CN-121981305-A - Big data driving-based intelligent management system for energy storage power grid

CN121981305ACN 121981305 ACN121981305 ACN 121981305ACN-121981305-A

Abstract

The invention discloses an intelligent management system of an energy storage power grid based on big data driving, which belongs to the technical field of energy storage power grids and comprises an acquisition module, a prediction module, an optimization module and a control module, wherein the acquisition module is used for acquiring historical information and carbon dioxide emission factors, the prediction module is used for predicting and acquiring electricity load power, wind-light output power, electricity price information and the charge state of a storage battery pack in the energy storage power grid in a next scheduling period based on the historical information, the optimization module is used for optimizing a scheduling algorithm by using the lowest operation and maintenance cost of the energy storage power grid in the next scheduling period and the minimum carbon dioxide emission amount as optimization targets based on the carbon dioxide emission factors and the prediction data in the next scheduling period, and the control module is used for determining a charging and discharging strategy of the storage battery pack in the next scheduling period based on the compromise solution and controlling charging and discharging of the storage battery pack. The system can give consideration to economic cost and environmental cost when intelligently managing the energy storage power grid.

Inventors

Liu Facan
Liang Yiyao
CAO CHUANZHAO
YANG CHAORAN
SUN ZHOUTING
LEI HAODONG
WANG CE
LI LONG
SHI JINGFENG
CAO XI
LIU MINGYI
HAN XU
CEN YUE

Assignees

华能广西清洁能源有限公司
中国华能集团清洁能源技术研究院有限公司

Dates

Publication Date: 20260505
Application Date: 20251022

Claims (7)

1. An intelligent management system of an energy storage power grid based on big data driving is characterized by comprising: The system comprises an acquisition module, a storage power grid, a storage battery and a power grid, wherein the acquisition module is used for acquiring historical information and carbon dioxide emission factors, and the historical information comprises historical wind-light output information, historical electricity load information, historical electricity price information and historical charge state of the storage battery pack in the storage power grid; The prediction module is used for predicting based on the historical information to obtain the power load power, wind-light output power, electricity price information and the charge state of a storage battery pack in the energy storage power grid in the next scheduling period; the optimization module is used for solving a pareto optimal solution set by utilizing a preset target energy optimization scheduling algorithm and determining a compromise solution in the pareto optimal solution set based on the carbon dioxide emission factor, the electricity load power, the wind-light output power, the electricity price information and the charge state of a storage battery in an energy storage grid in the next scheduling period, wherein the energy storage grid corresponding to the next scheduling period has the lowest operation and maintenance cost and the minimum carbon dioxide emission as optimization targets; and the control module is used for determining the charge-discharge strategy of the storage battery pack in the next scheduling period based on the compromise solution and controlling the charge-discharge of the storage battery pack in the next scheduling period based on the charge-discharge strategy.
2. The system of claim 1, wherein the historical wind-solar output information comprises historical state information, historical environmental information, and historical output power of a wind-solar power plant, wherein the prediction module comprises a wind-photon module, and wherein the wind-solar sub-module comprises: The wind-light prediction unit is used for predicting initial wind-light output power and corresponding typical power scenes of the next scheduling period of the wind-light power generation equipment based on the historical state information, the historical environment information and the historical output power; The wind-light error unit is used for acquiring wind-light error information of a typical power scene corresponding to the next scheduling period, wherein the wind-light error information represents error information between predicted initial wind-light output power and actual wind-light output power; And the wind-light adjusting unit is used for adjusting the initial wind-light output power based on wind-light error information of the next scheduling period to obtain wind-light output power of the next scheduling period.
3. The system of claim 2, wherein the wind-solar error unit comprises: the wind-light determining subunit is used for acquiring a plurality of error data for each typical power scene and determining wind-light error information corresponding to each typical power scene based on the plurality of error data; The wind-light scene subunit is used for predicting the environment information of the next scheduling period and determining a corresponding typical power scene based on the environment information of the next scheduling period; And the wind-light error subunit is used for determining wind-light error information corresponding to the next scheduling period based on the typical power scene corresponding to the next scheduling period.
4. The system of claim 1, wherein the optimization module comprises a selection sub-module, the selection sub-module comprising: a time period unit, configured to determine a power price time period corresponding to the next scheduling period; And the selection unit is used for selecting a preset energy optimization scheduling algorithm as a target energy scheduling optimization algorithm based on the charge state and the electricity price period of the next scheduling period.
5. The system of claim 4, wherein the preset energy-optimized scheduling algorithm includes a first optimization algorithm, a second optimization algorithm, and a third optimization algorithm, the state of charge includes charge, discharge, and charge-discharge, and the electricity rate period includes peak time and off-peak time, the selecting unit includes: The first algorithm subunit is configured to take the first optimization algorithm as a target energy optimization scheduling algorithm if the charge state of the next scheduling period is to be charged or discharged; And the second algorithm subunit is used for determining a power price period corresponding to the next scheduling period if the charge state of the next scheduling period is chargeable and dischargeable, taking the second optimization algorithm as a target energy optimization scheduling algorithm if the power price period is a peak, and taking the third optimization algorithm as a target energy optimization scheduling algorithm if the power price period is a non-peak period.
6. The system of claim 5, further comprising an algorithm building module, wherein the algorithm building module is configured to: Constructing a first optimization algorithm, a second optimization algorithm and a third optimization algorithm, wherein the first optimization algorithm, the second optimization algorithm and the third optimization algorithm comprise objective functions and constraint conditions as follows: objective function: In the objective function of the first optimization algorithm, In the objective functions of the second optimization algorithm and the third optimization algorithm, + Wherein, in the second optimization algorithm, In a third optimization algorithm, the first and second optimization algorithms, Constraint conditions: Wherein, the For the operation and maintenance costs of the energy storage grid, The cost of the battery pack for charging and discharging is the loss, For the maintenance cost factor of the battery pack, And The charge and discharge state variables of the battery pack in the schedule period are respectively 0 or 1, which indicates whether the corresponding state occurs, The power to charge the battery pack is supplied, For the discharge power of the accumulator battery, For the duration of one scheduling period, The depreciated cost of charging the battery pack, Penalty function for charging The depreciation cost for discharging the battery pack, As a function of the discharge penalty, For the commercial power purchase price in the electricity price information, For the amount of electricity purchased by the micro-grid to the external grid, Is that Selling The amount of the product is calculated, In order to obtain the carbon dioxide emission quantity, As the carbon dioxide emission factor, For the power of the electrical load at time t, The power of the wind and light output at the moment t, The link power at time t is the link power at time t, Positive values indicate that the micro-grid purchases electricity to the external grid, Characterizing micro-scale if negative the power grid sells electricity to an external power grid The charge/discharge power of the battery pack at time t, A positive value characterizes the battery pack charge, A negative value characterizes the battery pack discharge, In the form of a state of charge, In order to be at a minimum state of charge, Is the maximum state of charge.
7. The system of claim 1, wherein the battery pack comprises a plurality of batteries, the optimization module further comprises a scheduling sub-module, the scheduling sub-module comprising: The detection unit is used for detecting the running condition of each storage battery in the storage battery pack and determining whether an abnormal storage battery exists in the storage battery pack or not based on each running condition; And the updating unit is used for taking the rest storage batteries except the abnormal storage batteries as new storage batteries if the abnormal storage batteries exist in the storage batteries, and determining a charging and discharging strategy of the new storage batteries in the next dispatching period by utilizing a preset target energy optimization dispatching algorithm based on the new storage batteries.

Description

Big data driving-based intelligent management system for energy storage power grid Technical Field The invention belongs to the technical field of energy storage power grids, and particularly relates to an intelligent management system of an energy storage power grid based on big data driving. Background With the rapid development of renewable energy sources, the duty ratio of power generation equipment such as fans and photovoltaics in power supply is gradually increased. The significant intermittence and randomness of the fans and the photovoltaics provide a great challenge for the stable operation of the power system (or an external power grid). The energy storage power grid can store redundant electric energy when the generated energy is excessive and release the electric energy at the time of load peak, so that the key of stabilizing the power system is realized. Therefore, it is an important task to manage the energy storage grid. In the prior art, storage battery management in an energy storage power grid is generally combined with economic cost, and intelligent management on the energy storage power grid is realized by reducing the storage battery management cost. However, this approach often only considers direct economic costs, such as battery charge and discharge loss costs, ignoring environmental costs incurred when purchasing power to an external grid. Therefore, when the energy storage power grid is intelligently managed, how to consider the economic cost and the environmental cost becomes an urgent problem to be solved. It should be noted that the information disclosed in the above background section is only for enhancing understanding of the background of the application and thus may include information that does not form the prior art that is already known to those of ordinary skill in the art. Disclosure of Invention The present invention aims to solve at least one of the technical problems in the related art to some extent. The embodiment of the disclosure provides an intelligent management system for an energy storage power grid based on big data driving, so that economic cost and environmental cost can be considered when the intelligent management is performed on the energy storage power grid. In some embodiments, the big data driving-based energy storage grid intelligent management system comprises an acquisition module, a prediction module and an optimization module, wherein the acquisition module is used for acquiring historical information and carbon dioxide emission factors, the historical information comprises historical wind-solar power output information, historical electricity load information, historical electricity price information and historical charge states of storage batteries in an energy storage grid, the prediction module is used for predicting based on the historical information to obtain electricity load power, wind-solar power output power, electricity price information and charge states of storage batteries in the energy storage grid in a next scheduling period, the optimization module is used for determining a charge strategy of the storage batteries in the next scheduling period based on the carbon dioxide emission factors and the electricity load power, the output power, the electricity price information and the charge states of the storage batteries in the energy storage grid, the operation and maintenance cost of the energy storage grid corresponding to the next scheduling period is minimum and the carbon dioxide emission amount are optimized targets, a preset target energy optimization scheduling algorithm is utilized to solve a pareto optimal solution set, and a compromise solution in the pareto optimal solution is determined, and the charge strategy of the storage batteries in the next scheduling period is determined based on the compromise solution, and the charge strategy of the storage batteries in the next scheduling period is controlled to discharge the charge strategy of the storage batteries in the next scheduling period. In some embodiments, the historical wind-light output information comprises historical state information, historical environment information and historical output power of wind-light power generation equipment, the prediction module comprises a wind photon module, the wind-light sub-module comprises a wind-light prediction unit, a wind-light error unit and a wind-light adjustment unit, the wind-light prediction unit is used for predicting initial wind-light output power of a next scheduling period of the wind-light power generation equipment and a corresponding typical power scene based on the historical state information, the historical environment information and the historical output power, the wind-light error unit is used for obtaining wind-light error information of the typical power scene corresponding to the next scheduling period, the wind-light error information characterizes error information between the predicted initia