Inter-province spot monthly price measurement combination prediction method and device

Abstract

The invention discloses an inter-provincial spot goods monthly price measurement combined prediction method and device. The method comprises the steps of obtaining inter-provincial spot goods channel capacity constraint and clearing electric quantity and electricity price of each province in a channel area range; calculating an inter-provincial spot channel capacity constraint monthly mean value, inter-provincial spot market monthly transaction electric quantity, inter-provincial spot market monthly transaction average price and daily clearing average price in a channel capacity area range; constructing an inter-provincial spot monthly price measurement prediction model considering inter-provincial channels and regional electricity prices; the prediction result of the inter-provincial spot monthly price measurement prediction model is corrected to form a combined prediction result, and the inter-provincial spot monthly predicted electric quantity and the monthly predicted average price are output by adopting the technical scheme of the invention, factors such as inter-provincial spot channel capacity constraints, inter-provincial spot historical clearing values, weather, holidays and festivals and the like are fully considered, and the prediction accuracy of the inter-provincial spot monthly price measurement prediction model is improved. And determining inter-provincial spot monthly price measurement combination prediction.

Description

Technical Field

[0001] The present invention belongs to the field of power trading technology, and in particular to a method and device for predicting inter-provincial spot monthly volume and price combination. Background Art

[0002] With the construction of new power systems and a unified national power market, cross-regional and inter-provincial power transactions in my country will gradually increase in the future. As an important part of this, the inter-provincial power spot market will continue to play a role in balancing surpluses and shortages and promoting the large-scale allocation of abundant resources after its formal operation. Therefore, for the market participants in the inter-provincial power spot market, on the one hand, it is necessary to analyze the clearing volume and price of the inter-provincial spot market at each time point on a daily scale, and on the other hand, it is necessary to predict the clearing volume and price of the inter-provincial spot market in the next month to provide support for the declaration decision of power transactions in the next month, which also puts forward certain requirements for the monthly volume and price of inter-provincial spot.

[0003] Currently, there are few studies on inter-provincial spot market forecasting methods, and none of the existing methods predicts the monthly electricity purchase price in the inter-provincial spot market. Only in the intra-provincial spot market, the existing methods mainly use long short-term memory neural networks, time series and other related algorithms to directly predict the clearing prices at each point in time, and there are few forecasting methods for the overall monthly clearing situation of the spot market. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and device for predicting the monthly spot price combination between provinces.

[0005] To achieve the above object, the present invention adopts the following technical solution:

[0006] A method for forecasting monthly spot prices among provinces, comprising:

[0007] Step S1, obtaining the capacity constraints of the inter-provincial spot channel, and the cleared electricity volume and electricity price of each province within the channel area;

[0008] According to the inter-provincial spot channel capacity constraints, and the cleared electricity volume and electricity prices of each province within the channel area, the monthly average of the inter-provincial spot channel capacity constraints, the monthly transaction volume of the inter-provincial spot market, the monthly average transaction price of the inter-provincial spot market, and the daily average clearing price within the channel capacity area are obtained;

[0009] According to the monthly average of inter-provincial spot channel capacity constraints, monthly transaction volume of inter-provincial spot market, monthly transaction average price of inter-provincial spot market, and daily average price of clearing within the channel capacity area, a monthly inter-provincial spot volume and price forecasting model considering inter-provincial channels and regional electricity prices is constructed; among them, the monthly inter-provincial spot volume and price forecasting model includes: an inter-provincial volume forecasting model considering the similarity of inter-provincial channel capacity and transaction rate, a regression analysis forecasting model considering the correlation of regional electricity prices, and a trend extrapolation forecasting model based on historical clearing volume and price; the monthly volume and price of the inter-provincial spot market in the next month is forecasted by using the inter-provincial volume forecasting model, regression analysis forecasting model, and trend extrapolation forecasting model respectively;

[0010] The forecast results of the inter-provincial electricity forecast model, regression analysis forecast model and trend extrapolation forecast model are corrected to form a combined forecast result, and the monthly forecast inter-provincial spot electricity and monthly forecast average price are output.

[0011] As a preferred choice, based on the supply and demand situation in various provinces and cities being similar to the same period in history, the channel capacity being similar to that in the second half of last month, and the declared quantity being equal to the channel capacity, a prediction model is constructed which takes into account the similarity of channel capacity and transaction rate among provinces. The transaction volume and average transaction price for the next month are predicted by using the year-on-year changes in the power purchase transaction rate and the month-on-month changes in the power purchase capacity, combined with the transaction volume and average transaction price in the same period of previous years, last month and similar months.

[0012] As a preferred option, a regression analysis prediction model is constructed using the regional daily average clearing price as the independent variable and the daily average clearing price of the electricity purchasing decision-making entity as the dependent variable, and the inter-provincial spot clearing average price is predicted using the relationship between the regional average clearing price and the average clearing price of the electricity purchasing decision-making entity.

[0013] Preferably, the trend extrapolation prediction model calculates the historical electricity trend through moving average, takes historical data as a benchmark, selects N months as the moving average period for prediction, and obtains the transaction volume and average transaction price of the predicted month.

[0014] The present invention also provides an inter-provincial spot monthly volume and price combination prediction device, comprising:

[0015] The acquisition module is used to obtain the capacity constraints of the inter-provincial spot channel and the cleared electricity volume and electricity price of each province within the channel area;

[0016] The calculation module is used to obtain the monthly average of the inter-provincial spot channel capacity constraint, the monthly transaction volume of the inter-provincial spot market, the monthly average transaction price of the inter-provincial spot market, and the daily average clearing price within the channel capacity area according to the inter-provincial spot channel capacity constraint and the clearing volume and electricity price of each province within the channel area;

[0017] The prediction module is used to construct a monthly inter-provincial spot price prediction model that takes into account inter-provincial channels and regional electricity prices based on the monthly average of inter-provincial spot channel capacity constraints, the monthly transaction volume of the inter-provincial spot market, the monthly average transaction price of the inter-provincial spot market, and the daily average clearing price within the channel capacity area; wherein the monthly inter-provincial spot price prediction model includes: an inter-provincial electricity volume prediction model that takes into account the similarity of inter-provincial channel capacity and transaction rate, a regression analysis prediction model that takes into account the correlation of regional electricity prices, and a trend extrapolation prediction model based on historical clearing volume and price; the monthly inter-provincial spot market price is predicted by using the inter-provincial electricity volume prediction model, the regression analysis prediction model, and the trend extrapolation prediction model respectively;

[0018] The correction module is used to correct the prediction results of the inter-provincial electricity forecasting model, regression analysis forecasting model, and trend extrapolation forecasting model to form a combined forecasting result and output the monthly forecasted inter-provincial spot electricity and monthly forecasted average price.

[0019] Preferably, the prediction module is used to construct a prediction model that takes into account the similarity of inter-provincial channel capacity and transaction rate based on the supply and demand situation in each province and city being similar to the same period in history, the channel capacity being similar to the situation in the second half of last month, and the declared quantity being equal to the channel capacity. The model predicts the transaction volume and average transaction price for the next month by using the year-on-year changes in the power purchase transaction rate and the month-on-month changes in the power purchase capacity, combined with the transaction volume and average transaction price in the same period of previous years, last month and similar months.

[0020] Preferably, the prediction module is used to construct a regression analysis prediction model using the regional daily average clearing price as the independent variable and the electricity purchasing decision-making entity's daily average clearing price as the dependent variable, and to predict the inter-provincial spot clearing average price using the relationship between the regional average clearing price and the electricity purchasing decision-making entity's average clearing price.

[0021] Preferably, the prediction module is used to adopt a trend extrapolation prediction model to calculate the historical electricity trend through moving average, take historical data as a benchmark, select N months as the moving average period for prediction, and obtain the transaction volume and average transaction price of the predicted month.

[0022] The present invention fully considers the capacity constraints of inter-provincial spot channels, historical clearance values ​​of inter-provincial spot, weather, holidays and other factors to determine the monthly measurement and price combination forecast of inter-provincial spot. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0024] Figure 1This is a flow chart of the method for predicting the monthly inter-provincial spot price combination according to an embodiment of the present invention;

[0025] Figure 2 is the monthly electricity price history value in the specific embodiment of the present invention;

[0026] Figure 3 It is the result of regression analysis performed by using a regression analysis prediction model that takes into account the correlation of regional electricity prices in a specific embodiment of the present invention. DETAILED DESCRIPTION

[0027] 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.

[0028] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] Embodiment 1:

[0030] like Figure 1 As shown, an embodiment of the present invention provides a method for predicting monthly inter-provincial spot volume and price combination, comprising:

[0031] Step S1, obtaining the capacity constraints of the inter-provincial spot channel, and the cleared electricity volume and electricity price of each province within the channel area;

[0032] According to the inter-provincial spot channel capacity constraints, and the cleared electricity volume and electricity prices of each province within the channel area, the monthly average of the inter-provincial spot channel capacity constraints, the monthly transaction volume of the inter-provincial spot market, the monthly average transaction price of the inter-provincial spot market, and the daily average clearing price within the channel capacity area are obtained;

[0033] According to the monthly average of inter-provincial spot channel capacity constraints, monthly transaction volume of inter-provincial spot market, monthly transaction average price of inter-provincial spot market, and daily average price of clearing within the channel capacity area, a monthly inter-provincial spot volume and price forecasting model considering inter-provincial channels and regional electricity prices is constructed; among them, the monthly inter-provincial spot volume and price forecasting model includes: an inter-provincial volume forecasting model considering the similarity of inter-provincial channel capacity and transaction rate, a regression analysis forecasting model considering the correlation of regional electricity prices, and a trend extrapolation forecasting model based on historical clearing volume and price; the monthly volume and price of the inter-provincial spot market in the next month is forecasted by using the inter-provincial volume forecasting model, regression analysis forecasting model, and trend extrapolation forecasting model respectively;

[0034] The forecast results of the inter-provincial electricity forecast model, regression analysis forecast model and trend extrapolation forecast model are corrected to form a combined forecast result, and the monthly forecast inter-provincial spot electricity and monthly forecast average price are output.

[0035] As an implementation method of the present invention, in step S1, in step S1, the channel capacity constraint of inter-provincial spot every 15 minutes on day m month d is obtained. And the clearing electricity quantity and clearing electricity price of province i every 15 minutes within the shared inter-provincial channel area

[0036] As an implementation method of the present invention, in step S2, the monthly total capacity R of the inter-provincial spot channel is calculated. m , the electricity purchase decision-making body in month m, the monthly transaction volume of the inter-provincial spot market, Q 0,m , monthly average transaction price of inter-provincial spot market P 0,m , daily average transaction price P 0,d 、Monthly transaction rate of inter-provincial spot market in month m α m , the average monthly clearing price within the shared inter-provincial channel capacity area Daily average clearing price The specific ones are:

[0037]

[0038] Among them, D m The number of days in the mth month.

[0039]

[0040] in, They represent the transaction volume and transaction price of the power purchasing decision-making entity at time t on day d of month m. 0,d It is the average transaction price of the electricity purchasing decision-making entity on day d.

[0041]

[0042] in, They are respectively the cleared electricity volume and cleared electricity price at time t on day d of mth month in province i within the shared inter-provincial channel area.

[0043] As an implementation method of an embodiment of the present invention, in step S3, considering that the supply and demand situation in various provinces and cities is similar to the same period in history, the channel capacity is similar to the situation in the second half of last month, and the declared quantity is equal to the channel capacity, a prediction model considering the similarity of inter-provincial channel capacity and transaction rate is constructed, and the transaction volume and average transaction price of the next month are predicted by using the year-on-year change in the power purchase transaction rate and the month-on-month change in the power purchase capacity, combined with the transaction volume and average transaction price of the same period of previous years, last month and similar months.

[0044] Forecasted transaction volume = Forecasted declared volume × Forecasted transaction rate:

[0045]

[0046] in, is the predicted transaction volume for the mth month, is the predicted transaction rate for the mth month, Forecast declared capacity for month m.

[0047] Predicted transaction rate = weight 1 × historical month 1 transaction rate + weight 2 × historical month 2 transaction rate + weight m × historical month m transaction rate:

[0048]

[0049] Among them, λ m The weight of the electricity consumption in the mth month compared to the total electricity consumption in the selected M months

[0050] Forecasted declared electricity = predicted average declared capacity per day × number of days in the month:

[0051]

[0052] in, is the average daily declared capacity in the forecast month m, R m-1 This is the total capacity of inter-provincial spot channels last month.

[0053] As an implementation method of an embodiment of the present invention, in step S3, a regression analysis prediction model is constructed using the regional daily average clearing price as an independent variable and the daily average clearing price of the power purchasing decision-making entity as a dependent variable, and the inter-provincial spot clearing average price is predicted by using the relationship between the regional average clearing price and the average clearing price of the power purchasing decision-making entity.

[0054] Since the regional daily average clearing price is strongly correlated with the daily average clearing price of the electricity purchasing decision-making entity, a correlation analysis was conducted with the regional daily average clearing price as the independent variable and the daily average clearing price of the electricity purchasing decision-making entity as the dependent variable, and a regression analysis model was selected to predict the average clearing price of the electricity purchasing decision-making entity.

[0055]

[0056] in, are the average daily clearing prices of the purchasing decision-making entity and the average daily clearing prices of the region, respectively. D is the total number of days.

[0057] The following fitting formula is used between the average daily clearing price of the region and the average daily transaction price of the electricity purchasing decision-making entity:

[0058]

[0059] In this way, a and b are obtained, and the regression equation curve is obtained.

[0060] As an implementation method of an embodiment of the present invention, in step S3, the trend extrapolation prediction model uses trend extrapolation to make predictions. The historical electricity trend is calculated by moving average, and historical data is used as a benchmark. N months are selected as the moving average period for prediction to obtain the transaction volume and average transaction price of the predicted month. The use of moving average for trend extrapolation prediction can adapt to smooth predictions when historical sample data is small, and can reduce the impact of extreme values ​​in historical transaction volume fluctuations. The calculation formula is as follows:

[0061]

[0062] As an implementation method of the present invention, in step S4, the forecast results of the three models are corrected in combination with the supply and demand situation and the weather to form a combined forecast result, and the corrected inter-provincial spot monthly forecast electricity is output. Monthly average price forecast

[0063] The correction formula is:

[0064]

[0065]

[0066] Among them, ω m ,θ m They are respectively the monthly forecast inter-provincial spot electricity volume and the forecast average price correction coefficient. They are the predicted averages of monthly inter-provincial spot transaction volume and monthly average transaction price respectively.

[0067] Specific examples:

[0068] Taking the relevant data of a power purchasing decision-making entity as an example, the channel capacity and cleared electricity volume of the entity from 2023 to January 2024 are obtained. Figure 2 , as shown in Table 1 and Table 2. The monthly transaction volume and price in the next month, February 2024, are predicted.

[0069] Table 1

[0070] time Total channel capacity / MWh Total cleared electricity Transaction rate January 2023 150200.0 13969.0 9.30％ February 2023 775250.0 139470.8 17.99％ March 2023 486250.0 134784.9 27.72％ April 2023 692437.5 219706.2 31.73％ May 2023 673687.5 124198.7 18.44％ June 2023 204925.0 67121.9 32.75％ July 2023 308125.0 11881.8 3.86％ August 2023 337375.0 29174.5 8.65％ September 2023 1286125.0 443324.0 34.47％ October 2023 501050.0 148809.1 29.70％ November 2023 318262.5 65601.8 20.61％ December 2023 660135.5 77320.6 11.71％

[0071] Table 2

[0072]

[0073] The total declared electricity in February 2023 is 775.25 million kWh, with a transaction rate of 18%, a total of 28 days, an average daily channel electricity of 27,687.5 MWh, and an average daily clearing electricity of 4,981 MWh. The average daily declared capacity in January 2024 is 18,165 MWh. Taking into account the inter-provincial channel capacity constraints in January 2024, the average daily channel capacity (18,165 MWh) is used as the daily total declared electricity benchmark, and the declared capacity in February 2024 (29 days) is predicted to be 526,785 MWh. Based on the predicted monthly transaction rate of 18%, the average daily transaction electricity in February 2024 is predicted to be 3,270 MWh, and the monthly predicted transaction electricity is 94,820 MWh.

[0074] The correlation analysis was conducted with the average daily clearing price of the region as the independent variable and the average daily clearing price of the electricity purchasing entity as the dependent variable. The correlation coefficient r was 0.73509, indicating a high correlation. The fitting curve of the average clearing price of the region and the average clearing price of the electricity purchasing entity is: y = 0.6415x + 112.56766. Figure 3 The regional average clearing price is predicted to be 393.973 yuan / MWh by trend extrapolation, and the inter-provincial spot clearing price of the power purchaser is predicted based on the fitting curve, and the monthly average clearing price is 0.6415*393.973+112.56766=365.30 yuan / MWh.

[0075] The historical electricity trend is calculated by moving average. Based on historical data, the March of the same period last year is selected as the moving average period to predict the transaction volume and average transaction price in February 2024. The trend of weighted moving average is extrapolated using the historical transaction volume as the weight, and the predicted value of the average transaction price in February 2024 is 383.39 yuan / MWh. The calculation is as follows:

[0076] Table 3

[0077] month Power purchase / MWh <![CDATA[Average purchase price of electricity / yuan per MWh -1 > Weight January 2023 13969 324.13 4.85％ February 2023 139470.81 388.37 48.39％ March 2023 134784.9 384.38 46.76％ 288224.71 / 1

[0078] For the trend extrapolation method, the predicted value of the electricity volume traded in February 2024 is 96074.9 MWh, and the predicted value of the average transaction price in February 2024 is 383.39 yuan / MWh.

[0079] The predictions of the above different methods are as follows:

[0080] In addition, compared with the above prediction methods, considering the long Spring Festival holiday in February, the wind season, the difficulty in absorbing new energy, and the limited inter-provincial spot power purchase, the electricity price is taken as the average of the two methods, 374.35 yuan / MWh, and the power correction coefficient of 2 / 3 is considered. Finally, the inter-provincial spot power forecast in February 2024 is determined to be 68887 MWh. The final accuracy is shown in Table 4.

[0081] Table 4

[0082]

[0083] The above results are significantly improved compared with the original prediction accuracy of the electricity purchase entity. According to the forecast from March to May 2024, the inter-provincial spot forecast electricity in March 2024 is 134958.18 MWh, and the predicted average price is 365.73 yuan / MWh; the inter-provincial spot forecast electricity in April 2024 is 65454 MWh, and the predicted average price is 349.31 yuan / MWh; the inter-provincial spot forecast electricity in May 2024 is 73561 MWh, and the predicted average price is 364.74 yuan / MWh. From March to May 2024, the method proposed by the present invention can achieve an accuracy of 90% and 80% for electricity prices and electricity, which are both improved compared with the original.

[0084] Embodiment 2:

[0085] The embodiment of the present invention further provides a device for predicting monthly inter-provincial spot commodity prices, comprising:

[0086] The acquisition module is used to obtain the capacity constraints of the inter-provincial spot channel and the cleared electricity volume and electricity price of each province within the channel area;

[0087] The calculation module is used to obtain the monthly average of the inter-provincial spot channel capacity constraint, the monthly transaction volume of the inter-provincial spot market, the monthly average transaction price of the inter-provincial spot market, and the daily average clearing price within the channel capacity area according to the inter-provincial spot channel capacity constraint and the clearing volume and electricity price of each province within the channel area;

[0088] The prediction module is used to construct a monthly inter-provincial spot price prediction model that takes into account inter-provincial channels and regional electricity prices based on the monthly average of inter-provincial spot channel capacity constraints, the monthly transaction volume of the inter-provincial spot market, the monthly average transaction price of the inter-provincial spot market, and the daily average clearing price within the channel capacity area; wherein the monthly inter-provincial spot price prediction model includes: an inter-provincial electricity volume prediction model that takes into account the similarity of inter-provincial channel capacity and transaction rate, a regression analysis prediction model that takes into account the correlation of regional electricity prices, and a trend extrapolation prediction model based on historical clearing volume and price; the monthly inter-provincial spot market price is predicted by using the inter-provincial electricity volume prediction model, the regression analysis prediction model, and the trend extrapolation prediction model respectively;

[0089] The correction module is used to correct the prediction results of the inter-provincial electricity forecasting model, regression analysis forecasting model, and trend extrapolation forecasting model to form a combined forecasting result and output the monthly forecasted inter-provincial spot electricity and monthly forecasted average price.

[0090] As an implementation mode of an embodiment of the present invention, the prediction module is used to construct a prediction model that takes into account the similarity of inter-provincial channel capacity and transaction rate based on the supply and demand situation of each province and city being similar to the historical same period, the channel capacity being similar to the situation in the second half of the previous month, and the declared quantity being equal to the channel capacity. The prediction model is used to predict the transaction volume and average transaction price of the next month by using the year-on-year change in the power purchase transaction rate and the month-on-month change in the power purchase capacity, combined with the transaction volume and average transaction price of the same period of previous years, the previous month and similar months.

[0091] As an implementation mode of an embodiment of the present invention, the prediction module is used to construct a regression analysis prediction model using the regional daily average clearing price as an independent variable and the daily average clearing price of the electricity purchasing decision-making entity as a dependent variable, and to predict the inter-provincial spot clearing average price by using the relationship between the regional average clearing price and the average clearing price of the electricity purchasing decision-making entity.

[0092] As an implementation method of an embodiment of the present invention, the prediction module is used to adopt a trend extrapolation prediction model to calculate the historical electricity trend through moving average, take historical data as a benchmark, select N months as the moving average period for prediction, and obtain the transaction volume and average transaction price of the predicted month.

[0093] The embodiments described above are only descriptions of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary technicians in this field should all fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for forecasting monthly spot prices between provinces, characterized in that: include: Step S1, obtaining the capacity constraints of the inter-provincial spot channel, and the cleared electricity volume and electricity price of each province within the channel area; According to the inter-provincial spot channel capacity constraints, and the cleared electricity volume and electricity prices of each province within the channel area, the monthly average of the inter-provincial spot channel capacity constraints, the monthly transaction volume of the inter-provincial spot market, the monthly average transaction price of the inter-provincial spot market, and the daily average clearing price within the channel capacity area are obtained; According to the monthly average of inter-provincial spot channel capacity constraints, monthly transaction volume of inter-provincial spot market, monthly transaction average price of inter-provincial spot market, and daily average price of clearing within the channel capacity area, a monthly inter-provincial spot volume and price forecasting model considering inter-provincial channels and regional electricity prices is constructed; among them, the monthly inter-provincial spot volume and price forecasting model includes: an inter-provincial volume forecasting model considering the similarity of inter-provincial channel capacity and transaction rate, a regression analysis forecasting model considering the correlation of regional electricity prices, and a trend extrapolation forecasting model based on historical clearing volume and price; the monthly volume and price of the inter-provincial spot market in the next month is forecasted by using the inter-provincial volume forecasting model, regression analysis forecasting model, and trend extrapolation forecasting model respectively; The forecast results of the inter-provincial electricity forecast model, regression analysis forecast model and trend extrapolation forecast model are corrected to form a combined forecast result, and the monthly forecast inter-provincial spot electricity and monthly forecast average price are output.

2. The inter-provincial spot monthly quantity and price combination forecasting method according to claim 1, characterized in that: Based on the fact that the supply and demand situation in various provinces and cities is similar to the same period in history, the channel capacity is similar to that in the second half of last month, and the declared quantity is equal to the channel capacity, a prediction model is constructed which takes into account the similarity of channel capacity and transaction rate among provinces. The year-on-year changes in the power purchase transaction rate and the month-on-month changes in the power purchase capacity are used, combined with the transaction volume and the average transaction price in the same period of previous years, last month and similar months, to predict the transaction volume and the average transaction price for the next month.

3. The inter-provincial spot monthly quantity and price combination forecasting method as claimed in claim 2, characterized in that: A regression analysis prediction model is constructed with the regional daily average clearing price as the independent variable and the daily average clearing price of the power purchasing decision-making entity as the dependent variable. The inter-provincial spot clearing average price is predicted by using the relationship between the regional clearing average price and the clearing average price of the power purchasing decision-making entity.

4. The inter-provincial spot monthly quantity and price combination forecasting method as claimed in claim 3, characterized in that: The trend extrapolation prediction model calculates the historical electricity trend through moving average, takes historical data as the benchmark, selects N months as the moving average period for prediction, and obtains the transaction volume and average transaction price of the predicted month.

5. A device for predicting monthly spot prices between provinces, characterized in that: include: The acquisition module is used to obtain the capacity constraints of the inter-provincial spot channel and the cleared electricity volume and electricity price of each province within the channel area; The calculation module is used to obtain the monthly average of the inter-provincial spot channel capacity constraint, the monthly transaction volume of the inter-provincial spot market, the monthly average transaction price of the inter-provincial spot market, and the daily average clearing price within the channel capacity area according to the inter-provincial spot channel capacity constraint and the clearing volume and electricity price of each province within the channel area; The prediction module is used to construct a monthly inter-provincial spot price prediction model that takes into account inter-provincial channels and regional electricity prices based on the monthly average of inter-provincial spot channel capacity constraints, the monthly transaction volume of the inter-provincial spot market, the monthly average transaction price of the inter-provincial spot market, and the daily average clearing price within the channel capacity area; wherein the monthly inter-provincial spot price prediction model includes: an inter-provincial electricity volume prediction model that takes into account the similarity of inter-provincial channel capacity and transaction rate, a regression analysis prediction model that takes into account the correlation of regional electricity prices, and a trend extrapolation prediction model based on historical clearing volume and price; the monthly inter-provincial spot market price is predicted by using the inter-provincial electricity volume prediction model, the regression analysis prediction model, and the trend extrapolation prediction model respectively; The correction module is used to correct the prediction results of the inter-provincial electricity forecasting model, regression analysis forecasting model, and trend extrapolation forecasting model to form a combined forecasting result and output the monthly forecasted inter-provincial spot electricity and monthly forecasted average price.

6. The inter-provincial spot monthly quantity and price combination forecasting method according to claim 1, characterized in that: The prediction module is used to construct a prediction model that takes into account the similarity of inter-provincial channel capacity and transaction rate based on the fact that the supply and demand situation in each province and city is similar to the same period in history, the channel capacity is similar to that in the second half of last month, and the declared quantity is equal to the channel capacity. The year-on-year changes in the power purchase transaction rate and the month-on-month changes in the power purchase capacity are used, combined with the transaction volume and the average transaction price in the same period of previous years, last month and similar months, to predict the transaction volume and the average transaction price for the next month.

7. The inter-provincial spot monthly price combination forecasting device according to claim 6, characterized in that: The prediction module is used to construct a regression analysis prediction model using the regional daily average clearing price as the independent variable and the daily average clearing price of the power purchasing decision-making entity as the dependent variable, and to predict the inter-provincial spot clearing average price by using the relationship between the regional average clearing price and the average clearing price of the power purchasing decision-making entity.

8. The inter-provincial spot monthly price combination forecasting device according to claim 7, characterized in that: The prediction module is used to calculate the historical electricity trend through moving average using the trend extrapolation prediction model. Based on the historical data, N months are selected as the moving average period for prediction to obtain the transaction volume and average transaction price of the predicted month.

Images