Renewable energy monthly generating capacity prediction method and related device

Abstract

The invention discloses a renewable energy monthly generating capacity prediction method and a related device. The method comprises the following steps: acquiring first renewable energy generating capacity value data in a first historical time period, second renewable energy generating capacity data in a second historical time period and third renewable energy generating capacity data in a third historical time period of a target area, predicting a first renewable energy monthly generating capacity value corresponding to the target region in the target month based on the first renewable energy generating capacity value data, and predicting a second renewable energy monthly generating capacity value and a third renewable energy monthly generating capacity value at the same time, and determining a target renewable energy monthly generating capacity value corresponding to the target region in the target month based on the first renewable energy monthly generating capacity value, the second renewable energy monthly generating capacity value and the third renewable energy monthly generating capacity value. By adopting the embodiment of the invention, the renewable energy generating capacity can be accurately predicted.

Description

Technical Field

[0001] This invention relates to the field of power generation forecasting technology, and in particular to a method and related apparatus for forecasting monthly power generation values ​​of renewable energy. Background Technology

[0002] As the global energy structure transitions towards a clean and low-carbon model, the proportion of renewable energy in the power system continues to increase, becoming an important component of energy supply. Renewable energy power generation relies on natural resources such as solar, wind, and hydropower. Its output is affected by various factors such as meteorological conditions and terrain features, exhibiting obvious intermittency, volatility, and uncertainty. Accurately predicting the monthly power generation of renewable energy is of great significance for the safe and stable operation of the power system, the formulation of dispatch plans, and the optimal allocation of energy resources. However, it is currently impossible to accurately predict the power generation of renewable energy. Therefore, how to accurately predict the power generation of renewable energy is an urgent problem to be solved. Summary of the Invention

[0003] This application provides a method and related apparatus for predicting monthly renewable energy power generation, which can accurately predict renewable energy power generation.

[0004] In a first aspect, embodiments of this application provide a method for predicting monthly renewable energy generation values, including: Acquire data on the first renewable energy power generation value of the target region within a first historical time period, the second renewable energy power generation data within a second historical time period, and the third renewable energy power generation data within a third historical time period; the first historical time period includes the second historical time period, and the second historical time period includes the third historical time period. Based on the first renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the first renewable energy monthly power generation value; Based on the second renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the second renewable energy monthly power generation value; Based on the third renewable energy power generation data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the third renewable energy monthly power generation value; The target renewable energy monthly power generation value for the target region in the target month is determined based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value.

[0005] Secondly, embodiments of this application provide a device for predicting monthly renewable energy generation values, the device comprising: an acquisition unit and a processing unit; The acquisition unit is used to acquire data on the first renewable energy power generation value of the target region within a first historical time period, data on the second renewable energy power generation within a second historical time period, and data on the third renewable energy power generation within a third historical time period; the first historical time period includes the second historical time period, and the second historical time period includes the third historical time period. The processing unit is used to predict the monthly renewable energy power generation value of the target region in the target month based on the first renewable energy power generation value data, and obtain the first renewable energy monthly power generation value. Based on the second renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the second renewable energy monthly power generation value; Based on the third renewable energy power generation data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the third renewable energy monthly power generation value; The target renewable energy monthly power generation value for the target region in the target month is determined based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value.

[0006] Thirdly, embodiments of the present invention provide an electronic device, including: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor to cause the electronic device to perform the method as described in the first aspect.

[0007] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that is executed by a processor to implement the method as described in the first aspect.

[0008] Fifthly, embodiments of the present invention provide a computer program product including a non-transitory computer-readable storage medium storing a computer program, such that a computer performs the method as described in the first aspect.

[0009] Implementing the embodiments of the present invention has the following beneficial effects: As can be seen, the renewable energy monthly power generation prediction method described in this embodiment of the invention first acquires the first renewable energy power generation data for a target region within a first historical time period, the second renewable energy power generation data within a second historical time period, and the third renewable energy power generation data within a third historical time period, wherein the first historical time period includes the second historical time period, and the second historical time period includes the third historical time period. Then, based on the first renewable energy power generation data, the method predicts the renewable energy monthly power generation value for the target region in the target month to obtain the first renewable energy monthly power generation value. Based on the second renewable energy power generation data, the method predicts the renewable energy monthly power generation value for the target region in the target month to obtain the second renewable energy monthly power generation value. Based on the third renewable energy power generation data, the method predicts the renewable energy monthly power generation value for the target region in the target month to obtain the third renewable energy monthly power generation value. Finally, based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value, the method determines the target renewable energy monthly power generation value for the target region in the target month, thus enabling accurate prediction of renewable energy power generation. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of this application or the background art, the accompanying drawings used in the embodiments of this application or the background art will be described below.

[0011] Figure 1 This is a flowchart of a method for predicting monthly renewable energy power generation provided in the embodiments of this application; Figure 2 This is a flowchart illustrating how to determine the monthly power generation value of a first renewable energy source, as provided in an embodiment of this application. Figure 3 This is a flowchart illustrating how to determine the monthly power generation value of a first renewable energy source corresponding to solar energy, as provided in an embodiment of this application. Figure 4 This is a flowchart illustrating how to determine the monthly power generation value of a first renewable energy source corresponding to wind power, as provided in an embodiment of this application. Figure 5 This is a flowchart provided in an embodiment of the present application for determining the monthly power generation value of a first renewable energy source corresponding to hydropower; Figure 6 This is a flowchart illustrating how to determine a target monthly renewable energy generation value according to an embodiment of this application; Figure 7 This is a schematic diagram of the structure of a renewable energy monthly power generation prediction device provided in the embodiments of this application; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0012] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present application.

[0013] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0014] In this document, the term "implementation" means that a specific feature, structure, or characteristic described in connection with an implementation may be included in at least one implementation of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same implementation, nor is it a separate or alternative implementation mutually exclusive with other implementations. It will be explicitly and implicitly understood by those skilled in the art that the implementations described herein can be combined with other implementations.

[0015] Please see Figure 1 , Figure 1 This is a flowchart of a method for predicting monthly renewable energy generation provided in this application, including but not limited to the following steps: S101: Obtain the power generation data of the first renewable energy source in the first historical time period, the power generation data of the second renewable energy source in the second historical time period, and the power generation data of the third renewable energy source in the third historical time period for the target region.

[0016] In this embodiment, renewable energy refers to energy that can be continuously regenerated and sustainably utilized in nature. Common types include solar energy, wind energy, hydropower, biomass energy, geothermal energy, etc. These energy sources do not decrease with use and are environmentally friendly.

[0017] Solar power generation directly converts solar radiation into electricity using solar panels, or it uses solar collectors to heat water and generate steam, which drives a turbine to power a generator. The former is called photovoltaic (PV) power generation, and the latter is called solar thermal (CSP) power generation. Wind power generation uses wind turbines to capture wind energy, converting the kinetic energy of the wind into mechanical energy, which is then converted into electricity by a generator. Large-scale power generation is typically achieved through the coordinated operation of multiple wind turbines in a wind farm. Hydropower generation utilizes the potential and kinetic energy of flowing water. Hydropower stations are built to intercept water flow, creating a water level difference. The water flow impacts a turbine, which drives a generator to convert the water energy into electricity. This includes conventional hydropower stations and pumped-storage hydropower stations. Biomass power generation utilizes biomass resources such as crop straw, forestry waste, livestock manure, and household waste. It generates heat or gas through direct combustion, gasification, or fermentation, which then drives a generator to produce electricity. Biomass can also be converted into biofuel for power generation. Geothermal power generation involves extracting underground hot water or steam resources, using their heat energy to heat a working medium to produce high-pressure steam, which drives a steam turbine to generate electricity. It is suitable for areas rich in geothermal energy resources.

[0018] In this embodiment, the first historical time period includes the second historical time period, and the second historical time period includes the third historical time period. The three historical time periods are hierarchically contained within each other, with the scope decreasing sequentially. The first historical time period has the widest time span, completely encompassing the entire time of the second historical time period, which in turn completely encompasses the entire time of the third historical time period.

[0019] It should be explained that in this embodiment, a historical time period can correspond to a time window, namely a long-term window, a medium-term window, and a short-term window. The long-term window can be the past 24 months, the medium-term window can be the past 12 months, and the short-term window can be the past 6 months. In this embodiment, a bidirectional long short-term memory network can be used to capture forward and backward time dependencies. Specifically, by utilizing the characteristics of the bidirectional long short-term memory network model, the positive and negative dependencies of the monthly power generation data in the first, second, and third historical time periods are simultaneously mined. This considers both the impact of earlier historical power generation data on subsequent data and the correlation feedback of later historical power generation data on previous data, comprehensively capturing the time-related characteristics such as long-term, medium-term, and recent power generation trends, fluctuation patterns, and seasonal changes hidden in historical data of different time spans, making the process of predicting the power generation of the target month based on various historical data more accurate.

[0020] The primary renewable energy generation data represents the total electricity generated by all renewable energy sources in the target region over the broadest historical time period. Covering the largest time span, this data provides comprehensive historical renewable energy generation information, reflecting the scale and overall trend of renewable energy generation in the region over a longer period, and offering a long-term reference for subsequent forecasts.

[0021] The second renewable energy generation data refers to the total amount of electricity actually generated by various renewable energy sources in the target region during the second historical period, which falls within the middle of the scope. The second renewable energy generation data covers a shorter time span than the first historical period, focusing on a relatively recent period. This data reflects the changes in renewable energy generation in the region during the medium term, filtering out historical information that may no longer be of reference value due to its age.

[0022] The third renewable energy generation data refers to the total electricity generated by all renewable energy sources in the target region within the smallest historical time period. Covering the shortest time span, this data represents the most recent historical generation information among the three data sets, accurately reflecting the recent generation status and latest trends of renewable energy in the region, and better aligning with current energy production conditions.

[0023] S102: Based on the first renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the first renewable energy monthly power generation value.

[0024] In this embodiment, n historical monthly renewable energy power generation values ​​and the recording time corresponding to each value can be extracted from the first renewable energy power generation value data. Then, a statistical method is used to perform linear fitting on these n historical monthly power generation values ​​and their corresponding recording times to obtain a linear curve of renewable energy power generation value change that reflects the historical power generation change trend. Finally, based on the trend characteristics of the renewable energy power generation value change line, the first renewable energy monthly power generation value corresponding to the target month is calculated.

[0025] S103: Based on the second renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the second renewable energy monthly power generation value.

[0026] In this embodiment, multiple historical monthly renewable energy power generation values ​​and the recording time corresponding to each value can be extracted from the second renewable energy power generation value data. By using statistical methods to perform linear fitting on these historical monthly power generation values ​​and their recording times, a linear curve reflecting the power generation change trend within the second historical time period can be obtained. Then, the second renewable energy monthly power generation value corresponding to the target month can be calculated based on this linear curve.

[0027] S104: Based on the third renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the third renewable energy monthly power generation value.

[0028] In this embodiment, multiple historical monthly renewable energy generation values ​​and the recording time corresponding to each value can be extracted from the third renewable energy generation value data. Similarly, a statistical method is used to perform linear fitting on these historical monthly generation values ​​and their recording times to obtain a linear curve of renewable energy generation value change that fits the third historical time period. Finally, the third renewable energy monthly generation value corresponding to the target month is determined based on this linear curve.

[0029] S105: Determine the target renewable energy monthly power generation value for the target region in the target month based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value.

[0030] In this embodiment, the first historical average monthly renewable energy generation value within the first historical time period, the second historical average monthly renewable energy generation value within the second historical time period, and the third historical average monthly renewable energy generation value within the third historical time period are calculated respectively. Then, the difference between the first historical average monthly renewable energy generation value and the first renewable energy monthly power generation value is calculated to obtain the first difference value; the difference between the second historical average monthly renewable energy generation value and the second renewable energy monthly power generation value is calculated to obtain the second difference value; and the difference between the third historical average monthly renewable energy generation value and the third renewable energy monthly power generation value is calculated to obtain the third difference value. The first [value] is determined according to the rule that the smaller the difference, the greater the weight. The monthly renewable energy power generation value is assigned a first weight, a second weight, and a third weight. Then, the monthly renewable energy power generation value is multiplied by the first weight, the second by the second weight, and the third by the third weight to obtain a reference monthly renewable energy power generation value. Next, the installed renewable energy capacity for the target region in the target month is obtained, and an optimization factor corresponding to this installed capacity is determined. Finally, this optimization factor is used to optimize the reference monthly renewable energy power generation value to obtain the target monthly renewable energy power generation value for the target region in the target month.

[0031] As can be seen, by collecting three types of historical renewable energy power generation data from different time spans and layers in the target region, and independently predicting the power generation of the target month based on each type of data, three different predicted values ​​can be obtained. This approach can make full use of historical power generation information from the long term, medium term, and short term. It ensures the stability of the prediction by leveraging the overall trend reflected by the long-term data, improves the adaptability of the prediction by filtering out outdated and potentially invalid information through the medium term data, and enhances the timeliness of the prediction by capturing the latest power generation change trends through the short term data. Finally, by integrating the three predicted values ​​to determine the final target value, the approach effectively reduces the possible bias in predictions based on data from a single time period, reduces the impact of accidental factors on the prediction results, and makes the monthly renewable energy power generation prediction for the target month more comprehensive, accurate, and in line with the actual situation.

[0032] Please see Figure 2 , Figure 2 This application provides a flowchart for determining the monthly power generation value of a first renewable energy source, including but not limited to the following steps: S201: Determine the n historical monthly renewable energy power generation values ​​corresponding to the first renewable energy power generation value data and the recording time of the n historical monthly renewable energy power generation values ​​corresponding to the n historical monthly renewable energy power generation values.

[0033] In this embodiment, each historical monthly renewable energy power generation value corresponds to a historical monthly renewable energy power generation value recording time, where n is a positive integer.

[0034] Determining the n historical monthly renewable energy power generation values ​​recorded in the first renewable energy power generation value data, as well as the recording times of the n historical monthly renewable energy power generation values ​​corresponding to the n historical monthly renewable energy power generation values, can transform the scattered historical power generation data into a one-to-one corresponding regular data form. This clearly defines the time corresponding to each historical monthly power generation value, avoids analytical biases caused by data and time misalignment, and provides accurate and effective basic data support for subsequent linear fitting based on the correlation between time and power generation values ​​and for capturing historical power generation change trends.

[0035] S202: Based on the n historical monthly renewable energy power generation values ​​and the recording time of the n historical monthly renewable energy power generation values, a straight line is fitted to obtain the change line of renewable energy power generation values.

[0036] In this embodiment, a straight line is fitted based on the n historical monthly renewable energy power generation values ​​and the recording times of the n historical monthly renewable energy power generation values. The fitting process first uses the n historical monthly renewable energy power generation values ​​as dependent variables and the corresponding n recording times as independent variables to construct a data set corresponding to time and power generation values. Then, statistical fitting algorithms such as the least squares method are used to calculate a straight line that can best fit all data points. The slope of this straight line reflects the rate of change of historical power generation values ​​over time, and the intercept corresponds to the power generation reference value at a specific time base point. By continuously optimizing the straight line parameters, the sum of squares of the vertical distances from each data point to the straight line is minimized, and finally, a straight line representing the change pattern of renewable energy power generation values ​​that can comprehensively characterize the time change pattern of the n historical data is obtained.

[0037] S203: Determine the monthly renewable energy power generation value corresponding to the target month based on the linear change of the renewable energy power generation value.

[0038] In this embodiment, when determining the first monthly renewable energy power generation value corresponding to the target month based on the linear change in renewable energy power generation value, it is necessary to first adopt a corresponding adjustment method according to the energy type. If the renewable energy type is solar energy, the value corresponding to the target month is first found from the linear change as the first reference monthly renewable energy power generation value. Then, the average latitude of the target region and the average monthly sunshine duration of the target month are obtained, and the corresponding first adjustment parameter and second adjustment parameter are determined respectively. The first reference monthly renewable energy power generation value is adjusted using these two parameters to obtain the result. If the renewable energy type is wind energy, the value corresponding to the target month is extracted from the linear change as the second reference monthly renewable energy power generation value. The average monthly wind speed of the target month is obtained and the corresponding third adjustment parameter is determined. The second reference monthly renewable energy power generation value is adjusted using this parameter to obtain the result. If the renewable energy type is hydropower, the third reference monthly renewable energy power generation value corresponding to the target month is first obtained from the linear change. The average monthly precipitation and the average monthly ice-covered basin area of ​​the target month are collected to determine the corresponding fourth adjustment parameter and fifth adjustment parameter. The third reference monthly renewable energy power generation value is adjusted using these two parameters to obtain the final first monthly renewable energy power generation value. In this embodiment, solar, wind and hydropower are mainly used as examples to describe the monthly power generation value of renewable energy. In actual operation, the monthly power generation value of renewable energy corresponding to other renewable energy types can also be predicted.

[0039] As can be seen, the process first extracts n corresponding historical monthly renewable energy power generation values ​​and recording times from the primary renewable energy power generation data to ensure that the data used for analysis is well-organized and logically clear. Then, through linear fitting, the scattered historical data is transformed into a straight line that reflects the trend of power generation changes over time, intuitively presenting the long-term power generation change pattern. Finally, the power generation value of the target month is determined based on this straight line. The entire process relies on real historical data and clear trend modeling, which avoids the bias caused by single data or subjective judgment, and can reasonably predict future power generation through trend extension, making the prediction process more logical and reliable. This effectively improves the prediction accuracy of the primary renewable energy monthly power generation value corresponding to the target month.

[0040] Please see Figure 3 , Figure 3 This application provides a flowchart for determining the monthly power generation value of a first renewable energy source corresponding to solar energy, including but not limited to the following steps: S301: Determine the monthly renewable energy power generation value corresponding to the target month on the linear curve of renewable energy power generation value change, and obtain the first reference monthly renewable energy power generation value.

[0041] In this embodiment, the specific time position of the target month is first determined by using the linear change line of renewable energy power generation value obtained by fitting historical data. Then, according to the pattern of power generation change over time shown by the linear change line, the monthly renewable energy power generation value corresponding to the time position of the target month is found on the linear line. This value matched from the linear change line is the first reference monthly renewable energy power generation value.

[0042] S302: Obtain the average latitude corresponding to the target region.

[0043] In this embodiment, the average latitude directly affects the distribution of solar altitude angle and sunshine duration. The lower the latitude, the larger the solar altitude angle is, the shorter the path of solar radiation through the atmosphere, the less energy loss, and the higher the intensity of solar radiation reaching the ground. The higher the latitude, the smaller the solar altitude angle and the relatively weaker the radiation intensity. At the same time, latitude also affects the variation of sunshine duration in different seasons. These factors directly affect the power generation efficiency and total power generation of solar panels.

[0044] S303: Determine the first adjustment parameter corresponding to the average latitude.

[0045] In this embodiment, a knowledge graph containing the correlation between different latitude ranges, solar altitude angle, solar radiation intensity, and solar power generation efficiency can be constructed first. This graph integrates the mapping patterns between latitude and solar power generation-related factors in massive historical data, and clarifies the range of solar altitude angle, radiation intensity level, and corresponding power generation efficiency correction coefficient corresponding to different average latitudes. Then, the average latitude of the target region is used as the search condition to match the corresponding latitude range in the knowledge graph, and the core information such as the influence weight of solar radiation intensity and the power generation efficiency correction ratio associated with the range is extracted. Then, the information is integrated and calculated through the preset calculation logic in the graph, and finally, a first adjustment parameter that can accurately adapt to the characteristics of solar energy resources at that latitude is obtained, ensuring that the parameter can effectively correct the impact of latitude differences on power generation prediction.

[0046] It should be explained that the construction of a knowledge graph can also be achieved by first collecting monthly net electricity generation data from multiple countries and energy types, performing field cleaning, missing value imputation, and normalization to eliminate dimensional differences, and supplementing national attribute data and energy type features. Then, a graph database is used to define three types of core nodes: national nodes include attributes such as geographical location and economic level; energy type nodes distinguish between renewable energy and traditional energy; and electricity generation nodes record electricity generation values ​​within a specific time period. Next, two types of core relationships are designed: production and related values, representing a country producing a certain type of energy and related electricity generation nodes and specific values, respectively. Then, the node features are encoded, and multi-dimensional vectors are used to integrate information such as node type, node name, and normalized attribute values. Finally, based on the actual prediction target, a query language is used to extract a local subgraph containing target-related nodes and relationships, balancing computational efficiency and information integrity, thus completing the construction of a structured knowledge graph. When determining the first adjustment parameter corresponding to the average latitude, the core work is carried out by first using the constructed knowledge graph. This knowledge graph defines national nodes, renewable energy type nodes, and power generation nodes with geographical location attributes through a graph database, and establishes a structured relationship between the three through production and related numerical values. The node features have encoded national related attribute information. First, using the target region and solar energy as search criteria, a local subgraph containing the region's geographical location (average latitude) and historical solar power generation data is extracted using query language to ensure the relevance and completeness of the information obtained. Next, a multi-layer graph attention network is used to introduce edge relationship features when calculating the attention coefficient, mining the potential correlation between the target region's average latitude and historical solar power generation in the subgraph. At the same time, implicit information such as solar radiation intensity and power generation efficiency corresponding to the region's historical average latitude is combined. The features of neighboring nodes are integrated through a node update formula, and then a graph feature vector is obtained through global average pooling. Subsequently, the graph features are mapped to the same space with the temporal features captured by a bidirectional long short-term memory network. The attention weights of the two are calculated through a multi-head self-attention mechanism to complete feature fusion. Finally, based on the model training results optimized by the loss function and the fused spatiotemporal features, the first adjustment parameter adapted to the average latitude of the target region is output.

[0047] S304: Obtain the average monthly sunshine duration of the target region in the target month.

[0048] In this embodiment, the average monthly sunshine duration directly determines the effective power generation time of the solar panel and is a key factor affecting the amount of solar power generated. The longer the sunshine duration, the longer the solar panel receives solar radiation and performs photoelectric conversion, the more electricity is generated per unit time, and the higher the corresponding monthly renewable energy power generation value. Conversely, the shorter the sunshine duration, the less effective power generation time, resulting in a corresponding decrease in power generation.

[0049] S305: Determine the second adjustment parameter corresponding to the monthly average sunshine duration.

[0050] In this embodiment, when determining the second adjustment parameter corresponding to the monthly average sunshine duration, we can first use a knowledge graph to retrieve historical statistics on the monthly average sunshine duration for the same period as the target month in the target region, as well as the corresponding power generation fluctuation patterns. This process relies on the temporal correlation of meteorological attributes of the target region in the graph. Then, based on the correlation between sunshine duration intervals and power generation efficiency defined in the knowledge graph, we can clarify the specific interval to which the predicted sunshine duration for the target month belongs. Finally, we use the mapping rules between sunshine duration and adjustment coefficients stored in the graph, or a historical fitting model, to perform calculations. The core is to transform the positive correlation between sunshine duration and solar power generation in the knowledge graph into quantifiable adjustment coefficients, ultimately obtaining the second adjustment parameter.

[0051] When determining the second adjustment parameter corresponding to the monthly average sunshine duration, the core work can also be carried out by relying on the existing knowledge graph. This knowledge graph defines national nodes, renewable energy type nodes, and power generation nodes with geographical location attributes through a graph database, and establishes a structured relationship between the three through production and related numerical values. The node features have encoded national related attributes and sunshine duration related information. First, using the target region, solar energy, and target month as search criteria, a local subgraph containing the average monthly sunshine duration and corresponding historical solar power generation data for the target month in the region is extracted using query language. This ensures the relevance and completeness of the information obtained. Next, a multi-layer graph attention network is used, incorporating edge relationship features when calculating the attention coefficient to uncover the potential correlation between the average monthly sunshine duration of the target month and historical solar power generation in the subgraph. Simultaneously, implicit information such as the total solar radiation received and changes in power generation efficiency corresponding to the sunshine duration is combined. The features of neighboring nodes are integrated through a node update formula, and then a graph feature vector is obtained through global average pooling. Subsequently, this graph feature is mapped to the same space with the temporal features captured by a bidirectional long short-term memory network. The attention weights of the two are calculated through a multi-head self-attention mechanism, and feature fusion is completed. Finally, based on the model training results optimized by a loss function and the fused spatiotemporal features, a second adjustment parameter adapted to the average monthly sunshine duration of the target month in the target region is output to ensure that this parameter accurately reflects the impact of sunshine duration on solar power generation.

[0052] S306: Adjust the first reference monthly renewable energy power generation value based on the first adjustment parameter and the second adjustment parameter to obtain the first monthly renewable energy power generation value.

[0053] In this embodiment, the monthly power generation value of the first renewable energy source is calculated according to the following formula: Monthly power generation value of the first renewable energy source = monthly power generation value of the first reference renewable energy source × (1 + first adjustment parameter) × (1 + second adjustment parameter); According to the above formula, the first reference monthly renewable energy power generation value can be adjusted based on the first adjustment parameter and the second adjustment parameter to obtain the first monthly renewable energy power generation value.

[0054] As can be seen, the first reference monthly renewable energy power generation value is obtained by using the linear change of renewable energy power generation value, providing a basic benchmark for prediction. Then, the key factors affecting solar power generation, namely the average latitude of the target region and the average monthly sunshine duration of the target month, are specifically obtained. The corresponding first adjustment parameter and second adjustment parameter are determined respectively, which fully consider the differences in solar radiation intensity caused by latitude and the differences in effective power generation time caused by sunshine duration. By comprehensively correcting the first reference value through the two adjustment parameters, the deviation caused by single trend prediction can be effectively offset, making the final first monthly renewable energy power generation value more in line with the actual influencing factors of solar power generation, thereby significantly improving the accuracy and reliability of the monthly renewable energy power generation value prediction.

[0055] Please see Figure 4 , Figure 4 This application provides a flowchart for determining the monthly power generation value of a first renewable energy source corresponding to wind power, including but not limited to the following steps: S401: Determine the monthly renewable energy power generation value corresponding to the target month on the linear curve of renewable energy power generation value change, and obtain the second reference monthly renewable energy power generation value.

[0056] In this embodiment, based on the linear change of renewable energy power generation value obtained by fitting historical data, the specific time position of the target month is first determined. Then, according to the pattern of power generation change over time shown by the linear change, the monthly renewable energy power generation value corresponding to the time of the target month is matched on the linear change. This value obtained from the linear change is the second reference monthly renewable energy power generation value.

[0057] S402: Obtain the monthly average wind speed of the target region within the target month.

[0058] In this embodiment, the monthly average wind speed of the target area in the target month is the core factor affecting wind power generation. Wind speed directly determines the start-up status, operating efficiency, and power generation of the wind turbine. Within the rated wind speed range of the wind turbine, the higher the monthly average wind speed, the more wind energy the wind turbine captures, the greater the power generation, and the higher the corresponding monthly renewable energy power generation value. If the wind speed is lower than the wind turbine start-up threshold, it will not be able to generate effective power. If the wind speed is too high and exceeds the rated range, the wind turbine may trigger the protection mechanism to shut down, which will also lead to a decrease in power generation. Therefore, it is necessary to first obtain the monthly average wind speed of the target area in the target month.

[0059] S403: Determine the third adjustment parameter corresponding to the monthly average wind speed.

[0060] In this implementation, the historical monthly average wind speed statistics and corresponding power generation fluctuation patterns of the target region during the same period of the target month can be retrieved using a knowledge graph. This process relies on the temporal correlation of meteorological attributes of the target region in the graph. Then, based on the correlation between wind speed intervals and power generation efficiency in the knowledge graph, the specific interval to which the predicted wind speed of the target month belongs is determined. Finally, the mapping rules between wind speed and adjustment coefficients stored in the graph or the historical fitting model are used for calculation. The core is to transform the correlation between wind speed and wind power generation in the knowledge graph into quantifiable adjustment coefficients, and finally obtain the third adjustment parameter.

[0061] Alternatively, core work can be carried out by relying on an existing knowledge graph. This knowledge graph defines country nodes, renewable energy type nodes, and power generation nodes through a graph database, and establishes structured relationships among the three through production and related numerical values. The node features have encoded country-related attributes and wind speed correlation information. First, using the target region, wind energy, and target month as search conditions, a local subgraph containing the average monthly wind speed and corresponding historical wind power generation data for the target month in that region is extracted using query language, ensuring the relevance and completeness of the information obtained. Then, a multi-layer graph attention network is used to introduce attention coefficients when calculating the attention coefficients. By analyzing the incoming edge relationship features, we can uncover the potential correlation between the average monthly wind speed of the target month and historical wind power generation in the subgraph. We also combine implicit information such as wind energy capture and power generation efficiency changes corresponding to the wind speed. We integrate the features of neighboring nodes through the node update formula, and then obtain the graph feature vector through global average pooling. Subsequently, we map the graph features and the temporal features captured by the bidirectional long short-term memory network to the same space. We calculate the attention weights of the two through a multi-head self-attention mechanism and complete the feature fusion. Finally, we combine the training results of the model optimized by the loss function, and output a third adjustment parameter based on the fused spatiotemporal features to adapt to the average monthly wind speed of the target month in the target region.

[0062] S404: Adjust the second reference renewable energy monthly power generation value based on the third adjustment parameter to obtain the first renewable energy monthly power generation value.

[0063] In this embodiment, the monthly power generation value of the first renewable energy source is calculated according to the following formula: The monthly power generation value of the first renewable energy source = the monthly power generation value of the second reference renewable energy source × (1 + the third adjustment parameter); The second reference renewable energy monthly power generation value can be adjusted based on the third adjustment parameter according to the above formula to obtain the first renewable energy monthly power generation value.

[0064] As can be seen, the second reference monthly renewable energy power generation value is first obtained by using the linear change of renewable energy power generation value, providing a basic benchmark for wind power generation forecasting. Then, the core factor affecting wind power generation, namely the monthly average wind speed of the target region in the target month, is specifically obtained to determine the corresponding third adjustment parameter. This fully considers the impact of wind speed differences on the wind energy capture and operating efficiency of wind turbines. By accurately correcting the second reference value through this adjustment parameter, the shortcomings of single trend forecasting that does not take into account actual wind speed conditions can be effectively compensated for. This makes the final first renewable energy monthly power generation value more in line with the actual situation of wind power generation, greatly improving the accuracy and practicality of forecasting.

[0065] Please see Figure 5 , Figure 5 This application provides a flowchart for determining the monthly power generation value of a first renewable energy source corresponding to hydropower, including but not limited to the following steps: S501: Determine the monthly renewable energy power generation value corresponding to the target month on the linear curve of renewable energy power generation value change, and obtain the third reference monthly renewable energy power generation value.

[0066] In this embodiment, based on the linear change of renewable energy power generation value obtained by fitting historical hydropower power generation data, the specific time position of the target month is first determined. Then, according to the pattern of power generation change over time shown by the linear change, the monthly renewable energy power generation value corresponding to the time of the target month is matched on the linear change. This value obtained from the linear change is the third reference monthly renewable energy power generation value.

[0067] S502: Obtain the average monthly precipitation and average monthly ice-covered watershed area of ​​the target region in the target month.

[0068] In this embodiment, the average monthly precipitation in the target region during the target month is the core factor affecting hydropower generation. Precipitation directly determines the inflow of water into rivers and reservoirs. The more precipitation there is, the more water flows into the power generation area, the more abundant the water supply for hydropower generation, the higher the utilization rate of the installed power generation capacity, and the higher the corresponding monthly renewable energy power generation value. If the precipitation is too low, insufficient water inflow will lead to a shortage of water for power generation, which will limit the operating efficiency of the power generation equipment and thus reduce the power generation. Therefore, it is necessary to obtain the average monthly precipitation in the target region during the target month.

[0069] The monthly average ice-covered basin area of ​​the target region in the target month indirectly affects hydropower generation by influencing water flow conditions. The larger the ice-covered basin area, the smaller the available flowing water area. The water flow speed may be slowed down due to ice blockage, resulting in a reduction of effective water resources for hydropower conversion and thus reducing power generation. If the ice-covered basin area is small, most of the water area remains flowing, and the hydropower capture efficiency is higher. Therefore, it is necessary to obtain the monthly average ice-covered basin area of ​​the target region in the target month.

[0070] S503: Determine the fourth adjustment parameter corresponding to the monthly average precipitation and the fifth adjustment parameter corresponding to the monthly average ice-covered watershed area.

[0071] In this implementation, the historical monthly average precipitation statistics for the same period as the target month in the target region and the corresponding fluctuation pattern of hydropower generation can be retrieved using a knowledge graph. This process relies on the temporal correlation of hydrological attributes of the target region in the graph. Then, based on the correlation between precipitation intervals and power generation efficiency in the knowledge graph, the specific interval to which the predicted precipitation for the target month belongs is determined. Finally, the mapping rules between precipitation and adjustment coefficients stored in the graph or the historical fitting model are used for calculation. The core is to transform the correlation pattern between precipitation and hydropower generation in the knowledge graph into a quantifiable adjustment coefficient, and finally obtain the fourth adjustment parameter.

[0072] Alternatively, core work can be carried out by relying on an existing knowledge graph. This knowledge graph defines country nodes, renewable energy type nodes, and power generation nodes through a graph database, and establishes structured relationships among the three through production and related numerical values. The node features have encoded country-related attributes and precipitation-related information. First, using the target region, hydropower, and target month as search criteria, a local subgraph containing the average monthly precipitation and corresponding historical hydropower generation data for the target month in that region is extracted using query language, ensuring the relevance and completeness of the information obtained. Then, a multi-layer graph attention network is used, and the attention coefficient is introduced when calculating the attention coefficient. Edge relationship features are used to uncover the potential correlation between the average monthly precipitation of the target month and historical hydropower generation in the subgraph. Simultaneously, implicit information such as the water inflow and power generation capacity utilization corresponding to the precipitation is combined. The features of neighboring nodes are integrated through the node update formula, and then the graph feature vector is obtained through global average pooling. Subsequently, the graph features and the temporal features captured by the bidirectional long short-term memory network are mapped to the same space. The attention weights of the two are calculated through a multi-head self-attention mechanism to complete feature fusion. Finally, the model training results optimized by the loss function are combined, and based on the fused spatiotemporal features, a fourth adjustment parameter adapted to the average monthly precipitation of the target month in the target region is output.

[0073] First, the knowledge graph can be used to retrieve historical statistics on the average monthly frozen watershed area for the same period as the target month in the target region, as well as the corresponding fluctuations in hydropower generation. This process relies on the relationship between the climate attributes, hydrological attributes, and temporal correlation of the target region in the graph. Then, based on the correlation between the frozen watershed area intervals and power generation efficiency in the knowledge graph, the specific interval to which the predicted frozen watershed area for the target month belongs can be determined. Finally, the mapping rules between the frozen watershed area and the adjustment coefficient stored in the graph or the historical fitting model can be used for calculation. The core is to transform the correlation between the frozen watershed area and hydropower generation in the knowledge graph into quantifiable adjustment coefficients, and finally obtain the fifth adjustment parameter.

[0074] Alternatively, core work can be carried out by relying on an existing knowledge graph. This knowledge graph defines country nodes, renewable energy type nodes, and power generation nodes through a graph database, and establishes structured relationships among the three through production and related numerical values. The node features encode relevant national attributes and information related to the area of ​​frozen watersheds. First, using the target region, hydropower, and target month as search criteria, a local subgraph containing the average monthly frozen watershed area and corresponding historical hydropower generation data for the target month in that region is extracted using query language, ensuring the relevance and completeness of the information obtained. Then, a multi-layer graph attention network is used, introducing edge relationships when calculating the attention coefficient. The feature extraction process uncovers the potential correlation between the average monthly frozen watershed area of ​​the target month and historical hydropower generation in the subgraph. It also incorporates implicit information such as the effective flow area and flow velocity changes corresponding to the frozen watershed area. The features of neighboring nodes are integrated using a node update formula, and then global average pooling is applied to obtain a graph feature vector. This graph feature vector is then mapped to the same space along with temporal features captured by a bidirectional long short-term memory network. A multi-head self-attention mechanism is used to calculate the attention weights of both features and fuse them. Finally, based on the fused spatiotemporal features and the model training results optimized using a loss function, a fifth adjustment parameter is output to adapt to the average monthly frozen watershed area of ​​the target region for the target month.

[0075] S504: Adjust the third reference renewable energy monthly power generation value based on the fourth adjustment parameter and the fifth adjustment parameter to obtain the first renewable energy monthly power generation value.

[0076] In this embodiment, the monthly power generation value of the first renewable energy source is calculated according to the following formula: The monthly power generation value of the first renewable energy source = the monthly power generation value of the third reference renewable energy source × (1 + the fourth adjustment parameter) × (1 + the fifth adjustment parameter); According to the above formula, the third reference renewable energy monthly power generation value can be adjusted based on the fourth adjustment parameter and the fifth adjustment parameter to obtain the first renewable energy monthly power generation value.

[0077] As can be seen, the third reference monthly renewable energy power generation value is first obtained through the linear change of renewable energy power generation value, providing a basic benchmark for hydropower power generation prediction. Then, the key hydrological and climatic factors affecting hydropower generation, namely the monthly average precipitation and monthly average ice-covered basin area of ​​the target region in the target month, are specifically obtained. The corresponding fourth and fifth adjustment parameters are determined respectively, which fully consider the differences in water volume caused by precipitation and the differences in the effective power generation water area caused by the ice-covered basin area. The third reference monthly renewable energy power generation value is comprehensively corrected by the two adjustment parameters, which can effectively make up for the shortcomings of single trend prediction that does not take into account the actual hydrological and climatic conditions. This makes the final first renewable energy monthly power generation value more in line with the actual situation of hydropower generation, and greatly improves the accuracy and practicality of renewable energy monthly power generation value prediction.

[0078] Please see Figure 6 , Figure 6 This is a flowchart illustrating how to determine a target monthly renewable energy generation value, including but not limited to the following steps: S601: Determine the first weight value corresponding to the first monthly renewable energy power generation value, the second weight value corresponding to the second monthly renewable energy power generation value, and the third weight value corresponding to the third monthly renewable energy power generation value.

[0079] In this embodiment, the sum of the first weight, the second weight, and the third weight is 1.

[0080] For example, based on the first renewable energy power generation value data, the first historical average monthly renewable energy power generation value of the target region in the first historical time period is determined. Specifically, the average value of all monthly power generation in the target region in the first historical time period is calculated, and the value obtained by statistical averaging is the first historical average monthly renewable energy power generation value.

[0081] For example, the difference between the first historical average monthly renewable energy power generation value and the first renewable energy monthly power generation value is determined to obtain the first difference. Specifically, the first historical average monthly renewable energy power generation value and the first renewable energy monthly power generation value are compared, and the result obtained by subtracting the two values ​​is the first difference. The first difference reflects the degree of deviation between the first historical average level and the corresponding predicted power generation.

[0082] For example, based on the second renewable energy power generation data, the second historical average monthly renewable energy power generation value of the target region in the second historical time period is determined. Specifically, the average value of all monthly power generation in the target region in the second historical time period is calculated to finally obtain the second historical average monthly renewable energy power generation value.

[0083] For example, the difference between the second historical average monthly renewable energy generation value and the second renewable energy monthly power generation value is determined to obtain a second difference. Specifically, the second historical average monthly renewable energy generation value and the second renewable energy monthly power generation value are compared, and the result is obtained by subtracting the two values. This result is the second difference, which reflects the degree of deviation between the second historical average level and the corresponding predicted power generation.

[0084] For example, the third historical average monthly renewable energy power generation value of the target region in the third historical time period is determined based on the third renewable energy power generation data. Specifically, the third historical average monthly renewable energy power generation value can be obtained based on the average of all monthly power generation of the target region in the third historical time period.

[0085] For example, the difference between the third historical average monthly renewable energy power generation value and the third renewable energy monthly power generation value is determined to obtain the third difference value. Specifically, the third historical average monthly renewable energy power generation value and the third renewable energy monthly power generation value are compared, and the result is obtained by subtracting the two values. This result is the third difference value, which reflects the degree of deviation between the third historical average level and the corresponding predicted power generation.

[0086] For example, the first weight, the second weight, and the third weight are determined based on the first difference, the second difference, and the third difference. Specifically, the smaller the difference corresponding to the monthly renewable energy power generation value, the greater the weight of the monthly renewable energy power generation value. The size of the difference directly reflects the degree of deviation between the corresponding monthly renewable energy power generation value and the corresponding historical average level. The smaller the difference, the closer the power generation value is to the historical average pattern, and the higher the reference value and reliability. Therefore, a larger weight will be assigned. Conversely, the larger the difference, the more obvious the deviation of the power generation value from the historical average level, and the relatively lower the reference value. The corresponding weight will be smaller.

[0087] S602: Calculate a reference renewable energy monthly power generation value based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, the third renewable energy monthly power generation value, the first weight, the second weight, and the third weight.

[0088] In this embodiment, the reference monthly renewable energy generation value is calculated according to the following formula: Reference monthly renewable energy generation value = monthly renewable energy generation value of the first renewable energy source × first weight + monthly renewable energy generation value of the second renewable energy source × second weight + monthly renewable energy generation value of the third renewable energy source × third weight; According to the above formula, a reference monthly renewable energy power generation value can be obtained by calculating based on the first monthly renewable energy power generation value, the second monthly renewable energy power generation value, the third monthly renewable energy power generation value, the first weight, the second weight, and the third weight.

[0089] S603: Obtain the renewable energy installed capacity of the target region in the target month.

[0090] In this embodiment, the renewable energy installed capacity of the target region in the target month refers to the total capacity of power generation equipment actually put into operation in that region in that month, used to convert renewable energy sources such as wind, solar, and hydropower. The renewable energy installed capacity of the target region in the target month determines the maximum output potential of renewable energy power generation in that region. Under the premise of stable resource conditions and equipment operating efficiency, the larger the installed capacity, the larger the scale of equipment that can be put into power generation, the more renewable energy can be converted, and the higher the corresponding monthly power generation value is usually. If the installed capacity is insufficient, even if the resource conditions are excellent, the energy cannot be fully utilized due to the equipment capacity limitation, resulting in difficulty in increasing power generation. Therefore, it is necessary to obtain the renewable energy installed capacity of the target region in the target month.

[0091] S604: Determine the optimization factor corresponding to the installed capacity of the renewable energy.

[0092] In this embodiment, a mapping relationship between the installed capacity of renewable energy and the optimization factor can be preset, and the optimization factor corresponding to the installed capacity of renewable energy can be determined based on the mapping relationship.

[0093] S605: Optimize the reference renewable energy monthly power generation value based on the optimization factor to obtain the target renewable energy monthly power generation value.

[0094] In this embodiment, the target monthly renewable energy generation value is calculated according to the following formula: Target monthly renewable energy generation value = Reference monthly renewable energy generation value × (1 + optimization factor); Based on the above formula, the reference monthly renewable energy generation value can be optimized using the optimization factor to obtain the target monthly renewable energy generation value.

[0095] It can be seen that by combining weighted calculation to obtain the reference monthly renewable energy power generation value, the result fully takes into account the reliability differences of different power generation data. Then, by introducing the renewable energy installed capacity of the target region for the target month and determining the corresponding optimization factor, the reference value is specifically corrected through the optimization factor. This effectively makes up for the shortcomings of relying solely on weighted calculation without taking into account the actual situation of equipment scale. As a result, the final target monthly renewable energy power generation value is more in line with the actual power generation conditions of the region, thus improving the accuracy of the monthly renewable energy power generation prediction results.

[0096] In summary, implementing the embodiments of the present invention has the following beneficial effects: As can be seen, the renewable energy monthly power generation prediction method described in this embodiment of the invention first acquires the first renewable energy power generation data for a target region within a first historical time period, the second renewable energy power generation data within a second historical time period, and the third renewable energy power generation data within a third historical time period, wherein the first historical time period includes the second historical time period, and the second historical time period includes the third historical time period. Then, based on the first renewable energy power generation data, the method predicts the renewable energy monthly power generation value for the target region in the target month to obtain the first renewable energy monthly power generation value. Based on the second renewable energy power generation data, the method predicts the renewable energy monthly power generation value for the target region in the target month to obtain the second renewable energy monthly power generation value. Based on the third renewable energy power generation data, the method predicts the renewable energy monthly power generation value for the target region in the target month to obtain the third renewable energy monthly power generation value. Finally, based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value, the method determines the target renewable energy monthly power generation value for the target region in the target month, thus enabling accurate prediction of renewable energy power generation.

[0097] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of a renewable energy monthly power generation prediction device provided in an embodiment of this application. The renewable energy monthly power generation prediction device 700 includes: an acquisition unit 701 and a processing unit 702. The acquisition unit 701 is used to acquire data on the first renewable energy power generation value of the target region in a first historical time period, data on the second renewable energy power generation in a second historical time period, and data on the third renewable energy power generation in a third historical time period; the first historical time period includes the second historical time period, and the second historical time period includes the third historical time period. The processing unit 702 is used to predict the monthly renewable energy power generation value of the target region in the target month based on the first renewable energy power generation value data, and obtain the first renewable energy monthly power generation value. Based on the second renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the second renewable energy monthly power generation value; Based on the third renewable energy power generation data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the third renewable energy monthly power generation value; The target renewable energy monthly power generation value for the target region in the target month is determined based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value.

[0098] In some possible implementations, in predicting the monthly renewable energy generation value of the target region in the target month based on the first renewable energy generation value data to obtain the first monthly renewable energy generation value, the processing unit 702 is specifically used for: Determine n historical monthly renewable energy power generation values ​​corresponding to the first renewable energy power generation value data and the n historical monthly renewable energy power generation value recording times corresponding to the n historical monthly renewable energy power generation values; each historical monthly renewable energy power generation value corresponds to a historical monthly renewable energy power generation value recording time, where n is a positive integer; Based on the n historical monthly renewable energy power generation values ​​and the recording times of the n historical monthly renewable energy power generation values, a straight line is fitted to obtain the change line of renewable energy power generation values; The monthly renewable energy power generation value corresponding to the target month is determined based on the linear change in the renewable energy power generation value.

[0099] In some possible implementations, when the energy type of the renewable energy corresponding to the first renewable energy monthly power generation value is solar energy, the processing unit 702 is specifically used for determining the first renewable energy monthly power generation value corresponding to the target month based on the linear change of the renewable energy power generation value: Determine the monthly renewable energy generation value corresponding to the target month on the linear curve of renewable energy generation value change, and obtain the first reference monthly renewable energy generation value; Obtain the average latitude corresponding to the target region; Determine the first adjustment parameter corresponding to the average latitude; Obtain the average monthly sunshine duration of the target region in the target month; Determine a second adjustment parameter corresponding to the average monthly sunshine duration; The first reference monthly renewable energy power generation value is obtained by adjusting the first adjustment parameter and the second adjustment parameter.

[0100] In some possible implementations, when the energy type of the renewable energy corresponding to the first renewable energy monthly power generation value is wind energy, the processing unit 702 is specifically used for determining the first renewable energy monthly power generation value corresponding to the target month based on the linear change of the renewable energy power generation value: Determine the monthly renewable energy generation value corresponding to the target month on the linear curve of renewable energy generation value change, and obtain the second reference monthly renewable energy generation value; Obtain the monthly average wind speed for the target region within the target month; Determine the third adjustment parameter corresponding to the monthly average wind speed; The second reference renewable energy monthly power generation value is adjusted based on the third adjustment parameter to obtain the first renewable energy monthly power generation value.

[0101] In some possible implementations, when the energy type of the renewable energy corresponding to the first renewable energy monthly power generation value is hydropower, the processing unit 702 is specifically used for determining the first renewable energy monthly power generation value corresponding to the target month based on the linear change of the renewable energy power generation value: The monthly renewable energy generation value corresponding to the target month on the linear curve of renewable energy generation value change is determined to obtain the third reference monthly renewable energy generation value; Obtain the average monthly precipitation and average monthly ice-covered watershed area of ​​the target region within the target month; Determine the fourth adjustment parameter corresponding to the monthly average precipitation and the fifth adjustment parameter corresponding to the monthly average ice-covered watershed area; The third reference renewable energy monthly power generation value is adjusted based on the fourth adjustment parameter and the fifth adjustment parameter to obtain the first renewable energy monthly power generation value.

[0102] In some possible implementations, in determining the target renewable energy monthly power generation value for the target region in the target month based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value, the processing unit 702 is specifically used for: Determine a first weight corresponding to the first monthly renewable energy power generation value, a second weight corresponding to the second monthly renewable energy power generation value, and a third weight corresponding to the third monthly renewable energy power generation value; the sum of the first weight, the second weight, and the third weight is 1; A reference monthly renewable energy power generation value is obtained by calculating based on the first monthly renewable energy power generation value, the second monthly renewable energy power generation value, the third monthly renewable energy power generation value, the first weight, the second weight, and the third weight; Obtain the renewable energy installed capacity of the target region in the target month; Determine the optimization factor corresponding to the installed capacity of the renewable energy source; The target renewable energy monthly power generation value is obtained by optimizing the reference renewable energy monthly power generation value based on the optimization factor.

[0103] In some possible implementations, the processing unit 702 is specifically configured to: determine the first weight corresponding to the first renewable energy monthly power generation value, the second weight corresponding to the second renewable energy monthly power generation value, and the third weight corresponding to the third renewable energy monthly power generation value; Based on the first renewable energy power generation data, determine the first historical average monthly renewable energy power generation value of the target region within the first historical time period; The difference between the first historical average monthly renewable energy generation value and the first monthly renewable energy generation value is determined to obtain the first difference value; Based on the second renewable energy power generation data, determine the second historical average monthly renewable energy power generation value of the target region during the second historical time period; The difference between the second historical average monthly renewable energy generation value and the second monthly renewable energy generation value is determined to obtain the second difference value; Based on the aforementioned third renewable energy power generation data, determine the third historical average monthly renewable energy power generation value for the target region during the third historical time period; The difference in monthly renewable energy generation between the third historical average monthly renewable energy generation value and the third monthly renewable energy generation value is determined to obtain the third difference value; The first weight, the second weight, and the third weight are determined based on the first difference, the second difference, and the third difference; the smaller the difference corresponding to the monthly renewable energy power generation value, the greater the weight corresponding to the monthly renewable energy power generation value.

[0104] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. For example... Figure 8 As shown, the electronic device 800 includes a transceiver 801, a processor 802, and a memory 803. These are connected via a bus 804. The memory 803 stores computer programs and data, and the transceiver 801 can transmit data stored in the memory 803 to the processor 802. The program includes instructions for performing the following steps: Acquire data on the first renewable energy power generation value of the target region within a first historical time period, the second renewable energy power generation data within a second historical time period, and the third renewable energy power generation data within a third historical time period; the first historical time period includes the second historical time period, and the second historical time period includes the third historical time period. Based on the first renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the first renewable energy monthly power generation value; Based on the second renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the second renewable energy monthly power generation value; Based on the third renewable energy power generation data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the third renewable energy monthly power generation value; The target renewable energy monthly power generation value for the target region in the target month is determined based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value.

[0105] In some possible implementations, in order to predict the monthly renewable energy generation value of the target region in the target month based on the first renewable energy generation value data, and to obtain the first monthly renewable energy generation value, the above procedure includes instructions for performing the following steps: Determine n historical monthly renewable energy power generation values ​​corresponding to the first renewable energy power generation value data and the n historical monthly renewable energy power generation value recording times corresponding to the n historical monthly renewable energy power generation values; each historical monthly renewable energy power generation value corresponds to a historical monthly renewable energy power generation value recording time, where n is a positive integer; Based on the n historical monthly renewable energy power generation values ​​and the recording times of the n historical monthly renewable energy power generation values, a straight line is fitted to obtain the change line of renewable energy power generation values; The monthly renewable energy power generation value corresponding to the target month is determined based on the linear change in the renewable energy power generation value.

[0106] In some possible implementations, when the energy type of the renewable energy corresponding to the first renewable energy monthly power generation value is solar energy, the above procedure includes instructions for performing the following steps in determining the first renewable energy monthly power generation value corresponding to the target month based on the linear change of the renewable energy power generation value: Determine the monthly renewable energy generation value corresponding to the target month on the linear curve of renewable energy generation value change, and obtain the first reference monthly renewable energy generation value; Obtain the average latitude corresponding to the target region; Determine the first adjustment parameter corresponding to the average latitude; Obtain the average monthly sunshine duration of the target region in the target month; Determine a second adjustment parameter corresponding to the average monthly sunshine duration; The first reference monthly renewable energy power generation value is obtained by adjusting the first adjustment parameter and the second adjustment parameter.

[0107] In some possible implementations, when the energy type of the renewable energy corresponding to the first renewable energy monthly power generation value is wind energy, the above procedure includes instructions for performing the following steps in determining the first renewable energy monthly power generation value corresponding to the target month based on the linear change of the renewable energy power generation value: Determine the monthly renewable energy generation value corresponding to the target month on the linear curve of renewable energy generation value change, and obtain the second reference monthly renewable energy generation value; Obtain the monthly average wind speed for the target region within the target month; Determine the third adjustment parameter corresponding to the monthly average wind speed; The second reference renewable energy monthly power generation value is adjusted based on the third adjustment parameter to obtain the first renewable energy monthly power generation value.

[0108] In some possible implementations, when the energy type of the renewable energy corresponding to the first renewable energy monthly power generation value is hydropower, the above procedure includes instructions for performing the following steps in determining the first renewable energy monthly power generation value corresponding to the target month based on the linear change of the renewable energy power generation value: The monthly renewable energy generation value corresponding to the target month on the linear curve of renewable energy generation value change is determined to obtain the third reference monthly renewable energy generation value; Obtain the average monthly precipitation and average monthly ice-covered watershed area of ​​the target region within the target month; Determine the fourth adjustment parameter corresponding to the monthly average precipitation and the fifth adjustment parameter corresponding to the monthly average ice-covered watershed area; The third reference renewable energy monthly power generation value is adjusted based on the fourth adjustment parameter and the fifth adjustment parameter to obtain the first renewable energy monthly power generation value.

[0109] In some possible implementations, in determining the target renewable energy monthly power generation value for the target region in the target month based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value, the above procedure includes instructions for performing the following steps: Determine a first weight corresponding to the first monthly renewable energy power generation value, a second weight corresponding to the second monthly renewable energy power generation value, and a third weight corresponding to the third monthly renewable energy power generation value; the sum of the first weight, the second weight, and the third weight is 1; A reference monthly renewable energy power generation value is obtained by calculating based on the first monthly renewable energy power generation value, the second monthly renewable energy power generation value, the third monthly renewable energy power generation value, the first weight, the second weight, and the third weight; Obtain the renewable energy installed capacity of the target region in the target month; Determine the optimization factor corresponding to the installed capacity of the renewable energy source; The target renewable energy monthly power generation value is obtained by optimizing the reference renewable energy monthly power generation value based on the optimization factor.

[0110] In some possible implementations, the procedure includes instructions for performing the following steps in determining the first weight corresponding to the first monthly renewable energy generation value, the second weight corresponding to the second monthly renewable energy generation value, and the third weight corresponding to the third monthly renewable energy generation value: Based on the first renewable energy power generation data, determine the first historical average monthly renewable energy power generation value of the target region within the first historical time period; The difference between the first historical average monthly renewable energy generation value and the first monthly renewable energy generation value is determined to obtain the first difference value; Based on the second renewable energy power generation data, determine the second historical average monthly renewable energy power generation value of the target region during the second historical time period; The difference between the second historical average monthly renewable energy generation value and the second monthly renewable energy generation value is determined to obtain the second difference value; Based on the aforementioned third renewable energy power generation data, determine the third historical average monthly renewable energy power generation value for the target region during the third historical time period; The difference in monthly renewable energy generation between the third historical average monthly renewable energy generation value and the third monthly renewable energy generation value is determined to obtain the third difference value; The first weight, the second weight, and the third weight are determined based on the first difference, the second difference, and the third difference; the smaller the difference corresponding to the monthly renewable energy power generation value, the greater the weight corresponding to the monthly renewable energy power generation value.

[0111] It should be understood that the electronic devices mentioned in this application may include smartphones (such as Android phones, iOS phones, Windows Phones, etc.), tablets, PDAs, laptops, mobile internet devices (MIDs) or wearable devices, servers, edge computing nodes, etc. The above-mentioned electronic devices are merely examples and not exhaustive, and include, but are not limited to, the electronic devices described above.

[0112] This application also provides a computer-readable storage medium storing a computer program that is executed by a processor to implement some or all of the steps of any of the methods described in the above method embodiments.

[0113] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments.

[0114] It should be noted that, for the sake of simplicity, the aforementioned methods are described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are optional, and the actions and modules involved are not necessarily essential to this application.

[0115] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0116] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0117] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0118] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0119] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0120] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0121] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The above description of the embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for predicting monthly renewable energy power generation, characterized in that, include: Acquire data on the first renewable energy power generation value of the target region within a first historical time period, the second renewable energy power generation data within a second historical time period, and the third renewable energy power generation data within a third historical time period; the first historical time period includes the second historical time period, and the second historical time period includes the third historical time period. Based on the first renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the first renewable energy monthly power generation value; Based on the second renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the second renewable energy monthly power generation value; Based on the third renewable energy power generation data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the third renewable energy monthly power generation value; The target renewable energy monthly power generation value for the target region in the target month is determined based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value.

2. The method as described in claim 1, characterized in that, The step of predicting the monthly renewable energy generation value of the target region in the target month based on the first renewable energy generation value data to obtain the first monthly renewable energy generation value includes: Determine n historical monthly renewable energy power generation values ​​corresponding to the first renewable energy power generation value data and the n historical monthly renewable energy power generation value recording times corresponding to the n historical monthly renewable energy power generation values; each historical monthly renewable energy power generation value corresponds to a historical monthly renewable energy power generation value recording time, where n is a positive integer; Based on the n historical monthly renewable energy power generation values ​​and the recording times of the n historical monthly renewable energy power generation values, a straight line is fitted to obtain the change line of renewable energy power generation values; The monthly renewable energy power generation value corresponding to the target month is determined based on the linear change in the renewable energy power generation value.

3. The method as described in claim 2, characterized in that, When the energy type of the renewable energy corresponding to the first renewable energy monthly power generation value is solar energy, the step of determining the first renewable energy monthly power generation value corresponding to the target month based on the linear change of the renewable energy power generation value includes: Determine the monthly renewable energy generation value corresponding to the target month on the linear curve of renewable energy generation value change, and obtain the first reference monthly renewable energy generation value; Obtain the average latitude corresponding to the target region; Determine the first adjustment parameter corresponding to the average latitude; Obtain the average monthly sunshine duration of the target region in the target month; Determine a second adjustment parameter corresponding to the average monthly sunshine duration; The first reference monthly renewable energy power generation value is obtained by adjusting the first adjustment parameter and the second adjustment parameter.

4. The method as described in claim 2, characterized in that, When the energy type of the renewable energy corresponding to the first renewable energy monthly power generation value is wind energy, the step of determining the first renewable energy monthly power generation value corresponding to the target month based on the linear change of the renewable energy power generation value includes: Determine the monthly renewable energy generation value corresponding to the target month on the linear curve of renewable energy generation value change, and obtain the second reference monthly renewable energy generation value; Obtain the monthly average wind speed for the target region within the target month; Determine the third adjustment parameter corresponding to the monthly average wind speed; The second reference renewable energy monthly power generation value is adjusted based on the third adjustment parameter to obtain the first renewable energy monthly power generation value.

5. The method as described in claim 2, characterized in that, When the energy type of the renewable energy corresponding to the first renewable energy monthly power generation value is hydropower, the step of determining the first renewable energy monthly power generation value corresponding to the target month based on the linear change of the renewable energy power generation value includes: The monthly renewable energy generation value corresponding to the target month on the linear curve of renewable energy generation value change is determined to obtain the third reference monthly renewable energy generation value; Obtain the average monthly precipitation and average monthly ice-covered watershed area of ​​the target region within the target month; Determine the fourth adjustment parameter corresponding to the monthly average precipitation and the fifth adjustment parameter corresponding to the monthly average ice-covered watershed area; The third reference renewable energy monthly power generation value is adjusted based on the fourth adjustment parameter and the fifth adjustment parameter to obtain the first renewable energy monthly power generation value.

6. The method as described in claim 1, characterized in that, The step of determining the target renewable energy monthly power generation value for the target region in the target month based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value includes: Determine a first weight corresponding to the first monthly renewable energy power generation value, a second weight corresponding to the second monthly renewable energy power generation value, and a third weight corresponding to the third monthly renewable energy power generation value; the sum of the first weight, the second weight, and the third weight is 1; A reference monthly renewable energy power generation value is obtained by calculating based on the first monthly renewable energy power generation value, the second monthly renewable energy power generation value, the third monthly renewable energy power generation value, the first weight, the second weight, and the third weight; Obtain the renewable energy installed capacity of the target region in the target month; Determine the optimization factor corresponding to the installed capacity of the renewable energy source; The target renewable energy monthly power generation value is obtained by optimizing the reference renewable energy monthly power generation value based on the optimization factor.

7. The method as described in claim 6, characterized in that, The step of determining the first weight value corresponding to the first monthly renewable energy power generation value, the second weight value corresponding to the second monthly renewable energy power generation value, and the third weight value corresponding to the third monthly renewable energy power generation value includes: Based on the first renewable energy power generation data, determine the first historical average monthly renewable energy power generation value of the target region within the first historical time period; The difference between the first historical average monthly renewable energy generation value and the first monthly renewable energy generation value is determined to obtain the first difference value; Based on the second renewable energy power generation data, determine the second historical average monthly renewable energy power generation value of the target region during the second historical time period; The difference between the second historical average monthly renewable energy generation value and the second monthly renewable energy generation value is determined to obtain the second difference value; Based on the aforementioned third renewable energy power generation data, determine the third historical average monthly renewable energy power generation value for the target region during the third historical time period; The difference in monthly renewable energy generation between the third historical average monthly renewable energy generation value and the third monthly renewable energy generation value is determined to obtain the third difference value; The first weight, the second weight, and the third weight are determined based on the first difference, the second difference, and the third difference; the smaller the difference corresponding to the monthly renewable energy power generation value, the greater the weight corresponding to the monthly renewable energy power generation value.

8. A device for predicting monthly renewable energy power generation, characterized in that, The device includes: an acquisition unit and a processing unit; The acquisition unit is used to acquire data on the first renewable energy power generation value of the target region within a first historical time period, data on the second renewable energy power generation within a second historical time period, and data on the third renewable energy power generation within a third historical time period; the first historical time period includes the second historical time period, and the second historical time period includes the third historical time period. The processing unit is used to predict the monthly renewable energy power generation value of the target region in the target month based on the first renewable energy power generation value data, and obtain the first renewable energy monthly power generation value. Based on the second renewable energy power generation value data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the second renewable energy monthly power generation value; Based on the third renewable energy power generation data, predict the monthly renewable energy power generation value of the target region in the target month to obtain the third renewable energy monthly power generation value; The target renewable energy monthly power generation value for the target region in the target month is determined based on the first renewable energy monthly power generation value, the second renewable energy monthly power generation value, and the third renewable energy monthly power generation value.

9. An electronic device, characterized in that, The method includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for performing the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the method as described in any one of claims 1-7.

Images