Load trend prediction and optimization system based on big data

Abstract

The invention discloses a load trend prediction and optimization system based on big data, and relates to the technical field of power grid management systems, and the system integrates a plurality of charging stations, a state grid power supply system and a renewable energy power station in a region. The system collects meteorological data, the number of vehicles, power consumption, power generation and other data in real time through the data acquisition module, and preprocesses and integrates the data through the data management module. The central processing module constructs a prediction model by using the data, and accurately predicts the power supply amount required by each charging station and the power generation amount of the renewable energy power station. The prediction module provides a decision basis for the power distribution module according to the prediction model, and the power distribution module optimizes the power distribution conditions of the state grid power supply system and the renewable energy power station according to the prediction result. The system can plan power resource distribution in advance, effectively cope with power demand and supply changes, and improve the reliability and efficiency of power supply.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid management systems, and more specifically, to a load trend prediction and optimization system based on big data. Background Art

[0002] Big data refers to data sets that are huge in volume, complex in type and diverse, and cannot be captured, stored, managed and analyzed within a reasonable time using traditional data processing software. It covers all forms of data, from structured to unstructured, and is of great significance for improving decision-making efficiency, optimizing resource allocation and promoting innovation and development.

[0003] At present, it is not possible to accurately predict the charging capacity of each charging station and the power generation of renewable energy such as wind power and solar power in the area. This deficiency makes it difficult for the system to make effective plans in advance and cannot accurately predict future power demand and supply. Therefore, in actual operation, problems such as unreasonable resource allocation, power supply shortage or surplus may occur. This not only affects the operating efficiency of the system, but also may cause inconvenience to users and even cause economic losses. In order to improve the performance of the system and user experience, it is necessary to further develop and improve the prediction model so as to more accurately predict the charging capacity of each charging station and the power generation of renewable energy, so as to achieve more reasonable resource allocation and advance planning.

[0004] Therefore, in order to solve the above technical problems, this application proposes a load trend prediction and optimization system based on big data. Summary of the invention

[0005] In view of the deficiencies in the prior art, the purpose of the present invention is to provide a load trend prediction and optimization system based on big data.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a load trend prediction and optimization system based on big data, including multiple charging stations in the region, a state grid power supply system and a renewable energy power station, wherein the charging station is used to charge new energy vehicles along the way; the renewable energy power station includes but is not limited to a photovoltaic power station and a wind power station, and the electricity produced is used to supply power to multiple charging stations; the state grid power supply system is used to assist the renewable energy power station in supplying energy to multiple charging stations, and the load trend prediction and optimization system based on big data also includes;

[0007] A data collection module, which is connected to the local meteorological station, traffic control department, charging stations and renewable energy power stations through an interface. The data collection module is used to collect meteorological data in the area over a period of time, data on the number of new energy vehicles passing through each charging station, data on the power consumption of each charging station, and data on the power generation of renewable energy power stations. The meteorological data includes but is not limited to the temperature, wind speed, rainfall and daily sunshine time in the area;

[0008] The data management module is used to pre-process the data collected by the data collection module to ensure the security and reliability of the data, and then integrate the data into a unified data storage platform. The data management module supports data query and data access;

[0009] The central processing module is used to analyze the meteorological data stored in the data storage platform, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station, and the power generation data of the renewable energy power station, find the correlation between the number of new energy vehicles passing through each charging station and the power consumption data of the charging station on the route, find the correlation between the meteorological data and the power generation of the renewable energy power station, and build a prediction model;

[0010] The prediction module is directly connected to the data acquisition module through an interface, and predicts the power supply required by each charging station and the predicted power generation of the renewable energy power station based on the data collected by the data acquisition module and the prediction model, so as to predict whether the power generation of the renewable energy power station in the area during the time period can fully supply each charging station;

[0011] The power distribution module connects the signal input interface with the signal output port of the prediction module, and reasonably allocates the power distribution of the State Grid power supply system and the renewable energy power station according to the power supply required by each charging station predicted by the prediction module and the predicted power generation of the renewable energy power station.

[0012] Wherein, the data management module adopts RDBMS (relational database management system), including but not limited to MySQL or PostgreSQL to integrate and store data.

[0013] It should be noted that the central processing module also integrates a machine learning unit, which is used to analyze data through machine learning algorithms and build accurate prediction models to predict the power supply required for each charging station and the predicted power generation of renewable energy power stations, wherein the machine learning algorithms include but are not limited to decision trees, random forests, support vector machines or deep learning algorithms.

[0014] It is worth noting that the power distribution module is used to globally optimize the power distribution of the State Grid power supply system and renewable energy power stations through algorithms and based on the power supply required by each charging station predicted by the prediction module and the predicted power generation of the renewable energy power station. The algorithms used by the power distribution module include but are not limited to genetic algorithms and particle swarm optimization algorithms.

[0015] A load trend prediction and optimization method based on big data is applied to the above-mentioned load trend prediction and optimization system based on big data. The load trend prediction and optimization method based on big data includes the following steps:

[0016] Phase 1: Data collection and model building phase:

[0017] A: Through the data acquisition module, the network of the local meteorological department, the network of the traffic management department, the network of each charging station and the network of the renewable energy power station are connected to obtain the meteorological data in the area over a period of time, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station and the power generation data of the renewable energy power station;

[0018] B: Build a data management module, which uses a relational database management system to pre-process the collected data to ensure the reliability of the data, and stores the collected data through the relational database management system;

[0019] C: Build a central processing module. The central processing module uses machine learning algorithms to analyze the relationship between various data stored in the relational database management system: the relationship between the number of new energy vehicles passing through each charging station and the power consumption data of the charging stations on the route; the relationship between meteorological data and the power generation of renewable energy power stations, and then build a prediction model based on the correlation and machine learning algorithms;

[0020] Phase 2: Prediction and actual use phase:

[0021] D: Through the data collection module, the meteorological data in the region over a period of time, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station, and the power generation data of renewable energy power stations are collected, and these data are stored through a unified data storage platform;

[0022] E: The power supply required by each charging station and the predicted power generation of the renewable energy power station are predicted based on the prediction model constructed in step C and the data collected by the data collection module;

[0023] F: Based on the prediction results in step E, the power distribution of the state grid power supply system and renewable energy power stations is reasonably allocated.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] 1. In the present invention, the machine learning unit in the system central processing module integrates a variety of advanced machine learning algorithms, such as decision trees, random forests, support vector machines or deep learning algorithms, which can deeply explore patterns and associations in the data and build a prediction model to accurately predict the power supply required by each charging station and the power generation of renewable energy power stations.

[0026] 2. In the present invention, the power distribution module uses genetic algorithm and particle swarm optimization algorithm to globally optimize the power distribution of the state grid power supply system and renewable energy power stations. This intelligent power distribution strategy can minimize energy waste and cost while ensuring stable and reliable power supply at each charging station. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0028] Figure 1 This is a system block diagram of the load trend prediction and optimization system based on big data of the present invention. DETAILED DESCRIPTION

[0029] As shown in the system block diagram, the present invention provides a load trend prediction and optimization system based on big data, including multiple charging stations in the region, a state grid power supply system and a renewable energy power station, wherein the charging station is used to charge new energy vehicles along the way; the renewable energy power station includes but is not limited to a photovoltaic power station and a wind power station, and the electricity produced is used to supply power to multiple charging stations; the state grid power supply system is used to assist the renewable energy power station in supplying energy to multiple charging stations, and the load trend prediction and optimization system based on big data also includes:

[0030] A data collection module, which is connected to the local meteorological station, traffic control department, charging stations and renewable energy power stations through an interface. The data collection module is used to collect meteorological data in the area over a period of time, data on the number of new energy vehicles passing through each charging station, data on the power consumption of each charging station, and data on the power generation of renewable energy power stations. The meteorological data includes but is not limited to the temperature, wind speed, rainfall and daily sunshine time in the area;

[0031] The data management module is used to pre-process the data collected by the data collection module to ensure the security and reliability of the data, and then integrate the data into a unified data storage platform. The data management module supports data query and data access. The data management module uses RDBMS (relational database management system), including but not limited to MySQL or PostgreSQL, to integrate and store data;

[0032] A central processing module, which is used to analyze the meteorological data stored in the data storage platform, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station, and the power generation data of the renewable energy power station, find the correlation between the number of new energy vehicles passing through each charging station and the power consumption data of the charging station on the route, and find the correlation between the meteorological data and the power generation of the renewable energy power station, and build a prediction model. The central processing module is also integrated with a machine learning unit, which is used to analyze the data through a machine learning algorithm and build an accurate prediction model to predict the power supply required for each charging station and the predicted power generation of the renewable energy power station, wherein the machine learning algorithm includes but is not limited to a decision tree, a random forest, a support vector machine or a deep learning algorithm;

[0033] The power distribution module, the gas signal input interface is connected to the signal output port of the prediction module, and the power distribution of the state grid power supply system and the renewable energy power station is reasonably allocated according to the power supply required by each charging station and the predicted power generation of the renewable energy power station predicted by the prediction module. The power distribution module is used to perform global optimization allocation of the power distribution of the state grid power supply system and the renewable energy power station through an algorithm, and according to the power supply required by each charging station and the predicted power generation of the renewable energy power station predicted by the prediction module. Among them, the algorithm used by the power distribution module includes but is not limited to genetic algorithm and particle swarm optimization algorithm;

[0034] It should be noted that after the prediction model is built, the data subsequently collected by the data acquisition module is not only used as the input data of the prediction model to predict the power supply required for each charging station and the power generation of renewable energy power stations, but also as verification data for adjusting the prediction model. The prediction model is verified and adjusted in real time based on the meteorological data in the area, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station, and the power generation data of renewable energy power stations, so as to continuously optimize the prediction model and improve the prediction accuracy.

[0035] A load trend prediction and optimization method based on big data is applied to the above-mentioned load trend prediction and optimization system based on big data. The load trend prediction and optimization method based on big data includes the following steps:

[0036] Phase 1: Data collection and model building phase:

[0037] A: Through the data acquisition module, the network of the local meteorological department, the network of the traffic management department, the network of each charging station and the network of the renewable energy power station are connected to obtain the meteorological data in the area over a period of time, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station and the power generation data of the renewable energy power station;

[0038] B: Build a data management module, which uses a relational database management system to pre-process the collected data to ensure the reliability of the data, and stores the collected data through the relational database management system;

[0039] C: Build a central processing module. The central processing module uses machine learning algorithms to analyze the relationship between various data stored in the relational database management system: the relationship between the number of new energy vehicles passing through each charging station and the power consumption data of the charging stations on the route; the relationship between meteorological data and the power generation of renewable energy power stations, and then build a prediction model based on the correlation and machine learning algorithms;

[0040] Phase 2: Prediction and actual use phase:

[0041] D: Through the data collection module, the meteorological data in the region over a period of time, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station, and the power generation data of renewable energy power stations are collected, and these data are stored through a unified data storage platform;

[0042] E: The power supply required by each charging station and the predicted power generation of the renewable energy power station are predicted based on the prediction model constructed in step C and the data collected by the data collection module;

[0043] F: Based on the prediction results in step E, reasonably allocate the power distribution of the state grid power supply system and renewable energy power stations;

[0044] Among them, in step F, the power distribution of the state grid power supply system and the renewable energy power station is reasonably allocated, and the judgment method is as follows:

[0045] The total power supply required by each charging station in the area predicted by the prediction model is α, and the predicted power generation of renewable energy in the area during this period is β. The difference is calculated by the following formula:

[0046]

[0047] in, is the predicted supply-demand difference, B is the set percentage threshold, and then the judgment is made according to the following rules:

[0048]

[0049] in, When , it means that the predicted value of renewable energy power generation β cannot fully supply the predicted value of power supply required by each charging station α. ​​The power distribution module needs to plan the power distribution plan for each charging station in the area in advance through the state grid power supply system according to the difference to prevent power shortage. When , it means that the predicted value of renewable energy power generation β can fully supply the predicted value of power supply required by each charging station α. ​​At this time, the power distribution module can distribute the excess power of the renewable energy power station to other areas according to the difference to prevent energy waste.

[0050] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any ordinary technician in the industry can smoothly implement the present invention as shown in the drawings and described above. However, any equivalent changes, modifications and evolutions made by technicians familiar with the profession without departing from the scope of the technical solution of the present invention using the technical content disclosed above are all equivalent embodiments of the present invention. At the same time, any equivalent changes, modifications and evolutions made to the above embodiments based on the essential technology of the present invention are still within the protection scope of the technical solution of the present invention.

Claims

1. A load trend prediction and optimization system based on big data, including multiple charging stations in the region, the state grid power supply system and renewable energy power stations, characterized by: The load trend prediction and optimization system based on big data also includes; The data collection module is connected to the local meteorological station, traffic control department, charging stations and renewable energy power stations through the interface. The data collection module is used to collect meteorological data in the area over a period of time, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station, and the power generation data of the renewable energy power station; The data management module is used to pre-process the data collected by the data collection module to ensure the security and reliability of the data, and then integrate the data into a unified data storage platform; The central processing module is used to analyze the meteorological data stored in the data storage platform, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station, and the power generation data of the renewable energy power station, find the correlation between the number of new energy vehicles passing through each charging station and the power consumption data of the charging station on the route, find the correlation between the meteorological data and the power generation of the renewable energy power station, and build a prediction model; The prediction module is directly connected to the data acquisition module through an interface, and predicts the power supply required by each charging station and the predicted power generation of the renewable energy power station based on the data collected by the data acquisition module and the prediction model, so as to predict whether the power generation of the renewable energy power station in the area during the time period can fully supply each charging station; The power distribution module connects the signal input interface with the signal output port of the prediction module, and reasonably allocates the power distribution of the State Grid power supply system and the renewable energy power station according to the power supply required by each charging station predicted by the prediction module and the predicted power generation of the renewable energy power station.

2. The load trend prediction and optimization system based on big data according to claim 1 is characterized in that: The data management module uses RDBMS (relational database management system), including but not limited to MySQL or PostgreSQL to integrate and store data.

3. The load trend prediction and optimization system based on big data according to claim 2 is characterized in that: The central processing module is also integrated with a machine learning unit, which is used to analyze data through a machine learning algorithm and build a prediction model to predict the power supply required by each charging station and the predicted power generation of the renewable energy power station.

4. The load trend prediction and optimization system based on big data according to claim 3 is characterized in that: The power distribution module is used to globally optimize the power distribution of the state grid power supply system and the renewable energy power station through an algorithm and according to the power supply required by each charging station predicted by the prediction module and the predicted power generation of the renewable energy power station.

5. A method for load trend prediction and optimization based on big data, applied to the load trend prediction and optimization system based on big data according to any one of claims 1 to 4, characterized in that: The load trend prediction and optimization method based on big data includes the following steps: Phase 1: Data collection and model building phase: A: Through the data acquisition module, the network of the local meteorological department, the network of the traffic management department, the network of each charging station and the network of the renewable energy power station are connected to obtain the meteorological data in the area over a period of time, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station and the power generation data of the renewable energy power station; B: Build a data management module, which uses a relational database management system to pre-process the collected data to ensure the reliability of the data, and stores the collected data through the relational database management system; C: Build a central processing module. The central processing module uses machine learning algorithms to analyze the correlation between the data stored in the relational database management system: the correlation between the number of new energy vehicles passing through each charging station and the power consumption data of the charging stations on the route; the correlation between meteorological data and the power generation of renewable energy power stations, and then build a prediction model based on the correlation and machine learning algorithms; Phase 2: Prediction and actual use phase: D: Through the data collection module, the meteorological data in the region over a period of time, the number of new energy vehicles passing through each charging station, the power consumption data of each charging station, and the power generation data of renewable energy power stations are collected, and these data are stored through a unified data storage platform; E: The power supply required by each charging station and the predicted power generation of the renewable energy power station are predicted based on the prediction model constructed in step C and the data collected by the data collection module; F: Based on the prediction results in step E, the power distribution of the state grid power supply system and renewable energy power stations is reasonably allocated.

Images