Intelligent optimized dispatching system of compressed air energy storage power station

Abstract

The invention relates to the technical field of compressed air energy storage, and discloses an intelligent optimal scheduling system for a compressed air energy storage power station, which comprises a central control platform, a data acquisition and monitoring module, a load prediction and electricity price prediction module, a scheduling optimization decision module and a real-time control and execution module, the central control platform is respectively connected with the acquisition and monitoring module, the load prediction and electricity price prediction module and the real-time control and execution module, and the load prediction and electricity price prediction module is also connected with the scheduling optimization decision module. According to the intelligent optimization scheduling system of the compressed air energy storage power station, artificial intelligence, big data analysis and optimization control technologies are combined, an efficient and flexible energy storage scheduling platform is constructed, and the problems that an existing system is single in scheduling strategy, insufficient in real-time response, insufficient in economical efficiency optimization and the like are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of compressed air energy storage, and particularly relates to an intelligent optimization scheduling system for a compressed air energy storage power station. Background Art

[0002] With the transformation of the global energy structure and the rapid increase in the proportion of new energy power generation, the operation challenges faced by the power system are becoming increasingly severe. The access of intermittent renewable energy sources such as wind energy and solar energy has led to an increase in the load volatility of the power grid and an increase in the difficulty of frequency regulation. At the same time, due to insufficient flexibility, the role of traditional thermal power units in peak shaving and frequency modulation is gradually limited. To cope with the peak-valley difference of the power grid load, frequency fluctuations, and the uncertainty of new energy power generation, large-scale energy storage technologies have gradually become an important part of the power system. Among many energy storage technologies, compressed air energy storage (CAES) is widely regarded as one of the key technologies suitable for power grid peak shaving and frequency modulation due to its significant advantages such as large energy storage scale, long service life, and low operating cost.

[0003] The basic principle of a compressed air energy storage system is to utilize the surplus electric energy during the low-load period of the power grid, compress air through a compressor, and store it in an underground salt cavern, a high-pressure gas storage tank, or other gas storage devices. When the power grid load is at a peak or the output of new energy is insufficient, the system releases the stored compressed air to drive an expander to generate electricity and make up for the power gap. Compared with traditional energy storage methods (such as chemical battery energy storage), CAES has advantages such as large scale, low cost, and high reliability, and at the same time avoids the environmental pollution problems in chemical energy storage systems.

[0004] Although the compressed air energy storage technology already has certain commercial application conditions, the intelligence and optimization ability of its scheduling system still cannot meet the existing requirements, and it has the following problems: 1. Unintelligent scheduling: Most of the existing scheduling systems for compressed air energy storage power stations use simple rules or thresholds for judgment and scheduling, lacking intelligent optimization algorithms and strategies. This results in scheduling results that are often not precise and efficient enough, and cannot fully exert the energy storage and peak shaving capabilities of the compressed air energy storage power station. 2. Inaccurate model: The existing scheduling systems usually do not establish an accurate model of the compressed air energy storage power station and cannot accurately describe its energy storage, energy release, and interaction process with other power systems. This makes the scheduling results often deviate greatly from the actual operation situation, affecting the accuracy and reliability of scheduling. Summary of the Invention

[0005] The present invention provides an intelligent optimization scheduling system for a compressed air energy storage power station, which combines artificial intelligence, big data analysis, and optimization control technologies to build an efficient and flexible energy storage scheduling platform, and solves problems such as a single scheduling strategy, insufficient real-time response, and lack of economic optimization in the existing system.

[0006] The present invention provides an intelligent optimal scheduling system for a compressed air energy storage power station, which includes a central control platform, a data acquisition and monitoring module, a load forecasting and electricity price forecasting module, a scheduling optimization decision-making module, and a real-time control and execution module. The central control platform is respectively connected to the acquisition and monitoring module, the load forecasting and electricity price forecasting module, and the real-time control and execution module. The load forecasting and electricity price forecasting module is also connected to the scheduling optimization decision-making module;

[0007] The data acquisition and monitoring module real-time collects key parameters of the energy storage system and power grid operation data, and uploads the collected data to the central control platform to support data storage and processing;

[0008] The load forecasting and electricity price forecasting module, based on historical operation data, uses artificial intelligence algorithms to predict future power grid load fluctuations, new energy power generation curves, and electricity market price change trends;

[0009] The scheduling optimization decision-making module adopts a multi-objective optimization algorithm, and dynamically generates charge and discharge plans according to power grid demand, prediction results, and energy storage status to achieve the best operation strategy;

[0010] The real-time control and execution module converts the scheduling optimization decision into specific control instructions, and adjusts the operating states of compressors, expanders, and gas storage devices in real time through a PLC or a distributed control system.

[0011] Furthermore, it further includes a human-computer interaction and monitoring interface. The human-computer interaction and monitoring interface is connected to the central control platform. The human-computer interaction and monitoring interface provides an intuitive operation interface, displays the system operation status, real-time data, and scheduling strategies, and at the same time allows operators to manually adjust the scheduling plan or set key parameters.

[0012] Furthermore, it further includes a heat energy recovery and utilization module. The heat energy recovery and utilization module is connected to the scheduling optimization decision-making module. The heat energy recovery and utilization module integrates heat energy storage technology, stores the heat generated during the compressed air process and uses it for heating during the expansion process, and dynamically allocates heat energy resources through the intelligent optimization algorithm of the scheduling optimization decision-making module.

[0013] Furthermore, the scheduling optimization decision-making module is linked with the electricity market to achieve scheduling optimization, dynamically adjusts the energy storage plan to participate in the electricity spot market and ancillary service market, and provides frequency regulation and reserve services.

[0014] Furthermore, the data acquisition and monitoring module real-time collects key parameters of the energy storage system and power grid operation data from the energy storage device, sensors, and power grid side through sensors and communication devices; among them, the key parameters of the energy storage system include gas storage pressure, temperature, and equipment status, and the power grid operation data includes load, frequency, and electricity price.

[0015] Furthermore, the load forecasting and electricity price forecasting module performs time series forecasting on future power grid loads and new energy generation curves based on a deep neural network, and at the same time combines real-time power market data to construct an electricity price forecasting model to provide a high-precision future electricity price fluctuation trend; wherein, the deep neural network includes LSTM and GRU.

[0016] Furthermore, the real-time control and execution module adopts real-time control technology based on model predictive control, i.e., MPC, and combines the operating state of the power grid to dynamically adjust the operating parameters of the compressor and expander.

[0017] Furthermore, the operation process of the system is as follows:

[0018] S1. Data acquisition: Real-time operating data is collected from energy storage devices, sensors, and the power grid side, including gas storage pressure, temperature, load curves, and market electricity prices, etc.;

[0019] S2. Data processing and forecasting: The prediction model is used to analyze the power grid load, electricity price trend, and the operating state of the energy storage system to generate operating prediction data for a future set time period;

[0020] S3. Scheduling optimization: According to the prediction results and the current state of the energy storage system, the charge and discharge plan is optimized, and the operating power of the compressor and expander and the operation mode of the gas storage device are determined;

[0021] S4. Control execution: The control instructions generated by the scheduling optimization decision module are executed through the real-time control module to dynamically adjust the operation of the energy storage system;

[0022] S5. Real-time feedback and adjustment: The system monitors the operating state in real time and dynamically corrects the scheduling strategy according to the actual situation.

[0023] The beneficial effects of the present invention are as follows:

[0024] 1. Improve the operating efficiency of the energy storage system. The energy conversion efficiency is optimized through heat recovery technology and intelligent scheduling algorithms, effectively reducing energy losses during the compression and expansion processes and greatly improving the overall system efficiency. The dynamic optimization strategy adopts a multi-objective optimization algorithm to dynamically adjust the charge and discharge plan according to the real-time power grid demand and energy storage state, making full use of the gas storage capacity and equipment performance.

[0025] 2. Strengthen the power grid's peak shaving and frequency modulation capabilities and improve the rapid response ability. Through real-time monitoring and model predictive control (MPC) technology, the system can respond to power grid load fluctuations and frequency adjustment requirements within seconds, providing high-quality frequency modulation services for the power grid. Smooth load fluctuations: Collaborate with new energy generation to suppress the volatility of the power grid load and improve the operating stability of the power grid.

[0026] 3. Improve economic benefits. Through high-precision electricity price forecasting and optimization algorithms, the system can charge during low electricity price periods and discharge during peak periods, significantly enhancing economic benefits. Participate in the electricity market: Support real-time optimal scheduling in the spot market and ancillary service markets (such as frequency regulation and reserve), creating more revenue channels for energy storage systems.

[0027] 4. Achieve intelligence and automation. Based on artificial intelligence technology, the system can accurately predict grid load, new energy generation, and electricity price fluctuation trends, providing a reliable basis for dispatching decisions. Autonomous scheduling optimization: Combining big data analysis and optimal control, the system has achieved autonomous decision-making capabilities, reducing dependence on manual experience. Brief Description of the Drawings

[0028] Figure 1 It is a schematic structural diagram of the intelligent optimal scheduling system for a compressed air energy storage power station according to the present invention.

[0029] Figure 2 It is a schematic diagram of the operation process of the intelligent optimal scheduling system for a compressed air energy storage power station according to the present invention.

[0030] The realization, functional features, and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0031] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0032] As Figure 1 shown, the present invention provides an intelligent optimal scheduling system for a compressed air energy storage power station, including a central control platform, a data acquisition and monitoring module, a load forecasting and electricity price forecasting module, a scheduling optimization decision-making module, a real-time control and execution module, and a human-machine interaction and monitoring interface. The central control platform is respectively connected to the acquisition and monitoring module, the load forecasting and electricity price forecasting module, the real-time control and execution module, and the human-machine interaction and monitoring interface. The load forecasting and electricity price forecasting module is also connected to the scheduling optimization decision-making module, and the scheduling optimization decision-making module is also connected to the heat energy recovery and utilization module.

[0033] Data Acquisition and Monitoring Module:

[0034] The data acquisition and monitoring module is deployed on the energy storage device and the grid side, and real-time collects key parameters of the energy storage system (gas storage pressure, temperature, equipment status) and grid operation data (load, frequency, electricity price) from the energy storage device, sensors, and the grid side through sensors and communication devices, and uploads the collected data to the central control platform, supporting data storage and processing.

[0035] Load Forecasting and Electricity Price Forecasting Module:

[0036] The load forecasting and electricity price forecasting module predicts future power grid load fluctuations, new energy power generation curves, and electricity market price change trends based on historical operation data using artificial intelligence algorithms (such as deep learning and time series analysis). It provides highly accurate forecasting results to serve as a basis for dispatching decisions.

[0037] The load forecasting and electricity price forecasting module performs time series forecasting on future power grid load and new energy power generation curves based on deep neural networks (LSTM, GRU). Meanwhile, combining real-time data from the electricity market, it constructs an electricity price forecasting model to provide highly accurate future electricity price fluctuation trends, so as to enhance the foresight of dispatching decisions and avoid resource waste or system efficiency decline caused by forecasting deviations.

[0038] Dispatching optimization decision-making module:

[0039] The dispatching optimization decision-making module uses multi-objective optimization algorithms (such as genetic algorithms and particle swarm optimization) to comprehensively consider multiple indicators, including charge and discharge efficiency, gas storage capacity utilization rate, economic benefits, and system security. It dynamically generates charge and discharge plans according to grid demand, forecasting results, and energy storage status to achieve the best operation strategy.

[0040] Optimization objectives of the multi-objective optimization dispatching algorithm:

[0041] Energy efficiency: Maximize the energy conversion efficiency of the compression and expansion processes and reduce system energy consumption.

[0042] Economic benefits: Combine electricity price fluctuations, optimize the low-valley charging and peak-discharge strategies, and enhance economic benefits.

[0043] Security: Ensure the long-term stability of equipment on the premise of meeting the safe operation of the system.

[0044] Use multi-objective optimization algorithms (such as genetic algorithms and reinforcement learning) to dynamically adjust the charge and discharge plan, balance energy efficiency and economic benefits, and iteratively optimize decisions based on real-time data to adapt to the rapid changes in grid demand.

[0045] The dispatching optimization decision-making module system can dynamically adjust the energy storage plan to participate in the electricity spot market and ancillary service market, providing services such as frequency regulation and standby. It maximizes the dual value of the energy storage system in grid operation and market transactions.

[0046] Real-time control and execution module:

[0047] The real-time control and execution module converts the dispatching optimization decision into specific control instructions, and adjusts the operating states of compressors, expanders, and gas storage equipment in real time through a PLC or distributed control system (DCS). It supports second-level response to ensure the fast adaptability of the system in a dynamic power grid environment.

[0048] The real-time control and execution module adopts real-time control technology based on model predictive control (MPC), combines the operating state of the power grid, and dynamically adjusts the operating parameters of the compressor and expander. It supports millisecond-level data acquisition and second-level instruction response to ensure that the energy storage system can quickly respond to the frequency fluctuations and load changes of the power grid.

[0049] Human-machine interaction and monitoring interface:

[0050] The human-machine interaction and monitoring interface provides an intuitive operation interface, displays the system operating state, real-time data, and scheduling strategies, and at the same time allows operators to manually adjust the scheduling plan or set key parameters.

[0051] Thermal energy recovery and utilization module:

[0052] The thermal energy recovery and utilization module integrates thermal energy storage technology, stores the heat generated during the compressed air process and uses it for heating during the expansion process to improve the overall system efficiency. The thermal energy recovery and utilization module is seamlessly integrated with the scheduling system, and dynamically allocates thermal energy resources through intelligent optimization algorithms.

[0053] As Figure 2 shown, the operation process of the intelligent optimization scheduling system for a compressed air energy storage power station provided by the present invention is as follows:

[0054] S1. Data acquisition: Real-time acquisition of operation data from energy storage devices, sensors, and the power grid side, including gas storage pressure, temperature, load curve, market electricity price, etc.; upload to the central control platform for data cleaning, anomaly processing, and storage.

[0055] S2. Data processing and prediction: Use the prediction model to analyze the power grid load, electricity price trend, and the operation state of the energy storage system, generate operation prediction data for a future set time period, and provide input for scheduling optimization

[0056] S3. Scheduling optimization: According to the prediction results and the current state of the energy storage system, optimize the charge and discharge plan, determine the operating power of the compressor and expander, and the operation mode of the gas storage device. The scheduling algorithm comprehensively considers the energy storage state, power grid demand, and market conditions, and generates an optimal charge and discharge plan, including: charging time and rate, discharging time and power output, dynamic allocation of thermal energy utilization.

[0057] S4. Control execution: The control instructions generated by the scheduling optimization decision module are executed through the real-time control module to dynamically adjust the operation of the energy storage system; that is, the scheduling optimization results are converted into specific execution instructions through the real-time control module to adjust the operating state of the equipment (such as compressor start-stop, expander power adjustment, etc.).

[0058] S5. Real-time feedback and adjustment: The system monitors the operation state in real time, compares the optimization results, and dynamically corrects the scheduling strategy according to the actual situation.

[0059] The present invention can achieve the following beneficial effects:

[0060] 1. Improve the operating efficiency of the energy storage system

[0061] Optimization of energy conversion efficiency: Through heat recovery technology and intelligent scheduling algorithms, energy losses during the compression and expansion processes are effectively reduced, significantly improving the overall system efficiency.

[0062] Dynamic optimization strategy: Adopting a multi-objective optimization algorithm, the charge and discharge plan is dynamically adjusted according to real-time grid demands and the energy storage state, making full use of the gas storage capacity and equipment performance.

[0063] 2. Strengthen the peak shaving and frequency modulation capabilities of the power grid

[0064] Fast response ability: Through real-time monitoring and model predictive control (MPC) technology, the system can respond to grid load fluctuations and frequency adjustment demands within seconds, providing high-quality frequency modulation services for the power grid.

[0065] Smoothing load fluctuations: Collaborating with new energy generation, the volatility of the grid load is smoothed, improving the operating stability of the power grid.

[0066] 3. Increase economic benefits

[0067] Electricity price arbitrage: Through high-precision electricity price forecasting and optimization algorithms, the system can charge during low electricity price periods and discharge during high price periods, significantly enhancing economic benefits.

[0068] Participation in the electricity market: Support real-time optimal scheduling in the spot market and ancillary service markets (such as frequency modulation, reserve), creating more revenue channels for the energy storage system.

[0069] 4. Achieve intelligence and automation

[0070] Accurate prediction: Based on artificial intelligence technology, the system can accurately predict grid load, new energy generation, and electricity price fluctuation trends, providing a reliable basis for scheduling decisions.

[0071] Autonomous scheduling optimization: Combining big data analysis and optimal control, the system has achieved autonomous decision-making capabilities, reducing dependence on manual experience.

[0072] It should be noted that, in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article or method comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, apparatus, article or method. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, apparatus, article or method comprising such element.

[0073] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural or equivalent process transformations made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. An intelligent optimization and dispatching system for a compressed air energy storage power station, characterized in that: It includes a central control platform, a data acquisition and monitoring module, a load forecasting and electricity price forecasting module, a scheduling optimization decision module, and a real-time control and execution module. The central control platform is respectively connected to the acquisition and monitoring module, the load forecasting and electricity price forecasting module, and the real-time control and execution module. The load forecasting and electricity price forecasting module is also connected to the scheduling optimization decision module. The data acquisition and monitoring module collects key parameters of the energy storage system and power grid operation data in real time, and uploads the collected data to the central control platform to support data storage and processing; The load forecasting and electricity price forecasting module uses artificial intelligence algorithms based on historical operation data to predict future grid load fluctuations, new energy generation curves, and electricity market price trends; The dispatch optimization decision module adopts a multi-objective optimization algorithm to dynamically generate a charging and discharging plan based on grid demand, forecast results and energy storage status to achieve the best operation strategy; The real-time control and execution module converts the scheduling optimization decision into specific control instructions, and adjusts the operating status of the compressor, expander and gas storage equipment in real time through the PLC or distributed control system.

2. The intelligent optimization and dispatching system for compressed air energy storage power station according to claim 1 is characterized in that: It also includes a human-computer interaction and monitoring interface, which is connected to the central control platform. The human-computer interaction and monitoring interface provides an intuitive operation interface, displays the system operation status, real-time data and scheduling strategy, and allows operators to manually adjust the scheduling plan or set key parameters.

3. The intelligent optimization and dispatching system for compressed air energy storage power station according to claim 1 is characterized in that: It also includes a heat energy recovery and utilization module, which is connected to the scheduling optimization decision module. The heat energy recovery and utilization module integrates thermal energy storage technology, stores the heat generated during the air compression process and uses it for heating the expansion process, and dynamically allocates thermal energy resources through the intelligent optimization algorithm of the scheduling optimization decision module.

4. The intelligent optimization and dispatching system for compressed air energy storage power station according to claim 1 is characterized in that: The dispatch optimization decision module is linked with the power market to achieve dispatch optimization, dynamically adjust the energy storage plan to participate in the power spot market and ancillary service market, and provide frequency regulation and standby services.

5. The intelligent optimization and dispatching system for compressed air energy storage power station according to claim 1 is characterized in that: The data acquisition and monitoring module collects key parameters of the energy storage system and grid operation data in real time from the energy storage equipment, sensors and the grid side through sensors and communication devices; wherein the key parameters of the energy storage system include gas storage pressure, temperature, and equipment status, and the grid operation data includes load, frequency, and electricity price.

6. The intelligent optimization and dispatching system for compressed air energy storage power station according to claim 1 is characterized in that: The load forecasting and electricity price forecasting module performs time series forecasting on future power grid load and new energy power generation curve based on deep neural network, and builds an electricity price forecasting model in combination with real-time data of the electricity market to provide high-precision future electricity price fluctuation trends; wherein, the deep neural network includes LSTM and GRU.

7. The intelligent optimization and dispatching system for compressed air energy storage power station according to claim 1 is characterized in that: The real-time control and execution module adopts real-time control technology based on model predictive control, namely MPC, and dynamically adjusts the operating parameters of the compressor and the expander in combination with the operating status of the power grid.

8. The intelligent optimization and dispatching system for compressed air energy storage power station according to claim 1 is characterized in that: The operation process of the system is as follows: S1. Data collection: real-time collection of operating data from energy storage equipment, sensors and the grid side, including gas storage pressure, temperature, load curve and market electricity price; S2, data processing and prediction: Use the prediction model to analyze the grid load, electricity price trends and the operating status of the energy storage system, and generate operation prediction data for a set time period in the future; S3, Scheduling Optimization: Based on the prediction results and the current status of the energy storage system, optimize the charging and discharging plan, determine the operating power of the compressor and expander, and the operating mode of the gas storage equipment; S4, control execution: The control instructions generated by the dispatch optimization decision module are executed by the real-time control module to dynamically adjust the operation of the energy storage system; S5. Real-time feedback and adjustment: The system monitors the operating status in real time and dynamically modifies the scheduling strategy based on actual conditions.

Images