiency of the control method for the subsequent electric heat conversion rate and ensure the stable operation of the multi-energy system.

[0094] In some embodiments of the present application, the fluctuation trend of each historical operation data in the time period to be analyzed at all preset analysis time nodes is compared with the fluctuation trend of the historical balance capacity index in the characteristic fluctuation period at all preset analysis time nodes to obtain the degree of deviation of the fluctuation trend of each historical operation data and the historical balance capacity index;

[0095] Based on the time node comparison principle, each historical operation data in the analysis period is matched with the preset analysis time node of the historical balance capacity index in the characteristic fluctuation period to obtain multiple preset analysis time node groups;

[0096] Obtain the fluctuation values ​​of the first fluctuation feature and the second fluctuation feature of each preset analysis time node group and make a difference to obtain the fluctuation value difference of each preset analysis time node group;

[0097] Obtaining the fluctuation speeds of the first fluctuation feature and the second fluctuation feature of each preset analysis time node group and subtracting them to obtain the fluctuation speed difference value of each preset analysis time node group;

[0098] Generate the similarity between each historical operation data and the corresponding historical balance capability index according to the fluctuation trend deviation degree, the fluctuation value difference of each preset analysis time node group, and the fluctuation speed difference;

[0099] The calculation formula of the similarity is:

[0100]

[0101] Among them, D is the similarity, x1 is the first similarity conversion coefficient, q1 is the weight coefficient of the fluctuation trend, b1 is the degree of deviation of the fluctuation trend, x2 is the second similarity conversion coefficient, q2 is the weight coefficient of the fluctuation value, b2i is the fluctuation value difference of the i-th preset analysis time node group, m is the total number of preset analysis time node groups, x3 is the third similarity conversion coefficient, q3 is the weight coefficient of the fluctuation speed, and b3i is the fluctuation speed difference of the i-th preset analysis time node group.

[0102] In this embodiment, the time node comparison principle refers to comparing time nodes with the same time interval from the initial time node to the last time node, so as to obtain multiple matching preset analysis time node groups, and the preset analysis time node groups are all preset analysis time nodes in the time period to be analyzed and the corresponding preset analysis time nodes in the characteristic fluctuation time period.

[0103] In this embodiment, the degree of fluctuation trend deviation refers to the degree of deviation in the direction of the fluctuation trends of the first fluctuation feature and the second fluctuation feature and the value of the up and down fluctuations. The smaller the degree of fluctuation trend deviation, the smaller the difference in fluctuation value and the smaller the difference in fluctuation speed, the greater the similarity.

[0104] In this embodiment, by comparing the fluctuation characteristics of historical operating data with the corresponding historical balance capability index, the similarity of the fluctuations of the historical operating data and the historical balance capability index in the time period to be analyzed and the characteristic fluctuation period is determined, so as to accurately screen out the characteristic operating data and lay the foundation for the subsequent construction of the balance capability prediction model.

[0105] In some embodiments of the present application, a balancing capacity prediction model of a multi-energy system is constructed based on characteristic operation data and historical balancing capacity index, including:

[0106] Obtain the second fluctuation characteristics of the historical balance capacity index of all characteristic fluctuation periods and the first fluctuation characteristics of the characteristic operation data of the period to be analyzed corresponding to the characteristic fluctuation period;

[0107] According to the same characteristic operation data of all time periods to be analyzed and the first fluctuation characteristics of the same characteristic operation data, the training input data and the test input data are divided, and the historical balance capability index of the characteristic fluctuation period corresponding to the time period to be analyzed in the training input data and the second fluctuation characteristics of the historical balance capability index are used as training output data to obtain the initial balance capability prediction model of each characteristic operation data and the historical balance capability index;

[0108] Generate the credibility of the corresponding initial balance ability prediction model based on the test input data, and iteratively train the initial balance ability prediction model whose credibility is less than a preset credibility threshold until the credibility is greater than the preset credibility threshold;

[0109] According to the credibility of each initial balance ability prediction model, a fusion coefficient of the corresponding initial balance ability prediction model is set;

[0110] All initial balancing capacity prediction models and corresponding fusion coefficients are fused, and the fused model is set as the balancing capacity prediction model of the multi-energy system.

[0111] In this embodiment, the lag time refers to the length of time it takes for a mutation in the historical balance capability index to occur after a mutation in the characteristic operation data occurs. The shorter the lag time, the faster the corresponding characteristic operation data affects the historical balance capability index, and vice versa.

[0112] In this embodiment, model fusion of all initial balance capacity prediction models and corresponding weight coefficients refers to combining the capabilities of different initial balance capacity prediction models to compensate for the deviations and errors of a single initial balance capacity prediction model. Credibility refers to the accuracy of the initial balance capacity prediction model. When the credibility is greater, the fusion coefficient of the corresponding initial balance capacity prediction model is greater, that is, the proportion of the predicted value obtained by the corresponding initial balance capacity prediction model is greater, so as to achieve the closest and more accurate results, laying the foundation for the subsequent setting of the electrothermal conversion rate control method.

[0113] In some embodiments of the present application, generating a balance ability prediction index for a future period based on a balance ability prediction model includes:

[0114] Acquire the real-time characteristic operation data of the multi-energy system during the preset monitoring period, analyze the real-time characteristic operation data during the preset monitoring period, and determine the real-time fluctuation characteristics of the real-time characteristic operation data during the preset monitoring period;

[0115] All real-time characteristic operation data and the real-time fluctuation characteristics of the corresponding real-time characteristic operation data are input into the balance capacity prediction model to obtain the balance capacity prediction index for the future period.

[0116] In this embodiment, the preset monitoring period and the period to be analyzed are of the same length, and the real-time fluctuation characteristics include the fluctuation speed, fluctuation value and fluctuation trend of the real-time characteristic operation data within the preset monitoring period.

[0117] In this embodiment, the balancing capacity prediction model analyzes the real-time characteristic operation data of the preset monitoring period to obtain the balancing capacity prediction index in the future period and the predicted fluctuation value, predicted fluctuation speed and predicted fluctuation trend of the balancing capacity prediction index, thereby laying a data foundation for the subsequent formulation of a reasonable control plan for the electric-to-heat conversion rate, improving the effectiveness and accuracy of the control method, and ensuring the stable operation of the multi-energy system.

[0118] In some embodiments of the present application, the balance capability prediction index and the real-time electric-thermal conversion rate are analyzed according to a preset control analysis model to determine an initial control strategy, including:

[0119] Analyze the current balance ability prediction index based on the preset control analysis model to obtain a preset control strategy library corresponding to the current balance ability prediction index;

[0120] The preset control strategy library includes a plurality of preset electrothermal conversion rate differences of the current balance capability prediction index, and each preset electrothermal conversion rate difference is associated with a specific preset control strategy;

[0121] Acquire the real-time electrothermal conversion rate, and subtract the real-time electrothermal conversion rate from the standard electrothermal conversion rate corresponding to the current balance capacity prediction index to obtain the real-time electrothermal conversion rate difference;

[0122] A similarity analysis is performed between the real-time electrothermal conversion rate difference and several preset electrothermal conversion rate differences in the preset control strategy library, and the preset control strategy corresponding to the preset electrothermal conversion rate difference with the greatest similarity is set as the initial control strategy for the real-time electrothermal conversion rate.

[0123] In this embodiment, the preset control analysis model includes multiple historical balance capability indexes and the optimal historical control strategy for the historical electrothermal conversion rate under each historical balance capability index. The historical application degree of the optimal historical control strategy is greater than the preset application degree threshold and has the largest historical application degree among all historical control strategies corresponding to the historical electrothermal conversion rate.

[0124] In this embodiment, the similarity refers to the similarity between the real-time electrothermal conversion rate difference and the preset electrothermal conversion rate difference. The maximum similarity means that the difference between the real-time electrothermal conversion rate difference and the preset electrothermal conversion rate difference is the smallest.

[0125] In this embodiment, a preset control strategy library of the balancing capacity prediction index is determined by a preset control analysis model, and an initial control strategy is determined according to the similarity between the real-time electrothermal conversion rate difference and the preset electrothermal conversion rate difference to generate control instructions for the real-time electrothermal conversion rate. The inspection duration is set, and the initial control strategy is continuously optimized through real-time feedback to achieve the best control effect of the electrothermal conversion rate and ensure the stable operation of the multi-energy system.

[0126] In some embodiments of the present application, obtaining the actual application degree of the initial control strategy within the inspection time includes:

[0127] Pre-set multiple application evaluation indicators;

[0128] Acquire the real-time operation data within the inspection time, and determine the associated operation data of each application evaluation indicator according to the degree of association between the application evaluation indicator and the real-time operation data;

[0129] Comparing the associated operation data with the standard operation data corresponding to the application evaluation index to obtain a first deviation degree between the associated operation data and the standard operation data, and generating a sub-application degree of the associated operation data according to the first deviation degree;

[0130] Obtaining a second deviation degree between the associated operating data and the standard operating data before the initial control strategy, and generating a change trend and a change rate of the deviation degree from the second deviation degree of the associated operating data to the first deviation degree;

[0131] Generate a first compensation coefficient of the sub-application degree corresponding to the associated operation data according to the change trend; generate a second compensation coefficient of the sub-application degree corresponding to the associated operation data according to the change rate;

[0132] Generate an actual application degree of the initial control strategy according to the sub-application degree of the associated operation data, the first compensation coefficient, the second compensation coefficient, and the weight coefficient of the corresponding application evaluation index;

[0133] The calculation formula of the actual application degree is:

[0134]

[0135] Among them, Y is the actual application degree, f1 is the weight coefficient of the first application evaluation index, n1 is the total number of associated operation data of the first application evaluation index, Z1 s1 is the sub-application degree of the s1th associated running data of the first application evaluation indicator, c11 s1 is the first compensation coefficient of the s1th associated operation data of the first application evaluation index, c21 s1 is the second compensation coefficient of the s1th associated operation data of the first application evaluation index, Zr s1 is the sub-application degree of the srth associated running data of the rth application evaluation indicator, c1r sr is the first compensation coefficient of the srth associated operation data of the rth application evaluation index, c2r sr is the second compensation coefficient of the srth associated operating data of the rth application evaluation indicator, and nr is the total number of associated operating data of the rth application evaluation indicator.

[0136] In this embodiment, the inspection duration refers to the duration set in advance for inspecting the control effect of the initial control strategy, and the degree of correlation between the application evaluation index and the real-time operation data is set according to the correlation between the historical operation data and the application evaluation index.

[0137] In this embodiment, application evaluation indicators include system stability, power utilization effectiveness, performance efficiency, energy-saving efficiency, etc., and the change trend of the deviation degree includes a normal change trend, an abnormal change trend, and no change trend. When it is a normal change trend, the first compensation coefficient is 1, when it is an abnormal change trend, the first compensation coefficient is -1, and when it is no change trend, the first compensation coefficient is 0.5. When the change rate is greater, the second compensation coefficient is greater, and vice versa, the smaller it is, and the value range of the second compensation coefficient is (0.8, 1.2).

[0138] In this embodiment, whether the actual control effect of the initial control strategy meets the requirements is judged according to the actual application degree of the initial control strategy, and the deficiencies of the initial control strategy are discovered and adjusted in time to ensure the efficient and stable operation of the multi-energy system.

[0139] In some embodiments of the present application, judging whether to generate a correction instruction for the initial control strategy according to the actual balance capability index and the actual application degree includes:

[0140] Pre-set index difference threshold;

[0141] Obtain the index difference between the actual balance capability index and the balance capability prediction index at the same time node. If the index difference is less than the index difference threshold, no correction instruction is sent. If the index difference is greater than the index difference threshold, a first-level correction instruction of the initial control strategy is sent.

[0142] Pre-set application threshold;

[0143] If the actual application degree is greater than the application degree threshold, no correction instruction is sent;

[0144] If the actual application degree is less than the application degree threshold, a secondary correction instruction of the initial control strategy is sent.

[0145] In this embodiment, the first-level correction instruction is to analyze the actual balance capability index according to the preset control analysis model, re-determine the initial control strategy or fine-tune the current initial control strategy, and adjust the balance capability prediction model. The second-level correction instruction is to adjust the initial control strategy according to the difference between the actual application degree and the application degree threshold.

[0146] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A method for controlling the electrothermal conversion rate based on the prediction of the balancing capability, characterized in that: include: Obtain historical operation logs of the multi-energy system, analyze historical operation data and historical balance capacity index in each historical operation log, and determine characteristic operation data; A balancing capacity prediction model for a multi-energy system is constructed based on characteristic operation data and historical balancing capacity indexes, and a balancing capacity prediction index for future periods is generated based on the balancing capacity prediction model; Analyze the balancing capacity prediction index and the real-time electric-heat conversion rate according to a preset control analysis model, determine an initial control strategy, and generate a control instruction for the real-time electric-heat conversion rate based on the initial control strategy; The inspection time is set, the actual application degree of the initial control strategy within the inspection time is obtained, and whether to generate a correction instruction for the initial control strategy is determined according to the actual balance ability index and the actual application degree.

2. The electrothermal conversion rate control method based on balance capability prediction according to claim 1, characterized in that: Analyze the historical operation data and historical balance capability index in each historical operation log to determine the characteristic operation data, including: Obtain historical operation logs of multiple historical monitoring periods of the multi-energy system, and obtain each historical operation log to determine a historical balance capability index at each acquisition time node based on a preset balance capability index algorithm; Taking the historical monitoring duration of each historical monitoring cycle as the time reference line and the preset time interval as the collection time node, the historical operation data and the historical balance capacity index in the historical operation log of the corresponding historical monitoring cycle are obtained according to the collection time node, and mapped to the corresponding time reference line to obtain the impact analysis diagram of each historical monitoring cycle; Performing a fluctuation degree analysis on the historical balance capability index of all the collection time nodes in each impact analysis diagram, screening out the collection time nodes whose fluctuation degree of the historical balance capability index is greater than a preset fluctuation degree threshold, setting the screened adjacent collection time nodes as a characteristic fluctuation period, and determining the period to be analyzed for each characteristic fluctuation period; Obtain the historical operation data of each time period to be analyzed in the same impact analysis diagram, and determine whether the change degree of each historical operation data of the time period to be analyzed is greater than a preset change degree threshold. If not, remove the corresponding historical operation data; if so, retain the corresponding historical operation data; The first fluctuation feature of the retained historical operation data of each time period to be analyzed and the second fluctuation feature of the historical balance capability index of the corresponding characteristic fluctuation period are obtained, and the characteristic operation data are determined based on the first fluctuation feature and the second fluctuation feature.

3. The electrothermal conversion rate control method based on balance capability prediction according to claim 2, characterized in that: Determining characteristic operation data based on the first fluctuation characteristic and the second fluctuation characteristic includes: Determine the initial mutation time node of the retained historical operation data in the characteristic period to be analyzed, and obtain the first fluctuation feature of each retained historical operation data at the initial mutation time node and in the characteristic period to be analyzed, wherein the first fluctuation feature includes the fluctuation value, fluctuation speed and fluctuation trend of the corresponding historical operation data at the initial mutation time node and multiple preset analysis time nodes in the characteristic period to be analyzed; Obtaining a second fluctuation feature of the historical balance capacity index of the characteristic fluctuation period corresponding to each characteristic period to be analyzed, wherein the second fluctuation feature includes fluctuation values, fluctuation rates, and fluctuation trends of the historical balance capacity index at a plurality of preset analysis time nodes in the corresponding characteristic fluctuation period; Perform similarity analysis on the second fluctuation feature of the historical balance capacity index in the characteristic fluctuation period and the first fluctuation feature of each historical operation data in the period to be analyzed corresponding to the characteristic fluctuation period, screen out the historical operation data with a similarity greater than a preset similarity threshold, and set them as the focus operation data in the corresponding characteristic fluctuation period; Presetting a preset balance capability index interval, and determining the preset balance capability index interval in which the historical balance capability indexes of all characteristic fluctuation periods in different impact analysis diagrams are located; Comparing the concerned operation data in each characteristic fluctuation period in the same preset balance ability index interval, and obtaining the occurrence frequency of the same concerned operation data in each characteristic fluctuation period in the same preset balance ability index interval; If the occurrence frequency is less than the preset occurrence frequency threshold, the corresponding attention operation data is eliminated. If the occurrence frequency is greater than the preset occurrence frequency threshold, the corresponding attention operation data is retained and the retained attention operation data is set as the characteristic operation data.

4. The electrothermal conversion rate control method based on balance capability prediction according to claim 3, characterized in that: Compare the fluctuation trend of each historical operation data in the period to be analyzed at all preset analysis time nodes with the fluctuation trend of the historical balance capacity index in the characteristic fluctuation period at all preset analysis time nodes to obtain the degree of deviation of the fluctuation trend of each historical operation data and the historical balance capacity index; Based on the time node comparison principle, each historical operation data in the analysis period is matched with the preset analysis time node of the historical balance capacity index in the characteristic fluctuation period to obtain multiple preset analysis time node groups; Obtaining the fluctuation values ​​of the first fluctuation feature and the second fluctuation feature of each preset analysis time node group and making a difference to obtain the fluctuation value difference of each preset analysis time node group; Obtaining the fluctuation speeds of the first fluctuation feature and the second fluctuation feature of each preset analysis time node group and subtracting them to obtain the fluctuation speed difference value of each preset analysis time node group; Generate the similarity between each historical operation data and the corresponding historical balance capacity index according to the fluctuation trend deviation degree, the fluctuation value difference of each preset analysis time node group, and the fluctuation speed difference; The calculation formula of the similarity is: Among them, D is the similarity, x1 is the first similarity conversion coefficient, q1 is the weight coefficient of the fluctuation trend, b1 is the degree of deviation of the fluctuation trend, x2 is the second similarity conversion coefficient, q2 is the weight coefficient of the fluctuation value, b2i is the fluctuation value difference of the i-th preset analysis time node group, m is the total number of preset analysis time node groups, x3 is the third similarity conversion coefficient, q3 is the weight coefficient of the fluctuation speed, and b3i is the fluctuation speed difference of the i-th preset analysis time node group.

5. The method for controlling the electrothermal conversion rate based on the prediction of the balancing capability according to claim 4, characterized in that: A balancing capacity prediction model for a multi-energy system is constructed based on characteristic operation data and historical balancing capacity index, including: Obtain the second fluctuation characteristics of the historical balance capacity index of all characteristic fluctuation periods and the first fluctuation characteristics of the characteristic operation data of the period to be analyzed corresponding to the characteristic fluctuation period; According to the same characteristic operation data of all time periods to be analyzed and the first fluctuation characteristics of the same characteristic operation data, the training input data and the test input data are divided, and the historical balance capability index of the characteristic fluctuation period corresponding to the time period to be analyzed in the training input data and the second fluctuation characteristics of the historical balance capability index are used as training output data to obtain the initial balance capability prediction model of each characteristic operation data and the historical balance capability index; Generate the credibility of the corresponding initial balance ability prediction model based on the test input data, and iteratively train the initial balance ability prediction model whose credibility is less than a preset credibility threshold until the credibility is greater than the preset credibility threshold; According to the credibility of each initial balance ability prediction model, a fusion coefficient of the corresponding initial balance ability prediction model is set; All initial balancing capacity prediction models and corresponding fusion coefficients are fused, and the fused model is set as the balancing capacity prediction model of the multi-energy system.

6. The method for controlling the electrothermal conversion rate based on the prediction of the balancing capability according to claim 5, characterized in that: The balance ability prediction index for the future period is generated based on the balance ability prediction model, including: Acquire the real-time characteristic operation data of the multi-energy system during the preset monitoring period, analyze the real-time characteristic operation data during the preset monitoring period, and determine the real-time fluctuation characteristics of the real-time characteristic operation data during the preset monitoring period; All real-time characteristic operation data and the real-time fluctuation characteristics of the corresponding real-time characteristic operation data are input into the balance capacity prediction model to obtain the balance capacity prediction index for the future period.

7. The method for controlling the electrothermal conversion rate based on the prediction of the balancing capability according to claim 6, characterized in that: The balance capacity prediction index and real-time electric-thermal conversion rate are analyzed according to the preset control analysis model to determine the initial control strategy, including: Analyze the current balance ability prediction index based on the preset control analysis model to obtain a preset control strategy library corresponding to the current balance ability prediction index; The preset control strategy library includes a plurality of preset electrothermal conversion rate differences of the current balance capability prediction index, and each preset electrothermal conversion rate difference is associated with a specific preset control strategy; Acquire the real-time electrothermal conversion rate, and subtract the real-time electrothermal conversion rate from the standard electrothermal conversion rate corresponding to the current balance capacity prediction index to obtain the real-time electrothermal conversion rate difference; A similarity analysis is performed between the real-time electrothermal conversion rate difference and several preset electrothermal conversion rate differences in the preset control strategy library, and the preset control strategy corresponding to the preset electrothermal conversion rate difference with the greatest similarity is set as the initial control strategy for the real-time electrothermal conversion rate.

8. The method for controlling the electrothermal conversion rate based on the prediction of the balancing capability according to claim 7, characterized in that: Obtain the actual application of the initial control strategy within the inspection period, including: Pre-set multiple application evaluation indicators; Acquire the real-time operation data within the inspection time, and determine the associated operation data of each application evaluation indicator according to the degree of association between the application evaluation indicator and the real-time operation data; Comparing the associated operation data with the standard operation data corresponding to the application evaluation index to obtain a first deviation degree between the associated operation data and the standard operation data, and generating a sub-application degree of the associated operation data according to the first deviation degree; Obtaining a second deviation degree between the associated operating data and the standard operating data before the initial control strategy, and generating a change trend and a change rate of the deviation degree from the second deviation degree of the associated operating data to the first deviation degree; Generate a first compensation coefficient of the sub-application degree corresponding to the associated operation data according to the change trend; generate a second compensation coefficient of the sub-application degree corresponding to the associated operation data according to the change rate; Generate an actual application degree of the initial control strategy according to the sub-application degree of the associated operation data, the first compensation coefficient, the second compensation coefficient, and the weight coefficient of the corresponding application evaluation index; The calculation formula of the actual application degree is: Among them, Y is the actual application degree, f1 is the weight coefficient of the first application evaluation index, n1 is the total number of associated operation data of the first application evaluation index, Z1 s1 is the sub-application degree of the s1th associated running data of the first application evaluation indicator, c11 s1 is the first compensation coefficient of the s1th associated operation data of the first application evaluation index, c21 s1 is the second compensation coefficient of the s1th associated operation data of the first application evaluation index, Zr s1 is the sub-application degree of the srth associated running data of the rth application evaluation indicator, c1r sr is the first compensation coefficient of the srth associated operation data of the rth application evaluation index, c2r sr is the second compensation coefficient of the srth associated operating data of the rth application evaluation indicator, and nr is the total number of associated operating data of the rth application evaluation indicator.

9. The method for controlling the electrothermal conversion rate based on the prediction of the balancing capability according to claim 8, characterized in that: According to the actual balance capability index and the actual application degree, it is determined whether to generate a correction instruction for the initial control strategy, including: Pre-set index difference threshold; Obtain the index difference between the actual balance capability index and the balance capability prediction index at the same time node. If the index difference is less than the index difference threshold, no correction instruction is sent. If the index difference is greater than the index difference threshold, a first-level correction instruction of the initial control strategy is sent. Pre-set application threshold; If the actual application degree is greater than the application degree threshold, no correction instruction is sent; If the actual application degree is less than the application degree threshold, a secondary correction instruction of the initial control strategy is sent.

Images