Compressed air energy storage power station response time optimization method based on time sequence prediction

Abstract

The invention discloses a compressed air energy storage power station response time optimization method based on time sequence prediction, and the method comprises the following steps: collecting a local historical environment and power generation and power consumption data, and predicting the power generation and power consumption data on that day; respectively establishing a local total generating capacity model and a local power consumption model according to the collected data by using a GlunTS algorithm; establishing a scheduling instruction time sequence prediction model of a certain power plant by using data of the two models and historical data of scheduling the local energy storage power plant by a local power grid; predicting the possibility that the energy storage power plant is dispatched by a power grid within one hour in the future by using a dispatching instruction time sequence prediction model of a certain power plant; and if the possibility obtained by the prediction model exceeds a set threshold value, the energy storage and power generation system is prepared, so that a response can be made immediately when a scheduling instruction is received. The problem that the response time of compressed air energy storage is too long is solved, and therefore the air energy storage technology is suitable for market application and popularization.

Description

Technical Field

[0001] This patent relates to the field of compressed gas energy storage, and specifically to a method for optimizing the response time of a compressed air energy storage power station based on time series prediction. Background Art

[0003] At present, the mainstream energy storage power station technology routes are electrochemical energy storage and pumped storage. Among them, the widely used electrochemical energy storage has certain safety issues, and the harmless treatment cost of waste batteries is high, and the energy storage scale is limited, which has reached a development bottleneck. Although pumped storage is large in scale and high in efficiency, it is limited by geological conditions and has a long construction period, and has never been able to be rolled out on a large scale.

[0004] Compressed air energy storage is one of the important development directions of new energy storage technologies in the future because of its short construction period, few site selection restrictions, green environmental protection and zero emissions.

[0005] Compressed air energy storage is a physical energy storage technology based on rotating mechanical equipment. The process of energy storage and power generation depends on the operation of compressors and turbines. The start and stop of mechanical equipment requires a certain response time, ranging from several minutes to tens of minutes. Since the response time of compressed air energy storage is much longer than the millisecond response time based on electrochemical energy storage technology, and also longer than the response time of pumped storage technology, compressed air energy storage technology cannot be widely used. Summary of the invention

[0006] The purpose of the present invention is to provide a method for optimizing the response time of a compressed air energy storage power station based on time series prediction in response to the deficiencies of the prior art; through this method, it is predicted when the power grid will dispatch the local compressed air energy storage power station, and then a series of preparations are performed in advance for the energy storage system and the power generation system, so that a rapid response can be achieved when the power grid dispatch instruction arrives.

[0007] The technical purpose of the present invention is achieved by the following technical solutions: The method for optimizing the response time of a compressed air energy storage power station based on time series prediction includes the following steps: S1. Collect local historical environmental and power generation and consumption data, and make predictions on the current day’s power generation and consumption data; S2. Using the data collected in step S1 to establish a local total power generation model and a local power consumption model respectively using the GluonTS algorithm; S3. Using the data of the local total power generation model and the local power consumption model in step S2 and the historical data of the local power grid on the local energy storage power plant dispatch, establish a scheduling instruction timing prediction model for a power plant; S4. Use the dispatch instruction timing prediction model of a power plant in step S3 to predict the possibility of the energy storage power plant being dispatched by the power grid within the next hour; S5. If the probability obtained by the scheduling instruction timing prediction model of a power plant exceeds the set threshold, that is, it is believed that it may be dispatched by the power grid within the next hour, the energy storage and power generation systems will be prepared so that they can respond immediately when the scheduling instruction is received.

[0008] Preferably, the S1 is further configured to collect one of the local historical hydraulic data, the local wind power time series data or the local solar illumination information time series data; The local historical hydropower data corresponds to areas with more hydropower generation, the local wind power time series data corresponds to areas with more wind power generation; the collection of the local solar illumination information time series data corresponds to areas with more photovoltaic power generation.

[0009] Preferably, the local historical environmental data is local historical temperature time series data.

[0010] Preferably, the energy storage system preparation process in S5 includes: S511. Start the compressor sealing system; S512. Determine the temperature of the thermal oil / heat water; If the answer is "yes", go directly to the next step; If the judgment is "No", start the oil cooler / heater first to make the heat transfer oil meet the cooling requirements of the compressor, and then proceed to the next step; S513. Open the oil pump S514. Start the lubricating oil system; S515. Start the compressor and increase the speed; S516. Complete preparations for the energy storage phase.

[0011] Preferably, the power generation system preparation process in S5 includes: S521. Open the high-pressure gas chamber valve and the thermal oil pump to preheat the turbine main gas; S522. Determine the temperature of the turbine cylinder and rotor; If the temperature meets the requirements for warm or hot start, proceed to the next step; If the temperature does not meet the requirements of warm or hot start, open the main gas valve and regulating valve to preheat the cylinder before proceeding to the next step; S523. Open the shaft seal fan; S524. Start the lubricating oil system; S525. Start the turbine and start increasing the speed; S526. Complete preparations for the power generation phase.

[0012] Compared with the prior art, the present invention has the following beneficial effects: The present invention predicts when the power grid will dispatch the local compressed air energy storage power station, and then performs a series of preparations for the energy storage system and the power generation system in advance, so that it can respond quickly when the power grid dispatch instruction actually arrives. The adoption of this technical measure solves the problem of the long response time of compressed air energy storage, making air energy storage technology suitable for market promotion and application. At the same time, this method has the advantages of reducing power abandonment and optimizing the stability of regional power grid load. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is the overall flow chart of the present invention; Figure 2 It is a flow chart for establishing a scheduling instruction timing prediction model for a power plant; Figure 3 It is a flow chart of the energy storage system preparation process; Figure 4 It is a flow chart of the power generation system preparation process. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0015] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0016] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In addition, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0017] like Figure 1 — Figure 4 As shown, the compressed air energy storage power station response time optimization method based on time series prediction includes the following steps: S1. Collect local historical environmental data and power generation and consumption data, and predict the power generation and consumption data for the day. In actual use, the local historical environmental data is the local historical temperature time series data.

[0018] S2. Using the data collected in step S1 to establish a local total power generation model and a local power consumption model respectively using the GluonTS algorithm; S3. Using the data of the local total power generation model and the local power consumption model in step S2 and the historical data of the local power grid on the local energy storage power plant dispatch, establish a scheduling instruction timing prediction model for a power plant; S4. Use the dispatch instruction timing prediction model of a power plant in step S3 to predict the possibility of the energy storage power plant being dispatched by the power grid within the next hour; S5. If the probability obtained by the scheduling instruction timing prediction model of a power plant exceeds the set threshold, that is, it is believed that it may be dispatched by the power grid within the next hour, the energy storage and power generation systems will be prepared so that they can respond immediately when the scheduling instruction is received.

[0019] Through this method, it is predicted when the power grid will dispatch the local compressed air energy storage power station, and then a series of preparations are made in advance for the energy storage system and the power generation system, so that they can respond quickly when the power grid dispatch instruction arrives. The use of this technical measure solves the problem of the long response time of compressed air energy storage, making air energy storage technology suitable for market promotion and application. At the same time, this method has the advantages of reducing power abandonment and optimizing the stability of regional power grid load.

[0020] like Figure 2 As shown, in actual use, if one or more of hydropower, wind power or photovoltaic power exists locally, the one with a larger proportion will also be added in step S1.

[0021] Specifically, in step S1, one of local historical hydraulic data, local wind power time series data or local solar radiation information time series data is added.

[0022] Among them, the local historical hydropower data corresponds to areas with more hydropower generation; the local wind power time series data corresponds to areas with more wind power generation; and the collection of local solar radiation information time series data corresponds to areas with more photovoltaic power generation.

[0023] like Figure 3 As shown, in actual use, the energy storage system is an existing energy storage system, which includes a compressor sealing system, an oil cooler / heater, an oil pump, a lubricating oil system and a compressor, etc. When the energy storage system receives an energy storage system preparation instruction, it enters a preparation state before the grid dispatch instruction arrives.

[0024] Specifically, the energy storage system preparation process includes: S511. Start the compressor sealing system; S512. Determine the temperature of the thermal oil / heat water; If the answer is "yes", go directly to the next step; If the judgment is "No", start the oil cooler / heater first to make the heat transfer oil meet the cooling requirements of the compressor, and then proceed to the next step; S513. Open the oil pump S514. Start the lubricating oil system; S515. Start the compressor and increase the speed; S516. Complete preparations for the energy storage phase.

[0025] The above has completed the preparation work for the energy storage system. By adopting this technical measure, when the grid dispatching instruction comes, the load can be directly increased and energy storage can be started directly, which greatly reduces the response time.

[0026] like Figure 4 As shown, in actual use, the power generation system is an existing power generation system, which includes a high-pressure gas chamber, a thermal oil pump, a turbine, a turbine cylinder, a rotor, a shaft seal fan and a lubricating oil system, etc. When the power generation system receives a power generation system preparation instruction, it enters a preparation state before the power grid dispatch instruction arrives.

[0027] Specifically, the power generation system preparation process includes: S521. Open the high-pressure gas chamber valve and the thermal oil pump to preheat the turbine main gas; S522. Determine the temperature of the turbine cylinder and rotor; If the temperature meets the requirements for warm or hot start, proceed to the next step; If the temperature does not meet the requirements of warm or hot start, open the main gas valve and regulating valve to preheat the cylinder before proceeding to the next step; S523. Open the shaft seal fan; S524. Start the lubricating oil system; S525. Start the turbine and start to increase the speed; S526. Complete preparations for the power generation phase.

[0028] The above is the completion of the preparation work of the power generation system. With this technical measure, when the power grid dispatching instruction comes, the load can be directly increased and power generation can be started directly, which greatly reduces the response time.

[0029] The technical solutions provided by the embodiments of the present invention are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the embodiments of the present invention. The description of the above embodiments is only applicable to help understand the principles of the embodiments of the present invention. At the same time, for those skilled in the art, according to the embodiments of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for optimizing the response time of a compressed air energy storage power station based on time series prediction, characterized in that: The following steps are involved: S1. Collect local historical environmental and power generation and consumption data, and make predictions on the current day’s power generation and consumption data; S2. Using the data collected in step S1 to establish a local total power generation model and a local power consumption model respectively using the GluonTS algorithm; S3. Using the data of the local total power generation model and the local power consumption model in step S2 and the historical data of the local power grid on the local energy storage power plant dispatch, establish a scheduling instruction timing prediction model for a power plant; S4. Use the dispatch instruction timing prediction model of a power plant in step S3 to predict the possibility of the energy storage power plant being dispatched by the power grid within the next hour; S5. If the probability obtained by the scheduling instruction timing prediction model of a power plant exceeds the set threshold, that is, it is believed that it may be dispatched by the power grid within the next hour, the energy storage and power generation systems will be prepared so that they can respond immediately when the scheduling instruction is received.

2. The method for optimizing the response time of a compressed air energy storage power station based on time series prediction according to claim 1 is characterized in that: In the S1, one of collecting local historical hydraulic data, local wind power time series data or local solar illumination information time series data is added; The local historical hydropower data corresponds to areas with more hydropower generation, the local wind power time series data corresponds to areas with more wind power generation; the collection of the local solar illumination information time series data corresponds to areas with more photovoltaic power generation.

3. The method for optimizing the response time of a compressed air energy storage power station based on time series prediction according to claim 1 is characterized in that: The local historical environmental data is the local historical temperature time series data.

4. The method for optimizing the response time of a compressed air energy storage power station based on time series prediction according to claim 1, characterized in that: The energy storage system preparation process in S5 includes: S511. Start the compressor sealing system; S512. Determine the temperature of the thermal oil / heat water; If the answer is "yes", go directly to the next step; If the judgment is "No", start the oil cooler / heater first to make the heat transfer oil meet the cooling requirements of the compressor, and then proceed to the next step; S513. Open the oil pump S514. Start the lubricating oil system; S515. Start the compressor and increase the speed; S516. Complete preparations for the energy storage phase.

5. The method for optimizing the response time of a compressed air energy storage power station based on time series prediction according to claim 1, characterized in that: The power generation system preparation process in S5 includes: S521. Open the high-pressure gas chamber valve and the thermal oil pump to preheat the turbine main gas; S522. Determine the temperature of the turbine cylinder and rotor; If the temperature meets the requirements for warm or hot start, proceed to the next step; If the temperature does not meet the requirements of warm or hot start, open the main gas valve and regulating valve to preheat the cylinder before proceeding to the next step; S523. Open the shaft seal fan; S524. Start the lubricating oil system; S525. Start the turbine and start increasing the speed; S526. Complete preparations for the power generation phase.

Images