A method, device and storage medium for controlling power supply of electric load

Abstract

The present invention discloses a method, device and storage medium for controlling power supply of electric loads. The method comprises the following steps: in response to receiving a power load control request from a user, obtaining the power management contract of the user and the power consumption information of each power load in the power system within a target period; preprocessing the power consumption information of each power load in the power system within the target period to generate target preprocessing data; inputting the target preprocessing data into a trained load power supply management model to obtain the power supply information of each power load in the power system within the target period; determining the target power load according to the user's power management contract, and supplying power to the target power load according to the power supply information; the present invention can solve the technical problems in the prior art that power energy distribution is difficult to accurately distribute to individual users and the power energy utilization efficiency is not high enough.

Description

Technical Field

[0001] The present invention relates to a method, a device and a storage medium for controlling power supply of an electric load, and belongs to the technical field of power systems. Background Art

[0002] In traditional technologies, smart grids only manage power supply for larger areas. For example, for provincial or municipal power supply networks, regional power distribution is performed. This power distribution process is based on the power consumption ratio of each region, which is difficult to accurately allocate to individual users, and the energy utilization efficiency is not high enough. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method, device and storage medium for controlling power supply of electric loads, so as to solve the technical problems in the prior art that electric energy distribution is difficult to accurately distribute to individual users and the electric energy utilization efficiency is not high enough.

[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0005] In a first aspect, the present invention provides a method for controlling power supply to an electric load, comprising:

[0006] In response to receiving a power load control request from a user, obtaining the user's power management contract and power consumption information of each power load in the power system during a target period;

[0007] Preprocessing the power consumption information of each power load in the power system within the target period to generate target preprocessed data;

[0008] Input the target pre-processed data into the trained load power supply management model to obtain the power supply information of each power load in the power system during the target period;

[0009] The target power load is determined according to the user's power management contract, and power is supplied to the target power load according to the power supply information.

[0010] Optionally, the user's power management contract includes:

[0011] Obtain user information and power load information in the power system;

[0012] Matching users and power loads based on user information and power load information;

[0013] Generate the power load set corresponding to each user according to the matching results;

[0014] The power load set is used as the power management contract for power users.

[0015] Optionally, the power consumption information of the power load includes the power consumption time of the power load, the power consumption nature corresponding to the power consumption time, and the power consumption level.

[0016] Optionally, the preprocessing includes:

[0017] Determine the power usage priority of each power load based on the nature of power usage;

[0018] Determine the power supply proportion of each power load based on the power consumption level;

[0019] Each power load and its power consumption time, power consumption priority and power supply proportion are used as preprocessing data.

[0020] Optionally, the training of the load power supply management model includes:

[0021] Obtain the power consumption and supply information of each power load in the power system during each historical period;

[0022] Preprocessing the power consumption information of each power load in the power system in each historical period to generate historical preprocessed data;

[0023] Constructing a data sample set based on each historical pre-processed data and its corresponding power supply information;

[0024] A load power supply management model is constructed based on a convolutional neural network, and the load power supply management model is constructed through training of a data sample set.

[0025] Optionally, supplying power to the target power load according to the power supply information further includes:

[0026] Obtaining the probability of each target power load adjusting its power supply information;

[0027] If the probability of the adjustment operation is greater than a preset probability threshold, the adjustment operation is recorded as a valid operation and the record is stored.

[0028] In a second aspect, the present invention provides an electric load power supply control device, the device comprising:

[0029] an information acquisition module, configured to, in response to receiving a user's power load control request, acquire the user's power management contract and power consumption information of each power load in the power system during a target period;

[0030] A preprocessing module is used to preprocess the power consumption information of each power load in the power system within the target period to generate target preprocessing data;

[0031] The model prediction module is used to input the target pre-processed data into the trained load power supply management model to obtain the power supply information of each power load in the power system during the target period;

[0032] The load power supply module is used to determine the target power load according to the user's power management contract and supply power to the target power load according to the power supply information.

[0033] In a third aspect, the present invention provides an electric load power supply control device, comprising a processor and a storage medium;

[0034] The storage medium is used to store instructions;

[0035] The processor is configured to operate according to the instructions to execute the steps of the above method.

[0036] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when executed by a processor.

[0037] Compared with the prior art, the present invention has the following beneficial effects:

[0038] The present invention provides a power load power supply control method, device and storage medium. By constructing a load power supply management model, when receiving a power load control request, the power consumption information of each power load in the power system within the target time period is input into the constructed load power supply management model to obtain power supply information, and then the target power load is obtained according to the user's power management contract, and power is supplied to the target power load. Compared with the existing technology, the user power supply management in the target power system is realized through the load power supply management model and the user's power management contract, avoiding the technical problems in the existing technology that the power energy distribution is difficult to accurately distribute to individual users and the power energy utilization efficiency is not high enough, thereby improving the efficiency of power distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 This is a flow chart of a method for controlling power supply to an electric load provided in the first embodiment of the present invention;

[0040] Figure 2 This is a flow chart of the training process of the load power supply management model provided in the first embodiment of the present invention. DETAILED DESCRIPTION

[0041] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and are not intended to limit the scope of protection of the present invention.

[0042] Example 1:

[0043] like Figure 1 As shown, an embodiment of the present invention provides a method for controlling power supply of an electric load, comprising the following steps:

[0044] 1. In response to receiving a user's power load control request, obtaining the user's power management contract and power consumption information of each power load in the power system during the target period;

[0045] (1) The user's electricity management contract includes:

[0046] Obtain user information and power load information in the power system;

[0047] Matching users and power loads based on user information and power load information;

[0048] Generate the power load set corresponding to each user according to the matching results;

[0049] The power load set is used as the power management contract for power users.

[0050] Power management contracts can be stored on the blockchain to ensure transparent management of electric energy. Power management contracts are management contracts formulated based on various power loads in different power systems and are generally applicable to specific target power systems.

[0051] (2) The power system may refer to a power grid system consisting of all power loads within a geographical area, or may refer to a power load network consisting of power loads of individual users, where an individual user may refer to a single electricity account.

[0052] 2. Preprocess the power consumption information of each power load in the power system during the target period to generate target preprocessed data;

[0053] 2.1. The power consumption information of the power load includes the power consumption time of the power load, the power consumption nature corresponding to the power consumption time, and the power consumption level.

[0054] 2.2 Preprocessing includes:

[0055] The power priority of each power load is determined according to the nature of power consumption; the nature of power consumption includes: industrial power consumption, commercial power consumption and residential power consumption, etc. The power priority based on the nature of power consumption can be that residential power consumption has a higher priority than commercial power consumption, and commercial power consumption has a higher priority than industrial power consumption. In addition, when dividing the priorities, the priority of commercial power consumption can also be equal to that of industrial power consumption, and the power supply ratio is 1:1.

[0056] The power supply ratio of each power load is determined based on the power consumption level. The process of determining the power supply ratio of each power load based on the power consumption level can be based on the ratio between the power consumption of each power load in the same period of time, and then allocating the proportion of power supply required. For example, if the existing power load A and power load B are recorded in the blockchain, and the power consumption levels of the two in one day are 1:2, then when the two power loads are subsequently powered, the power supply ratio can be allocated to 1:2.

[0057] Each power load and its power consumption time, power consumption priority and power supply proportion are used as preprocessing data.

[0058] 3. Input the target pre-processed data into the trained load power supply management model to obtain the power supply information of each power load in the power system during the target period;

[0059] like Figure 2 As shown, the training of the load power supply management model includes:

[0060] Obtain the power consumption and supply information of each power load in the power system during each historical period;

[0061] Preprocessing the power consumption information of each power load in the power system in each historical period to generate historical preprocessed data;

[0062] Constructing a data sample set based on each historical pre-processed data and its corresponding power supply information;

[0063] A load power supply management model is constructed based on a convolutional neural network, and the load power supply management model is constructed through training of a data sample set.

[0064] During the training process, historical pre-processed data is input into the load power supply management model to generate predicted power supply information. The loss is calculated based on the predicted power supply information and the actual power supply information. The model parameters are optimized based on the loss backpropagation, and the training is finally completed after multiple rounds of iterations.

[0065] 4. Determine the target power load according to the user's power management contract, and supply power to the target power load based on the power supply information.

[0066] The supplying of power to the target power load according to the power supply information further includes:

[0067] Obtaining the probability of each target power load adjusting its power supply information;

[0068] If the probability of the adjustment operation is greater than a preset probability threshold, the adjustment operation is recorded as a valid operation and the record is stored.

[0069] The probability of an adjustment operation refers to the calculation of the probability of adjusting the current power supply information of each power load at the current moment to the power supply information predicted by the preset load power supply management model based on the historical adjustment records recorded in the blockchain as data samples.

[0070] Example 2:

[0071] An embodiment of the present invention provides a power load power supply control device, the device comprising:

[0072] an information acquisition module, configured to, in response to receiving a user's power load control request, acquire the user's power management contract and power consumption information of each power load in the power system during a target period;

[0073] A preprocessing module is used to preprocess the power consumption information of each power load in the power system within the target period to generate target preprocessing data;

[0074] The model prediction module is used to input the target pre-processed data into the trained load power supply management model to obtain the power supply information of each power load in the power system during the target period;

[0075] The load power supply module is used to determine the target power load according to the user's power management contract and supply power to the target power load according to the power supply information.

[0076] Example 3:

[0077] Based on the first embodiment, the embodiment of the present invention provides an electric load power supply control device, including a processor and a storage medium;

[0078] The storage medium is used to store instructions;

[0079] The processor is configured to operate according to the instructions to execute the steps of the above method.

[0080] Example 4:

[0081] Based on the first embodiment, the embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the above method are implemented.

[0082] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0083] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0084] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0085] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0086] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for controlling power supply of an electric load, characterized in that: include: In response to receiving a power load control request from a user, obtaining the user's power management contract and power consumption information of each power load in the power system during a target period; The power management contract of the user includes: obtaining user information and power load information in the power system; matching the user and the power load according to the user information and the power load information; generating a power load set corresponding to each user according to the matching result; and using the power load set as the power management contract of the power user; Preprocessing the power consumption information of each power load in the power system within the target period to generate target preprocessed data; Inputting the target preprocessed data into the trained load power supply management model to obtain the power supply information of each power load in the power system during the target period; training the load power supply management model includes: obtaining the power consumption information and power supply information of each power load in the power system during each historical period; preprocessing the power consumption information of each power load in the power system during each historical period to generate historical preprocessed data; constructing a data sample set based on each historical preprocessed data and its corresponding power supply information; constructing a load power supply management model based on a convolutional neural network, and training the constructed load power supply management model through the data sample set; The target power load is determined according to the user's power management contract, and the target power load is supplied with power according to the power supply information. It also includes: obtaining the probability of each target power load adjusting its power supply information; if the probability of the adjustment operation is greater than a preset probability threshold, the adjustment operation is recorded as a valid operation and the record is stored.

2. The method for controlling power supply of an electric load according to claim 1, wherein: The power consumption information of the power load includes the power consumption time of the power load, the power consumption nature corresponding to the power consumption time, and the power consumption level.

3. The power load power supply control method according to claim 2, characterized in that: The pretreatment includes: Determine the power usage priority of each power load based on the nature of power usage; Determine the power supply proportion of each power load based on the power consumption level; Each power load and its power consumption time, power consumption priority and power supply proportion are used as preprocessing data.

4. A power load power supply control device, characterized in that: The device comprises: An information acquisition module is configured to, in response to receiving a user's power load control request, acquire the user's power management contract and power consumption information of each power load in the power system during a target period; the user's power management contract comprises: acquiring user information and power load information in the power system; matching the user and the power load based on the user information and the power load information; generating a power load set corresponding to each user based on the matching result; and using the power load set as the power management contract of the power user; A preprocessing module is used to preprocess the power consumption information of each power load in the power system within the target period to generate target preprocessing data; The model prediction module is used to input the target pre-processed data into the trained load power supply management model to obtain the power supply information of each power load in the power system during the target period; the training of the load power supply management model includes: obtaining the power consumption information and power supply information of each power load in the power system during each historical period; pre-processing the power consumption information of each power load in the power system during each historical period to generate historical pre-processed data; constructing a data sample set based on each historical pre-processed data and its corresponding power supply information; constructing a load power supply management model based on a convolutional neural network, and training the constructed load power supply management model through the data sample set; The load power supply module is used to determine the target power load of the user based on the power management contract, supply power to the target power load based on the power supply information, and at the same time, obtain the probability of each target power load adjusting its power supply information; if the probability of the adjustment operation is greater than a preset probability threshold, the adjustment operation is recorded as a valid operation and the record is stored.

5. An electric load power supply control device, characterized in that: including processors and storage media; The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images