A method for pricing electricity prices for pumped storage power stations

Abstract

A method for pricing electricity prices for pumped storage power stations, which relates to the technical field of electricity price pricing, monitors in real time the grid load and power supply and demand operation dynamic data within a preset range of a target pumped storage power station, and the operation status data of the internal equipment of the pumped storage power station; constructs an electricity price pricing lookup table, and builds a long-term prediction model based on the historical data information of the pumped storage power station to predict the grid and power supply operation status data of the current monitoring period, and sets the initial electricity price of the current monitoring period; compares the real-time collected data of the current monitoring period with the corresponding prediction data, and proposes an adjusted and updated electricity price for the current monitoring period based on the comparison result, which significantly improves the response speed and accuracy of the electricity price pricing of the pumped storage power station. This method is applicable to the pricing strategies and methods of pumped storage power stations under the market-oriented operation mode, and is also applicable to the monitoring and evaluation of the electricity prices of pumped storage power stations at this stage.

Description

Technical Field

[0001] The invention relates to the technical field of electricity price pricing, and in particular to an electricity price pricing method for a pumped storage power station. Background Art

[0002] The prior art CN114201858A "A pricing method for real-time electricity prices of new energy" uses the standardized-Euclidean distance to mine the relevant factors affecting the real-time electricity prices of new energy, including the system electricity price, the predicted grid-connected amount of new energy and the predicted load demand, and proposes the fitting function relationship between each relevant factor and the real-time electricity price of new energy; on the demand side, the price demand response elasticity matrix is ​​used to represent the functional relationship between the electricity price and the load size; the functional relationship on both sides is included in the cost-effectiveness target, and a min-max model is established as a real-time supply and sale pricing model for the "source-load" real-time supply and demand; considering different scenarios, a min-max multi-scenario objective function is established, and the model is transformed and solved using the Lagrangian optimization duality theory;

[0003] The prior art CN114493639A "A node electricity price pricing method considering elastic load contracts" builds a DC optimal power flow model of the power system considering the elastic load contract according to the specific content of the elastic load contract signed between the power user and the power market operator; the Lagrangian equation of the model is obtained according to the DC optimal power flow model of the power system; Step 3: According to the Lagrangian equation, the node electricity price calculation formula considering the elastic load contract is obtained. By proposing a node electricity price pricing method considering the elastic load contract, it can accurately characterize the impact of the elastic load contract on the node electricity price, accurately reflect the supply and demand relationship of the power load, and provide a reference for the formulation of electricity prices in the power market.

[0004] The above technologies do not comprehensively consider the impact of water resource characteristic data and meteorological characteristic data within the preset range of the target pumped-storage power station on electricity price pricing, and cannot accurately predict the changing trends of water resource characteristic data and meteorological characteristic data within the preset range of the target pumped-storage power station, and reasonably formulate electricity prices at different times according to the changing trends. How to comprehensively consider, evaluate and adjust electricity prices from multiple aspects to adapt to changes in the market and environment is an issue that we urgently need to solve. Summary of the invention

[0005] In order to solve the above technical problems, the object of the present invention is to provide a method for pricing electricity prices for a pumped storage power station, comprising the following steps:

[0006] Step S1: deploying sensors according to geographical data within a preset range of the target pumped-storage power station and historical natural environment meteorological data, and simultaneously monitoring water resource characteristic data and meteorological characteristic data within a preset range of the target pumped-storage power station in real time;

[0007] A power grid load monitoring node and an equipment operation monitoring node are set in the pumped storage power station; the power grid load monitoring node is used to monitor the power grid load data within a preset range of the pumped storage power station in real time, mark the monitoring time, and set the monitoring cycle; the equipment operation monitoring node is used to monitor the operating status data of the internal equipment of the pumped storage power station in real time, mark the monitoring time, and set the monitoring cycle;

[0008] Step S2: construct an electricity price pricing lookup table, build a long-term prediction model based on the historical data information of the pumped storage power station, predict the current monitoring period and the power supply and demand power station internal equipment operation status data, supplemented by predicting water resources and weather, and set the initial electricity price of the current monitoring period;

[0009] Step S3: compare the grid load and power supply and demand operation status data, power station internal equipment operation status data, water resources and meteorological characteristics data collected in real time during the current monitoring period with the corresponding forecast data, and propose an updated and adjusted electricity price for the current monitoring period based on the comparison result;

[0010] In a feasible implementation, sensors are deployed according to geographic data within a preset range of a target pumped-storage power station and historical natural environment meteorological data to monitor water resource characteristic data and meteorological characteristic data within a preset range of the target pumped-storage power station in real time, and the process includes:

[0011] Obtain GIS geographic data within a preset range of the target pumped-storage power station through GIS means, obtain terrain features within the preset range of the target pumped-storage power station through GIS geographic data, identify water resource features in the terrain features, obtain location information of water resource features within the preset range of the target pumped-storage power station, and obtain water resource feature monitoring indicators based on the water resource features;

[0012] Using Internet technology to obtain historical natural environment meteorological data within a preset range of the target pumped-storage power station, and determining meteorological characteristic monitoring indicators within the preset range of the target pumped-storage power station based on the historical natural environment meteorological data;

[0013] Determine the corresponding sensor type according to the water resource characteristic indicators and meteorological characteristic monitoring indicators, and obtain the coverage of each type of sensor. According to the location information of the water resource characteristics and the coverage of each type of sensor, obtain the layout location of each type of sensor within the preset range;

[0014] Sensors are deployed within a preset range of the target pumped-storage power station according to the deployment locations of various types of sensors. The sensors are used to monitor the water resource characteristic data and meteorological characteristic data within the preset range of the target pumped-storage power station in real time according to the water resource characteristic monitoring indicators and meteorological characteristic monitoring indicators, mark the monitoring time, and set the monitoring cycle.

[0015] In a feasible implementation, the process of constructing an electricity price pricing lookup table includes:

[0016] The electricity price threshold intervals corresponding to different conditions are preset, and an electricity price pricing lookup table is constructed according to the electricity price threshold intervals corresponding to different conditions.

[0017] In a feasible implementation, based on the historical data information of the pumped storage power station, a long-term prediction model is constructed to predict the current monitoring period and set the initial electricity price of the current monitoring period. The process includes:

[0018] Building a long-term prediction model based on deep learning, obtaining data of the pumped-storage power station in several historical monitoring cycles as a historical data set, dividing the historical data set into a training set and a test set, and performing real-time learning and training on the long-term prediction model;

[0019] Input the training set into the long-term prediction model for training until the loss function training is stable, save the model parameters, test the long-term prediction model with the test set until it meets the preset requirements, and output the long-term prediction model;

[0020] The data of the current monitoring period of the pumped-storage power station is obtained through the long-term prediction model, and the estimated electricity price threshold range of the current monitoring period is obtained based on the data of the current monitoring period and the electricity price pricing lookup table, and an electricity price is randomly selected from the electricity price threshold range as the initial electricity price of the current monitoring period.

[0021] In a feasible implementation, the grid load and power supply and demand operation status data, power station internal equipment operation status data, water resources and meteorological characteristics data collected in real time during the current monitoring period are compared with the corresponding forecast data, and an updated and adjusted electricity price for the current monitoring period is proposed based on the comparison result. The process includes:

[0022] Obtain real-time water resource characteristic data and real-time meteorological characteristic data of the current monitoring period collected by various types of sensors within the preset range of the pumped storage power station;

[0023] Preset the error threshold corresponding to the water resources meteorological characteristic data, use the water resources characteristic prediction data and meteorological characteristic prediction data of the current monitoring period as standard reference data, compare the real-time water resources characteristic data and real-time meteorological characteristic data of the current monitoring period with the corresponding standard reference data, and obtain the error value between the real-time water resources characteristic data and real-time meteorological characteristic data and the corresponding standard reference data;

[0024] Determine whether the error values ​​of the real-time water resource characteristic data, the real-time meteorological characteristic data and the corresponding standard reference data all fall within the corresponding error threshold interval. If they all fall within, continue to maintain the initial electricity price of the current monitoring period;

[0025] If they are not evenly distributed, the initial electricity price of the current monitoring period will be dynamically updated.

[0026] In a feasible implementation, the initial electricity price of the current monitoring period is dynamically updated, and the process includes:

[0027] Pre-constructing an ultra-short-term electricity price fuzzy control model, the evaluation indicators of which are water resource characteristic data and meteorological characteristic data, and the output is the electricity price, pre-setting the membership function, electricity price range and indicator weight matrix of the ultra-short-term electricity price fuzzy control model, dividing the electricity price range into several fuzzy subsets, and using the electricity price pricing lookup table as the fuzzy adaptive rule table of the ultra-short-term electricity price fuzzy control model;

[0028] The real-time water resource characteristic data and real-time meteorological characteristic data of the current monitoring period are input into the ultra-short-term electricity price fuzzy control model. The ultra-short-term electricity price fuzzy control model obtains the membership matrix of each fuzzy subset corresponding to the real-time water resource characteristic data and real-time meteorological characteristic data of the current monitoring period through fuzzy comprehensive evaluation, and obtains the membership coefficient of each fuzzy subset according to the membership matrix and indicator weight matrix of each fuzzy subset, screens out the electricity price range corresponding to the fuzzy subset with the highest membership coefficient, eliminates the initial electricity price of the current monitoring period, and randomly selects an electricity price from the electricity price range as the electricity price of the current monitoring period.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] Construct an electricity price pricing lookup table, build a long-term prediction model based on the historical data information of the pumped-storage power station, predict the water resource characteristic data, meteorological characteristic data, power grid load data and operating status data of the current monitoring period, and set the initial electricity price of the current monitoring period. Compare the water resource characteristic data, meteorological characteristic data, power grid load data and operating status data collected in real time during the current monitoring period with the corresponding prediction data, and update the initial electricity price of the current monitoring period based on the comparison results. By quickly adjusting the output power when the water resource characteristic data, meteorological characteristic data, power grid load data and operating status data change, the response speed and accuracy of the electricity price pricing of the pumped-storage power station are significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a schematic diagram of a method for pricing electricity for a pumped-storage power station according to an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0033] like Figure 1 As shown, the electricity price pricing method of the pumped storage power station includes the following steps:

[0034] Step S1: Deploy sensors according to geographic data within a preset range of the target pumped-storage power station and historical natural environment meteorological data, monitor water resource characteristic data and meteorological characteristic data within a preset range of the target pumped-storage power station in real time, and set monitoring nodes in the pumped-storage power station to monitor power grid load data within a preset range of the pumped-storage power station and operating status data of internal equipment of the pumped-storage power station in real time;

[0035] Step S2: construct an electricity price pricing lookup table, build a long-term prediction model based on the historical data information of the pumped storage power station, predict the water resource characteristic data, meteorological characteristic data, power grid load data and operation status data of the current monitoring period, and set the initial electricity price of the current monitoring period;

[0036] Step S3: Compare the water resource characteristic data, meteorological characteristic data, grid load data and operation status data collected in real time during the current monitoring period with the corresponding forecast data, and update the initial electricity price of the current monitoring period according to the comparison result.

[0037] It should be further explained that, in the specific implementation process, sensors are deployed according to the geographical data within the preset range of the target pumped-storage power station and the historical natural environment meteorological data, and the water resource characteristic data and meteorological characteristic data within the preset range of the target pumped-storage power station are monitored in real time. The process includes:

[0038] Obtain GIS geographic data within the preset range of the target pumped-storage power station through GIS means, obtain terrain features within the preset range of the target pumped-storage power station through GIS geographic data, identify water resource features in the terrain features, obtain location information of water resource features within the preset range of the target pumped-storage power station, and obtain water resource feature monitoring indicators based on the water resource features; these terrain features and water resource distribution features include terrain height, river and lake locations, and soil types, etc.;

[0039] Using Internet technology to obtain historical natural environment meteorological data within a preset range of the target pumped-storage power station, and determining meteorological characteristic monitoring indicators within the preset range of the target pumped-storage power station based on the historical natural environment meteorological data; the monitoring indicators include rainfall, temperature, humidity, wind speed, etc.;

[0040] Integrate the above geographic data with meteorological data to establish a comprehensive data set for the target area of ​​the pumped storage power station;

[0041] Determine the corresponding sensor type according to the water resource characteristic indicators and meteorological characteristic monitoring indicators, such as rainfall sensors, water level sensors, temperature sensors, etc.; and obtain the coverage of each type of sensor, and obtain the layout of each type of sensor within the preset range according to the location information of water resource characteristics and the coverage of each type of sensor to ensure coverage of the entire target area; consider factors including key water resource points (such as reservoirs, rivers), typical terrain points (such as mountains, valleys) and typical meteorological points (such as wind vents, wetlands); install the above sensors and calibrate them to ensure the accuracy and reliability of data collection.

[0042] Deploy sensors within a preset range of the target pumped-storage power station according to the deployment positions of various types of sensors. The sensors are used to monitor water resource characteristic data and meteorological characteristic data within a preset range of the target pumped-storage power station in real time according to water resource characteristic monitoring indicators and meteorological characteristic monitoring indicators, mark monitoring time, and set a monitoring cycle;

[0043] It should be further explained that, in the specific implementation process, the water resource characteristics within the preset range of the target pumped storage power station include:

[0044] Water body distribution and water source location: the distribution of water bodies within the preset range, including rivers, lakes and reservoirs, etc., and the water source location, i.e. the starting point where the pumped storage power station obtains water;

[0045] Basin characteristics: The characteristics of the water resources basin within the preset range, including the water catchment area, main rivers and tributary networks;

[0046] It should be further explained that, in the specific implementation process, the water resource characteristic monitoring indicators include:

[0047] Water flow velocity, water volume, water level elevation data and water quality data of water bodies within a preset range;

[0048] Among them, the changes in water flow velocity and water volume within a preset range, including data such as average flow velocity, peak flow velocity and average annual water volume, have an important impact on the energy conversion efficiency and power generation capacity of the power station. At the same time, the water level elevation data reflects the changes in the altitude of the water body. In a pumped-storage power station, the water level elevation is an important factor in determining the hydropower reserve and power generation capacity of the power station. For example, when a pumped-storage power station needs electricity, it will use a water pump to pump water from the downstream to the high water tank upstream. When power generation is needed, the water will be released from the high water tank to the downstream through a turbine generator to generate electricity. Therefore, the water level is one of the most important water resources for a pumped-storage power station. Under the same downstream load, the change amount and rate of water level are key factors in determining the maximum output power and energy storage capacity of the pumped storage power station. Water quality data include dissolved oxygen content, water temperature, pH value, suspended solids and pollutant content in the water, etc. These data can evaluate the impact of water quality on the operation and equipment loss of the pumped storage power station. For example, the pumped storage power station needs to use a turbine generator when converting water energy. The turbine generator has requirements for the flow, pressure and quality of water, especially the purity and particulate matter content of water. The quality of water determines the efficiency and life of the turbine generator, and also determines the potential safety hazards of power generation and transmission of the pumped storage power station.

[0049] It should be further explained that, in the specific implementation process, the historical natural environment meteorological data include:

[0050] Flood and drought data: Includes historical and statistical data on floods and droughts within a preset range, including flood frequency, peak flow, and duration of drought periods. These data help to select appropriate water resources management strategies to cope with different water resource changes.

[0051] It should be further explained that, in the specific implementation process, the meteorological characteristic monitoring indicators within the preset range of the pumped storage power station include:

[0052] rainfall, evaporation, and temperature;

[0053] These data can help pumped-storage power stations predict changes in water levels. In rainy seasons, the water level of the reservoir may rise, allowing the pumped-storage power station to store more hydropower for subsequent power generation. In dry seasons, the water level drops, and it may be necessary to reduce or stop pumping storage and focus on power generation. Therefore, meteorological data plays a vital role in reservoir water level management.

[0054] It should be further explained that, in the specific implementation process, a monitoring node is set in the pumped storage power station to monitor the grid load data within the preset range of the pumped storage power station and the operating status data of the internal equipment of the pumped storage power station in real time. The process includes:

[0055] Setting up grid load monitoring nodes and equipment operation monitoring nodes in pumped storage power stations;

[0056] The grid load monitoring node is used to monitor the grid load data within a preset range of the pumped storage power station in real time, mark the monitoring time, and set the monitoring cycle;

[0057] The equipment operation monitoring node is used to monitor the operation status data of the internal equipment of the pumped storage power station in real time, mark the monitoring time, and set the monitoring cycle.

[0058] The electricity price of a pumped-storage power station is related to the grid data of the regional power grid to which the pumped-storage power station is integrated. When the power supply is tight during the peak load period of the power grid, the pumped-storage power station can balance the power grid demand by releasing stored energy. Therefore, the electricity price of a pumped-storage power station may rise due to the increase in demand during the peak load period of the power grid. On the contrary, when the power grid load is low, the pumped-storage power station can store energy when there is sufficient energy. Therefore, the electricity price may fall due to the oversupply during the low load period of the power grid.

[0059] There is a certain connection between the electricity price pricing of pumped-storage power stations and the operating data of pumped-storage power stations. The operating efficiency and cost of pumped-storage power stations will also affect the electricity price pricing. The operating efficiency refers to the proportion of water energy that the power station can convert into electrical energy. Power stations with high operating efficiency can provide electricity more effectively, which may gain certain advantages in electricity price pricing. In addition, the operating and maintenance costs of pumped-storage power stations will also affect the electricity price pricing. Power stations with lower costs may be more competitive in pricing. High-efficiency and low-cost operation may lead to lower electricity prices, while low-efficiency and high-cost operation may lead to higher electricity prices.

[0060] It should be further explained that, in the specific implementation process, the process of building the electricity price pricing lookup table includes:

[0061] The electricity price threshold intervals corresponding to different water resource characteristic data, meteorological characteristic data, power grid load data and operating status data are preset, and an electricity price pricing lookup table is constructed according to the electricity price threshold intervals corresponding to different water resource characteristic data, meteorological characteristic data, power grid load data and operating status data.

[0062] It should be further explained that, in the specific implementation process, based on the historical data information of the pumped storage power station, a long-term prediction model is constructed to predict the water resource characteristic data, meteorological characteristic data, grid load data and operation status data of the current monitoring period, and set the initial electricity price of the current monitoring period. The process includes:

[0063] Build a long-term prediction model based on deep learning, obtain water resource characteristic data, meteorological characteristic data, power grid load data and operation status data of the pumped storage power station in several historical monitoring cycles as a historical data set, divide the historical data set into a training set and a test set to perform real-time learning and training on the long-term prediction model;

[0064] Input the training set into the long-term prediction model for training until the loss function training is stable, save the model parameters, test the long-term prediction model with the test set until it meets the preset requirements, and output the long-term prediction model;

[0065] The water resource characteristic prediction data, meteorological characteristic prediction data, grid load prediction data and operation status prediction data of the pumped-storage power station in the current monitoring period are obtained through the long-term prediction model, and the estimated electricity price threshold range of the current monitoring period is obtained according to the water resource characteristic prediction data, meteorological characteristic prediction data, grid load prediction data and operation status prediction data of the current monitoring period and the electricity price pricing lookup table, and an electricity price is randomly selected from the electricity price threshold range as the initial electricity price of the current monitoring period.

[0066] It should be further explained that, in the specific implementation process, the water resource characteristic data, meteorological characteristic data, power grid load data and operation status data collected in real time during the current monitoring period are compared with the corresponding forecast data, and the initial electricity price of the current monitoring period is updated according to the comparison result. The process includes:

[0067] Acquire the real-time water resource characteristic data and real-time meteorological characteristic data of the current monitoring period collected by various types of sensors within the preset range of the pumped-storage power station, and at the same time acquire the real-time grid load data and real-time operation status data of the current monitoring period collected by the grid load monitoring nodes and equipment operation monitoring nodes in the pumped-storage power station;

[0068] Preset error thresholds corresponding to water resource characteristic data, meteorological characteristic data, power grid load data, and operating status data, use the water resource characteristic prediction data, meteorological characteristic prediction data, power grid load prediction data, and operating status prediction data of the current monitoring period as standard reference data, compare the real-time water resource characteristic data, real-time meteorological characteristic data, real-time power grid load data, and real-time operating status data of the current monitoring period with the corresponding standard reference data, and obtain error values ​​between the real-time water resource characteristic data, real-time meteorological characteristic data, real-time power grid load data, and real-time operating status data and the corresponding standard reference data;

[0069] Determine whether the error values ​​of the real-time water resource characteristic data, real-time meteorological characteristic data, real-time power grid load data and real-time operation status data and the corresponding standard reference data all fall within the corresponding error threshold intervals. If they all fall within, continue to maintain the initial electricity price of the current monitoring period;

[0070] If they are not evenly distributed, the initial electricity price of the current monitoring period will be dynamically updated.

[0071] It should be further explained that, in the specific implementation process, the initial electricity price of the current monitoring period is dynamically updated, and the process includes:

[0072] Pre-constructing an ultra-short-term electricity price fuzzy control model, the evaluation indicators of which are water resource characteristic data, meteorological characteristic data, power grid load data and operation status data, and the output is the electricity price, pre-setting the membership function, electricity price range and indicator weight matrix of the ultra-short-term electricity price fuzzy control model, dividing the electricity price range into several fuzzy subsets, and using the electricity price pricing lookup table as the fuzzy adaptive rule table of the ultra-short-term electricity price fuzzy control model;

[0073] The real-time water resource characteristic data, real-time meteorological characteristic data, real-time power grid load data and real-time operation status data of the current monitoring period are input into the ultra-short-term electricity price fuzzy control model. The ultra-short-term electricity price fuzzy control model obtains the membership matrix of each fuzzy subset corresponding to the real-time water resource characteristic data, real-time meteorological characteristic data, real-time power grid load data and real-time operation status data of the current monitoring period through fuzzy comprehensive evaluation, and obtains the membership coefficient of each fuzzy subset according to the membership matrix and indicator weight matrix of each fuzzy subset, screens out the electricity price range corresponding to the fuzzy subset with the highest membership coefficient, eliminates the initial electricity price of the current monitoring period, and randomly selects an electricity price from the electricity price range as the electricity price of the current monitoring period.

[0074] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for pricing electricity for a pumped storage power station, characterized in that: The following steps are involved: Step S1: deploying sensors according to geographical data within a preset range of the target pumped-storage power station and historical natural environment meteorological data, and simultaneously monitoring water resource characteristic data and meteorological characteristic data within a preset range of the target pumped-storage power station in real time; A power grid load monitoring node and an equipment operation monitoring node are set in the pumped storage power station; the power grid load monitoring node is used to monitor the power grid load data within a preset range of the pumped storage power station in real time, mark the monitoring time, and set the monitoring cycle; the equipment operation monitoring node is used to monitor the operating status data of the internal equipment of the pumped storage power station in real time, mark the monitoring time, and set the monitoring cycle; Step S2: construct an electricity price pricing lookup table, build a long-term prediction model based on the historical data information of the pumped storage power station, predict the current monitoring period and the power supply and demand power station internal equipment operation status data, supplemented by predicting water resources and weather, and set the initial electricity price of the current monitoring period; Among them, the process of building a long-term prediction model based on the historical data information of the pumped storage power station, predicting the current monitoring period and setting the initial electricity price of the current monitoring period includes: Construct a long-term prediction model based on deep learning, obtain data of the pumped-storage power station in several historical monitoring cycles as a historical data set, divide the historical data set into a training set and a test set, and perform real-time learning and training on the long-term prediction model; input the training set into the long-term prediction model for training until the loss function training is stable, and save the model parameters, test the long-term prediction model through the test set until it meets the preset requirements, and output the long-term prediction model; The data of the current monitoring period of the pumped storage power station is obtained through the long-term prediction model, and the estimated electricity price threshold interval of the current monitoring period is obtained according to the data of the current monitoring period and the electricity price pricing lookup table, and an electricity price is randomly selected from the electricity price threshold interval as the initial electricity price of the current monitoring period; Step S3: Compare the grid load and power supply and demand operating status data, power station internal equipment operating status data, water resources and meteorological characteristics data collected in real time during the current monitoring period with the corresponding forecast data, and propose an updated and adjusted electricity price for the current monitoring period based on the comparison results.

2. The electricity price pricing method of a pumped storage power station according to claim 1, characterized in that: Sensors are deployed according to the geographic data within the preset range of the target pumped-storage power station and the historical natural environment meteorological data to monitor the water resource characteristic data and meteorological characteristic data within the preset range of the target pumped-storage power station in real time. The process includes: Obtain GIS geographic data within a preset range of the target pumped-storage power station through GIS means, obtain terrain features within the preset range of the target pumped-storage power station through GIS geographic data, identify water resource features in the terrain features, obtain location information of water resource features within the preset range of the target pumped-storage power station, and obtain water resource feature monitoring indicators based on the water resource features; Using Internet technology to obtain historical natural environment meteorological data within a preset range of the target pumped-storage power station, and determining meteorological characteristic monitoring indicators within the preset range of the target pumped-storage power station based on the historical natural environment meteorological data; Determine the corresponding sensor type according to the water resource characteristic indicators and meteorological characteristic monitoring indicators, and obtain the coverage of each type of sensor. According to the location information of the water resource characteristics and the coverage of each type of sensor, obtain the layout location of each type of sensor within the preset range; Sensors are deployed within a preset range of the target pumped-storage power station according to the deployment locations of various types of sensors. The sensors are used to monitor the water resource characteristic data and meteorological characteristic data within the preset range of the target pumped-storage power station in real time according to the water resource characteristic monitoring indicators and meteorological characteristic monitoring indicators, mark the monitoring time, and set the monitoring cycle.

3. The electricity price pricing method of a pumped storage power station according to claim 1, characterized in that: The process of constructing the electricity price pricing lookup table includes: The electricity price threshold intervals corresponding to different conditions are preset, and an electricity price pricing lookup table is constructed according to the electricity price threshold intervals corresponding to different conditions.

4. The method for pricing electricity for a pumped storage power station according to claim 1, characterized in that: The grid load and power supply and demand operation status data, power station internal equipment operation status data, water resources and meteorological characteristics data collected in real time during the current monitoring period are compared with the corresponding forecast data, and the updated and adjusted electricity price of the current monitoring period is proposed based on the comparison results. The process includes: Obtain real-time water resource characteristic data and real-time meteorological characteristic data of the current monitoring period collected by various types of sensors within the preset range of the pumped storage power station; Preset the error threshold corresponding to the water resources meteorological characteristic data, use the water resources characteristic prediction data and meteorological characteristic prediction data of the current monitoring period as standard reference data, compare the real-time water resources characteristic data and real-time meteorological characteristic data of the current monitoring period with the corresponding standard reference data, and obtain the error value between the real-time water resources characteristic data and real-time meteorological characteristic data and the corresponding standard reference data; Determine whether the error values ​​of the real-time water resource characteristic data, the real-time meteorological characteristic data and the corresponding standard reference data all fall within the corresponding error threshold interval. If they all fall within, continue to maintain the initial electricity price of the current monitoring period; If they are not evenly distributed, the initial electricity price of the current monitoring period will be dynamically updated.

5. The electricity price pricing method of a pumped storage power station according to claim 4, characterized in that: Dynamically update the initial electricity price of the current monitoring period. The process includes: Pre-constructing an ultra-short-term electricity price fuzzy control model, the evaluation indicators of which are water resource characteristic data and meteorological characteristic data, and the output is the electricity price, pre-setting the membership function, electricity price range and indicator weight matrix of the ultra-short-term electricity price fuzzy control model, dividing the electricity price range into several fuzzy subsets, and using the electricity price pricing lookup table as the fuzzy adaptive rule table of the ultra-short-term electricity price fuzzy control model; The real-time water resource characteristic data and real-time meteorological characteristic data of the current monitoring period are input into the ultra-short-term electricity price fuzzy control model. The ultra-short-term electricity price fuzzy control model obtains the membership matrix of each fuzzy subset corresponding to the real-time water resource characteristic data and real-time meteorological characteristic data of the current monitoring period through fuzzy comprehensive evaluation, and obtains the membership coefficient of each fuzzy subset according to the membership matrix and indicator weight matrix of each fuzzy subset, screens out the electricity price range corresponding to the fuzzy subset with the highest membership coefficient, eliminates the initial electricity price of the current monitoring period, and randomly selects an electricity price from the electricity price range as the electricity price of the current monitoring period.

Images