Auxiliary decision-making method for power trading based on power generation forecast

Abstract

The present invention provides an auxiliary decision-making method for power trading based on power generation prediction, which relates to the technical field of data processing. The method comprises: predicting the power generation in a target area through a power prediction platform, determining the predicted power generation data, determining the power demand index according to the power supply index in the target area and based on the historical power usage data of the target area, constructing the power supply and demand factor of the target area, constructing the power floating curve, and determining the power fluctuation information to assist in optimizing the power trading decision. The present invention solves the technical problem in the prior art that the predicted power generation is not considered when making auxiliary decisions for power trading, resulting in low efficiency of auxiliary decisions for power trading, and realizes the rationalization and accuracy of power generation prediction when making auxiliary decisions for power trading, thereby improving the efficiency of auxiliary decisions for power trading.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an auxiliary decision-making method for power trading based on power generation prediction. Background Art

[0002] Power trading strategy refers to the act of making profits by making reasonable trading strategies to buy and sell power in the power market. The formulation of power trading strategy needs to consider many factors such as market supply and demand, power price fluctuations, power quality requirements, etc., so it requires certain professional knowledge and experience.

[0003] The formulation of power trading strategies needs to consider the supply and demand situation in the market. In the power market, the supply and demand relationship is one of the main factors affecting the fluctuation of power prices. Therefore, when formulating power trading strategies, it is necessary to pay attention to the supply and demand situation in the market and adjust the trading strategies in time to obtain better trading results.

[0004] The present invention solves the technical problem in the prior art that the predicted power generation is not considered when making auxiliary decisions for power trading, resulting in low efficiency of auxiliary decisions for power trading. It realizes the rationalization and accuracy of power generation prediction when making auxiliary decisions for power trading, thereby improving the efficiency of auxiliary decisions for power trading. Summary of the invention

[0005] The present application provides an auxiliary decision-making method for power trading based on power generation forecast, which is used to solve the technical problem in the prior art that the power trading auxiliary decision-making is inefficient due to the lack of consideration of the predicted power generation when making auxiliary decisions.

[0006] In view of the above problems, the present application provides an auxiliary decision-making method for power trading based on power generation forecasting.

[0007] In a first aspect, the present application provides an auxiliary decision-making method for power trading based on power generation prediction, the method comprising: predicting the power generation in the target area through the power prediction platform, and determining the predicted power generation data, wherein the predicted power generation data includes a long-term power generation prediction result and a short-term power generation prediction result; obtaining the power supply index in the target area through the long-term power generation prediction result and the short-term power generation prediction result; determining the power demand index based on the historical power usage data of the target area; constructing the power supply and demand factor of the target area according to the power supply index and the power demand index; constructing a power floating curve based on the power supply and demand factor; determining the power fluctuation information through the power floating curve, and assisting in optimizing the power trading decision based on the power fluctuation information.

[0008] In a second aspect, the present application provides an auxiliary decision-making system for power trading based on power generation prediction, the system comprising: a prediction module, the prediction module is used to predict the power generation in the target area through the power prediction platform, and determine the predicted power generation data, wherein the predicted power generation data includes the long-term power generation prediction result and the short-term power generation prediction result; a supply index acquisition module, the supply index acquisition module is used to obtain the power supply index in the target area through the long-term power generation prediction result and the short-term power generation prediction result; an power demand index acquisition module, the power demand index acquisition module is used to determine the power demand index based on the historical power usage data of the target area; a supply and demand factor construction module, the supply and demand factor construction module is used to construct the power supply and demand factor of the target area according to the power supply index and the power demand index; a curve construction module, the curve construction module is used to construct a power floating curve based on the power supply and demand factor; an auxiliary optimization module, the auxiliary optimization module is used to determine the power fluctuation information through the power floating curve, and perform auxiliary optimization on power trading decisions based on the power fluctuation information.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The power trading decision-making assistance method based on power generation prediction provided in the present application relates to the field of data processing technology, solves the technical problem in the prior art that the predicted power generation is not considered when making power trading decision-making assistance, resulting in low efficiency of power trading decision-making assistance, and realizes reasonable and accurate prediction of power generation when making power trading decision-making assistance, thereby improving the efficiency of power trading decision-making assistance. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flow chart of a power trading decision-making assistance method based on power generation forecasting is provided for this application;

[0012] Figure 2 A schematic diagram of the data flow of power generation prediction in the power transaction auxiliary decision-making method based on power generation prediction is provided for this application;

[0013] Figure 3 A schematic diagram of the process of constructing a power floating curve in a power trading auxiliary decision-making method based on power generation forecast is provided for this application;

[0014] Figure 4 A schematic diagram of the process of obtaining power fluctuation information in a power trading auxiliary decision-making method based on power generation forecast is provided for this application;

[0015] Figure 5 A schematic diagram of the structure of an auxiliary decision-making system for power trading based on power generation forecasting is provided for this application.

[0016] Explanation of the reference numerals: prediction module 1, supply index acquisition module 2, electricity demand index acquisition module 3, supply and demand factor construction module 4, curve construction module 5, auxiliary optimization module 6. DETAILED DESCRIPTION

[0017] The present application provides an auxiliary decision-making method for power trading based on power generation forecast, which is used to solve the technical problem in the prior art that the power trading auxiliary decision-making fails to take the predicted power generation into consideration when making power trading auxiliary decisions, resulting in low efficiency of power trading auxiliary decision-making.

[0018] Embodiment 1

[0019] like Figure 1 As shown, the embodiment of the present application provides an auxiliary decision method for power trading based on power generation prediction, which is applied to an auxiliary decision system for power trading based on power generation prediction, and the auxiliary decision system for power trading based on power generation prediction is communicatively connected with an electric quantity prediction platform, and the method includes:

[0020] Step S100: predicting the power generation in the target area through the power prediction platform to determine predicted power generation data, wherein the predicted power generation data includes a long-term power generation prediction result and a short-term power generation prediction result;

[0021] Furthermore, if Figure 2 As shown, step S100 of the present application also includes:

[0022] Step S110: performing a macro-forecast of power generation in the target area through the power forecasting platform in combination with the historical power generation data of the power station to determine the adequacy of power supply of the power system;

[0023] Step S120: determining the long-term prediction result of the power generation based on the adequacy of the power supply of the power system;

[0024] Step S130: performing power generation micro-forecasting on the target area through the power forecasting platform combined with the short-term power forecasting data to determine the short-term power variation range of the power system;

[0025] Step S140: determining the short-term prediction result of power generation based on the short-term power variation interval of the power system;

[0026] Step S150: integrating the long-term power generation prediction result and the short-term power generation prediction result, and acquiring the predicted power generation data of the target area according to the data integration result.

[0027] Furthermore, step S150 of the present application includes:

[0028] Step S151: performing weight allocation on the long-term power generation forecast result and the short-term power generation forecast result to obtain a weight allocation result;

[0029] Step S152: performing weight training on the long-term power generation prediction result and the short-term power generation prediction result according to the weight allocation result, and obtaining the long-term power generation prediction result with weight and the short-term power generation prediction result with weight;

[0030] Step S153: performing data integration on the weighted long-term prediction result of power generation and the weighted short-term prediction result of power generation to determine the data integration result.

[0031] Specifically, the power trading decision-making assistance method based on power generation prediction provided in the embodiment of the present application is applied to the power trading decision-making assistance system based on power generation prediction. The power trading decision-making assistance system based on power generation prediction is communicatively connected with an electricity prediction platform, and the electricity prediction platform is used to collect electricity parameters.

[0032] In order to achieve accurate prediction of power generation in the target area, it is first necessary to combine the power generation historical data of the power plant through the power prediction platform. The power generation historical data of the power plant refers to the total electric energy produced by the power plant in the historical period, and make a macro prediction of power generation in the target area, which refers to the ability to continuously meet the power and power demand of users during the historical period, and to maintain this ability during load peaks and planned and unplanned component outages, so as to determine the adequacy of the power supply of the power system. Furthermore, using the adequacy of the power supply of the power system as basic data, it can assist in formulating scheduling plans for conventional power regulation, build a long-term power balance system, ensure the adequacy of the power supply of the power system at the macro level, and then determine the long-term prediction results of power generation.

[0033] The electricity quantity prediction platform is combined with the data of short-term power prediction. The data of short-term power prediction refers to the prediction of the electric power change of the power network within a period of time according to the real-time status of the power network, including the historical active power data of the power station, so as to make a micro-forecast of power generation in the target area, and determine the short-term power change range of the power system according to the predicted upper limit of the electric power change of the power network and the predicted lower limit of the electric power change of the power network, and then use the short-term power change range of the power system as the electric power reference data, and on this basis, determine the short-term prediction result of power generation.

[0034] Furthermore, data integration of the long-term prediction results and the short-term prediction results of power generation refers to weight training of the long-term prediction results and the short-term prediction results of power generation based on weight allocation, that is, weight training needs to be based on a large amount of data aggregation and accurate determination of weights before targeted calculation. For example, the weight allocation ratio of the long-term prediction results and the short-term prediction results of power generation can be the first influence coefficient: the second influence coefficient is 4:6, then the influence parameters after the weight training process are the first influence parameter*0.4 and the second influence parameter*0.6, respectively. According to the weight training result, the long-term prediction results of power generation with weights and the short-term prediction results of power generation with weights are obtained. Finally, data integration of the long-term prediction results of power generation with weights and the short-term prediction results of power generation with weights refers to data collection, sorting and cleaning of the long-term prediction results of power generation with weights and the short-term prediction results of power generation with weights from different data sources, respectively, and loading them into a new data source after conversion, recording them as data integration results, and obtaining the predicted power generation data of the target area according to the data integration results, which serves as an important reference for the later realization of auxiliary decision-making for power trading based on power generation prediction.

[0035] Step S200: obtaining the power supply index in the target area through the long-term power generation prediction result and the short-term power generation prediction result;

[0036] Specifically, using the above-mentioned long-term power generation forecast results and short-term power generation forecast results as basic data, the power generation of the power stations in the target area is predicted respectively, which means that the data of the adequacy of the power supply of the power system contained in the long-term power generation forecast results and the short-term power forecast in the short-term power generation forecast results are extracted respectively, and the maximum allowable power transmission power in the circuit contained in the target area is calculated according to the adequacy of the power supply of the power system to obtain the power transmission capacity coefficient, and the allowable output power under the rated temperature rise in the target area is calculated according to the short-term power forecast data to obtain the total non-aged capacity in the target area, and finally the total capacity of the generator is multiplied by the power transmission capacity coefficient, and the data obtained after the product is output as the power supply index in the target area, thereby ensuring the realization of auxiliary decision-making for power trading based on power generation forecast.

[0037] Step S300: determining an electricity demand index based on the historical electricity usage data of the target area;

[0038] Specifically, by retrieving the electricity consumption records in the target area, according to the electricity consumption, electricity capacity and growth of the target area in previous years and months in the electricity consumption records, the changes in the electricity consumption structure in the target area over the years are determined. Based on the changes in the electricity consumption structure over the years, the historical electricity usage data of the target area is extracted according to the changes in the electricity consumption structure over the years. According to the electricity usage data of the electricity structure, electricity consumption scale, and electricity price data, the daily electricity consumption in the target area over the years is determined, and recorded as the electricity demand index in the target area, laying a solid foundation for the subsequent realization of auxiliary decision-making for electricity trading based on power generation forecasts.

[0039] Step S400: constructing an electricity supply and demand factor for the target area according to the electricity supply index and the electricity demand index;

[0040] Specifically, the power supply index and the power demand index are used as construction data, and the power balance index of the target area is calculated by the following power supply and demand balance calculation formula:

[0041]

[0042] Among them, Q is the power balance index of the target area, b is the power supply index of the target area, and k is the power demand index of the target area.

[0043] The calculated power balance index reflects the balance between power supply and power demand in the target area. When the power balance index is 100, it is considered that the power supply and power demand in the target area are completely balanced. When the power supply and demand balance index is greater than 100, it is considered that the power supply in the target area is sufficient. When the power supply and demand balance index is less than 100, it is considered that the power demand in the target area is in excess. The power supply and demand factors in the target area are constructed according to the power balance index, and the power balance index is proportional to the power supply and demand factors. The larger the power balance index, the larger the power supply and demand factors. It has a limited role in auxiliary decision-making for power trading based on power generation forecasts.

[0044] Step S500: constructing an electric power floating curve based on the electric power supply and demand factor;

[0045] Furthermore, if Figure 3 As shown, step S500 of the present application also includes:

[0046] Step S510: factorizing the power supply and demand factors to obtain power supply factors and power demand factors;

[0047] Step S520: using the power supply factor as a first coordinate axis and the power demand factor as a second coordinate axis;

[0048] Step S530: constructing a power supply and demand coordinate system according to the first coordinate axis and the second coordinate axis;

[0049] Step S540: Based on the power fluctuation coefficient, the power information is identified in the power supply and demand coordinate system to construct the power floating curve.

[0050] Specifically, the electricity supply and demand factors obtained by the above calculation are used as the basic construction data. The electricity supply and demand factors are first factorized, which means that the electricity supply and demand factors are divided according to the electricity supply and electricity demand in the target area, and the factors with electricity supply in the electricity supply and demand factors are recorded as electricity supply factors, and the factors with electricity demand in the electricity supply and demand factors are recorded as electricity demand factors. Furthermore, the electricity supply factor is recorded as the first coordinate axis with kilowatt as the horizontal axis, and the electricity demand factor is recorded as the second coordinate axis with kilowatt as the vertical axis. The initial position of the first coordinate axis is connected with the initial position of the second coordinate axis, and the connection point is used as the origin. The coordinate system constructed is recorded as the electricity supply and demand coordinate system.

[0051] Furthermore, the power fluctuation coefficient in the target area is calculated by the following power fluctuation coefficient calculation formula:

[0052]

[0053] Among them, △P% is the power fluctuation coefficient, P' is the line loss power, P is the head end transmission power, n is the weight value of the line loss power, m is the weight value of the head section transmission power, and i is the number of the identification power information.

[0054] Based on the power fluctuation coefficient, the fluctuating power information is marked in the power supply and demand coordinate system. Finally, the marked points are connected adjacently to complete the construction of the power floating curve, so as to serve as reference data for the subsequent power trading auxiliary decision-making based on power generation forecasts.

[0055] Step S600: Determine power fluctuation information through the power floating curve, and assist in optimizing power trading decisions based on the power fluctuation information.

[0056] Furthermore, if Figure 4 As shown, step S600 of the present application also includes:

[0057] Step S610: acquiring power price data and power quality data based on the identified power information in the power floating curve;

[0058] Step S620: determining power price fluctuation information according to the supply and demand factors and the power price data in the target area;

[0059] Step S630: determining the power quality fluctuation information according to the supply and demand factors and the power quality data in the target area;

[0060] Step S640: Acquire the power fluctuation information based on the power price fluctuation information and the power quality fluctuation information.

[0061] Furthermore, step S600 of the present application also includes:

[0062] Step S650: setting a power fluctuation evaluation period;

[0063] Step S660: collecting periodic data of power through the power fluctuation evaluation cycle to obtain collection results;

[0064] Step S670: comparing the fluctuation range of the collected results with the expected power fluctuation evaluation results to obtain a power fluctuation range comparison result;

[0065] Step S680: generating power fluctuation feedback data according to the power fluctuation amplitude result, and assisting in optimizing the power trading decision through the power fluctuation feedback data.

[0066] Specifically, the power fluctuation information is finally determined through the power floating curve constructed as above, which means that based on the marked power information in the power floating curve, the power consumption information, power billing period information, and power quality information in the marked power information are extracted, and the power price data is obtained according to the power consumption information and the power billing period information. The power price data refers to the on-grid electricity price, the mutual power supply price between power grids, the power grid sales price and other data in the power production process in the target area. The power quality data is obtained according to the power consumption information and the power quality information. The power quality data refers to the quality of the electric energy provided to the target area, which is usually measured by indicators such as voltage, frequency and waveform. Further, according to the supply and demand factors, power prices and power quality information in the target area, the power price data is obtained. According to the grid data, to determine the electricity price fluctuation information in the target area, it means comparing the electricity price data with the electricity price corresponding to the supply and demand factors, marking the electricity price points where the increase or decrease of electricity price is greater than 30%, and recording the marked information as the electricity price fluctuation information. Furthermore, according to the supply and demand factors and power quality data in the target area, to determine the power quality fluctuation information, it means comparing the power quality data with the power quality corresponding to the supply and demand factors, marking the power quality points where the increase or decrease of power quality is greater than 30%, and recording the marked information as the power quality fluctuation information. Finally, the power price fluctuation information and the power quality fluctuation information are added to the power fluctuation information for improvement.

[0067] First, the power fluctuation evaluation cycle is set, where the power fluctuation evaluation cycle is set according to the specific power fluctuation information. Secondly, the auxiliary optimization of power trading decisions conforms to the genetic algorithm rules. The essence of the genetic algorithm is to continuously perform random searches in the solution space, continuously generate new solutions during the search process, and retain the algorithm with better solutions. The implementation difficulty is relatively low, and relatively satisfactory results can be obtained in a short time. When using genetic algorithms, they directly operate on structural objects, there is no limitation on derivatives and function continuity, and they have inherent implicit parallelism and better global optimization capabilities. They use probabilistic optimization methods, and can automatically obtain and guide the optimized search space without determining rules, and adaptively adjust the search direction. Therefore, it is used as a search algorithm for auxiliary optimization of power trading decisions.

[0068] The obtained collection results are calculated according to the genetic algorithm to obtain expected power fluctuation evaluation results, which are obtained by collecting periodic data of power fluctuations in the set power fluctuation evaluation period, and the obtained expected power fluctuation evaluation results correspond to the obtained actual power fluctuation effect evaluation results one by one, and the obtained actual power fluctuation effect evaluation results are obtained by collecting power fluctuation periodic data in the power fluctuation evaluation period, and by comparing the expected power fluctuation evaluation results with the actual power fluctuation effect evaluation results, a power fluctuation amplitude comparison result of the two is obtained, and power fluctuation feedback data is further generated according to the obtained power fluctuation amplitude comparison result, wherein when the power fluctuation feedback data is used to assist in optimizing power trading decisions, based on the comparison between the above-mentioned expected power fluctuation evaluation results and the actual power fluctuation effect evaluation results, a prediction value with the closest similarity is obtained, and the corresponding training data is the training data for assisting in optimizing the power trading decisions, so as to ensure high efficiency when assisting in optimizing the power trading decisions.

[0069] To sum up, the power trading decision-making assistance method based on power generation prediction provided in the embodiment of the present application includes at least the following technical effects, which realizes the rational and accurate prediction of power generation when making power trading decision-making assistance, thereby improving the efficiency of power trading decision-making assistance.

[0070] Embodiment 2

[0071] Based on the same inventive concept as the power transaction auxiliary decision method based on power generation prediction in the aforementioned embodiment, Figure 5 As shown, the present application provides an auxiliary decision-making system for power trading based on power generation forecasting, the system comprising:

[0072] Prediction module 1, the prediction module 1 is used to predict the power generation in the target area through the power prediction platform, and determine the predicted power generation data, wherein the predicted power generation data includes the long-term power generation prediction result and the short-term power generation prediction result;

[0073] A supply index acquisition module 2, the supply index acquisition module 2 is used to acquire the power supply index in the target area through the long-term power generation prediction result and the short-term power generation prediction result;

[0074] An electricity demand index acquisition module 3, the electricity demand index acquisition module 3 is used to determine the electricity demand index based on the historical electricity usage data of the target area;

[0075] A supply and demand factor construction module 4, wherein the supply and demand factor construction module 4 is used to construct the power supply and demand factor of the target area according to the power supply index and the power demand index;

[0076] A curve construction module 5, the curve construction module 5 is used to construct an electric power floating curve based on the electric power supply and demand factor;

[0077] The auxiliary optimization module 6 is used to determine the power fluctuation information through the power floating curve, and to perform auxiliary optimization on the power trading decision based on the power fluctuation information.

[0078] Furthermore, the system also includes:

[0079] A macro prediction module, which is used to perform a macro prediction of power generation in the target area through the power prediction platform in combination with the historical power generation data of the power station, and determine the adequacy of power supply in the power system;

[0080] A long-term prediction module, the long-term prediction module is used to determine the long-term prediction result of the power generation based on the margin of the power supply of the power system;

[0081] A micro-forecasting module, which is used to perform a micro-forecast of power generation in the target area by combining the power forecasting platform with the data of short-term power forecasting, and determine the short-term power variation range of the power system;

[0082] A short-term prediction module, the short-term prediction module is used to determine the short-term prediction result of the power generation based on the short-term power change interval of the power system;

[0083] The first data integration module is used to integrate the long-term power generation prediction results and the short-term power generation prediction results, and obtain the predicted power generation data of the target area according to the data integration results.

[0084] Furthermore, the system also includes:

[0085] A weight allocation module, the weight allocation module is used to perform weight allocation on the long-term power generation prediction result and the short-term power generation prediction result to obtain a weight allocation result;

[0086] A weight training module, the weight training module is used to perform weight training on the long-term power generation prediction result and the short-term power generation prediction result according to the weight allocation result, and obtain the long-term power generation prediction result with weight and the short-term power generation prediction result with weight;

[0087] The second data integration module is used to integrate the weighted long-term prediction result of the power generation and the weighted short-term prediction result of the power generation to determine the data integration result.

[0088] Furthermore, the system also includes:

[0089] A factor decomposition module, wherein the factor decomposition module is used to factorize the power supply and demand factors to obtain power supply factors and power demand factors;

[0090] A coordinate axis construction module, wherein the coordinate axis construction module is used to use the power supply factor as a first coordinate axis and the power demand factor as a second coordinate axis;

[0091] A coordinate system construction module, wherein the coordinate system construction module is used to construct a power supply and demand coordinate system according to the first coordinate axis and the second coordinate axis;

[0092] A curve module is used to construct the power floating curve by identifying power information in the power supply and demand coordinate system based on the power fluctuation coefficient.

[0093] Furthermore, the system also includes:

[0094] A power data module, the power data module is used to obtain power price data and power quality data based on the identified power information in the power floating curve;

[0095] An electricity price fluctuation module, the electricity price fluctuation module is used to determine electricity price fluctuation information according to the supply and demand factors and the electricity price data in the target area;

[0096] A power quality fluctuation module, the power quality fluctuation module is used to determine the power quality fluctuation information according to the supply and demand factors and the power quality data in the target area;

[0097] A power fluctuation module is used to obtain the power fluctuation information based on the power price fluctuation information and the power quality fluctuation information.

[0098] Furthermore, the system also includes:

[0099] A cycle module, the cycle module is used to set a power fluctuation evaluation cycle;

[0100] A data acquisition module, the data acquisition module is used to collect periodic data of power through the power fluctuation evaluation period to obtain collection results;

[0101] A comparison module, the comparison module is used to compare the fluctuation range of the collection results with the expected power fluctuation evaluation results to obtain a power fluctuation range comparison result;

[0102] A feedback module is used to generate power fluctuation feedback data according to the power fluctuation amplitude result, and to assist in optimizing the power trading decision through the power fluctuation feedback data.

[0103] Through the above-mentioned detailed description of the auxiliary decision-making method for power trading based on power generation forecast in this specification, those skilled in the art can clearly know the auxiliary decision-making system for power trading based on power generation forecast in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0104] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A power trading decision-making assistance method based on power generation forecast, characterized in that: The method is applied to an auxiliary decision-making system for power trading based on power generation prediction, wherein the auxiliary decision-making system for power trading based on power generation prediction is communicatively connected with an electric quantity prediction platform, and the method comprises: The power generation in the target area is predicted by the power prediction platform to determine predicted power generation data, wherein the predicted power generation data includes a long-term power generation prediction result and a short-term power generation prediction result; Obtaining the power supply index in the target area through the long-term power generation prediction result and the short-term power generation prediction result; Determining an electricity demand index based on historical electricity usage data of the target area; Constructing the power supply and demand factor of the target area according to the power supply index and the power demand index; Based on the power supply and demand factors, construct a power floating curve; Determine power fluctuation information through the power floating curve, and assist in optimizing power trading decisions based on the power fluctuation information; Among them, constructing the power floating curve includes: Factoring the power supply and demand factors to obtain power supply factors and power demand factors; Taking the power supply factor as the first coordinate axis and the power demand factor as the second coordinate axis; Constructing a power supply and demand coordinate system according to the first coordinate axis and the second coordinate axis; Based on the power fluctuation coefficient, the power information is identified in the power supply and demand coordinate system to construct the power floating curve; The determining of the power fluctuation information comprises: Based on the identified power information in the power floating curve, acquiring power price data and power quality data; Determining electricity price fluctuation information according to the supply and demand factors and the electricity price data in the target area; Determining the power quality fluctuation information according to the supply and demand factors and the power quality data in the target area; Acquiring the power fluctuation information based on the power price fluctuation information and the power quality fluctuation information; Wherein, the step of determining the predicted power generation data includes: The power forecasting platform is used to combine the historical power generation data of the power station to perform a macro-forecast of power generation in the target area to determine the adequacy of power supply in the power system; Determining the long-term prediction result of the power generation based on the adequacy of the power supply of the power system; The power generation micro-forecast of the target area is performed by combining the power forecast platform with the short-term power forecast data to determine the short-term power change range of the power system; Determining the short-term prediction result of the power generation based on the short-term power variation interval of the power system; The long-term power generation prediction result and the short-term power generation prediction result are integrated, and the predicted power generation data of the target area is obtained according to the data integration result.

2. The method according to claim 1, characterized in that The method also includes: Performing weight allocation on the long-term power generation forecast result and the short-term power generation forecast result to obtain a weight allocation result; Performing weight training on the long-term power generation prediction result and the short-term power generation prediction result according to the weight allocation result, to obtain the long-term power generation prediction result with weight and the short-term power generation prediction result with weight; The weighted long-term prediction result of power generation and the weighted short-term prediction result of power generation are data integrated to determine the data integration result.

3. The method according to claim 1, characterized in that The power fluctuation coefficient is as follows: Among them, ΔP% is the power fluctuation coefficient, P' is the line loss power, P is the head end transmission power, n is the weight value of the line loss power, m is the weight value of the head section transmission power, and i is the number of the identification power information.

4. The method according to claim 1, characterized in that Auxiliary optimization of power trading decisions is performed based on the power fluctuation information, and the method further includes: Set the power fluctuation evaluation period; Collecting periodic data of power through the power fluctuation evaluation cycle to obtain collection results; Comparing the fluctuation range of the collected results with the expected power fluctuation evaluation results to obtain a power fluctuation range comparison result; The power fluctuation feedback data is generated according to the power fluctuation amplitude result, and the power trading decision is assisted and optimized by the power fluctuation feedback data.

5. The power trading auxiliary decision-making system based on power generation forecast is characterized by: The power transaction auxiliary decision-making system based on power generation prediction is communicatively connected with the power generation prediction platform, and the system includes: A prediction module, the prediction module is used to predict the power generation in the target area through the power prediction platform, and determine the predicted power generation data, wherein the predicted power generation data includes a long-term power generation prediction result and a short-term power generation prediction result; A supply index acquisition module, the supply index acquisition module is used to obtain the power supply index in the target area through the long-term power generation prediction result and the short-term power generation prediction result; An electricity demand index acquisition module, the electricity demand index acquisition module is used to determine the electricity demand index based on the historical electricity usage data of the target area; A supply and demand factor construction module, the supply and demand factor construction module is used to construct the power supply and demand factor of the target area according to the power supply index and the power demand index; A curve construction module, the curve construction module is used to construct an electric power floating curve based on the electric power supply and demand factor; An auxiliary optimization module, the auxiliary optimization module is used to determine power fluctuation information through the power floating curve, and perform auxiliary optimization on power trading decisions based on the power fluctuation information; Wherein, the system further comprises: A factor decomposition module, wherein the factor decomposition module is used to factorize the power supply and demand factors to obtain power supply factors and power demand factors; A coordinate axis construction module, wherein the coordinate axis construction module is used to use the power supply factor as a first coordinate axis and the power demand factor as a second coordinate axis; A coordinate system construction module, wherein the coordinate system construction module is used to construct a power supply and demand coordinate system according to the first coordinate axis and the second coordinate axis; A curve module, the curve module is used to construct the power floating curve by identifying the power information in the power supply and demand coordinate system based on the power fluctuation coefficient; A power data module, the power data module is used to obtain power price data and power quality data based on the identified power information in the power floating curve; An electricity price fluctuation module, the electricity price fluctuation module is used to determine electricity price fluctuation information according to the supply and demand factors and the electricity price data in the target area; A power quality fluctuation module, the power quality fluctuation module is used to determine the power quality fluctuation information according to the supply and demand factors and the power quality data in the target area; A power fluctuation module, the power fluctuation module is used to obtain the power fluctuation information based on the power price fluctuation information and the power quality fluctuation information; A macro prediction module, which is used to perform a macro prediction of power generation in the target area through the power prediction platform in combination with the historical power generation data of the power station, and determine the adequacy of power supply in the power system; A long-term prediction module, the long-term prediction module is used to determine the long-term prediction result of the power generation based on the margin of the power supply of the power system; A micro-forecasting module, which is used to perform a micro-forecast of power generation in the target area by combining the power forecasting platform with the data of short-term power forecasting, and determine the short-term power variation range of the power system; A short-term prediction module, the short-term prediction module is used to determine the short-term prediction result of the power generation based on the short-term power change interval of the power system; The first data integration module is used to integrate the long-term power generation prediction results and the short-term power generation prediction results, and obtain the predicted power generation data of the target area according to the data integration results.

Images