Power grid load prediction method

Abstract

The invention relates to the technical field of power grid load prediction, and discloses a power grid load prediction method, which comprises the following steps that: step 1, a data acquisition module is connected with a power grid company through a network to acquire historical power grid load data of a current region, and also acquires wind energy historical power generation data and solar energy historical power generation data; step 2, the data acquisition module acquires wind energy data per hour of the current area and forms a wind energy data set, step 3, the data acquisition module acquires solar energy data per hour of the current area and forms a solar energy data set, and step 4, the data acquisition module acquires meteorological data and forms a meteorological data set. Step 5, the load prediction module calculates a historical wind energy index and a historical solar energy index; step 6, the load prediction module calculates a wind power generation amount and a solar power generation amount; step 7, the load prediction module calculates a current energy total amount; and step 8, the energy optimization module evaluates power grid supply and demand balance according to the current energy total amount.

Description

Technical Field

[0001] The invention relates to the technical field of power grid load prediction, and in particular to a power grid load prediction method. Background Art

[0002] Load forecasting is a process of predicting how much electricity will be needed at a given time and how that demand will affect the utility grid. It is critical to ensuring that there is sufficient electricity to meet usage needs while avoiding waste and inefficiency. Electricity load forecasting is the key to power system operation planning and is essential to avoiding power outages. Load forecasts cover both the short term (hours or days in advance) and the long term (months or years in advance). The accuracy of these forecasts directly affects the cost and reliability of the entire power system.

[0003] Accurate load forecasting ensures that there is enough electricity supply to meet demand at any given time, thereby maintaining the balance and stability of the power grid. With this reliability, higher efficiency and cost savings can be achieved. Load forecasting enables utilities to better manage their resources through demand response programs, which change usage patterns by incentivizing consumers to reduce electricity consumption during peak hours. Load forecasting is a complex and important process that uses historical data, weather forecasts, machine learning, artificial intelligence and other technical means to support the efficient operation and planning of power systems. With the continuous advancement of technology, the accuracy and efficiency of load forecasting will be further improved, making an important contribution to the sustainable development of the power system.

[0004] Renewable energy such as wind and solar energy are important factors affecting grid load forecasting. How to integrate renewable energy such as wind and solar energy into the grid is crucial. Different existing grid load forecasting methods have different advantages and applicable scenarios. Time series analysis is suitable for short-term forecasting, machine learning and deep learning methods can handle complex nonlinear relationships, and hybrid models and scenario-based methods can improve the comprehensive forecasting capabilities and the ability to cope with different situations. However, none of them fully combines the impact of renewable energy such as wind and solar energy on grid load forecasting. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present invention provides a power grid load forecasting method, which has the ability to forecast wind energy, solar energy and the power grid in combination with multiple meteorological factors, can more accurately forecast the power grid load, and effectively integrate the power generation capacity of wind and solar energy, improve the operating efficiency and reliability of the power grid, reduce the use of traditional power generation to a certain extent, save costs and reduce carbon emissions, etc., and solves the problem that the existing power grid load forecasting method does not fully combine the impact of renewable energy sources such as wind energy and solar energy on power grid load forecasting.

[0006] To achieve the above object, the present invention provides the following technical solution: a power grid load forecasting method, comprising the following steps: Step 1: The data acquisition module connects to the power grid company through the network to obtain the historical power grid load data DW of the current area, and also obtains the historical wind power generation data FN and the historical solar power generation data TY; Step 2: The data acquisition module connects to the wind farm platform system through the network to obtain hourly wind energy data in the current area and form a wind energy data set; Step 3: The data acquisition module connects to the photovoltaic system through the network to obtain the hourly solar energy data of the current area and form a solar energy data set; Step 4: The data acquisition module connects to the meteorological station through the network to obtain hourly meteorological data and form a meteorological data set; Step 5: The load forecasting module calculates the historical wind energy index FNzs and the historical solar energy index TYzs respectively through the historical grid load data DW, the historical wind energy generation data FN and the historical solar energy generation data TY; Step 6: The load forecasting module calculates the wind power generation FNd l and the solar power generation TYdl through the wind power data set, the solar power data set, the meteorological data set, the historical wind power index FNzs, and the historical solar power index TYzs; Step 7: The load forecasting module calculates the current total energy NYxs by combining the wind power generation FNdl and the solar power generation TYdl; Step 8: The energy optimization module evaluates the grid supply and demand balance based on the current total energy NYxs.

[0007] Preferably, in step 2, the expression of the wind energy data set is: {Fs, Fx, Qy}, wherein Fs represents the wind speed data in the wind energy data set, Fx represents the wind direction data in the wind energy data set, and Qy represents the air pressure data in the wind energy data set.

[0008] Preferably, in step three, the expression of the solar energy data set is: {Rz, Fs, Yl}, wherein Rz represents the sunshine index in the solar energy data set, Fs represents the solar radiation intensity in the solar energy data set, and Yl represents the cloud cover data in the solar energy data set.

[0009] Preferably, in step 4, the expression of the meteorological data set is: {Wd, Sd, Js}, wherein Wd represents the temperature data in the meteorological data set, Sd represents the humidity data in the meteorological data set, and Js represents the precipitation data in the meteorological data set.

[0010] Preferably, in step 5, the historical wind energy index FNzs is calculated as follows: In the above formula, FN represents the historical wind power generation data, DW represents the historical grid load data, and the historical wind power generation data divided by the historical grid load data is the historical wind energy index.

[0011] Preferably, in step 5, the historical solar energy index TYzs is calculated as follows: In the above formula, TY represents the historical solar power generation data, DW represents the historical grid load data, and the historical solar power generation data divided by the historical grid load data is the historical solar energy index.

[0012] Preferably, in step 6, the calculation method of wind energy generation FNdl is as follows: FNdl=(Fs+Fx+Qy)*(Wd+Sd+Js)*FNzs In the above formula, Fs+Fx+Qy represents the sum of wind speed, wind direction and air pressure in the wind energy data set, and Wd+Sd+Js represents the sum of temperature, humidity and precipitation in the meteorological data set. The sum of the wind energy data set multiplied by the sum of the meteorological data set and then multiplied by the historical wind energy index is the wind energy generation.

[0013] Preferably, in step 6, the calculation method of the solar power generation TYdl is as follows: TYdl=(Rz+Fs+Yl)*(Wd+Sd+Js)*TYzs In the above formula, Rz+Fs+Yl represents the sum of sunshine index, solar radiation intensity and cloud cover in the solar data set, and Wd+Sd+Js represents the sum of temperature, humidity and precipitation in the meteorological data set. The sum of the solar data set is multiplied by the sum of the meteorological data set, and then multiplied by the historical solar index to obtain the solar power generation.

[0014] Preferably, in step 7, the current total energy amount NYxs is calculated as follows: NYxs=FNdl+TYdl Preferably, in step eight: the energy optimization module evaluates the supply and demand balance of the power grid according to the current total energy amount NYxs. When the current total energy amount increases significantly and reduces the demand for traditional power generation, the power generation combination of the power grid is adjusted to reduce the use of traditional power generation. When the current total energy amount is higher than the actual value, the power grid operation strategy is adjusted to increase the backup power supply to ensure the stability of the power grid.

[0015] Compared with the prior art, the present invention provides a power grid load forecasting method, which has the following beneficial effects: 1. The present invention collects wind speed, wind direction and air pressure as reference factors for wind energy data. In the grid load forecast, the influence of wind speed, wind direction and air pressure on wind power generation is fully considered. The sunshine index, solar radiation intensity and cloud cover are collected as reference factors for solar energy data. In the grid load forecast, the influence of sunshine index, solar radiation intensity and cloud cover on solar power generation is fully considered. By combining temperature, humidity and precipitation as reference factors for meteorological data, the factors brought by meteorological data such as temperature, humidity and precipitation are taken into account when analyzing and processing solar energy and wind energy data, so that the forecast evaluation is more accurate and comprehensive, and the accuracy of the forecast is improved.

[0016] 2. The present invention calculates wind power generation FNdl, solar power generation TYdl, and current total energy NYxs by combining the current regional historical power grid load data DW, wind power historical power generation data FN, solar power historical power generation data TY, wind data set, solar data set, and meteorological data set, thereby realizing the prediction of wind power, solar energy, and power grid by combining multiple factors. The power grid load can be predicted more accurately, and the power generation capacity of wind and solar energy can be effectively integrated to improve the operating efficiency and reliability of the power grid, reduce the use of traditional power generation to a certain extent, and save costs and reduce carbon emissions. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the structural system of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. 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.

[0019] See also Figure 1 , a power grid load forecasting method, comprising the following steps: Step 1: The data acquisition module connects to the power grid company through the network to obtain the historical power grid load data DW of the current area, and also obtains the historical wind power generation data FN and the historical solar power generation data TY; Based on the historical grid load data, wind power generation data and solar power generation data of the current region, wind power, solar power and grid data can be fully combined to more comprehensively understand the changing trend of grid load and facilitate more accurate prediction of future load demand; Step 2: The data acquisition module connects to the wind farm platform system through the network to obtain hourly wind energy data in the current area and form a wind energy data set; The expression of the wind energy data set is: {Fs, Fx, Qy}, where Fs represents the wind speed data in the wind energy data set, Fx represents the wind direction data in the wind energy data set, and Qy represents the air pressure data in the wind energy data set; By collecting wind speed, wind direction and air pressure as reference factors for wind energy data, the impact of wind speed, wind direction and air pressure on wind power generation is fully considered in the grid load forecast, making the forecast evaluation more accurate and comprehensive; Step 3: The data acquisition module connects to the photovoltaic system through the network to obtain the hourly solar energy data of the current area and form a solar energy data set; The expression of the solar energy data set is: {Rz, Fs, Yl}, where Rz represents the sunshine index in the solar energy data set, Fs represents the solar radiation intensity in the solar energy data set, and Yl represents the cloud cover data in the solar energy data set; By collecting sunshine index, solar radiation intensity and cloud cover as reference factors for solar energy data, the impact of sunshine index, solar radiation intensity and cloud cover on solar power generation is fully considered in the grid load forecast, making the forecast evaluation more accurate and comprehensive; Step 4: The data acquisition module connects to the meteorological station through the network to obtain hourly meteorological data and form a meteorological data set; The expression of the meteorological data set is: {Wd, Sd, Js}, where Wd represents the temperature data in the meteorological data set, Sd represents the humidity data in the meteorological data set, and Js represents the precipitation data in the meteorological data set; By combining temperature, humidity, and precipitation as reference factors for meteorological data, the influence of meteorological data such as temperature, humidity, and precipitation is taken into account when analyzing and processing solar energy and wind energy data, thus improving the accuracy of prediction; Step 5: The load forecasting module calculates the historical wind energy index FNzs and the historical solar energy index TYzs respectively through the historical grid load data DW, the historical wind energy generation data FN and the historical solar energy generation data TY; The historical wind energy index FNzs is calculated as follows: In the above formula, FN represents the historical wind power generation data, DW represents the historical grid load data, and the historical wind power generation data divided by the historical grid load data is the historical wind energy index; The historical solar index TYzs is calculated as follows: In the above formula, TY represents the historical solar power generation data, DW represents the historical grid load data, and the historical solar power generation data divided by the historical grid load data is the historical solar energy index; Step 6: The load forecasting module calculates the wind power generation FNdl and the solar power generation TYdl through the wind power data set, the solar power data set, the meteorological data set, the historical wind power index FNzs, and the historical solar power index TYzs; The calculation method of wind power generation FNdl is as follows: FNdl=(Fs+Fx+Qy)*(Wd+Sd+Js)*FNzs In the above formula, Fs+Fx+Qy represents the sum of wind speed, wind direction and air pressure in the wind energy data set, and Wd+Sd+Js represents the sum of temperature, humidity and precipitation in the meteorological data set. The wind energy data set sum is multiplied by the meteorological data set sum, and then multiplied by the historical wind energy index to get the wind energy generation. The calculation method of solar power generation TYdl is as follows: TYdl=(Rz+F s+Yl)*(Wd+Sd+Js)*TYzs In the above formula, Rz+Fs+Yl represents the sum of sunshine index, solar radiation intensity and cloud cover in the solar data set, and Wd+Sd+Js represents the sum of temperature, humidity and precipitation in the meteorological data set. The sum of the solar data set is multiplied by the sum of the meteorological data set, and then multiplied by the historical solar index to get the solar power generation. Step 7: The load forecasting module calculates the current total energy NYxs by combining the wind power generation FNdl and the solar power generation TYdl; The current total energy amount NYxs is calculated as follows: NYxs=FNdl+TYdl Step 8: The energy optimization module evaluates the grid supply and demand balance based on the current total energy amount NYxs. When the current total energy amount increases significantly and reduces the demand for traditional power generation, the grid's power generation mix is ​​adjusted to reduce the use of traditional power generation. When the current total energy amount is higher than the actual value, the grid operation strategy is adjusted to increase backup power supplies to ensure grid stability.

[0020] By combining the current regional historical power grid load data DW, wind power historical generation data FN, solar power historical generation data TY, wind data set, solar data set, and meteorological data set to calculate wind power generation FNdl, solar power generation TYdl, and the current total energy NYx3, it is possible to combine multiple factors to predict wind power, solar energy, and the power grid, which can more accurately predict the power grid load and effectively integrate the power generation capacity of wind and solar energy, improve the operating efficiency and reliability of the power grid, and reduce the use of traditional power generation to a certain extent, so as to save costs and reduce carbon emissions.

[0021] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for predicting power grid load, characterized in that: The following steps are involved: Step 1: The data acquisition module connects to the power grid company through the network to obtain the historical power grid load data DW of the current area, and also obtains the historical wind power generation data FN and the historical solar power generation data TY; Step 2: The data acquisition module connects to the wind farm platform system through the network to obtain hourly wind energy data in the current area and form a wind energy data set; Step 3: The data acquisition module connects to the photovoltaic system through the network to obtain the hourly solar energy data of the current area and form a solar energy data set; Step 4: The data acquisition module connects to the meteorological station through the network to obtain hourly meteorological data and form a meteorological data set; Step 5: The load forecasting module calculates the historical wind energy index FNzs and the historical solar energy index TYzs respectively through the historical grid load data DW, the historical wind energy generation data FN and the historical solar energy generation data TY; Step 6: The load forecasting module calculates the wind power generation FNdl and the solar power generation TTdl through the wind energy data set, the solar energy data set, the meteorological data set, the historical wind energy index FNzs, and the historical solar energy index TYzs; Step 7: The load forecasting module calculates the current total energy NYxs by combining the wind power generation FNdl and the solar power generation TYdl; Step 8: The energy optimization module evaluates the grid supply and demand balance based on the current total energy NYXs.

2. A power grid load forecasting method according to claim 1, characterized in that: In the step 2, the expression of the wind energy data set is: {Fs, Fx, Qy}, where Fs represents the wind speed data in the wind energy data set, Fx represents the wind direction data in the wind energy data set, and Qy represents the air pressure data in the wind energy data set.

3. A power grid load forecasting method according to claim 2, characterized in that: In the step 3, the expression of the solar energy data set is: {Rz, Fs, Yl}, where Rz represents the sunshine index in the solar energy data set, Fs represents the solar radiation intensity in the solar energy data set, and Yl represents the cloud cover data in the solar energy data set.

4. A power grid load forecasting method according to claim 3, characterized in that: In the step 4, the expression of the meteorological data set is: {Wd, Sd, Js}, where Wd represents the temperature data in the meteorological data set, Sd represents the humidity data in the meteorological data set, and Js represents the precipitation data in the meteorological data set.

5. A method for predicting power grid load according to claim 4, characterized in that: In step 5, the historical wind energy index FNzs is calculated as follows: In the above formula, FN represents the historical wind power generation data, DW represents the historical grid load data, and the historical wind power generation data divided by the historical grid load data is the historical wind energy index.

6. A method for predicting power grid load according to claim 5, characterized in that: In step 5, the calculation method of the historical solar energy index TYzs is as follows: In the above formula, TY represents the historical solar power generation data, DW represents the historical grid load data, and the historical solar power generation data divided by the historical grid load data is the historical solar energy index.

7. A method for predicting power grid load according to claim 6, characterized in that: In step 6, the calculation method of wind energy generation FNdl is as follows: FNdl=(Fs+Fx+Qy)*(Wd+Sd+Js)*FNzs In the above formula, Fs+Fx+Qy represents the sum of wind speed, wind direction and air pressure in the wind energy data set, and Wd+Sd+Js represents the sum of temperature, humidity and precipitation in the meteorological data set. The sum of the wind energy data set multiplied by the sum of the meteorological data set and then multiplied by the historical wind energy index is the wind energy generation.

8. A method for predicting power grid load according to claim 7, characterized in that: In step 6, the calculation method of solar power generation TYdl is as follows: TYdl=(Rz+Fs+Yl)*(Wd+Sd+Js)*TYzs In the above formula, Rz+Fs+Yl represents the sum of sunshine index, solar radiation intensity and cloud cover in the solar data set, and Wd+Sd+Js represents the sum of temperature, humidity and precipitation in the meteorological data set. The sum of the solar data set is multiplied by the sum of the meteorological data set, and then multiplied by the historical solar index to obtain the solar power generation.

9. A method for predicting power grid load according to claim 8, characterized in that: In step 7, the current total energy amount NYxs is calculated as follows: NYxs=FNdl+TYdl.

10. A method for predicting power grid load according to claim 9, characterized in that: In step eight: the energy optimization module evaluates the supply and demand balance of the power grid based on the current total energy amount NYxs. When the current total energy amount increases significantly and reduces the demand for traditional power generation, the power generation combination of the power grid is adjusted to reduce the use of traditional power generation. When the current total energy amount is higher than the actual value, the power grid operation strategy is adjusted to increase backup power supply to ensure the stability of the power grid.

Images