CN117335416A

CN117335416A - Method, device, equipment and storage medium for optimizing power load

Info

Publication number: CN117335416A
Application number: CN202311578038.2A
Authority: CN
Inventors: 章寒冰; 叶吉超; 黄慧; 徐永海; 胡鑫威; 张程翔; 丁宁; 季奥颖; 王笑棠; 娄冰; 汪华; 陈冰恽; 潘昭光; 朱利锋; 吴新华
Original assignee: State Grid Zhejiang Electric Power Co Ltd; Lishui Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Current assignee: State Grid Zhejiang Electric Power Co Ltd; Lishui Power Supply Co of State Grid Zhejiang Electric Power Co Ltd
Priority date: 2023-11-24
Filing date: 2023-11-24
Publication date: 2024-01-02
Anticipated expiration: 2043-11-24
Also published as: CN117335416B

Abstract

The invention discloses a method, a device, equipment and a storage medium for optimizing power load, which comprise the following steps: acquiring all electric equipment and operation parameters thereof in enterprise users, and constructing an equipment topological graph among the electric equipment; acquiring real-time data of total power consumption load of enterprise users in a preset time period, and further calculating to obtain a first power consumption prediction result in a future time period through a power consumption load prediction model; acquiring historical data of the power utilization load of each power utilization device of enterprise users in a preset time period, and calculating to obtain second power utilization load prediction values corresponding to each power utilization device in a future time period through each power utilization device prediction model; obtaining a predicted value difference value through the first electric load predicted value and the second electric load predicted value among the electric equipment; and obtaining target execution quantity of each electric equipment according to the predicted difference value, and formulating an optimization strategy of all the electric equipment, so as to optimize the electric load of all the electric equipment based on the optimization strategy.

Description

Method, device, equipment and storage medium for optimizing power load

Technical Field

The present invention relates to the field of power grid application technologies, and in particular, to a method, an apparatus, a device, and a storage medium for optimizing an electrical load.

Background

The electric load is the sum of the electric power taken by the electric equipment of the electric energy user to the electric power system at a certain moment, and when the electric load is larger, the electric power taken by the electric equipment of the electric energy user to the electric power system is larger, so that the electric power taken by a certain electric energy user is easy to occupy larger electric power during the electricity utilization peak period, especially for the enterprise electric user, and the problems of running and power failure of the electric power circuit are caused.

At present, a method for optimizing the electricity load of a user mainly comprises the steps of formulating an electricity load optimizing strategy for an enterprise user through an intelligent algorithm, wherein the electricity load optimizing strategy is mainly realized by taking the enterprise user as an electricity whole, but because different electric power production equipment and other equipment exist in the enterprise, the whole enterprise electricity is used as the optimization of the electricity load strategy, the actual production efficiency of the enterprise is easy to be lower, and the normal production activity of the enterprise is influenced, so the electricity load optimizing method has certain limitation that the electricity load optimizing of the enterprise user cannot be accurately and reliably realized, the optimizing efficiency is low, the optimizing strategy is complex to be difficult to execute in actual application, and the enterprise user cannot be enabled to be accurately, efficiently and reliably realize the electricity load optimizing.

Therefore, there is a need for a method that can improve the accuracy, reliability and efficiency of power load optimization.

Disclosure of Invention

The invention provides a method, a device, equipment and a storage medium for optimizing power loads, which are used for solving the technical problems that the power load optimization of enterprise users cannot be accurately and reliably realized in the prior art, the optimization efficiency is low, the execution of an optimization strategy is complex, and the actual application is difficult.

In order to solve the above technical problems, an embodiment of the present invention provides a method for optimizing an electrical load, including:

acquiring all electric equipment and operation parameters thereof in enterprise users, and constructing an equipment topological graph among the electric equipment according to linkage relations among the electric equipment;

acquiring real-time data of total electricity load of enterprise users in a preset time period, constructing an electricity load prediction model according to the real-time data, and calculating to obtain a first electricity prediction result in a future time period through the electricity load prediction model;

acquiring historical data of the power utilization load of each power utilization device of enterprise users in a preset time period, sequentially constructing each power utilization device prediction model according to the historical data, and sequentially calculating to obtain second power utilization load prediction values corresponding to each power utilization device in a future time period through each power utilization device prediction model; wherein, each electric equipment has a second electricity load pre-measurement;

Decomposing the first electricity prediction result according to the equipment topological graph, so as to obtain a first electricity load prediction value among the electric equipment, and obtaining a predicted value difference value through the first electricity load prediction value and a second electricity load prediction value among the electric equipment; each electric equipment is decomposed to obtain a corresponding first electric load pre-measurement value;

and according to the corresponding preset measurement difference value of each electric device, combining with a preset target output requirement to obtain target execution quantity of each electric device, and formulating an optimization strategy of all the electric devices according to the target execution quantity, so as to optimize the electric loads of all the electric devices of users in the enterprise respectively based on the optimization strategy.

As a preferred scheme, the method includes the steps of obtaining all electric equipment and operation parameters thereof in enterprise users, and constructing an equipment topological graph among the electric equipment according to linkage relations among the electric equipment, specifically:

acquiring all electric equipment and operation parameters thereof in enterprise users, and respectively dividing the electric equipment into production-end equipment and management-end equipment according to the operation parameters of each electric equipment;

Obtaining side relations among all production end devices according to the linkage relations among the production end devices, and constructing a topology diagram of the production end devices by taking the production end devices as nodes;

and adding nodes of the management end equipment into the production end equipment topological graph, and connecting the nodes of the management end equipment with the production end equipment according to the connection relation between the management end equipment and the production end equipment, so as to construct the equipment topological graph between the electric equipment.

As a preferred scheme, the method includes the steps that real-time data of total electricity load of enterprise users in a preset time period are obtained, an electricity load prediction model is built according to the real-time data, and further a first electricity prediction result in a future time period is obtained through calculation of the electricity load prediction model, specifically:

acquiring initial real-time data of total power load of enterprise users in a preset time period, and digitizing the initial real-time data, so that abnormal values and outliers of the digitized real-time data are corrected according to the average value of the initial real-time data, and real-time data are obtained;

constructing an initial electricity load prediction model, and inputting the real-time data into the initial electricity load prediction model as training data to perform model training so as to obtain an electricity load prediction model;

Predicting the electricity load in a future period of time through the electricity load prediction model to obtain a prediction result;

comparing the prediction result with real-time data in the same time period to obtain a prediction difference value;

when the prediction difference value is larger than a preset value, acquiring an actual power consumption load in the time period, comparing the prediction result with the actual power consumption load, correcting the power consumption load prediction model according to the comparison result, and predicting a result output by the power consumption load in the time period by the corrected power consumption load prediction model to be used as a first power consumption prediction result;

and when the prediction difference value is smaller than a preset value, taking the prediction result as a first power prediction result.

As a preferred scheme, the method includes the steps that historical data of the power utilization load of each power utilization device of enterprise users in a preset time period are obtained, each power utilization device prediction model is sequentially constructed according to the historical data, and then second power utilization load prediction values corresponding to each power utilization device in a future time period are obtained through calculation through each power utilization device prediction model, specifically:

acquiring historical data of power loads of production end devices and management end devices of enterprise users in a preset time period;

Sequentially constructing initial first electric equipment prediction models corresponding to all production end equipment, taking historical data of electric loads of all production end equipment as training data of the initial first electric equipment prediction models corresponding to the production end equipment, and training to obtain first electric equipment prediction models corresponding to all production end equipment; each production end device is provided with a corresponding initial first electric equipment prediction model and a trained first electric equipment prediction model;

constructing an initial second electric equipment prediction model common to all the management end devices, taking historical data of electric loads of all the management end devices as training data of the initial second electric equipment prediction model, and training to obtain second electric equipment prediction models corresponding to all the management end devices; the second electric equipment prediction model corresponds to all management end equipment;

obtaining second electricity load pre-measurement of each production end device in sequence through the first electricity consumption device prediction model, and obtaining second electricity loads and measurement of all management end devices through the second electricity consumption device prediction model; each production end device has a corresponding second power consumption load predicted by a corresponding first power consumption device prediction model, and all management end devices only have a common second power consumption load and measurement.

constructing a corresponding initial third electric equipment prediction model for each production end device, taking historical data of electric loads of each production end device as training data of the corresponding initial third electric equipment prediction model, and training to obtain a third electric equipment prediction model corresponding to each production end device; each production end device is provided with a corresponding initial third electric equipment prediction model and a trained third electric equipment prediction model;

constructing a corresponding initial fourth electric equipment prediction model for each management end device, taking the historical data of the electric load of each management end device as the training data of the corresponding initial fourth electric equipment prediction model, and training to obtain a fourth electric equipment prediction model corresponding to each management end device; each production end device is provided with a corresponding initial fourth electric equipment prediction model and a trained fourth electric equipment prediction model;

And sequentially obtaining second electricity load prediction values of each production end device through the third electricity consumption device prediction model, and sequentially obtaining second electricity load prediction values of each management end device through the fourth electricity consumption device prediction model.

As a preferred solution, the decomposing the first electrical prediction result according to the device topology graph, so as to obtain a first electrical load prediction value between the electrical devices, specifically:

according to the equipment topological graph, the operation relation and the operation parameters of the management end equipment are obtained, and the operation relation and the operation parameters of the production end equipment are obtained;

according to the operation relation and the operation parameters of the management end devices and the operation relation and the operation parameters of the production end devices, the first electricity prediction results of the electric devices are sequentially decomposed, so that the decomposition sequence is determined through the operation relation of the electric devices, and according to the operation parameters of the electric devices, the first electricity prediction results of the electric devices are decomposed according to the decomposition sequence, and therefore the first electricity load prediction values of the management end devices and the production end devices are obtained.

As a preferred solution, the target execution amount of each electric device is obtained by combining the preset target output requirement according to the preset measurement difference value corresponding to each electric device, and the optimization strategy of all the electric devices is formulated according to the target execution amount, specifically:

according to the corresponding predicted difference value of each electric device, correcting the future electric load of each electric device, thereby obtaining an initial target execution amount;

the initial target execution amount corresponding to the electric equipment is adjusted by combining with a preset target output requirement, so that the target execution amount of each electric equipment is obtained;

formulating an initial optimization strategy according to the target execution amount, and inputting the initial optimization strategy into the equipment topological graph to verify the executability of the initial optimization strategy;

when the initial optimization strategy has the executable performance, the initial optimization strategy is used as a final optimization strategy;

when the initial optimization strategy does not have the executable performance, the operation data of each electric equipment generated when the initial optimization strategy is input into the equipment topological graph is obtained, and the initial optimization strategy is corrected according to the operation data of each electric equipment, so that a final optimization strategy is obtained after correction.

Correspondingly, the invention also provides a device for optimizing the electric load, which comprises: the system comprises a construction module, a first prediction module, a second prediction module, a prediction difference module and an optimization strategy module;

the construction module is used for acquiring all electric equipment and operation parameters thereof in enterprise users and constructing an equipment topological graph among the electric equipment according to linkage relations among the electric equipment;

the first prediction module is used for acquiring real-time data of total electricity load of enterprise users in a preset time period, constructing an electricity load prediction model according to the real-time data, and further calculating to obtain a first electricity prediction result in a future time period through the electricity load prediction model;

the second prediction module is used for acquiring historical data of the power utilization load of each power utilization device of an enterprise user in a preset time period, sequentially constructing each power utilization device prediction model according to the historical data, and further sequentially calculating to obtain second power utilization load prediction values corresponding to each power utilization device in a future time period through each power utilization device prediction model; wherein, each electric equipment has a second electricity load pre-measurement;

The prediction difference module is used for decomposing the first electricity prediction result according to the equipment topological graph so as to obtain a first electricity load prediction value among the electric equipment, and obtaining a prediction difference value through the first electricity load prediction value and a second electricity load prediction value among the electric equipment; each electric equipment is decomposed to obtain a corresponding first electric load pre-measurement value;

the optimizing strategy module is used for obtaining target execution amount of each electric equipment according to the preset target output requirement and combining the preset target output requirement corresponding to each electric equipment, and formulating optimizing strategies of all the electric equipment according to the target execution amount, so that the optimizing of the electric loads of all the electric equipment of users in the enterprise is respectively carried out based on the optimizing strategies.

Correspondingly, the invention also provides a terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the method for optimizing the electrical load according to any one of the above when executing the computer program.

Correspondingly, the invention further provides a computer readable storage medium, which comprises a stored computer program, wherein the computer program is used for controlling equipment where the computer readable storage medium is located to execute the method for optimizing the electric load according to any one of the above.

Compared with the prior art, the embodiment of the invention has the following beneficial effects:

according to the technical scheme, the operation parameters and the historical data of each electric equipment are obtained, the electric topology graph is constructed, the electric load in a period of time in the future can be predicted more accurately, meanwhile, the first electric prediction result and the second electric load prediction value of each electric equipment are combined, difference value calculation can be performed, the prediction accuracy is further improved, the electric load is predicted and optimized based on the real-time data and the historical data, the prediction reliability can be improved through comprehensive analysis of multi-source data, the prediction error is reduced, a more accurate electric load optimization scheme is provided, modeling and prediction are performed on different equipment and linkage relations based on the electric equipment and the operation parameters of an actual enterprise user, pertinence and practicability are achieved, customized electric load optimization can be performed according to actual conditions, the actual demands of the enterprise user are met, the electric loads of each electric equipment can be calculated and optimized in parallel through constructing the electric topology graph and the prediction model of each electric equipment, the calculation efficiency is improved, and the efficiency and the energy utilization efficiency of the electric equipment is further improved according to the preset target demand optimization strategy.

Drawings

Fig. 1: the method for optimizing the power consumption load comprises the following steps of;

fig. 2: the embodiment of the invention provides a structure diagram of a device for optimizing electric loads.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

Example 1

Referring to fig. 1, a method for optimizing an electrical load according to an embodiment of the present invention includes steps S101 to S105:

step S101, acquiring all electric equipment and operation parameters thereof in enterprise users, and constructing an equipment topological graph among the electric equipment according to linkage relations among the electric equipment.

As a preferred scheme of this embodiment, the method obtains all electric devices and operation parameters thereof in the enterprise user, and constructs a device topology diagram between the electric devices according to a linkage relationship between the electric devices, specifically:

Acquiring all electric equipment and operation parameters thereof in enterprise users, and respectively dividing the electric equipment into production-end equipment and management-end equipment according to the operation parameters of each electric equipment; obtaining side relations among all production end devices according to the linkage relations among the production end devices, and constructing a topology diagram of the production end devices by taking the production end devices as nodes; and adding nodes of the management end equipment into the production end equipment topological graph, and connecting the nodes of the management end equipment with the production end equipment according to the connection relation between the management end equipment and the production end equipment, so as to construct the equipment topological graph between the electric equipment.

In this embodiment, based on the electric equipment and the operation parameters of the enterprise users, the enterprise users are divided into production-side equipment and management-side equipment, and an equipment topology graph is constructed according to the linkage relationship between the equipment. The device topology diagram is a device network structure diagram formed by nodes and edges, wherein the nodes are various production end devices and management end devices, and the edges are linkage relations among the production end devices and/or the management end devices, for example: for steel production enterprises, the electric load of steel-making equipment (production end equipment) and steel rolling equipment (production end equipment) are positively correlated, the electric load of the steel-making equipment is increased when the steel yield of the steel-making equipment is increased, and the steel yield is increased to drive the steel rolling equipment to process more steel, so that the electric load of the steel-rolling equipment is increased. It will be appreciated that the linkage between devices may be derived manually or from changes in historical operating data of the powered device.

In the embodiment, the relevance and the mutual influence among the devices can be deeply known by dividing the production-side device and the management-side device and establishing the side relationship among the devices, so that the linkage relationship among the devices and the influence of the linkage relationship on the power load can be recognized and understood. Meanwhile, the structure and the connection relation of the electric equipment of the enterprise user can be clearly shown by constructing the equipment topological graph, and the connection between the production end equipment and the management end equipment is included, so that the layout and the scheduling of the electric equipment are optimized, and the operation efficiency and the energy utilization efficiency of the equipment are improved. Further, equipment faults and errors can be rapidly located through the equipment topological graph, and influences of the fault equipment on other equipment are found, so that efficiency of fault diagnosis and maintenance is improved, maintenance planning of the equipment can be optimized through the topological graph, and reliability and usability of the equipment are improved. In addition, by constructing the equipment topological graph, more accurate electricity load prediction and optimization can be supported, and by combining the relevance and topological structure between the equipment, more reasonable electricity utilization strategies and scheduling schemes can be formulated, so that the energy utilization efficiency is improved, and the electricity utilization cost is reduced.

Step S102, acquiring real-time data of total electricity load of enterprise users in a preset time period, constructing an electricity load prediction model according to the real-time data, and calculating to obtain a first electricity prediction result in a future time period through the electricity load prediction model.

As a preferred solution of this embodiment, the method includes obtaining real-time data of total power consumption load of an enterprise user in a preset time period, and constructing a power consumption load prediction model according to the real-time data, so as to calculate a first power consumption prediction result in a future time period through the power consumption load prediction model, where the first power consumption prediction result specifically includes:

acquiring initial real-time data of total power load of enterprise users in a preset time period, and digitizing the initial real-time data, so that abnormal values and outliers of the digitized real-time data are corrected according to the average value of the initial real-time data, and real-time data are obtained; constructing an initial electricity load prediction model, and inputting the real-time data into the initial electricity load prediction model as training data to perform model training so as to obtain an electricity load prediction model; predicting the electricity load in a future period of time through the electricity load prediction model to obtain a prediction result; comparing the prediction result with real-time data in the same time period to obtain a prediction difference value; when the prediction difference value is larger than a preset value, acquiring an actual power consumption load in the time period, comparing the prediction result with the actual power consumption load, correcting the power consumption load prediction model according to the comparison result, and predicting a result output by the power consumption load in the time period by the corrected power consumption load prediction model to be used as a first power consumption prediction result; and when the prediction difference value is smaller than a preset value, taking the prediction result as a first power prediction result.

In this embodiment, real-time electricity load data of an enterprise user is obtained, an initial electricity load prediction model is constructed based on the data, and a first electricity prediction result is obtained by comparing and correcting with an actual electricity load.

In the embodiment, the initial real-time data is subjected to abnormal value and outlier correction through digital processing and mean value comparison, so that the accuracy and reliability of the data are improved, and the influence of the abnormal data on power load prediction is reduced. The accuracy and the adaptability of the prediction model can be improved by constructing an initial power utilization load prediction model and using real-time data to perform model training, the prediction model can predict the power utilization load in a future period by using information such as modes, trends and the like in historical data, and meanwhile, a prediction result is compared with the real-time data to obtain a prediction difference value. Judging whether the predicted difference value is larger than a preset value according to the preset value; if the predicted difference is larger than the preset value, the predicted difference is larger and the correction is needed. And the prediction model is corrected by comparing the actual power load with the prediction result, so that the accuracy and reliability of prediction are improved. And further, according to the corrected electricity load prediction model, predicting the electricity load in the time period and outputting a first electricity prediction result, wherein it can be understood that the prediction result can be used as a preliminary electricity load prediction to provide a reference for subsequent electricity scheduling and optimization.

Step 103, acquiring historical data of the power utilization load of each power utilization device of enterprise users in a preset time period, sequentially constructing each power utilization device prediction model according to the historical data, and sequentially calculating to obtain second power utilization load prediction values corresponding to each power utilization device in a future time period through each power utilization device prediction model; wherein, each consumer has a second electrical load prediction.

As a preferred scheme of this embodiment, the method includes the steps of obtaining historical data of power consumption loads of all electric devices of enterprise users in a preset time period, sequentially constructing prediction models of all electric devices according to the historical data, and sequentially calculating second power consumption load prediction values corresponding to all the electric devices in a future time period through the prediction models of all the electric devices, specifically:

acquiring historical data of power loads of production end devices and management end devices of enterprise users in a preset time period; sequentially constructing initial first electric equipment prediction models corresponding to all production end equipment, taking historical data of electric loads of all production end equipment as training data of the initial first electric equipment prediction models corresponding to the production end equipment, and training to obtain first electric equipment prediction models corresponding to all production end equipment; each production end device is provided with a corresponding initial first electric equipment prediction model and a trained first electric equipment prediction model; constructing an initial second electric equipment prediction model common to all the management end devices, taking historical data of electric loads of all the management end devices as training data of the initial second electric equipment prediction model, and training to obtain second electric equipment prediction models corresponding to all the management end devices; the second electric equipment prediction model corresponds to all management end equipment; obtaining second electricity load pre-measurement of each production end device in sequence through the first electricity consumption device prediction model, and obtaining second electricity loads and measurement of all management end devices through the second electricity consumption device prediction model; each production end device has a corresponding second power consumption load predicted by a corresponding first power consumption device prediction model, and all management end devices only have a common second power consumption load and measurement.

In this embodiment, based on historical data of enterprise users, prediction models of electric equipment of production end equipment and management end equipment are respectively constructed, and second electricity load predicted values and actual measurement values are obtained through the prediction models. By constructing an independent first electric equipment prediction model for each production end device, the electric load of each device can be predicted more accurately, a unified management end prediction model is performed, and by constructing a personalized first electric equipment prediction model and a unified second electric equipment prediction model, multi-level electric load prediction is realized, an evaluation reference for comparison with measured data is provided, so that the prediction accuracy and effect can be improved, and support is provided for electric management and optimization of enterprise users.

In this embodiment, by constructing an independent first electric equipment prediction model for each production end device, the electric load of each device can be predicted more accurately, and according to the historical data of the device, the prediction model can capture the specific electric mode and change trend of the device better. By constructing the second electric equipment prediction model common to all the management end equipment, the electric load of the management end equipment can be predicted more efficiently, the workload of model construction and maintenance can be reduced, and the adaptability and generalization capability of the model can be improved to a certain extent. Meanwhile, through the first electric equipment prediction model and the second electric equipment prediction model, the second electric load prediction quantity of the production end equipment and the second electric load prediction quantity of the management end equipment can be obtained, so that more detailed and comprehensive electric load prediction information can be provided, and electric scheduling and optimization decision is supported. And comparing the predicted second electricity load with the measured value, the accuracy and the reliability of the prediction model can be evaluated. By comparing the results, the prediction error and deviation can be found, and the prediction model can be adjusted and optimized according to the needs, so that the accuracy and practicability of prediction are improved.

As another preferable scheme of this embodiment, the method includes the steps of obtaining historical data of power consumption load of each power consumption device of an enterprise user in a preset time period, sequentially constructing prediction models of each power consumption device according to the historical data, sequentially passing through the prediction models of each power consumption device, and calculating to obtain second power consumption load prediction values corresponding to each power consumption device in a future time period, where the second power consumption load prediction values are specifically:

acquiring historical data of power loads of production end devices and management end devices of enterprise users in a preset time period; constructing a corresponding initial third electric equipment prediction model for each production end device, taking historical data of electric loads of each production end device as training data of the corresponding initial third electric equipment prediction model, and training to obtain a third electric equipment prediction model corresponding to each production end device; each production end device is provided with a corresponding initial third electric equipment prediction model and a trained third electric equipment prediction model; constructing a corresponding initial fourth electric equipment prediction model for each management end device, taking the historical data of the electric load of each management end device as the training data of the corresponding initial fourth electric equipment prediction model, and training to obtain a fourth electric equipment prediction model corresponding to each management end device; each production end device is provided with a corresponding initial fourth electric equipment prediction model and a trained fourth electric equipment prediction model; and sequentially obtaining second electricity load prediction values of each production end device through the third electricity consumption device prediction model, and sequentially obtaining second electricity load prediction values of each management end device through the fourth electricity consumption device prediction model.

In this embodiment, by constructing a corresponding initial third electric equipment prediction model for each production end device and a corresponding initial fourth electric equipment prediction model for each management end device, it can be ensured that all the obtained prediction results are based on each electric equipment, but not the results corresponding to all the electric equipment.

Step S104, decomposing the first electricity prediction result according to the equipment topological graph, so as to obtain a first electricity load prediction value among the electric equipment, and obtaining a predicted value difference value through the first electricity load prediction value and a second electricity load prediction value among the electric equipment; each electric equipment is decomposed to obtain a corresponding first electric load predicted value.

As a preferred solution of this embodiment, the decomposing the first electrical prediction result according to the device topology map, so as to obtain a first electrical load prediction value between the electrical devices, specifically:

According to the equipment topological graph, the operation relation and the operation parameters of the management end equipment are obtained, and the operation relation and the operation parameters of the production end equipment are obtained; according to the operation relation and the operation parameters of the management end devices and the operation relation and the operation parameters of the production end devices, the first electricity prediction results of the electric devices are sequentially decomposed, so that the decomposition sequence is determined through the operation relation of the electric devices, and according to the operation parameters of the electric devices, the first electricity prediction results of the electric devices are decomposed according to the decomposition sequence, and therefore the first electricity load prediction values of the management end devices and the production end devices are obtained.

In this embodiment, the first electricity prediction result is decomposed according to the operation relationship and the operation parameters between the device topology graph and the devices, so as to obtain the first electricity load prediction amount of each management end device and each production end device, thereby improving the accuracy and the practicability of the prediction, and providing support for the electricity management and the scheduling of enterprise users.

In this embodiment, the difference between the predicted values is the first electrical load predicted value and the second electrical load predicted value between the electrical apparatuses, and since each electrical apparatus has a first electrical load predicted value calculated from real-time data and a second electrical load predicted value calculated from historical data, the difference between the real-time data and the historical data can be accurately obtained by calculating the predicted values obtained from the real-time data and the historical data, so that adjustment of the predicted data is realized, and the accuracy of prediction is improved.

It can be understood that through the operation relationship between the equipment topological graph and the equipment, the operation relationship and the mutual influence between each management end equipment and production end equipment can be deeply known, so that the decomposition sequence and the decomposition mode can be accurately determined, the accuracy and the reliability of the decomposition result are improved, the reasonable decomposition sequence can be determined according to the operation relationship and the operation parameters between the equipment, the decomposition process can be optimized through the reasonable decomposition sequence, the calculation amount and the complexity are reduced, and the decomposition efficiency and the decomposition accuracy are improved.

Further, the first electricity prediction result is decomposed through the decomposition sequence and the equipment operation parameters to obtain first electricity load prediction values of the management end equipment and the production end equipment, and the mutual influence and the relevance among the equipment can be accurately considered in the decomposition process by considering the operation parameters among the equipment, and the prediction values can provide detailed prediction information of electricity loads of the equipment, support electricity dispatching and optimization decision, improve the prediction accuracy of the electricity loads of the equipment and better reflect the actual operation condition.

Step 105, according to the corresponding preset difference value of each electric device, combining with a preset target output requirement to obtain a target execution amount of each electric device, and according to the target execution amount, formulating an optimization strategy of all the electric devices, and further respectively optimizing the electric loads of all the electric devices of users in the enterprise based on the optimization strategy.

As a preferred solution of this embodiment, the obtaining a target execution amount of each electric device according to the preset target output requirement and the corresponding preset target output requirement of each electric device, and formulating an optimization strategy of all electric devices according to the target execution amount specifically includes:

according to the corresponding predicted difference value of each electric device, correcting the future electric load of each electric device, thereby obtaining an initial target execution amount; the initial target execution amount corresponding to the electric equipment is adjusted by combining with a preset target output requirement, so that the target execution amount of each electric equipment is obtained; formulating an initial optimization strategy according to the target execution amount, and inputting the initial optimization strategy into the equipment topological graph to verify the executability of the initial optimization strategy; when the initial optimization strategy has the executable performance, the initial optimization strategy is used as a final optimization strategy; when the initial optimization strategy does not have the executable performance, the operation data of each electric equipment generated when the initial optimization strategy is input into the equipment topological graph is obtained, and the initial optimization strategy is corrected according to the operation data of each electric equipment, so that a final optimization strategy is obtained after correction.

In the embodiment, the target execution amount of each device can be more accurately determined by correcting the predicted difference value of each electric device, so that the accuracy and the actual feasibility of the target execution amount are improved, and the operation of the electric device is ensured to accord with the expected target. And an initial optimization strategy is formulated according to the target execution amount so as to realize the preset target output requirement, and the executability of the strategy can be initially verified by combining the equipment topological graph and the initial optimization strategy, and a foundation is provided for subsequent optimization. When the initial optimization strategy does not have the executable performance, the initial optimization strategy is corrected according to the operation data in the equipment topological graph, so that problems and defects in the optimization strategy can be found by analyzing the operation data of the electric equipment, and corresponding adjustment and correction are performed to obtain the final optimization strategy which is more in line with the actual situation. And finally, a final optimization strategy is obtained through verification and correction, and after the strategy is corrected, the strategy has better executability and adaptability, can realize the target output requirement in actual operation, and improves the efficiency of electric equipment and the energy utilization efficiency.

The implementation of the above embodiment has the following effects:

Example two

Referring to fig. 2, an apparatus for optimizing electrical load according to an embodiment of the present invention includes: a construction module 201, a first prediction module 202, a second prediction module 203, a prediction difference module 204, and an optimization strategy module 205.

The construction module 201 is configured to obtain all electric devices and operation parameters thereof in an enterprise user, and construct a device topology graph between the electric devices according to a linkage relationship between the electric devices.

The first prediction module 202 is configured to obtain real-time data of a total power consumption load of an enterprise user in a preset time period, construct a power consumption load prediction model according to the real-time data, and further calculate a first power consumption prediction result in a future time period according to the power consumption load prediction model.

The second prediction module 203 is configured to obtain historical data of power consumption loads of each power consumption device of an enterprise user in a preset time period, sequentially construct each power consumption device prediction model according to the historical data, and sequentially calculate a second power consumption load prediction value corresponding to each power consumption device in a future time period through each power consumption device prediction model; wherein, each consumer has a second electrical load prediction.

The prediction difference module 204 is configured to decompose the first electrical prediction result according to the device topology graph, so as to obtain a first electrical load prediction value between each electrical device, and obtain a predicted difference value by predicting the first electrical load and the second electrical load between each electrical device; each electric equipment is decomposed to obtain a corresponding first electric load predicted value.

The optimization policy module 205 is configured to combine the preset target output requirements according to the preset measurement difference value corresponding to each electric device to obtain a target execution amount of each electric device, and formulate an optimization policy of all electric devices according to the target execution amount, so as to optimize the electric loads of all electric devices of users in the enterprise based on the optimization policy.

It will be clear to those skilled in the art that, for convenience and brevity of description, reference may be made to the corresponding process in the foregoing method embodiment for the specific working process of the above-described apparatus, which is not described herein again.

The implementation of the above embodiment has the following effects:

Example III

Correspondingly, the invention also provides a terminal device, comprising: a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the method of power load optimization as in any one of the embodiments above when the computer program is executed.

The terminal device of this embodiment includes: a processor, a memory, a computer program stored in the memory and executable on the processor, and computer instructions. The processor, when executing the computer program, implements the steps of the first embodiment described above, such as steps S101 to S105 shown in fig. 1. Alternatively, the processor, when executing the computer program, performs the functions of the modules/units in the above-described apparatus embodiments, for example, the optimization strategy module 205.

The computer program may be divided into one or more modules/units, which are stored in the memory and executed by the processor to accomplish the present invention, for example. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program in the terminal device. For example, the optimization policy module 205 is configured to obtain a target execution amount of each electric device according to a preset target output requirement in combination with a preset target difference value corresponding to each electric device, and formulate an optimization policy of all the electric devices according to the target execution amount, so as to optimize the electric loads of all the electric devices of users in the enterprise based on the optimization policy.

The terminal equipment can be computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The terminal device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of a terminal device and does not constitute a limitation of the terminal device, and may include more or less components than illustrated, or may combine some components, or different components, e.g., the terminal device may further include an input-output device, a network access device, a bus, etc.

The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the terminal device, and which connects various parts of the entire terminal device using various interfaces and lines.

The memory may be used to store the computer program and/or the module, and the processor may implement various functions of the terminal device by running or executing the computer program and/or the module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the mobile terminal, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.

Wherein the terminal device integrated modules/units may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as stand alone products. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software development medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.

Example IV

Correspondingly, the invention further provides a computer readable storage medium, which comprises a stored computer program, wherein the computer program controls a device where the computer readable storage medium is located to execute the method for optimizing the electric load according to any one of the embodiments.

The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention, and are not to be construed as limiting the scope of the invention. It should be noted that any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art without departing from the spirit and principles of the present invention are intended to be included in the scope of the present invention.

Claims

1. A method of power load optimization, comprising:

2. The method for optimizing power consumption load according to claim 1, wherein the method is characterized in that all electric equipment and operation parameters thereof in enterprise users are obtained, and a device topology diagram among the electric equipment is constructed according to linkage relations among the electric equipment, specifically:

3. The method for optimizing the power consumption load according to claim 2, wherein the method is characterized in that the method comprises the steps of obtaining real-time data of total power consumption load of enterprise users in a preset time period, constructing a power consumption load prediction model according to the real-time data, and further calculating to obtain a first power consumption prediction result in a future time period through the power consumption load prediction model, wherein the method is specifically as follows:

4. The method for optimizing the power consumption load according to claim 3, wherein the method is characterized in that the historical data of the power consumption load of each power consumption device of the enterprise user in a preset time period is obtained, each power consumption device prediction model is sequentially constructed according to the historical data, and further the second power consumption load prediction amount corresponding to each power consumption device in a future time period is calculated through each power consumption device prediction model in sequence, specifically:

5. The method for optimizing the power consumption load according to claim 3, wherein the method is characterized in that the historical data of the power consumption load of each power consumption device of the enterprise user in a preset time period is obtained, each power consumption device prediction model is sequentially constructed according to the historical data, and further the second power consumption load prediction amount corresponding to each power consumption device in a future time period is calculated through each power consumption device prediction model in sequence, specifically:

6. The method for optimizing electrical loads according to claim 4 or 5, wherein the decomposing the first electrical prediction result according to the device topology map, so as to obtain a first electrical load prediction value between electrical devices, specifically is:

7. The method for optimizing power consumption load according to claim 6, wherein the obtaining the target execution amount of each electric device according to the preset target output requirement and the corresponding preset target output requirement, and formulating an optimization strategy of all electric devices according to the target execution amount comprises:

8. An apparatus for optimizing electrical load, comprising: the system comprises a construction module, a first prediction module, a second prediction module, a prediction difference module and an optimization strategy module;

9. A terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the method of power load optimization according to any one of claims 1 to 7 when executing the computer program.

10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the method of optimizing the electrical load according to any one of claims 1 to 7.