Smart city electricity consumption quantity prediction system

Abstract

The invention relates to a smart city electricity consumption prediction system. The system comprises a prediction execution mechanism and a prediction execution mechanism, the electric quantity prediction module is used for intelligently predicting a prediction value of the electric quantity of the target block in the current time segment by adopting an electric quantity prediction model on the basis of the number of electric equipment in the target block, the average value of rated power of the electric equipment, the number of residents and the electric quantity of each part corresponding to each historical time segment of the target block before the current time segment; and the allocation processing mechanism is used for allocating a corresponding number of power consumption quotas for the current time segment of the target block based on the predicted value. Through the system, the automatic encoder neural network which is designed in a targeted manner can be adopted to intelligently predict the total power consumption of the target block in the current time segment based on the power consumption information of the target block, and then corresponding advanced configuration of electric energy reserve is executed, so that the power consumption demand and the power saving demand of the block are both considered.

Description

Technical Field

[0001] The present invention relates to the field of electricity consumption management, and more specifically, to a smart city electricity consumption prediction system. Background Art

[0002] Electricity management is the activity of calculating electricity charges according to the set electricity price, the actual electricity consumption of users and the records of the electric energy metering device, and collecting electricity charges in a timely and accurate manner. Electricity management includes four interrelated links: meter reading, accounting, charging and comprehensive statistics. Since electricity is a commodity that cannot be stored, its output, transmission and sales have the special requirement of continuity, which makes it impossible for this commodity to achieve a sales model of one hand for money and one hand for goods. Therefore, the electricity market must adopt the principles of fair competition, voluntary mutual benefit and mutual benefit in accordance with the law. According to the records of the electric energy metering device installed by the user, the electric energy consumed by the user in a certain period of time is determined, and after calculation and verification, the electricity charges payable by the user are collected.

[0003] At present, in the electricity management within the city, the electricity that each block will need to consume in future time segments is usually configured in advance on a block-by-block basis. Since the actual electricity consumption data of each block cannot be accurately predicted in advance, there will inevitably be a mismatch between the electricity reserved in advance and the actual electricity consumed, which will either cause a waste of electricity or cause insufficient power supply. Summary of the invention

[0004] In order to solve the technical problems in the related fields, the present invention provides a smart city electricity consumption prediction system, which uses the number of power-consuming equipment in the target block, the average value of the rated power of the power-consuming equipment, the number of residents and the power consumption corresponding to each historical time segment of the target block before the current time segment as the basic data for executing the total power consumption prediction of the current time segment of the target block to ensure the validity and stability of the prediction result, introduces an object building device for performing each learning action on the autoencoder neural network to obtain the autoencoder neural network after completing each learning action and uses it as a power prediction model to perform intelligent prediction of the total power consumption of the current time segment of the target block, and also allocates a corresponding amount of power quota for the current time segment of the target block based on the predicted value of the power consumption of the target block in the current time segment according to the intelligent prediction, wherein the corresponding amount of power quota allocated for the current time segment of the target block is a preset multiple of the predicted value of the power consumption of the target block in the current time segment according to the intelligent prediction, thereby taking into account the power demand of the block and the power saving demand.

[0005] According to the present invention, a smart city power consumption prediction system is provided, the system comprising: Configure a collection device for collecting various block configuration data of the target block, wherein the various block configuration data of the target block are the number of electrical equipment, the average value of the rated power of the electrical equipment, and the number of residents in the target block; An object building device is used to perform each learning action on the autoencoder neural network to obtain the autoencoder neural network after completing each learning action and output it as a power prediction model; A content acquisition device, used to acquire the power consumption of the target block corresponding to each historical time segment before the current time segment, wherein the number of each historical time segment is proportional to the number of power-consuming devices in the target block; The prediction execution mechanism is connected to the configuration collection device, the object construction device and the content acquisition device respectively, and is used to adopt the power prediction model to intelligently predict the power consumption value of the target block in the current time segment based on the number of power-consuming devices in the target block, the average value of the rated power of the power-consuming devices and the number of residents, and the power consumption corresponding to each historical time segment before the current time segment of the target block; An allocation processing mechanism, connected to the prediction execution mechanism, is used to allocate a corresponding amount of electricity quota for the current time segment of the target block based on the predicted value of the electricity consumption of the target block in the current time segment predicted by intelligent prediction; Wherein, allocating a corresponding amount of electricity quota for the current time segment of the target block based on the predicted value of the electricity consumption of the target block in the current time segment according to the intelligent prediction includes: the corresponding amount of electricity quota allocated for the current time segment of the target block is a preset multiple of the predicted value of the electricity consumption of the target block in the current time segment according to the intelligent prediction; The object building device is used to perform each learning action on the autoencoder neural network to obtain the autoencoder neural network after completing each learning action and output it as the power prediction model, including: the number of each learning action performed by the autoencoder neural network is monotonically positively correlated with the distribution area of ​​the target block; Among them, a collection device is configured to collect various block configuration data of the target block, and the various block configuration data of the target block are the number of electrical equipment in the target block, the average value of the rated power of the electrical equipment, and the number of residents, including: the average value of the rated power of the electrical equipment in the target block is the arithmetic mean of the respective rated power values ​​corresponding to each electrical equipment in the target block.

[0006] The present invention needs to have at least the following outstanding essential features: Substantive feature A: The number of electrical equipment in the target block, the average value of the rated power of the electrical equipment, the number of residents, and the electricity consumption of each historical time segment before the current time segment of the target block are used as the basic data for the prediction of the total electricity consumption of the target block in the current time segment to ensure the validity and stability of the prediction results; Substantive feature B: Introducing an object building device to perform each learning action on the autoencoder neural network, so as to obtain the autoencoder neural network after each learning action and use it as an electricity prediction model to perform intelligent prediction of the total electricity consumption of the target block in the current time segment; Substantive feature C: The predicted value of the target block's electricity consumption in the current time segment based on intelligent prediction is used to allocate a corresponding amount of electricity quota for the target block in the current time segment, wherein the corresponding amount of electricity quota allocated for the target block in the current time segment is a preset multiple of the predicted value of the target block's electricity consumption in the current time segment based on intelligent prediction, thereby taking into account the block's electricity demand and electricity saving needs.

[0007] The smart city electricity consumption prediction system of the present invention is stable and easy to operate. Since it can use the targeted designed autoencoder neural network to intelligently predict the total electricity consumption of the target block in the current time segment based on the various electricity consumption information of the target block, and then perform the corresponding advance configuration of the electric energy reserve, it takes into account the electricity demand of the block and the demand for electricity saving, avoiding the waste of electricity or causing power shortage. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Those skilled in the art may better understand the numerous advantages of the present invention by referring to the accompanying drawings, in which: Figure 1 It is a structural schematic diagram of a smart city electricity consumption prediction system according to the primary embodiment of the present invention.

[0009] Figure 2 It is a structural schematic diagram of a smart city electricity consumption prediction system according to a secondary embodiment of the present invention.

[0010] Figure 3 2 is a schematic diagram of the structure of a smart city electricity consumption prediction system according to another embodiment of the present invention. DETAILED DESCRIPTION

[0011] Figure 1 1 is a schematic diagram of the structure of a smart city power consumption prediction system according to the primary embodiment of the present invention, the system comprising: Configure a collection device for collecting various block configuration data of the target block, wherein the various block configuration data of the target block are the number of electrical equipment, the average value of the rated power of the electrical equipment, and the number of residents in the target block; An object building device is used to perform each learning action on the autoencoder neural network to obtain the autoencoder neural network after completing each learning action and output it as a power prediction model; A content acquisition device, used to acquire the power consumption of the target block corresponding to each historical time segment before the current time segment, wherein the number of each historical time segment is proportional to the number of power-consuming devices in the target block; For example, the content acquisition device is used to acquire the power consumption corresponding to each historical time segment before the current time segment of the target block, and the number of each historical time segment is proportional to the number of power-consuming devices in the target block, including: selecting a content conversion function to represent the content conversion relationship that the number of each historical time segment is proportional to the number of power-consuming devices in the target block; The prediction execution mechanism is connected to the configuration collection device, the object construction device and the content acquisition device respectively, and is used to adopt the power prediction model to intelligently predict the power consumption value of the target block in the current time segment based on the number of power-consuming devices in the target block, the average value of the rated power of the power-consuming devices and the number of residents, and the power consumption corresponding to each historical time segment before the current time segment of the target block; An allocation processing mechanism, connected to the prediction execution mechanism, is used to allocate a corresponding amount of electricity quota for the current time segment of the target block based on the predicted value of the electricity consumption of the target block in the current time segment predicted by intelligent prediction; Wherein, allocating a corresponding amount of electricity quota for the current time segment of the target block based on the predicted value of the electricity consumption of the target block in the current time segment according to the intelligent prediction includes: the corresponding amount of electricity quota allocated for the current time segment of the target block is a preset multiple of the predicted value of the electricity consumption of the target block in the current time segment according to the intelligent prediction; The object building device is used to perform each learning action on the autoencoder neural network to obtain the autoencoder neural network after completing each learning action and output it as the power prediction model, including: the number of each learning action performed by the autoencoder neural network is monotonically positively correlated with the distribution area of ​​the target block; Wherein, a collection device is configured to collect various block configuration data of the target block, wherein the various block configuration data of the target block are the number of electrical equipment, the average value of the rated power of the electrical equipment and the number of residents in the target block, including: the average value of the rated power of the electrical equipment in the target block is the arithmetic mean of the values ​​of the rated power of each share corresponding to each electrical equipment in the target block; Among them, the corresponding amount of electricity quota allocated for the current time segment of the target block is a preset multiple of the predicted value of the electricity consumption of the target block in the current time segment predicted by intelligent prediction, including: the value of the preset multiple is between 1.05-1.10.

[0012] Figure 2 It is a structural schematic diagram of a smart city electricity consumption prediction system according to a secondary embodiment of the present invention.

[0013] and Figure 1 different, Figure 2 The smart city electricity consumption prediction system in the system can also include the following components: A voltage supply interface, connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device, respectively, for providing the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with their respective required working voltages; The voltage supply interface is respectively connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device, and is used to provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with the required working voltages respectively, including: the working voltages required by the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device respectively include 3.3 volts and 5 volts; The voltage supply interface is connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device respectively, and is used to provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with the required working voltages respectively, and further includes: the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device are arranged around the voltage supply interface and are isolated from the voltage supply interface by different electromagnetic shielding mechanisms respectively; The prediction execution mechanism, the configuration acquisition device, the object construction device, and the content acquisition device are configured around the voltage supply interface and are isolated from the voltage supply interface by using different electromagnetic shielding mechanisms, including: the distances from the different electromagnetic shielding mechanisms used by the prediction execution mechanism, the configuration acquisition device, the object construction device, and the content acquisition device to the voltage supply interface are equal; And wherein the prediction execution mechanism, the configuration acquisition device, the object building device and the content acquisition device are configured around the voltage supply interface and are isolated from the voltage supply interface by different electromagnetic shielding mechanisms respectively, and also includes: the internal structures of the different electromagnetic shielding mechanisms respectively used by the prediction execution mechanism, the configuration acquisition device, the object building device and the content acquisition device are the same.

[0014] Figure 3 2 is a schematic diagram of the structure of a smart city electricity consumption prediction system according to another embodiment of the present invention.

[0015] and Figure 1 different, Figure 3 The smart city electricity consumption prediction system in the system can also include the following components: a radiation sensing device, connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device, respectively, for providing the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with respective numerical sensing operations of real-time electromagnetic radiation amounts; Wherein, the radiation sensing device is respectively connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device, and is used to provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with respective numerical sensing operations of real-time electromagnetic radiation quantities, including: the radiation sensing device includes a plurality of radiation sensing units, which are used to provide respective numerical sensing operations of real-time electromagnetic radiation quantities for the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device; The radiation sensing device includes a plurality of radiation sensing units, which are used to respectively provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with respective numerical sensing operations of real-time electromagnetic radiation amounts, including: the internal structures of the plurality of radiation sensing units are the same; And wherein, the radiation sensing device includes multiple radiation sensing units, which are used to provide respective numerical sensing operations of real-time electromagnetic radiation quantities for the prediction execution mechanism, the configuration acquisition device, the object building device and the content acquisition device, respectively, including: the multiple radiation sensing units are respectively equipped with respective radiation alarm components.

[0016] In addition, in the smart city electricity consumption prediction system, the electricity consumption prediction model is used to intelligently predict the electricity consumption of the target block in the current time segment based on the number of electrical equipment in the target block, the average value of the rated power of electrical equipment and the number of residents, and the electricity consumption corresponding to each historical time segment before the current time segment of the target block. The predicted value includes: performing octal value conversion on the number of electrical equipment in the target block, the average value of the rated power of electrical equipment and the number of residents, and the electricity consumption corresponding to each historical time segment before the current time segment of the target block, and then inputting them into the electricity consumption prediction model to run the electricity prediction model to obtain the output of the predicted value of the electricity consumption of the target block in the current time segment.

[0017] Although the present invention has been specifically shown and described with reference to the preferred embodiments of the present invention, it will be appreciated by those skilled in the art that various changes in form and details may be made without departing from the spirit and scope of the present invention as set forth in the appended claims. In addition, although elements of the present invention are described or claimed in the singular, the plural is also encompassed unless expressly stated to be limited to the singular.

Claims

1. A smart city electricity consumption prediction system, characterized in that: The system comprises: Configure a collection device for collecting various block configuration data of the target block, wherein the various block configuration data of the target block are the number of electrical equipment, the average value of the rated power of the electrical equipment, and the number of residents in the target block; An object building device is used to perform each learning action on the autoencoder neural network to obtain the autoencoder neural network after completing each learning action and output it as a power prediction model; A content acquisition device, used to acquire the power consumption of the target block corresponding to each historical time segment before the current time segment, wherein the number of each historical time segment is proportional to the number of power-consuming devices in the target block; The prediction execution mechanism is connected to the configuration collection device, the object construction device and the content acquisition device respectively, and is used to adopt the power prediction model to intelligently predict the power consumption value of the target block in the current time segment based on the number of power-consuming devices in the target block, the average value of the rated power of the power-consuming devices and the number of residents, and the power consumption corresponding to each historical time segment before the current time segment of the target block; An allocation processing mechanism, connected to the prediction execution mechanism, is used to allocate a corresponding amount of electricity quota for the current time segment of the target block based on the predicted value of the electricity consumption of the target block in the current time segment predicted by intelligent prediction; Wherein, allocating a corresponding amount of electricity quota for the current time segment of the target block based on the predicted value of the electricity consumption of the target block in the current time segment according to the intelligent prediction includes: the corresponding amount of electricity quota allocated for the current time segment of the target block is a preset multiple of the predicted value of the electricity consumption of the target block in the current time segment according to the intelligent prediction; The object building device is used to perform each learning action on the autoencoder neural network to obtain the autoencoder neural network after completing each learning action and output it as the power prediction model, including: the number of each learning action performed by the autoencoder neural network is monotonically positively correlated with the distribution area of ​​the target block; Among them, a collection device is configured to collect various block configuration data of the target block, and the various block configuration data of the target block are the number of electrical equipment in the target block, the average value of the rated power of the electrical equipment, and the number of residents, including: the average value of the rated power of the electrical equipment in the target block is the arithmetic mean of the respective rated power values ​​corresponding to each electrical equipment in the target block.

2. The smart city electricity consumption prediction system according to claim 1, characterized in that: The corresponding amount of electricity quota allocated for the current time segment of the target block is a preset multiple of the predicted value of the electricity consumption of the target block in the current time segment predicted by intelligent prediction, including: the value of the preset multiple is between 1.05-1.

10.

3. The smart city electricity consumption prediction system according to claim 2, characterized in that: The system further comprises: A voltage supply interface, connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device, respectively, for providing the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with their respective required working voltages; Among them, the voltage supply interface is respectively connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device, and is used to provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with the required working voltages respectively, including: the working voltages required by the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device respectively include 3.3 volts and 5 volts.

4. The smart city power consumption prediction system according to claim 3, characterized in that: A voltage supply interface is respectively connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device, and is used to provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with their respective required working voltages. The prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device are also configured around the voltage supply interface and are respectively isolated from the voltage supply interface by different electromagnetic shielding mechanisms.

5. The smart city power consumption prediction system according to claim 4, characterized in that: The prediction execution mechanism, the configuration collection device, the object construction device and the content acquisition device are configured around the voltage supply interface and are isolated from the voltage supply interface by different electromagnetic shielding mechanisms, including: the distances from the prediction execution mechanism, the configuration collection device, the object construction device and the content acquisition device to the voltage supply interface are equal.

6. The smart city power consumption prediction system according to claim 4, characterized in that: The prediction execution mechanism, the configuration collection device, the object construction device and the content acquisition device are configured around the voltage supply interface and are isolated from the voltage supply interface by different electromagnetic shielding mechanisms respectively. It also includes: the internal structures of the different electromagnetic shielding mechanisms respectively used by the prediction execution mechanism, the configuration collection device, the object construction device and the content acquisition device are the same.

7. The smart city electricity consumption prediction system according to claim 2, characterized in that: The system further comprises: a radiation sensing device, connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device, respectively, for providing the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with respective numerical sensing operations of real-time electromagnetic radiation amounts; Among them, the radiation sensing device is respectively connected to the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device, and is used to provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with respective numerical sensing operations of real-time electromagnetic radiation quantities, including: the radiation sensing device includes multiple radiation sensing units, which are used to provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with respective numerical sensing operations of real-time electromagnetic radiation quantities.

8. The smart city electricity consumption prediction system according to claim 7, characterized in that: The radiation sensing device includes a plurality of radiation sensing units, which are used to provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with respective numerical sensing operations of real-time electromagnetic radiation quantities, including: the internal structures of the plurality of radiation sensing units are the same.

9. The smart city power consumption prediction system according to claim 7, characterized in that: The radiation sensing device includes a plurality of radiation sensing units, which are used to provide the prediction execution mechanism, the configuration acquisition device, the object construction device and the content acquisition device with respective numerical sensing operations of real-time electromagnetic radiation quantities, including: the plurality of radiation sensing units are respectively equipped with respective radiation alarm components.

Images