Electricity price prediction method and device considering renewable energy sources, equipment, medium and product

Abstract

The invention discloses an electricity price prediction method and device considering renewable energy sources, equipment, a medium and a product, and relates to the technical field of electricity price analysis and prediction, and the method comprises the steps: determining the target weather information of a to-be-predicted region, the target electricity load of a user side, the first target power generation power of a power grid side, and the equipment information of new energy power generation equipment; processing the target meteorological information and the equipment information to obtain second target power generation power of the new energy power generation equipment; and processing the target electrical load, the first target generated power and the second target generated power by using an autoregressive average heterovariance model to obtain a target electricity price of the to-be-predicted region. According to the technical scheme of the invention, the environment information of the to-be-predicted region is combined, the meteorological information and the equipment information of the new energy power generation equipment are fused, and the accurate power generation power of the new energy power generation equipment is obtained, so that the accuracy of the predicted electricity price is improved, and the profit of a new energy enterprise and the stability of a power system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electricity price analysis and prediction, and in particular to an electricity price prediction method, device, equipment, medium and product taking renewable energy into consideration. Background Art

[0002] The efficiency of electricity trading in the power system, the decision-making of market participants and the operation of wind power plants are all closely related to electricity prices. Electricity prices are affected by factors such as supply and demand, market structure, cost, weather, and timing, and are highly uncertain and nonlinear. Therefore, the accuracy of electricity price forecasting is one of the important issues in the power market.

[0003] At present, the electricity price forecasting method is to use the theories and models of statistics or economics to process the historical data of the power system, such as the power load on the user side, the power generation power on the grid side, and the power generation power of new energy power generation equipment, and then evaluate the electricity price in the power market. However, new energy power generation equipment such as wind power and photovoltaic power generation has strong instability and volatility. There is an error between the power generation power of new energy power generation equipment determined based on historical data and the actual output power of new energy power generation equipment. The accuracy of the predicted electricity price is low. Inappropriate pricing methods will reduce the profitability of new energy companies and even affect the stability of the power system. Summary of the invention

[0004] The present invention provides a method, device, equipment, medium and product for predicting electricity prices taking renewable energy into consideration, aiming to improve the accuracy of predicted electricity prices, increase the profitability of new energy enterprises and the stability of the power system.

[0005] According to one aspect of the present invention, a method for predicting electricity prices considering renewable energy is provided, the method comprising:

[0006] Determine the target meteorological information of the area to be predicted, the target power load on the user side, the first target power generation power on the grid side, and the equipment information of the new energy power generation equipment;

[0007] Processing the target meteorological information and the equipment information to obtain a second target power generation power of the new energy power generation equipment;

[0008] The target electricity load, the first target power generation power and the second target power generation power are processed by using the autoregressive mean heteroskedasticity model to obtain the target electricity price of the area to be predicted.

[0009] Optionally, determining the target meteorological information of the area to be predicted includes: determining the initial meteorological information of the area to be predicted; based on predetermined meteorological data features, identifying abnormal information in the initial meteorological information to obtain abnormal meteorological information; determining whether the abnormal meteorological information meets the meteorological information update conditions; if the abnormal meteorological information does not meet the meteorological information update conditions, processing the initial meteorological information according to a preset meteorological information adjustment plan to obtain the target meteorological information; if the abnormal meteorological information meets the meteorological information update conditions, correcting the abnormal meteorological information according to the mean of the initial meteorological information, updating the initial meteorological information based on the correction result, and returning to execute the step of identifying the abnormal information in the initial meteorological information based on the predetermined meteorological data features to obtain the abnormal meteorological information.

[0010] Optionally, determining the target power load on the user side and the first target power generation power on the grid side in the area to be predicted includes: processing historical load information on the user side within a preset time period to obtain a reference load and load change trend on the user side; determining the target power load based on the load change trend, the reference load and the electricity price forecast demand; processing the first historical power generation power information on the grid side within the preset time period to obtain a reference power generation power and power generation change trend on the grid side; determining the first target power generation power based on the electricity price forecast demand, the reference power generation power and the power generation change trend.

[0011] Optionally, the target meteorological information and equipment information are processed to obtain a second target power generation of the new energy power generation equipment, including: determining a second historical power generation information of the new energy power generation equipment, wherein the second historical power generation information includes at least one candidate power generation and at least one candidate meteorological information, and the candidate meteorological information and the candidate power generation correspond one to one; determining that the candidate meteorological information in the second historical power generation information that has the highest matching degree with the target meteorological information is the intermediate meteorological information; determining whether the matching degree between the intermediate meteorological information and the target meteorological information meets a preset meteorological information matching condition; if the matching degree between the intermediate meteorological information and the target meteorological information meets the preset meteorological information matching condition, determining that the candidate power generation corresponding to the intermediate meteorological information is the second target power generation.

[0012] Optionally, the target power load, the first target power generation power and the second target power generation power are processed using an autoregressive mean heteroskedasticity model to obtain a target electricity price for the area to be predicted, including: using an autoregressive mean exogenous model to process the target power load, the first target power generation power and the second target power generation power to obtain candidate electricity prices for the area to be predicted; using an autoregressive heteroskedasticity exogenous model to adjust the candidate electricity prices to obtain the target electricity price.

[0013] Optionally, an autoregressive mean heteroscedasticity model is used to process the target power load, the first target power generation power, and the second target power generation power to obtain a target electricity price for the area to be predicted, including: determining historical electricity price information for the area to be predicted, wherein the historical electricity price information includes at least one electricity price data and at least one time stamp, and the time stamp and the electricity price data correspond one to one; using an autoregressive mean exogenous model to process the target meteorological information and the historical electricity price information to obtain an electricity price residual for the area to be predicted; using an autoregressive heteroscedasticity exogenous model to process the electricity price residual, the first target power generation power, and the second target power generation power to obtain the target electricity price.

[0014] According to another aspect of the present invention, a device for predicting electricity prices taking into account renewable energy is provided. The device for predicting electricity prices taking into account renewable energy is used to implement the method for predicting electricity prices taking into account renewable energy in any embodiment of the present invention. The device comprises:

[0015] An acquisition module is used to determine target meteorological information of the area to be predicted, target power load on the user side, first target power generation power on the grid side, and equipment information of new energy power generation equipment;

[0016] A determination module, used for processing target meteorological information and equipment information to obtain a second target power generation power of the new energy power generation equipment;

[0017] The execution module is used to process the target power load, the first target power generation power and the second target power generation power by using the autoregressive mean heteroscedasticity model to obtain the target electricity price of the area to be predicted.

[0018] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:

[0019] at least one processor; and a memory communicatively coupled to the at least one processor;

[0020] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the electricity price prediction method considering renewable energy in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for enabling a processor to implement the electricity price prediction method considering renewable energy in any embodiment of the present invention when the computer instructions are executed.

[0022] According to another aspect of the present invention, a computer program product is provided. The computer program product includes a computer program. When the computer program is executed by a processor, the method for predicting electricity prices considering renewable energy according to any embodiment of the present invention is implemented.

[0023] The electricity price prediction method considering renewable energy of the present invention comprises: determining the target meteorological information of the area to be predicted, the target power load on the user side, the first target power generation power on the grid side and the equipment information of the new energy power generation equipment; processing the target meteorological information and the equipment information to obtain the second target power generation power of the new energy power generation equipment; using the autoregressive mean heteroscedasticity model, processing the target power load, the first target power generation power and the second target power generation power to obtain the target electricity price of the area to be predicted. The technical scheme of the present invention combines the environmental information of the area to be predicted, integrates the meteorological information and the equipment information of the new energy power generation equipment, obtains the accurate power generation power of the new energy power generation equipment, and processes the target power load, the first target power generation power and the second target power generation power through the autoregressive mean heteroscedasticity model. The autoregressive mean heteroscedasticity model can not only consider the autocorrelation of the time series and the influence of external factors, but also suppress the impact of the volatility of the load information and the new energy power generation equipment on the electricity price, thereby improving the accuracy of the predicted electricity price, and improving the profitability of the new energy enterprise and the stability of the power system. It solves the problems that new energy power generation equipment such as wind power and photovoltaic power generation have strong instability and volatility, there is an error between the power generation power of new energy power generation equipment determined according to historical data and the actual output power of new energy power generation equipment, the accuracy of the predicted electricity price is low, and inappropriate pricing methods will reduce the profitability of new energy companies and even affect the stability of the power system.

[0024] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0026] Figure 1 It is a flow chart of a method for predicting electricity prices taking renewable energy into consideration provided by the present invention;

[0027] Figure 2 It is a structural schematic diagram of an electricity price prediction device considering renewable energy provided by the present invention;

[0028] Figure 3 It is a structural schematic diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0029] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0031] Figure 1 This is a flow chart of a method for predicting electricity prices taking into account renewable energy provided by the present invention. This embodiment can be applied to determining the electricity market price under the grid connection of new energy, improving the accuracy of electricity price prediction, maintaining the stability of the power system, etc. The method can be executed by the electricity price prediction device taking into account renewable energy provided by the present invention. The device can be implemented in the form of hardware and / or software. In a specific embodiment, the device can be integrated into an electronic device. The following embodiments will be described by taking the device integrated into an electronic device as an example. Figure 1 , the method specifically comprises the following steps:

[0032] S101, determining target meteorological information of the area to be predicted, target power load on the user side, first target power generation power on the grid side, and equipment information of new energy power generation equipment.

[0033] Among them, the area to be predicted can be an area where electricity price estimation is required. The area to be predicted can be based on a certain town, a certain urban area or a certain province, or it can be other ranges. The target meteorological information can be understood as the weather information of the area to be predicted, including light intensity, wind force, light time, etc.; the target electricity load on the user side can be understood as the electricity demand of power users in the area to be predicted predicted by the load solution scheme; the first target power generation power on the grid side can be understood as the power generation capacity of the grid in the area to be predicted predicted by the grid power generation power solution scheme; the equipment information of new energy power generation equipment can be understood as the type, quantity and model of new energy power generation equipment in the area to be predicted, which is used to measure the power generation capacity of new energy power generation equipment.

[0034] Specifically, the types of new energy power generation equipment include wind power generation equipment, photovoltaic power generation equipment, etc. The quantity can be understood as the number of wind power generation equipment and / or photovoltaic power generation equipment, and the model can be understood as the identification of wind power generation equipment and / or photovoltaic power generation equipment. Different types of power generation equipment have different power generation capacities. The total power generation capacity of new energy power generation equipment can be determined based on the type, model and quantity of power generation equipment. The advantage of this setting is that accurate and comprehensive electricity price-related data can be obtained to better evaluate the electricity price in the area to be predicted.

[0035] Optionally, determining the target meteorological information of the area to be predicted includes: determining the initial meteorological information of the area to be predicted; based on predetermined meteorological data features, identifying abnormal information in the initial meteorological information to obtain abnormal meteorological information; determining whether the abnormal meteorological information meets the meteorological information update conditions; if the abnormal meteorological information does not meet the meteorological information update conditions, processing the initial meteorological information according to a preset meteorological information adjustment plan to obtain the target meteorological information; if the abnormal meteorological information meets the meteorological information update conditions, correcting the abnormal meteorological information according to the mean of the initial meteorological information, updating the initial meteorological information based on the correction result, and returning to execute the step of identifying the abnormal information in the initial meteorological information based on the predetermined meteorological data features to obtain the abnormal meteorological information.

[0036] Among them, the initial meteorological information can be understood as the weather data of the area to be predicted within a certain time period, which can be one day, three days or five days, or ten days, fifteen days or twenty days. The specific time period length is related to the acquisition rules of the initial meteorological information. However, there may be abnormal data in the initial meteorological information, such as abnormal temperature data, abnormal light intensity data, etc.; the meteorological data characteristics can be understood as the evaluation parameters used to determine whether there are abnormal data in the initial meteorological information, such as light intensity range, light intensity change mode, wind speed range, wind speed change mode, etc. The meteorological information update condition can be understood as the basis for evaluating whether the initial meteorological information can be normalized. Once there is abnormal information in the initial meteorological information, it is determined that it needs to be updated and meets the meteorological information update condition. Only the initial meteorological information without abnormal information can be normalized, that is, it does not need to be updated and does not meet the meteorological information update condition. The normalized data (i.e., the target meteorological data) has a higher standard and uniformity, which is used to determine the electricity price of the area to be predicted, which may save the time consumed by the electricity price prediction work.

[0037] The update condition of meteorological information is that there is data exceeding three standard deviations in the data of the initial meteorological information. Specifically, after obtaining the initial meteorological characteristics, the Laida criterion will be used to identify each meteorological information in the initial meteorological information according to the characteristics of the meteorological data to determine whether there is abnormal data. Assuming that the initial meteorological information follows a normal distribution, meteorological data that exceeds the preset interval is abnormal data and needs to be corrected by the mean method.

[0038] This embodiment requires that the distribution interval P(|x-μ|>3σ)≤0.0027, where x represents the initial meteorological information, which includes n meteorological data, and μ represents the mean of the initial meteorological information. x i represents the i-th meteorological data, σ represents the standard deviation of the initial meteorological information, This embodiment will use the mean value to replace the meteorological data that exceeds the interval (μ-3σ, μ+3σ), and continue to determine whether there is abnormal data in the new initial meteorological information, the determination method is as above, until there is no meteorological data exceeding (μ-3σ, μ+3σ). Further, the normalization processing method is Among them, T tj The normalized initial meteorological information is the target meteorological information, xt,j represents the initial meteorological information before normalization, that is, the initial meteorological information after abnormal processing, x j represents the mean value of the jth grid point, s j represents the standard deviation of the j-th grid point.

[0039] Optionally, determining the target power load on the user side and the first target power generation power on the grid side in the area to be predicted includes: processing historical load information on the user side within a preset time period to obtain a reference load and load change trend on the user side; determining the target power load based on the load change trend, the reference load and the electricity price forecast demand; processing the first historical power generation power information on the grid side within the preset time period to obtain a reference power generation power and power generation change trend on the grid side; determining the first target power generation power based on the electricity price forecast demand, the reference power generation power and the power generation change trend.

[0040] Among them, the preset time period can be understood as a period of time before the current moment, such as a week, a month, three months, etc. The power load or power generation power of the power grid in the future period is predicted with the latest data, which can ensure the real-time nature of the data and obtain the most accurate prediction conclusion with the least processing resources. The demand for electricity price prediction can be understood as the date or time period for which the electricity price needs to be predicted. Taking one month as an example, assuming that the current date is the 5th, the historical load information can be understood as the user-side power consumption information between the 5th of last month and the 4th of this month, the reference load can be understood as the mean or mode of the historical load information, and the load change trend can be understood as the change of the user-side power consumption in the future period determined based on the change of the daily load data in the historical load information compared to the reference load, for example, increase A1, reduce B1, remain unchanged, etc. Similarly. The first historical power generation information can be understood as the power generation information of the power grid between the 5th of last month and the 4th of this month, the reference power generation can be understood as the mean or mode of the first historical power generation information, and the power generation change trend can be understood as the change pattern of the power generation of the power grid in the future period determined based on the change of the daily power generation data in the first historical power generation information compared with the reference power generation, for example, increasing A2, decreasing B2, keeping unchanged, etc.

[0041] The advantage of this setting is that the user-side electricity consumption and the power generation capacity of the power grid in the future can be predicted based on historical data. This work is done before or in parallel with the electricity price prediction work, avoiding the need to process raw data when predicting electricity prices, reducing the workload of electricity price prediction work, saving processor data processing resources, and improving electricity price prediction efficiency.

[0042] S102: Process the target meteorological information and the equipment information to obtain a second target power generation power of the new energy power generation equipment.

[0043] The second target power generation may be understood as the power generation of the new energy power generation equipment in a certain period of time in the future or the real-time power generation of the new energy power generation equipment.

[0044] The power generation capacity of new energy power generation equipment is different under different weather conditions, and the power generation capacity of new energy power generation equipment composed of different types, models and quantities of power generation equipment is also different. Specifically, the target meteorological information and equipment information are processed to obtain the second target power generation of the new energy power generation equipment, which can be understood as determining the current power generation of the new energy power generation equipment based on the target meteorological information of the area to be predicted and the type, model and number of the new energy power generation equipment; it can also be understood as predicting the weather in the future period of the area to be predicted based on the historical target meteorological information, and determining the power generation of the new energy power generation equipment in the future period of time in combination with the type, model and number of the new energy power generation equipment.

[0045] In one embodiment, S102 may specifically include: determining the second historical power generation information of the new energy power generation equipment, wherein the second historical power generation information includes at least one candidate power generation and at least one candidate meteorological information, and the candidate meteorological information and the candidate power generation correspond one to one; determining that the candidate meteorological information with the highest matching degree with the target meteorological information in the second historical power generation information is the intermediate meteorological information; determining whether the matching degree between the intermediate meteorological information and the target meteorological information meets the preset meteorological information matching condition; if the matching degree between the intermediate meteorological information and the target meteorological information meets the preset meteorological information matching condition, determining that the candidate power generation corresponding to the intermediate meteorological information is the second target power generation.

[0046] Specifically, the second historical power generation information can be divided into time periods according to hours or days, and at least one candidate power generation and at least one candidate meteorological information are obtained. This embodiment does not limit this. Assuming that the preset meteorological information matching condition is that the matching degree between the intermediate meteorological information and the target meteorological information is higher than 80%, the candidate power generation corresponding to the candidate meteorological information with the highest matching degree with the target meteorological information in the second historical power generation information and a matching degree higher than 80% is determined as the second target power generation. The advantage of this setting is that the power generation of new energy power generation equipment with high accuracy considering weather information can be quickly obtained.

[0047] S103: Using an autoregressive mean heteroscedasticity model, the target power load, the first target power generation power and the second target power generation power are processed to obtain a target electricity price for the area to be predicted.

[0048] Among them, the autoregressive mean heteroskedasticity model is a model with multi-dimensional information processing capabilities, improving data stability and reducing data volatility, for example, the pre-trained autoregressive moving average exogenous (ARMAX)-exponential generalized autoregressive conditional heteroskedasticity exogenous (GARCHX) model. It is worth noting that the autoregressive mean heteroskedasticity model can also be an ARMAX model and a GARCHX model. The target electricity price can be understood as the electricity price of the power market in the future after considering renewable energy and weather information.

[0049] Specifically, the target electricity price of the area to be predicted is y=f(x1,x2,x3), where x1 represents the target electricity load, x2 represents the first target power generation, x3 represents the second target power generation, and f(·) represents the processing logic of the autoregressive mean heteroscedasticity model. Exemplarily, the target electricity load, the first target power generation, and the second target power generation are input into the autoregressive mean heteroscedasticity model to obtain the target electricity price of the area to be predicted.

[0050] In one embodiment, S103 may specifically include: using an autoregressive mean exogenous model to process the target power load, the first target power generation power and the second target power generation power to obtain candidate electricity prices for the area to be predicted; using an autoregressive heteroscedasticity exogenous model to adjust the candidate electricity prices to obtain the target electricity price.

[0051] Among them, the candidate electricity price can be understood as the electricity price of the area to be predicted obtained by using the autoregressive mean exogenous model (i.e. ARMAX) model alone. ARMAX can take weather information into account, and the accuracy of the candidate electricity price is improved to a certain extent, but ARMAX cannot avoid the asymmetry of load and the volatility of new energy power generation equipment. Therefore, it is necessary to use the autoregressive heteroscedastic exogenous model (i.e. GARCHX) to optimize and adjust the candidate electricity price to obtain the electricity price (i.e. target electricity price) of the area to be predicted with better accuracy and stability.

[0052] Specific, candidate electricity prices Among them, α0 represents the average coefficient, p represents the autoregressive lag order, q represents the moving average lag order, R represents the total number of meteorological data, X t,k represents the change of the kth meteorological data at time t, α i represents the first target power generation, represents the second target power generation. Further, the target power price P = g(P t ), g(·) represents the processing logic of the GARCHX model.

[0053] The values ​​of p and q are related to the autocorrelation function (ACF) and partial autocorrelation function (PACF) of the electricity price series. Specifically, the partial autocorrelation Among them, r k represents the estimated value of the autocorrelation coefficient at the k-order lag, r1 represents the estimated value of the autocorrelation coefficient at the 1-order lag, and Δ represents the logical correlation variable of the partial autocorrelation, which is related to the restriction conditions, p, q and correlation relationship of the time series.

[0054] For example, the autocorrelation function of the electricity price time series shows different forms of attenuation with the increase of the lag order, including exponential attenuation and sine wave attenuation, and gradually tends to zero. The partial autocorrelation function tends to zero after k>p, showing p-order truncation, and the parameter p can be identified based on the truncation of the partial autocorrelation function. The autocorrelation function tends to 0 after k>q, showing q-order truncation, and the parameter q can be identified based on the truncation of the autocorrelation function.

[0055] In another embodiment, S103 may specifically include: determining historical electricity price information of the area to be predicted, wherein the historical electricity price information includes at least one electricity price data and at least one time identifier, and the time identifier and the electricity price data correspond one to one; using an autoregressive mean exogenous model to process the target meteorological information and the historical electricity price information to obtain the electricity price residual of the area to be predicted; using an autoregressive heteroscedastic exogenous model to process the electricity price residual, the first target power generation power and the second target power generation power to obtain the target electricity price.

[0056] The higher the order of the ARMAX model, the stronger its ability to describe the object sample, but the higher the order, the more parameters there are, which is prone to overfitting. Among them, the electricity price residual can be understood as the error sequence after determining the appropriate order and fitting the ARMAX model. For example, the Akaike information criterion (AIC) and the Bayesian information criterion (BIC) are used to determine the order of the ARMAX model, and the error sequence obtained after fitting the ARMAX model is used to improve the accuracy of electricity price prediction.

[0057] Specifically, the target electricity price of the area to be predicted is E=O(S1, S2, S3, S4), where S1 represents the target electricity load, S2 represents the first target power generation power, S3 represents the second target power generation power, S4 represents the electricity price residual, and O(·) represents the processing logic of the GARCHX model.

[0058] It is worth noting that GARCHX can also determine the target electricity price in another way: target electricity price Ex = KT + β1*X1 + β2*X2, where KT represents the conventional demand variable of the power system, which is the variable obtained by integrating the load information on the user side and the power generation power on the grid side. β1 represents the first new energy coefficient, X1 represents the percentage of wind power generation in the total power generation, β2 represents the second new energy coefficient, and X2 represents the percentage of photovoltaic power generation in the total power generation.

[0059] The technical solution of this embodiment integrates the environmental information (i.e., meteorological information) of the predicted area and the equipment information of the new energy power generation equipment to obtain the accurate power generation of the new energy power generation equipment, and processes the target power load, the first target power generation and the second target power generation through the autoregressive average heteroscedasticity model. The autoregressive average heteroscedasticity model can not only consider the autocorrelation of the time series and the influence of external factors, but also suppress the impact of the volatility of load information and new energy power generation equipment on electricity prices, improve the accuracy of the predicted electricity price, and improve the profitability of new energy enterprises and the stability of the power system. It solves the problems that new energy power generation equipment such as wind power and photovoltaic power generation equipment has strong instability and volatility, there is an error between the power generation of new energy power generation equipment determined according to historical data and the actual output power of new energy power generation equipment, the accuracy of the predicted electricity price is low, and inappropriate pricing methods will reduce the profitability of new energy enterprises and even affect the stability of the power system.

[0060] Figure 2 Schematic diagram of the structure of a device for predicting electricity prices taking renewable energy into consideration provided by the present invention. Figure 2 As shown, the device includes: an acquisition module 201, a determination module 202 and an execution module 203.

[0061] The acquisition module 201 is used to determine the target meteorological information of the area to be predicted, the target power load on the user side, the first target power generation power on the grid side and the equipment information of the new energy power generation equipment.

[0062] The determination module 202 is used to process the target meteorological information and the equipment information to obtain the second target power generation of the new energy power generation equipment.

[0063] The execution module 203 is used to process the target power load, the first target power generation power and the second target power generation power by using the autoregressive mean heteroscedasticity model to obtain the target electricity price of the area to be predicted.

[0064] Optionally, the acquisition module 201 is specifically used to determine the initial meteorological information of the area to be predicted; based on predetermined meteorological data features, identify abnormal information in the initial meteorological information to obtain abnormal meteorological information; determine whether the abnormal meteorological information meets the meteorological information update conditions; if the abnormal meteorological information does not meet the meteorological information update conditions, process the initial meteorological information according to a preset meteorological information adjustment plan to obtain target meteorological information; if the abnormal meteorological information meets the meteorological information update conditions, correct the abnormal meteorological information according to the mean of the initial meteorological information, update the initial meteorological information based on the correction result, and return to execute the step of identifying the abnormal information in the initial meteorological information based on the predetermined meteorological data features to obtain abnormal meteorological information.

[0065] Optionally, the acquisition module 201 is specifically used to process the historical load information on the user side within a preset time period to obtain the reference load and load change trend on the user side; determine the target power load based on the load change trend, the reference load and the electricity price forecast demand; process the first historical power generation information on the grid side within the preset time period to obtain the reference power generation and power generation change trend on the grid side; determine the first target power generation based on the electricity price forecast demand, the reference power generation and the power generation change trend.

[0066] Optionally, determination module 202 is specifically used to determine second historical power generation information of the new energy power generation equipment, wherein the second historical power generation information includes at least one candidate power generation and at least one candidate meteorological information, and the candidate meteorological information and the candidate power generation correspond one to one; determine that the candidate meteorological information in the second historical power generation information that has the highest matching degree with the target meteorological information is the intermediate meteorological information; determine whether the matching degree between the intermediate meteorological information and the target meteorological information meets the preset meteorological information matching condition; if the matching degree between the intermediate meteorological information and the target meteorological information meets the preset meteorological information matching condition, determine that the candidate power generation corresponding to the intermediate meteorological information is the second target power generation.

[0067] Optionally, execution module 203 is specifically used to use an autoregressive mean exogenous model to process the target power load, the first target power generation power and the second target power generation power to obtain candidate electricity prices for the area to be predicted; and use an autoregressive heteroscedasticity exogenous model to adjust the candidate electricity prices to obtain the target electricity price.

[0068] Optionally, execution module 203 is specifically used to determine historical electricity price information of the area to be predicted, wherein the historical electricity price information includes at least one electricity price data and at least one time identifier, and the time identifier and the electricity price data correspond one to one; use an autoregressive mean exogenous model to process the target meteorological information and historical electricity price information to obtain the electricity price residual of the area to be predicted; use an autoregressive heteroscedasticity exogenous model to process the electricity price residual, the first target power generation power and the second target power generation power to obtain the target electricity price.

[0069] The electricity price prediction device considering renewable energy provided in this embodiment can execute the electricity price prediction method considering renewable energy provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0070] Figure 3 : is a schematic diagram of the structure of an electronic device provided by the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0071] like Figure 3 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (also called random access memory, RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0072] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0073] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a method for predicting electricity prices considering renewable energy.

[0074] In some embodiments, the electricity price prediction method considering renewable energy can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the electricity price prediction method considering renewable energy described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute the electricity price prediction method considering renewable energy by any other appropriate means (for example, by means of firmware).

[0075] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0076] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0077] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0078] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0079] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server) or a computing system that includes middleware components (e.g., an application server) or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein) or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0080] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0081] In one embodiment, the present invention further includes a computer program product, the computer program product includes a computer program, and when the computer program is executed by a processor, the method for predicting electricity prices considering renewable energy according to any embodiment of the present invention is implemented.

[0082] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present invention, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0083] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0084] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting electricity prices considering renewable energy, characterized in that: include: Determine the target meteorological information of the area to be predicted, the target power load on the user side, the first target power generation power on the grid side, and the equipment information of the new energy power generation equipment; Processing the target meteorological information and the equipment information to obtain a second target power generation power of the new energy power generation equipment; The target power load, the first target power generation power and the second target power generation power are processed by using an autoregressive mean heteroscedasticity model to obtain a target electricity price for the area to be predicted.

2. The method according to claim 1, characterized in that Determining the target meteorological information of the area to be predicted includes: Determining the initial meteorological information of the area to be predicted; Based on predetermined meteorological data features, abnormal information in the initial meteorological information is identified to obtain abnormal meteorological information; Determining whether the abnormal meteorological information meets the meteorological information update condition; If the abnormal meteorological information does not meet the meteorological information update condition, the initial meteorological information is processed according to a preset meteorological information adjustment scheme to obtain the target meteorological information; If the abnormal meteorological information meets the meteorological information update condition, the abnormal meteorological information is corrected according to the mean value of the initial meteorological information, the initial meteorological information is updated based on the correction result, and the step of returning to execute the abnormal information in the initial meteorological information based on the predetermined meteorological data features to obtain the abnormal meteorological information.

3. The method according to claim 1, characterized in that The step of determining a target power load on the user side of the region to be predicted and a first target power generation power on the grid side includes: Process the historical load information on the user side within a preset time period to obtain the reference load and load change trend on the user side; Determining the target power load based on the load change trend, the reference load and the electricity price forecast demand; Processing the first historical power generation information on the grid side within a preset time period to obtain a reference power generation and a power generation change trend on the grid side; The first target power generation is determined based on the electricity price forecast demand, the reference power generation and the power generation change trend.

4. The method according to claim 1, characterized in that: The processing of the target meteorological information and the equipment information to obtain a second target power generation power of the new energy power generation equipment includes: Determine second historical power generation information of the new energy power generation equipment, wherein the second historical power generation information includes at least one candidate power generation and at least one candidate meteorological information, and the candidate meteorological information and the candidate power generation correspond one to one; Determine the candidate meteorological information with the highest matching degree with the target meteorological information in the second historical power generation information as the intermediate meteorological information; Determining whether the matching degree between the intermediate meteorological information and the target meteorological information satisfies a preset meteorological information matching condition; If the matching degree between the intermediate meteorological information and the target meteorological information satisfies the preset meteorological information matching condition, it is determined that the candidate power generation corresponding to the intermediate meteorological information is the second target power generation.

5. The method according to claim 1, characterized in that The method of using the autoregressive mean heteroscedastic model to process the target power load, the first target power generation power, and the second target power generation power to obtain the target electricity price of the area to be predicted includes: The target power load, the first target power generation power and the second target power generation power are processed by using an autoregressive mean exogenous model to obtain a candidate power price for the area to be predicted; The candidate electricity price is adjusted by using an autoregressive heteroskedastic exogenous model to obtain the target electricity price.

6. The method according to claim 1, characterized in that The method of using the autoregressive mean heteroscedastic model to process the target power load, the first target power generation power, and the second target power generation power to obtain the target electricity price of the area to be predicted includes: Determine the historical electricity price information of the area to be predicted, wherein the historical electricity price information includes at least one electricity price data and at least one time mark, and the time mark and the electricity price data correspond one to one; The target meteorological information and the historical electricity price information are processed by using an autoregressive mean exogenous model to obtain the electricity price residual of the area to be predicted; The target electricity price is obtained by processing the electricity price residual, the first target power generation and the second target power generation using an autoregressive heteroskedastic exogenous model.

7. An electricity price prediction device considering renewable energy, characterized in that: The method for predicting electricity prices considering renewable energy as claimed in any one of claims 1 to 6, wherein the device for predicting electricity prices considering renewable energy comprises: An acquisition module is used to determine target meteorological information of the area to be predicted, target power load on the user side, first target power generation power on the grid side, and equipment information of new energy power generation equipment; A determination module, configured to process the target meteorological information and the equipment information to obtain a second target power generation power of the new energy power generation equipment; The execution module is used to process the target power load, the first target power generation power and the second target power generation power by using an autoregressive mean heteroscedasticity model to obtain a target electricity price for the area to be predicted.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the electricity price prediction method considering renewable energy as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the electricity price prediction method considering renewable energy as described in any one of claims 1 to 6 when executed.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the method for predicting electricity prices taking renewable energy into consideration according to any one of claims 1 to 6.

Images