Load aggregation management method and system based on intelligent scheduling

Abstract

The application discloses a load aggregation management method and system based on intelligent scheduling, and the method comprises the following steps: obtaining historical power consumption records and corresponding user information of a plurality of power users; predicting a power consumption response strategy corresponding to each power user according to the user information; predicting future power consumption demand corresponding to each power user according to the historical power consumption records; and determining a power load distribution strategy corresponding to at least two power users based on an intelligent scheduling algorithm according to the power consumption response strategy and the future power consumption demand. It can be seen that the application can realize accurate power load optimization based on user characteristics and demand prediction, improve power grid scheduling efficiency and stability, and reduce energy waste and load overload risk.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a load aggregation management method and system based on intelligent scheduling. BACKGROUND

[0002] With the rapid development of smart grid technology, power companies are increasingly attaching importance to optimizing energy distribution and improving grid stability through precise load management. Existing technologies usually collect historical power consumption records and basic user information of power users, and use simple statistical analysis or fixed scheduling rules to develop power consumption distribution schemes to meet grid operation requirements. The existing solutions lack dynamic prediction of user power consumption response strategies and future demand, making it difficult to accurately develop personalized load distribution strategies. The commonly used unified scheduling method cannot adapt to the complex power consumption mode of multi-user scenarios, resulting in low grid scheduling efficiency, easy energy waste or load overload, and limiting the stability and energy utilization efficiency of grid operation. Therefore, the existing technology has defects and needs to be improved. SUMMARY

[0003] The technical problem to be solved by the present application is to provide a load aggregation management method and system based on intelligent scheduling, which can realize precise power load optimization based on user characteristics and demand prediction, improve grid scheduling efficiency and stability, and reduce energy waste and load overload risk.

[0004] To solve the above technical problems, the first aspect of the present application discloses a load aggregation management method based on intelligent scheduling, which comprises:

[0005] Obtaining historical power consumption records and corresponding user information of a plurality of power users;

[0006] According to the user information, predicting the power consumption response strategy corresponding to each power user;

[0007] According to the historical power consumption records, predicting the future power consumption demand corresponding to each power user;

[0008] According to the power consumption response strategy and the future power consumption demand, determining the power load distribution strategy corresponding to at least two power users based on an intelligent scheduling algorithm.

[0009] As an optional implementation, in the first aspect of the present application, the power consumption response strategy includes a mathematical relationship of the power consumption behavior parameter corresponding to the power user changing with at least one of the time period type, the electricity price, the power consumption terminal type and the power load distribution quota; and the power consumption behavior parameter includes at least one of the power consumption, the continuous power consumption time and the power consumption peak value.

[0010] As an optional implementation, in the first aspect of the present application, the user information comprises at least one of a user location, a user household type, a user number of electricity users, a user terminal type, and a user physiological parameter.

[0011] As an optional implementation, in the first aspect of the present application, the predicting of the electricity response strategy corresponding to each of the electricity users according to the user information comprises:

[0012] For each of the electricity users, at least one associated user corresponding to the electricity user is determined from all the other electricity users;

[0013] The user information of the electricity user is input into the trained electricity response prediction neural network to obtain a predicted electricity response strategy corresponding to the electricity user;

[0014] The user information corresponding to all the associated users is input into the trained electricity response prediction neural network to obtain an associated electricity response strategy corresponding to each of the associated users;

[0015] According to the mathematical relationship model parameters corresponding to each of the associated user response strategies, the mathematical relationship model parameters of the predicted electricity response strategy are corrected to obtain the electricity response strategy corresponding to the electricity user.

[0016] As an optional implementation, in the first aspect of the present application, the information similarity between the user information of the associated user and the user information of the electricity user is greater than a preset similarity threshold.

[0017] As an optional implementation, in the first aspect of the present application, the correcting of the mathematical relationship model parameters of the predicted electricity response strategy according to the mathematical relationship model parameters corresponding to each of the associated user response strategies to obtain the electricity response strategy corresponding to the electricity user comprises:

[0018] For each of the associated user response strategies, an associated weight proportional to the information similarity corresponding to the associated user corresponding to the associated user response strategy is calculated;

[0019] The product of the mathematical relationship model parameters corresponding to the associated user response strategy and the associated weight is calculated to obtain the corrected model parameters corresponding to the associated user response strategy;

[0020] The average of the corrected model parameters corresponding to all the associated user response strategies and the mathematical relationship model parameters of the predicted electricity response strategy is calculated to obtain the corrected mathematical model parameters of the predicted electricity response strategy, and the electricity response strategy corresponding to the electricity user is obtained.

[0021] As an optional implementation, in the first aspect of the present application, the prediction of the future electricity demand of each of the power users according to the historical electricity consumption records comprises:

[0022] inputting the historical electricity consumption records of each of the power users into a trained LSTM neural network to obtain the future electricity demand of each of the power users; the LSTM neural network is trained by a training data set comprising a plurality of training user electricity consumption record sequences.

[0023] As an optional implementation, in the first aspect of the present application, the determination of the power load distribution strategy of at least two of the power users based on the intelligent scheduling algorithm according to the electricity consumption response strategy and the future electricity demand comprises:

[0024] screening all the power users with the future electricity demand greater than a preset demand threshold to obtain a plurality of high-load users;

[0025] determining the objective function to include the total value of the allocation quotas of all the high-load users in the allocation scheme reaching a minimum;

[0026] determining the constraint condition to include:

[0027] the allocation quota of each of the high-load users in the allocation scheme is greater than the quota reference value corresponding to the future electricity demand;

[0028] the allocation quota of each of the high-load users in the allocation scheme is proportional to the electricity change rate corresponding to the electricity consumption response strategy corresponding to the high-load user; the strategy priority is obtained by calculating the change rate of the electricity behavior parameter obtained by substituting the electricity consumption response strategy corresponding to the high-load user into the corresponding allocation quota;

[0029] the quota difference between the allocation quotas of any two of the high-load users in the allocation scheme is less than the corresponding difference threshold; the difference threshold is inversely proportional to the information similarity between the user information corresponding to the two high-load users;

[0030] based on the scheduling optimization algorithm, iteratively calculating all the high-load users according to the objective function and the constraint condition until an optimal allocation scheme is obtained to determine the power load distribution strategy.

[0031] The second aspect of the embodiment of the present application discloses a load aggregation management system based on intelligent scheduling, which comprises:

[0032] an acquisition module for acquiring the historical electricity consumption records and corresponding user information of a plurality of power users;

[0033] a first prediction module configured to predict, according to the user information, an electricity consumption response strategy corresponding to each of the electricity users;

[0034] a second prediction module configured to predict, according to the historical electricity consumption records, a future electricity demand corresponding to each of the electricity users;

[0035] a distribution module configured to determine, according to the electricity consumption response strategy and the future electricity demand, an electricity load distribution strategy corresponding to at least two of the electricity users based on an intelligent scheduling algorithm.

[0036] As an optional implementation form, in the second aspect, the electricity consumption response strategy comprises a mathematical relationship of an electricity consumption behavior parameter corresponding to the electricity user varying with at least one of a time period type, an electricity price, an electricity consumption terminal type and an electricity load distribution quota; and the electricity consumption behavior parameter comprises at least one of an electricity consumption amount, a continuous electricity consumption time length and an electricity consumption power peak value.

[0037] As an optional implementation form, in the second aspect, the user information comprises at least one of a user location, a user house type, a user electricity consumption number, a user terminal type and a user personnel physiological parameter.

[0038] As an optional implementation form, in the second aspect, the first prediction module predicts, according to the user information, the electricity consumption response strategy corresponding to each of the electricity users in the following specific manner:

[0039] for each of the electricity users, at least one associated user corresponding to the electricity user is determined from all the other electricity users;

[0040] user information of the electricity user is input into a trained electricity consumption response prediction neural network to obtain a predicted electricity consumption response strategy corresponding to the electricity user;

[0041] user information of all the associated users is input into the trained electricity consumption response prediction neural network to obtain an associated electricity consumption response strategy corresponding to each of the associated users;

[0042] a mathematical relationship model parameter of the predicted electricity consumption response strategy is corrected according to a mathematical relationship model parameter corresponding to each of the associated electricity response strategies to obtain the electricity consumption response strategy corresponding to the electricity user.

[0043] As an optional implementation form, in the second aspect, an information similarity between the user information of the associated user and the user information of the electricity user is greater than a preset similarity threshold.

[0044] As an optional implementation, in the second aspect of the present application, the first prediction module corrects the mathematical relationship model parameters of the predicted electricity response strategy according to the mathematical relationship model parameters corresponding to each of the associated user response strategies, to obtain the specific mode of the electricity response strategy corresponding to the power user, including:

[0045] For each of the associated user response strategies, an associated weight proportional to the information similarity corresponding to the associated user corresponding to the associated user response strategy is calculated;

[0046] The product of the mathematical relationship model parameters corresponding to the associated user response strategy and the associated weight is calculated to obtain the correction model parameters corresponding to the associated user response strategy;

[0047] The average of the correction model parameters corresponding to all the associated user response strategies and the mathematical relationship model parameters of the predicted electricity response strategy is calculated to obtain the corrected mathematical model parameters of the predicted electricity response strategy, and the electricity response strategy corresponding to the power user is obtained.

[0048] As an optional implementation, in the second aspect of the present application, the second prediction module predicts the specific mode of the future electricity demand corresponding to each of the power users according to the historical electricity records, including:

[0049] The historical electricity records corresponding to each of the power users are input into the trained LSTM neural network to obtain the future electricity demand corresponding to each of the power users; the LSTM neural network is trained by a training data set including a plurality of training user electricity record sequences.

[0050] As an optional implementation, in the second aspect of the present application, the distribution module determines the specific mode of the power load distribution strategy corresponding to at least two of the power users based on an intelligent scheduling algorithm according to the electricity response strategy and the future electricity demand, including:

[0051] All of the power users whose future electricity demand is greater than a preset demand threshold are screened out to obtain a plurality of high-load users;

[0052] The objective function is determined to include the total value of the allocation quota corresponding to all of the high-load users in the allocation scheme reaching a minimum;

[0053] The constraint condition includes:

[0054] The allocation quota corresponding to each of the high-load users in the allocation scheme is greater than the quota reference value corresponding to the future electricity demand;

[0055] The allocation quota corresponding to each of the high-load users in the allocation scheme is proportional to the electricity change rate corresponding to the electricity response strategy corresponding to the high-load user; the strategy priority is obtained by calculating the change rate of the electricity behavior parameter obtained by substituting the electricity response strategy corresponding to the high-load user into the corresponding allocation quota;

[0056] The quota difference between the allocation quotas corresponding to any two of the high-load users in the allocation scheme is less than the corresponding difference threshold; the difference threshold is inversely proportional to the information similarity between the user information corresponding to the two high-load users;

[0057] Based on the scheduling optimization algorithm, all the high-load users are iteratively calculated according to the target function and the constraint condition until an optimal allocation scheme is obtained, so as to determine the power load allocation strategy.

[0058] The third aspect of the present application discloses another load aggregation management system based on intelligent scheduling, which comprises:

[0059] A memory storing executable program codes;

[0060] A processor coupled with the memory;

[0061] The processor calls the executable program codes stored in the memory to execute part or all of the steps of the load aggregation management method based on intelligent scheduling disclosed in the first aspect of the present application.

[0062] The fourth aspect of the present application discloses a computer storage medium storing computer instructions, which are called to execute part or all of the steps of the load aggregation management method based on intelligent scheduling disclosed in the first aspect of the present application.

[0063] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0064] The present application predicts the electricity response strategy and future electricity demand of each user by obtaining the historical electricity records and user information of multiple power users, and determines the power load allocation strategy of at least two users based on the intelligent scheduling algorithm and the two, so as to realize accurate power load optimization based on user characteristics and demand prediction, improve the efficiency and stability of power grid scheduling, and reduce energy waste and load overload risk. BRIEF DESCRIPTION OF DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description only show some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative effort.

[0066] Figure 1 is a flow diagram of a load aggregation management method based on intelligent scheduling disclosed by an embodiment of the present application.

[0067] Figure 2 is a structural diagram of a load aggregation management system based on intelligent scheduling disclosed by an embodiment of the present application.

[0068] Figure 3 is a structural diagram of another load aggregation management system based on intelligent scheduling disclosed by an embodiment of the present application. DETAILED DESCRIPTION

[0069] In order to make the technical personnel in the art better understand the present application scheme, the following will combine the drawings in the embodiments of the present application, and the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only some of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application.

[0070] The terms "first", "second", and the like in the specification of the present application and the above-mentioned drawings are used to distinguish different objects, not to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product or equipment.

[0071] In this paper, the "embodiment" means that the specific features, structures or characteristics described in conjunction with the embodiment can be included in at least one embodiment of the present application. The phrase appears in the specification at various places does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0072] The application discloses a load aggregation management method and system based on intelligent scheduling, which predicts the power consumption response strategy and future power consumption demand of each power user by obtaining the historical power consumption records and user information of multiple power users, determines the power load distribution strategy of at least two users based on the intelligent scheduling algorithm and the two, so as to realize accurate power load optimization based on user characteristics and demand prediction, improve the power grid scheduling efficiency and stability, and reduce energy waste and load overload risk. The following will be described in detail.

[0073] Embodiment one

[0074] Please refer to Figure 1 , Figure 1 is a flowchart of a load aggregation management method based on intelligent scheduling disclosed by the embodiment of the application. Among them, Figure 1 The load aggregation management method based on intelligent scheduling described can be applied in a data processing system / data processing equipment / data processing server (wherein the server includes a local processing server or a cloud processing server). As Figure 1 shown, the load aggregation management method based on intelligent scheduling can include the following operations:

[0075] 101, obtaining the historical power consumption records and corresponding user information of multiple power users.

[0076] 102, according to the user information, predicting the power consumption response strategy corresponding to each power user.

[0077] 103, according to the historical power consumption records, predicting the future power consumption demand corresponding to each power user.

[0078] 104, according to the power consumption response strategy and the future power consumption demand, determining the power load distribution strategy corresponding to at least two power users based on the intelligent scheduling algorithm.

[0079] As can be seen, the above-mentioned embodiment of the application predicts the power consumption response strategy and future power consumption demand of each power user by obtaining the historical power consumption records and user information of multiple power users, determines the power load distribution strategy of at least two users based on the intelligent scheduling algorithm and the two, so as to realize accurate power load optimization based on user characteristics and demand prediction, improve the power grid scheduling efficiency and stability, and reduce energy waste and load overload risk.

[0080] As an optional embodiment, in the above-mentioned steps, the power consumption response strategy includes the mathematical relationship of the power consumption behavior parameters corresponding to the power user changing with at least one of the time period type, the electricity price, the power consumption terminal type and the power load distribution quota; the power consumption behavior parameters include at least one of the power consumption, the continuous power consumption time length and the power consumption peak value.

[0081] It can be seen that through the above optional embodiments, the mathematical relationship and parameter type of the electricity response strategy are defined to effectively characterize the electricity behavior characteristics of the user, assist in realizing accurate power load optimization based on user characteristics and demand prediction, improve the efficiency and stability of power grid dispatching, and reduce the risk of energy waste and load overload.

[0082] As an optional embodiment, in the above step, the user information includes at least one of the user location, the user house type, the user electricity number, the user terminal type, and the user personnel physiological parameter.

[0083] It can be seen that through the above optional embodiments, the content of the user information is defined to effectively characterize the user characteristics, assist in realizing accurate power load optimization based on user characteristics and demand prediction, improve the efficiency and stability of power grid dispatching, and reduce the risk of energy waste and load overload.

[0084] As an optional embodiment, in the above step, according to the user information, the electricity response strategy corresponding to each power user is predicted, including:

[0085] For each power user, at least one associated user corresponding to the power user is determined among all other power users;

[0086] The user information of the power user is input into the trained electricity response prediction neural network to obtain the predicted electricity response strategy corresponding to the power user;

[0087] The user information corresponding to all associated users is input into the trained electricity response prediction neural network to obtain the associated electricity response strategy corresponding to each associated user;

[0088] According to the mathematical relationship model parameters corresponding to each associated user response strategy, the mathematical relationship model parameters of the predicted electricity response strategy are corrected to obtain the electricity response strategy corresponding to the power user.

[0089] It can be seen that through the above optional embodiments, by identifying the associated users with user information similarity exceeding the threshold value for each power user, and inputting the user information of the user and the associated users into the trained electricity response prediction neural network to generate the predicted and associated electricity response strategies, the mathematical relationship model parameters of the associated user strategies are used to correct the predicted strategy parameters to determine the final electricity response strategy, thereby realizing accurate electricity response strategy optimization based on user association and neural network prediction, improving the accuracy of power load distribution and the efficiency of power grid operation, and reducing the risk of energy distribution imbalance.

[0090] As an optional embodiment, in the above step, the information similarity between the user information of the associated user and the user information of the power user is greater than a preset similarity threshold.

[0091] It can be seen that through the above optional embodiments, the information similarity characteristics of the associated users are defined to effectively combine the strategy parameters of the associated users to realize the precise electricity response strategy prediction based on the associated user weighting correction, assist in realizing the precise electricity load optimization based on the user characteristics and demand prediction, improve the efficiency and stability of power grid dispatching, and reduce the risk of energy waste and load overload.

[0092] As an optional embodiment, in the above step, the mathematical relationship model parameters of the predicted electricity response strategy are corrected according to the mathematical relationship model parameters corresponding to each associated user response strategy, to obtain the electricity response strategy corresponding to the electricity user, including:

[0093] For each associated user response strategy, an associated weight corresponding to the associated user is calculated in proportion to the information similarity corresponding to the associated user response strategy;

[0094] The product of the mathematical relationship model parameters corresponding to the associated user response strategy and the associated weight is calculated to obtain the correction model parameters corresponding to the associated user response strategy;

[0095] The average value of the correction model parameters corresponding to all associated user response strategies and the mathematical relationship model parameters of the predicted electricity response strategy is calculated to obtain the corrected mathematical model parameters of the predicted electricity response strategy, and the electricity response strategy corresponding to the electricity user is obtained.

[0096] It can be seen that through the above optional embodiments, by identifying the associated users for each electricity user and calculating the associated weight proportional to the information similarity of the response strategy, the correction model parameters are obtained based on the product of the weight and the mathematical relationship model parameters of the associated user response strategy, and the final electricity response strategy is determined by taking the average value of all correction model parameters and the predicted electricity response strategy parameters, thereby realizing the precise electricity response strategy prediction based on the associated user weighting correction, improving the accuracy of electricity load distribution and the efficiency of power grid operation, and reducing the risk of energy distribution error.

[0097] As an optional embodiment, in the above step, the future electricity demand corresponding to each electricity user is predicted according to the historical electricity records, including:

[0098] The historical electricity records corresponding to each electricity user are input into the trained LSTM neural network to obtain the future electricity demand corresponding to each electricity user; the LSTM neural network is trained by a training data set including a plurality of training user electricity record sequences.

[0099] It can be seen that, through the above optional embodiments, by inputting the historical power consumption records of each power user into the trained LSTM neural network to predict future power consumption demand, precise power consumption demand prediction based on time series analysis is realized, the accuracy of power load distribution strategy and the efficiency of power grid operation are improved, and the risk of energy supply shortage or excess is reduced.

[0100] As an optional embodiment, in the above step, based on the smart scheduling algorithm, the power load distribution strategy corresponding to the at least two power users is determined according to the power consumption response strategy and the future power consumption demand, comprising:

[0101] All power users with future power consumption demand greater than a preset demand threshold are screened out to obtain a plurality of high-load users;

[0102] The target function includes that the total value of the allocation quota corresponding to all high-load users in the allocation scheme reaches a minimum;

[0103] The constraint condition includes:

[0104] The allocation quota corresponding to each high-load user in the allocation scheme is greater than the quota reference value corresponding to the future power consumption demand;

[0105] The allocation quota corresponding to each high-load user in the allocation scheme is proportional to the power consumption change rate corresponding to the power consumption response strategy corresponding to the high-load user; optionally, the strategy priority is obtained by calculating the change rate of the power consumption behavior parameter obtained after the power consumption response strategy corresponding to the high-load user is substituted into the corresponding allocation quota;

[0106] The difference between the allocation quotas corresponding to any two high-load users in the allocation scheme is less than the corresponding difference threshold; optionally, the difference threshold is inversely proportional to the information similarity between the user information corresponding to the two high-load users;

[0107] Based on the scheduling optimization algorithm, the target function and the constraint condition are used to iteratively calculate all high-load users until the optimal allocation scheme is obtained, and the power load distribution strategy is determined.

[0108] It can be seen that, through the above optional embodiments, by screening high-load users with future power consumption demand exceeding the threshold and setting the target function to minimize the total value of the allocation quota, combined with the constraint conditions that the allocation quota is higher than the demand reference value, proportional to the power consumption change rate of the power consumption response strategy, and the difference between the allocation quotas of any two high-load users is less than the threshold inversely proportional to the user information similarity, the optimal allocation scheme is iteratively calculated based on the scheduling optimization algorithm as the power load distribution strategy, thereby realizing precise load distribution based on demand and response strategy, improving the efficiency and stability of power grid scheduling, and reducing the risk of uneven energy distribution and overload.

[0109] Embodiment Two

[0110] Please refer to Figure 2 , Figure 2 is a structural schematic diagram of a load aggregation management system based on intelligent scheduling disclosed by an embodiment of the present application. In the diagram, Figure 2 The load aggregation management system based on intelligent scheduling described above can be applied in a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). As Figure 2 indicated, the load aggregation management system based on intelligent scheduling can include:

[0111] The acquisition module 201 is configured to acquire historical power consumption records of a plurality of power users and corresponding user information.

[0112] The first prediction module 202 is configured to predict a power consumption response strategy corresponding to each power user according to the user information.

[0113] The second prediction module 203 is configured to predict a future power consumption demand corresponding to each power user according to the historical power consumption records.

[0114] The distribution module 204 is configured to determine a power load distribution strategy corresponding to at least two power users based on an intelligent scheduling algorithm according to the power consumption response strategy and the future power consumption demand.

[0115] As can be seen, the above embodiment of the present application predicts the power consumption response strategy and the future power consumption demand of each power user by acquiring the historical power consumption records and the user information of a plurality of power users, determines the power load distribution strategy of at least two users based on the intelligent scheduling algorithm in combination with the two, and thus can realize accurate power load optimization based on user characteristics and demand prediction, improve the efficiency and stability of power grid scheduling, and reduce the risk of energy waste and load overload.

[0116] As an optional embodiment, the power consumption response strategy includes a mathematical relationship of a power consumption behavior parameter corresponding to the power user changing with at least one of a time period type, an electricity price, a power consumption terminal type, and a power load distribution quota; and the power consumption behavior parameter includes at least one of a power consumption amount, a continuous power consumption duration, and a power consumption peak value.

[0117] As can be seen, through the above optional embodiment, the mathematical relationship and the parameter type of the power consumption response strategy are limited to effectively represent the power consumption behavior characteristics of the user, to assist in realizing accurate power load optimization based on user characteristics and demand prediction, to improve the efficiency and stability of power grid scheduling, and to reduce the risk of energy waste and load overload.

[0118] As an optional embodiment, the user information includes at least one of a user location, a user house type, a user power consumption number, a user terminal type, and a user personnel physiological parameter.

[0119] It can be seen that through the above optional embodiments, the content of the user information is limited to effectively represent the user characteristics, thereby assisting in realizing the accurate power load optimization based on the user characteristics and demand prediction, improving the efficiency and stability of power grid dispatching, and reducing the risk of energy waste and load overload.

[0120] As an optional embodiment, the first prediction module predicts a specific way of the electricity consumption response strategy corresponding to each power user according to the user information, including:

[0121] For each power user, at least one associated user corresponding to the power user is determined among all other power users;

[0122] The user information of the power user is input into the trained electricity consumption response prediction neural network to obtain a predicted electricity consumption response strategy corresponding to the power user;

[0123] The user information corresponding to all associated users is input into the trained electricity consumption response prediction neural network to obtain an associated electricity consumption response strategy corresponding to each associated user;

[0124] According to the mathematical relationship model parameters corresponding to each associated user response strategy, the mathematical relationship model parameters of the predicted electricity consumption response strategy are corrected to obtain the electricity consumption response strategy corresponding to the power user.

[0125] It can be seen that through the above optional embodiments, by identifying the associated users with user information similarity exceeding the threshold value for each power user, and inputting the user information of the user and the associated users into the trained electricity consumption response prediction neural network to generate the predicted and associated electricity consumption response strategies, the mathematical relationship model parameters of the associated user strategies are used to correct the predicted strategy parameters to determine the final electricity consumption response strategy, thereby realizing the accurate electricity consumption response strategy optimization based on user association and neural network prediction, improving the accuracy of power load distribution and the efficiency of power grid operation, and reducing the risk of energy distribution imbalance.

[0126] As an optional embodiment, the information similarity between the user information of the associated user and the user information of the power user is greater than a preset similarity threshold.

[0127] It can be seen that through the above optional embodiments, the information similarity characteristics of the associated users are limited to effectively combine the strategy parameters of the associated users to realize the accurate electricity consumption response strategy prediction based on the weighted correction of the associated users, thereby assisting in realizing the accurate power load optimization based on the user characteristics and demand prediction, improving the efficiency and stability of power grid dispatching, and reducing the risk of energy waste and load overload.

[0128] As an optional embodiment, the first prediction module corrects the mathematical relationship model parameters of the predicted electricity response strategy according to the mathematical relationship model parameters corresponding to each associated user response strategy, to obtain the specific mode of the electricity response strategy corresponding to the power user, including:

[0129] For each associated user response strategy, an associated weight proportional to the information similarity of the associated user corresponding to the associated user response strategy is calculated;

[0130] The product of the mathematical relationship model parameters corresponding to the associated user response strategy and the associated weight is calculated to obtain the correction model parameters corresponding to the associated user response strategy;

[0131] The average of the correction model parameters corresponding to all associated user response strategies and the mathematical relationship model parameters of the predicted electricity response strategy is calculated to obtain the corrected mathematical model parameters of the predicted electricity response strategy, and the electricity response strategy corresponding to the power user is obtained.

[0132] As can be seen, through the above optional embodiment, by identifying the associated users for each power user and calculating the associated weight proportional to the information similarity of the response strategy, the correction model parameters are obtained based on the product of the weight and the mathematical relationship model parameters of the associated user response strategy, and the final electricity response strategy is determined by taking the average of all correction model parameters and the predicted electricity response strategy parameters, thereby realizing the precise electricity response strategy prediction based on the associated user weighting correction, improving the accuracy of the electricity load distribution and the efficiency of the power grid operation, and reducing the risk of energy distribution error.

[0133] As an optional embodiment, the second prediction module predicts the specific mode of the future electricity demand corresponding to each power user according to the historical electricity records, including:

[0134] The historical electricity records corresponding to each power user are input into the trained LSTM neural network to obtain the future electricity demand corresponding to each power user; the LSTM neural network is trained by a training data set including a plurality of training user electricity record sequences.

[0135] As can be seen, through the above optional embodiment, by inputting the historical electricity records of each power user into the trained LSTM neural network to predict the future electricity demand, the precise electricity demand prediction based on time series analysis is realized, the accuracy of the electricity load distribution strategy and the efficiency of the power grid operation are improved, and the risk of energy supply shortage or excess is reduced.

[0136] As an optional embodiment, the distribution module determines the specific mode of the electricity load distribution strategy corresponding to at least two power users based on the intelligent scheduling algorithm according to the electricity response strategy and the future electricity demand, including:

[0137] screening all power users with future electricity demand greater than a preset demand threshold to obtain a plurality of high-load users;

[0138] determining that the target function includes a total value of the allocation quota corresponding to all high-load users in the allocation scheme reaching a minimum;

[0139] determining that the constraint condition includes:

[0140] the allocation quota corresponding to each high-load user in the allocation scheme is greater than the quota reference value corresponding to the future electricity demand;

[0141] the allocation quota corresponding to each high-load user in the allocation scheme is proportional to the electricity change rate corresponding to the electricity response strategy corresponding to the high-load user; optionally, the strategy priority is obtained by calculating the change rate of the electricity behavior parameter obtained after the electricity response strategy corresponding to the high-load user is substituted into the corresponding allocation quota;

[0142] the difference value between the allocation quota corresponding to any two high-load users in the allocation scheme is less than the corresponding difference value threshold; optionally, the difference value threshold is inversely proportional to the information similarity between the user information corresponding to the two high-load users;

[0143] based on the dispatching optimization algorithm, iteratively calculating all high-load users according to the target function and the constraint condition until the optimal allocation scheme is obtained to determine the power load allocation strategy.

[0144] As can be seen, through the above optional embodiments, by screening high-load users with future electricity demand exceeding the threshold and setting the target function to minimize the total value of the allocation quota, in combination with the constraint conditions that the allocation quota is higher than the demand reference value, proportional to the electricity change rate of the electricity response strategy, and the difference value between any two high-load users is less than the threshold inversely proportional to the user information similarity, the optimal allocation scheme is iteratively calculated based on the dispatching optimization algorithm as the power load allocation strategy, thereby realizing precise load allocation based on demand and response strategy, improving the efficiency and stability of power grid dispatching, and reducing the risk of uneven energy distribution and overload.

[0145] Embodiment Three

[0146] Please refer to Figure 3 , Figure 3 The application discloses another kind of load aggregation management system based on intelligent dispatching. Figure 3 The described load aggregation management system based on intelligent dispatching is applied to data processing system / data processing equipment / data processing server (wherein the server includes local processing server or cloud processing server). As Figure 3 shown, the load aggregation management system based on intelligent dispatching can include:

[0147] a memory 301 storing executable program code;

[0148] a processor 302 coupled with the memory 301;

[0149] The processor 302 invokes the executable program code stored in the memory 301 to perform the steps of the intelligent scheduling based load aggregation management method described in Embodiment One.

[0150] Embodiment Four

[0151] The embodiments of the present application disclose a computer readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to perform the steps of the intelligent scheduling based load aggregation management method described in Embodiment One.

[0152] Embodiment Five

[0153] The embodiments of the present application disclose a computer program product comprising a non-transitory computer readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the intelligent scheduling based load aggregation management method described in Embodiment One.

[0154] The above describes specific embodiments of the present application, other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than those described in the embodiments and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown or sequential order in order to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

[0155] The systems, apparatuses, modules or units illustrated by the above embodiments specifically can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0156] For the convenience of description, the above apparatuses are described in various units respectively by functions. Of course, the functions of each unit can be implemented in the same or more software and / or hardware when implementing the present specification.

[0157] Those skilled in the art will appreciate that embodiments of the present description can be readily used as a method, an apparatus (system) or a computer program product. Accordingly, embodiments of the present description can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, and the like) embodying computer readable program code.

[0158] The present description is described in reference to flow diagrams and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the present description. It will be understood that each block of the flow diagrams and / or block diagrams, and combinations of blocks in the flow diagrams and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processing device or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks.

[0159] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flow diagrams and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks. Figure 1 one or more functions specified in the flow diagram and / or block diagram block or blocks.

[0161] In one typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0162] The memory can include non-persistent memory and / or volatile memory, such as random access memory (RAM) and / or cache memory, non-volatile memory, etc. in the form of computer-readable media. The memory is an example of computer-readable media.

[0163] Computer-readable media includes permanent and non-permanent, movable and non-movable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media such as modulated data signals and carriers.

[0164] It should also be noted that the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles or devices that include a series of elements not only include those elements, but also include other elements not explicitly listed or inherent to such processes, methods, articles or devices. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method, article or device including the element.

[0165] The specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. The specification can also be practiced in a distributed computing environment, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

[0166] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0167] It should be noted that the disclosed load aggregation management method and system based on intelligent scheduling are only the preferred embodiments of the present application, and are used to illustrate the technical solutions of the present application, but not to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent ones. The modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A load aggregation management method based on intelligent scheduling, characterized in that, The method comprises: obtaining historical power consumption records and corresponding user information of a plurality of power users; predicting, according to the user information, a power consumption response strategy corresponding to each of the power users; the power consumption response strategy comprises a mathematical relationship of a power consumption behavior parameter corresponding to the power user changing with at least one of a time period type, an electricity price, a power consumption terminal type, and a power load allocation quota; predicting, according to the historical power consumption records, a future power consumption demand corresponding to each of the power users; determining, according to the power consumption response strategy and the future power consumption demand, a power load allocation strategy corresponding to at least two of the power users based on an intelligent scheduling algorithm, comprising: screening all the power users whose future power consumption demand is greater than a preset demand threshold to obtain a plurality of high-load users; determining a target function comprising a total value of the allocation quota corresponding to all the high-load users in an allocation scheme reaching a minimum; determining a constraint condition comprising: the allocation quota corresponding to each of the high-load users in the allocation scheme being greater than a quota reference value corresponding to the future power consumption demand; the allocation quota corresponding to each of the high-load users in the allocation scheme being proportional to a power consumption change rate corresponding to the power consumption response strategy corresponding to the high-load user; the strategy priority being obtained by calculating a change rate of the power consumption behavior parameter obtained by substituting the power consumption response strategy corresponding to the high-load user into the corresponding allocation quota; a quota difference value between the allocation quota corresponding to any two of the high-load users in the allocation scheme being less than a corresponding difference threshold; the difference threshold being inversely proportional to an information similarity between the user information corresponding to the two high-load users; based on a scheduling optimization algorithm, iteratively calculating all the high-load users according to the target function and the constraint condition until an optimal allocation scheme is obtained to determine the power load allocation strategy. 2.The smart-scheduling based load aggregation management method of claim 1, wherein, The power consumption behavior parameter comprises at least one of a power consumption amount, a continuous power consumption duration, and a power consumption power peak value. 3.The smart-scheduling based load aggregation management method of claim 1, wherein, The user information comprises at least one of a user location, a user house type, a user power consumption number, a user terminal type, and a user personnel physiological parameter. 4.The smart-scheduling based load aggregation management method of claim 1, wherein, The prediction of the power consumption response strategy corresponding to each of the power users according to the user information comprises: for each of the power users, determining at least one associated user corresponding to the power user among all the other power users; inputting the user information of the power user into a trained power consumption response prediction neural network to obtain a predicted power consumption response strategy corresponding to the power user; inputting the user information of all the associated users into the trained power consumption response prediction neural network to obtain an associated power consumption response strategy corresponding to each of the associated users; modifying a mathematical relationship model parameter of the predicted power consumption response strategy according to a mathematical relationship model parameter corresponding to each of the associated power consumption response strategies to obtain the power consumption response strategy corresponding to the power user. 5.The smart-scheduling based load aggregation management method of claim 4, wherein, The information similarity between the user information of the associated user and the user information of the power user is greater than a preset similarity threshold. 6.The smart-scheduling based load aggregation management method of claim 5, wherein, The method comprises the following steps: For each of the associated power consumption response strategies, an associated weight is calculated in proportion to the information similarity between the associated user and the associated power consumption response strategy; The product of the mathematical relationship model parameter corresponding to the associated power consumption response strategy and the associated weight is calculated to obtain the correction model parameter corresponding to the associated power consumption response strategy; The average of the correction model parameters corresponding to all the associated power consumption response strategies and the mathematical relationship model parameter of the predicted power consumption response strategy is calculated to obtain the corrected mathematical model parameter of the predicted power consumption response strategy, and the power consumption response strategy corresponding to the power user is obtained. 7.The smart-scheduling based load aggregation management method of claim 1, wherein, The method comprises the following steps: The historical power consumption records of each of the power users are input into the trained LSTM neural network to obtain the future power consumption demand corresponding to each of the power users; the LSTM neural network is trained by a training data set comprising a plurality of training user power consumption record sequences.

8. A load aggregation management system based on intelligent dispatching, characterized in that, The system comprises: An acquisition module is configured to acquire historical power consumption records and corresponding user information of a plurality of power users; A first prediction module is configured to predict a power consumption response strategy corresponding to each of the power users according to the user information; the power consumption response strategy comprises a mathematical relationship of a power consumption behavior parameter corresponding to the power user changing with at least one of a time period type, an electricity price, a power consumption terminal type, and a power load allocation quota; A second prediction module is configured to predict a future power consumption demand corresponding to each of the power users according to the historical power consumption records; An allocation module is configured to determine a power load allocation strategy corresponding to at least two of the power users based on an intelligent scheduling algorithm according to the power consumption response strategy and the future power consumption demand, comprising: All the power users with the future power consumption demand greater than a preset demand threshold are screened out to obtain a plurality of high-load users; A target function is determined to include a total value of the allocation quota corresponding to all the high-load users in the allocation scheme reaching a minimum; The constraint conditions include: The allocation quota corresponding to each of the high-load users in the allocation scheme is greater than a quota reference value corresponding to the future power consumption demand; The allocation quota corresponding to each of the high-load users in the allocation scheme is proportional to a power consumption change rate corresponding to the power consumption response strategy corresponding to the high-load user; the strategy priority is obtained by calculating the change rate of the power consumption behavior parameter obtained by substituting the allocation quota corresponding to the high-load user into the power consumption response strategy corresponding to the high-load user; The quota difference between the allocation quotas corresponding to any two of the high-load users in the allocation scheme is less than a corresponding difference threshold; the difference threshold is inversely proportional to the information similarity between the user information corresponding to the two high-load users. Based on the scheduling optimization algorithm, all the high-load users are iteratively calculated according to the target function and the constraint condition until an optimal allocation scheme is obtained, and a power load allocation strategy is determined.

9. A load aggregation management system based on intelligent dispatching, characterized in that, The system comprises: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the intelligent scheduling-based load aggregation management method according to any one of claims 1-7.

Images