Search

CN-121984237-A - New energy system, new energy system energy scheduling method and edge gateway

CN121984237ACN 121984237 ACN121984237 ACN 121984237ACN-121984237-A

Abstract

The application discloses a new energy system, a new energy system energy scheduling method and an edge gateway, which relate to the technical field of new energy, wherein the new energy system comprises: the intelligent power supply system comprises an inverter, a direct current source and an edge gateway, wherein the edge gateway is respectively in communication connection with the inverter and the intelligent power supply, the operation data of the direct current source and the multidimensional operation data of each intelligent power supply are obtained through multiplexing the communication and edge calculation functions of the edge gateway, so that the total power consumption load data of the intelligent power supply in a future preset time period is obtained based on the multidimensional operation data prediction of each intelligent power supply, and the scheduling instruction generated based on the total power consumption load data of the intelligent power supply in the future preset time period and the operation data of the direct current source is sent to the inverter to realize the energy scheduling of a new energy system. The application abandons the traditional mode of measuring the total power by relying on the intelligent ammeter, and reduces the hardware cost and the installation complexity of the new energy system.

Inventors

  • YANG FAN
  • FAN RENKAI
  • HE PENG

Assignees

  • 南京光献科技有限公司

Dates

Publication Date
20260505
Application Date
20260123

Claims (12)

  1. 1. The new energy system is characterized by comprising an inverter, a direct current source and an edge gateway; The direct current side of the inverter is connected with the direct current source, and the direct current source comprises at least one of a photovoltaic panel and an energy storage battery; The alternating-current side grid-connected port of the inverter is connected with a power grid; The alternating current side load port of the inverter is connected with at least one intelligent electric equipment; The edge gateway is respectively in communication connection with the inverter and the intelligent electric equipment to acquire the running data of the direct current source and the multidimensional running data of each intelligent electric equipment; The edge gateway obtains scheduling instructions generated based on total power load data of the intelligent electric equipment and operation data of the direct current source in a future preset time period, and sends the scheduling instructions to the inverter, wherein the total power load data of the intelligent electric equipment in the future preset time period is obtained through prediction based on multidimensional operation data of each intelligent electric equipment.
  2. 2. The new energy system of claim 1, wherein the edge gateway is deployed with a load prediction model corresponding to each of the intelligent powered devices; The edge gateway extracts the multidimensional characteristics in the multidimensional operation data of the intelligent electric equipment, inputs the multidimensional characteristics into a load prediction model corresponding to the intelligent electric equipment, obtains the power load data of the intelligent electric equipment in the future preset time period, and generates a scheduling instruction based on the total power load data of the intelligent electric equipment in the future preset time period and the operation data of the direct current source.
  3. 3. The new energy system of claim 1, wherein the edge gateway sends the operation data of the direct current source and the multidimensional operation data of each intelligent electric device to a network side device; the network side equipment extracts the multidimensional characteristics in the multidimensional operation data of the intelligent electric equipment, inputs the multidimensional characteristics into a load prediction model corresponding to the intelligent electric equipment, obtains the electric load data of the intelligent electric equipment in the future preset time period, generates a scheduling instruction based on the total electric load data of the intelligent electric equipment in the future preset time period and the operation data of the direct current source, and sends the scheduling instruction to the edge gateway.
  4. 4. The new energy system of claim 3, wherein the network side device receives the multidimensional operation data of the target intelligent electric equipment sent by the mobile terminal, and updates or generates the load prediction model corresponding to the target intelligent electric equipment according to the multidimensional operation data of the target intelligent electric equipment.
  5. 5. The new energy system of any one of claims 2-4, wherein the multi-dimensional features include a power time sequence and a power influencing parameter, the power influencing parameter including at least one of an operation mode, a setting parameter and an operation environment parameter, the power influencing parameters corresponding to different intelligent electric devices being all the same or not the same; The load prediction model comprises a sequence decomposition module, a linear module, a nonlinear module, a multi-scale module and a full-connection layer; The sequence decomposition module decomposes the power time sequence into trend data and regularity data; the linear module extracts trend characteristics in the trend data; The nonlinear module extracts regularity characteristics in the regularity data; The multi-scale module carries out multi-scale decomposition on the multi-dimensional characteristics, extracts correlation among different scales and cross-characteristic dimension correlation, and obtains multi-scale time sequence characteristics; And the full connection layer maps the trend characteristic, the regularity characteristic and the multi-scale time sequence characteristic into electricity load data of the intelligent electric equipment in the future preset time period.
  6. 6. The new energy system of claim 5, wherein the nonlinear module comprises a multi-layer perceptron and at least one depth separable convolution, the nonlinear module performs Pating operations on the regularity data and inputs the regularity data subjected to Pating operations into the depth separable convolution for regularity feature extraction, the regularity feature being processed by reshape of the multi-layer perceptron for output.
  7. 7. The new energy system of claim 5, wherein the multi-scale module sequentially performs fast fourier transform, multi-scale scaling and feature decomposition operations on the multi-dimensional features to obtain K scale features, sequentially inputs the K scale features into corresponding depth separable convolutions to perform feature extraction and reshape processing to output uniform dimensions, captures multi-dimensional feature correlations by using a multi-head attention mechanism, and uniformly processes the output by Reshape back.
  8. 8. The new energy system of any one of claims 1-4, wherein the edge gateway is integrated inside the inverter or the edge gateway is not integrated inside the inverter.
  9. 9. The utility model provides a new energy system energy scheduling method which is characterized in that is applied to the edge gateway in the new energy system, the new energy system still includes dc-to-ac converter and direct current source, the direct current side of dc-to-ac converter is connected the direct current source, the direct current source includes at least one of photovoltaic board and energy storage battery, the electric wire netting is connected to the ac side grid-connected mouth of dc-to-ac converter, at least one intelligent consumer is connected to the ac side load mouth of dc-to-ac converter, the edge gateway respectively with dc-to-ac converter and intelligent consumer communication connection, the new energy system energy scheduling method includes: acquiring operation data of the direct current source and multidimensional operation data of each intelligent electric equipment; Acquiring scheduling instructions generated based on total power load data of intelligent electric equipment and operation data of the direct current source in a future preset time period, wherein the total power load data of the intelligent electric equipment in the future preset time period is obtained by prediction based on multidimensional operation data of each intelligent electric equipment; and sending the scheduling instruction to an inverter.
  10. 10. The method for scheduling new energy system energy according to claim 9, wherein the obtaining the scheduling instruction generated based on the total power load data of the intelligent electric equipment and the operation data of the direct current source for the future preset time period includes: extracting multi-dimensional characteristics in the multi-dimensional operation data of the intelligent electric equipment; Inputting the multidimensional characteristics into a load prediction model corresponding to the intelligent electric equipment to obtain electric load data of the intelligent electric equipment in the future preset time period; And scheduling instructions generated based on the total power load data of the intelligent electric equipment and the running data of the direct current source in the future preset time period.
  11. 11. The method for scheduling new energy system energy according to claim 9, wherein the obtaining the scheduling instruction generated based on the total power load data of the intelligent electric equipment and the operation data of the direct current source for the future preset time period includes: Transmitting the operation data of the direct current source and the multidimensional operation data of each intelligent electric device to network side equipment so that the network side equipment extracts multidimensional features in the multidimensional operation data of the intelligent electric devices, inputting the multidimensional features into a load prediction model corresponding to the intelligent electric devices to obtain power utilization load data of the intelligent electric devices in the future preset time period, and generating a scheduling instruction based on the total power utilization load data of the intelligent electric devices in the future preset time period and the operation data of the direct current source; and receiving the scheduling instruction sent by the network side equipment.
  12. 12. An edge gateway for performing the new energy system energy scheduling method of any one of claims 9 to 11.

Description

New energy system, new energy system energy scheduling method and edge gateway Technical Field The application relates to the technical field of new energy, in particular to a new energy system, an energy scheduling method of the new energy system and an edge gateway. Background With the development of photovoltaic technology, more and more families install new energy systems comprising photovoltaic panels and energy storage batteries, and normal operation of the new energy systems is guaranteed by coordinating power among photovoltaic power generation, charging and discharging of the energy storage batteries and household loads. The intelligent ammeter is one of core equipment of the new energy system, and the total load power of the family is measured in real time through the intelligent ammeter, so that the inverter is output and adjusted according to the total load of the family, or the future household electricity demand is predicted according to the total load of the family, and the inverter is output and adjusted. However, the smart meter not only increases the hardware cost of the new energy system, but also increases the installation complexity. Disclosure of Invention In view of the above problems, the application provides a new energy system, a new energy system energy scheduling method and an edge gateway, which abandon the traditional mode of relying on the intelligent ammeter to measure the total power and reduce the hardware cost and the installation complexity of the new energy system. The specific scheme is as follows: the first aspect of the application provides a new energy system, which comprises an inverter, a direct current source and an edge gateway; The direct current side of the inverter is connected with the direct current source, and the direct current source comprises at least one of a photovoltaic panel and an energy storage battery; The alternating-current side grid-connected port of the inverter is connected with a power grid; The alternating current side load port of the inverter is connected with at least one intelligent electric equipment; The edge gateway is respectively in communication connection with the inverter and the intelligent electric equipment to acquire the running data of the direct current source and the multidimensional running data of each intelligent electric equipment; The edge gateway obtains scheduling instructions generated based on total power load data of the intelligent electric equipment and operation data of the direct current source in a future preset time period, and sends the scheduling instructions to the inverter, wherein the total power load data of the intelligent electric equipment in the future preset time period is obtained through prediction based on multidimensional operation data of each intelligent electric equipment. In one possible implementation, the edge gateway is deployed with a load prediction model corresponding to each intelligent electric device; The edge gateway extracts the multidimensional characteristics in the multidimensional operation data of the intelligent electric equipment, inputs the multidimensional characteristics into a load prediction model corresponding to the intelligent electric equipment, obtains the power load data of the intelligent electric equipment in the future preset time period, and generates a scheduling instruction based on the total power load data of the intelligent electric equipment in the future preset time period and the operation data of the direct current source. In one possible implementation, the edge gateway sends the operation data of the direct current source and the multidimensional operation data of each intelligent electric equipment to network side equipment; the network side equipment extracts the multidimensional characteristics in the multidimensional operation data of the intelligent electric equipment, inputs the multidimensional characteristics into a load prediction model corresponding to the intelligent electric equipment, obtains the electric load data of the intelligent electric equipment in the future preset time period, generates a scheduling instruction based on the total electric load data of the intelligent electric equipment in the future preset time period and the operation data of the direct current source, and sends the scheduling instruction to the edge gateway. In one possible implementation, the network side device receives the multidimensional operation data of the target intelligent electric equipment sent by the mobile terminal, and updates or generates a load prediction model corresponding to the target intelligent electric equipment according to the multidimensional operation data of the target intelligent electric equipment. In one possible implementation, the multi-dimensional characteristic comprises a power time sequence and a power influence parameter, wherein the power influence parameter comprises at least one of an operation mode, a setting pa