New energy station optimization control method based on deviation evaluation key factor analysis

Abstract

The application relates to the technical field of new energy station optimization control, and discloses a new energy station optimization control method based on bias examination key factor analysis, which comprises the following steps: obtaining real-time operation data of a new energy station to be optimized; calculating the real-time operation data according to a preset sequence to obtain characteristic values of each key factor, diagnosing the characteristic values based on a judgment condition of each key factor, and determining a first key factor satisfying the judgment condition as a leading influence factor; determining a corresponding operation mode according to the leading influence factor, and determining a dispatching strategy of the new energy station to be optimized according to the operation mode; and issuing a control instruction corresponding to the dispatching strategy to the new energy station to be optimized, so that the new energy station to be optimized executes the control instruction. Through multi-factor identification and multi-modal dynamic cooperative control, the application solves the problems of high bias examination cost and single and low-efficiency control strategy of the new energy station.

Description

Technical Field

[0001] This invention relates to the field of optimization control technology for new energy power plants, specifically to an optimization control method for new energy power plants based on the analysis of key factors in deviation assessment. Background Technology

[0002] Currently, renewable energy power plants mainly employ the following technical means to meet assessment requirements. In power forecasting, methods such as improving meteorological data sources and optimizing forecasting algorithms are commonly used, including physical modeling, statistical learning, and artificial intelligence algorithms. Physical modeling establishes a power generation calculation model based on numerical weather forecasts and power plant equipment parameters; statistical learning uses historical data for regression analysis and time series forecasting; and artificial intelligence algorithms use machine learning techniques such as neural networks and support vector machines to uncover the complex nonlinear relationship between meteorological factors and power generation. In power control, the main reliance is on the coordinated operation of Automatic Generation Control (AGC) systems and energy storage systems. AGC systems track the planned curve by adjusting the active power output of generating units in real time, while energy storage systems, with their rapid response characteristics, smooth power fluctuations on a second- or minute-level timescale. In addition, some power plants also adopt a planned application optimization strategy, developing more reasonable day-ahead power generation plans by analyzing historical data and market information.

[0003] However, existing optimized control methods have significant shortcomings in practical applications, resulting in persistently high deviation assessment costs for renewable energy power plants. This is because the control strategies are simplistic and inefficient, focusing solely on strictly tracking the planned curve while ignoring electricity market price signals, which is detrimental to power plant profitability. Furthermore, there is a lack of accurate diagnostic capabilities for the root causes of deviations, insufficient utilization of regulation resources such as energy storage, and poor coordination among various control components. Summary of the Invention

[0004] This invention provides an optimized control method for new energy power plants based on the analysis of key factors in deviation assessment, which solves the problems of high deviation assessment costs and inefficient, single control strategies for new energy power plants.

[0005] In a first aspect, the present invention provides an optimization control method for new energy power plants based on the analysis of key factors in deviation assessment, the method comprising:

[0006] The process involves: acquiring real-time operational data of the renewable energy power plants to be optimized; calculating the characteristic values ​​of each key factor based on a preset sequence; diagnosing the characteristic values ​​based on the judgment conditions of each key factor; identifying the first key factor that meets the judgment conditions as the dominant influencing factor; determining the key factors and their judgment conditions based on the historical operational data and historical deviation assessment data of the renewable energy power plants to be optimized; determining the corresponding operational mode based on the dominant influencing factor; and determining the scheduling strategy for the renewable energy power plants to be optimized according to the operational mode; and issuing the control commands corresponding to the scheduling strategy to the renewable energy power plants to be optimized so that they can execute the control commands.

[0007] This invention provides an optimized control method for new energy power plants based on the analysis of key factors in deviation assessment. It determines key factors and judgment conditions based on the power plant's historical operation and deviation assessment data, ensuring that the selection of key factors and the setting of judgment conditions align with the actual operating characteristics of the power plant. This overcomes the insufficient adaptability of generalized standards, making subsequent factor diagnosis more targeted. The method diagnoses the first dominant influencing factor that meets the conditions in a preset order, accurately and quickly locating the core factors currently affecting deviation assessment, avoiding ambiguity caused by multiple factors, and making subsequent control more targeted. Furthermore, it matches the corresponding operating mode and formulates a scheduling strategy based on the dominant influencing factor, ensuring that the scheduling strategy is highly adapted to the current core operating status of the power plant, overcoming the limitations of a single control mode, and making the strategy formulation more aligned with actual management and control needs. Finally, it issues the control commands corresponding to the scheduling strategy to the power plant and promotes their execution, transforming the formulated adaptive scheduling strategy into the actual control actions of the power plant.

[0008] In one optional implementation, the step of determining key factors based on historical operating data and historical deviation assessment data of the renewable energy power station to be optimized includes: Based on the historical operation data of the new energy power stations to be optimized in different time periods, the characteristic values ​​of each candidate factor in different prediction time periods are calculated. Based on the characteristic values ​​of each candidate factor in different prediction time periods and the historical deviation assessment data in different prediction time periods, the correlation coefficient between each candidate factor and the historical deviation assessment data is calculated. Key factors are selected from the candidate factors based on the correlation coefficient.

[0009] This invention provides an optimized control method for new energy power plants based on the analysis of key factors in deviation assessment. By calculating the characteristic values ​​of each candidate factor for different prediction time periods using historical operating data of the new energy power plant at different time periods, the method ensures that the characteristic values ​​of the candidate factors match the operating patterns and deviation assessment dimensions of the power plant at different power prediction stages. This allows the characteristic values ​​to accurately reflect the actual state of the candidate factors at the corresponding stages. Furthermore, by calculating the correlation coefficients between the characteristic values ​​of the candidate factors and historical deviation assessment data within different prediction time periods, the method can accurately quantify the degree of correlation between each candidate factor and the overall deviation assessment of the power plant at a specific prediction stage, aligning with the actual needs of multi-dimensional assessment of deviation electricity fees and assessment electricity fees. By screening key factors from the candidate factors based on the correlation coefficients, the method can effectively eliminate candidate factors with weak correlation to the overall deviation assessment, ensuring that the selected key factors are the core factors truly affecting the deviation assessment of the power plant, providing a comprehensive and accurate basis for subsequent diagnosis of dominant influencing factors. In one optional implementation, the historical deviation assessment data includes historical electricity deviation assessment data and historical power deviation assessment data. Historical power deviation assessment data is determined based on the power deviation between the actual power generation and the day-ahead declared power generation of the new energy power plants to be optimized in different forecast periods, as well as the real-time electricity price; historical power deviation assessment data is determined based on the deviation between the predicted power and the actual power of the new energy power plants to be optimized in different forecast periods.

[0010] The new energy power plant optimization control method based on the analysis of key factors in deviation assessment provided by this invention divides historical deviation assessment data into historical electricity deviation assessment data and historical power deviation assessment data. This aligns with the actual situation of deviation assessment for new energy power plants, which is divided into two core dimensions: electricity deviation and power prediction deviation. It also matches the assessment classification of deviation electricity fees and power prediction assessment electricity fees. The calculation method of historical electricity deviation assessment data strictly follows the actual accounting rules of electricity deviation assessment, which uses the amount of electricity deviation combined with real-time electricity prices for punitive settlement. Historical power deviation assessment data is determined based on the deviation between predicted power and actual power in different prediction time periods, matching the judgment logic of power prediction assessment, which is centered on the accuracy of power prediction.

[0011] In one optional implementation, the key factors include real-time electricity price difference indicators, prediction error indicators, and power fluctuation indicators. Characteristic values ​​for each key factor are calculated from real-time operating data in a preset order. Based on the judgment conditions for each key factor, the characteristic values ​​are diagnosed, and the first key factor that meets the judgment conditions is identified as the dominant influencing factor, including: The characteristic value of the real-time electricity price difference index at different times is calculated based on the absolute value of the difference between the real-time electricity price and the day-ahead electricity price in the real-time data. If the characteristic value of the real-time electricity price difference index exceeds the first preset threshold and the duration exceeds the first preset duration, the real-time electricity price difference index is determined as the dominant influencing factor. If the real-time electricity price difference index does not meet the corresponding judgment condition, the characteristic value of the prediction error index is calculated based on the absolute value of the difference between the actual power generation and the predicted power. If the characteristic value of the prediction error index exceeds the second preset threshold and the duration exceeds the second preset duration, the prediction error index is determined as the dominant influencing factor. If the real-time electricity price difference index and the prediction error index do not meet their respective judgment conditions, the characteristic value of the power fluctuation index is calculated based on the power fluctuation amplitude within the preset time window. If the characteristic value of the power fluctuation index exceeds the third preset threshold and the duration exceeds the third preset duration, the power fluctuation index is determined as the dominant influencing factor.

[0012] The new energy power plant optimization control method provided by this invention, based on the analysis of key factors in deviation assessment, identifies three core key factors: real-time electricity price difference, prediction error, and power fluctuation. It calculates characteristic values ​​for each indicator in a preset order and performs judgments according to their respective judgment conditions, avoiding the logical confusion of parallel judgments of multiple factors and ensuring the hierarchical and orderly diagnosis of dominant influencing factors. A dedicated characteristic value calculation method is designed for each indicator, allowing the characteristic values ​​to accurately and objectively quantify the actual state of each indicator, providing a reliable quantitative basis for judgment. This avoids misjudgment of dominant factors, improves the accuracy of diagnostic results, and lays a precise foundation for subsequent rapid matching and adaptation of operating modes, ensuring the efficiency of real-time control of the power plant.

[0013] In one optional implementation, the corresponding operating mode is determined based on the dominant influencing factors, and the scheduling strategy for the new energy power station to be optimized is determined according to the operating mode, including: If the real-time electricity price difference is the dominant influencing factor, the economic mode is activated. The net revenue of different discharge strategies is calculated using a pre-established revenue-penalty analysis model. When the net revenue is positive, the energy storage system in the new energy power station to be optimized performs a discharge operation. The net revenue is determined based on the revenue generated by the discharge strategy and the difference between the power deviation assessment data.

[0014] The new energy power station optimization control method based on the analysis of key factors in deviation assessment provided by this invention initiates an economic mode for scenarios where the real-time electricity price difference index is the dominant influencing factor. It calculates the net revenue of different discharge strategies through a pre-established revenue-penalty analysis model, and incorporates the market revenue generated by energy storage discharge and the cost brought by the power deviation assessment into the same accounting system. This achieves a comprehensive quantitative evaluation of revenue and assessment costs, avoiding the actual revenue loss caused by only considering the discharge revenue and ignoring the assessment penalty. The positive net revenue is used as the criterion for determining whether the energy storage system should perform a discharge operation, avoiding revenue loss or increased assessment costs caused by blind discharge operations.

[0015] In one optional implementation, the corresponding operating mode is determined based on the dominant influencing factors, and the scheduling strategy for the new energy power station to be optimized is determined according to the operating mode, including: If the prediction error index is the dominant influencing factor, the prediction correction mode is activated. The predicted power is calculated using the pre-established power prediction model, and the model parameters of the power prediction model are corrected to obtain the corrected predicted power result.

[0016] The new energy power plant optimization control method provided by this invention, based on the analysis of key factors in deviation assessment, initiates a prediction correction mode for scenarios where prediction error is the dominant influencing factor. This allows the power plant's control actions to precisely focus on power prediction deviation. By using a pre-established power prediction model to calculate the predicted power, the model parameters of the power prediction model are corrected to obtain the corrected predicted power result. This method optimizes the model from the core influencing level of power prediction, rather than simply correcting the predicted value. It can fundamentally improve the accuracy of power prediction and effectively reduce the deviation assessment risk caused by excessive prediction error. At the same time, the corrected predicted power result can provide a more realistic power reference for the subsequent power plant power dispatch, further enhancing the scientificity and rationality of the power plant dispatch strategy.

[0017] In one optional implementation, the corresponding operating mode is determined based on the dominant influencing factors, and the scheduling strategy for the new energy power station to be optimized is determined according to the operating mode, including: If power fluctuation is the dominant influencing factor, the priority tracking mode is activated to optimize the charging and discharging strategy of the energy storage system in the new energy power station with the goal of minimizing power deviation.

[0018] The present invention provides an optimized control method for new energy power plants based on the analysis of key factors in deviation assessment. For scenarios where power fluctuation is the dominant influencing factor, a priority tracking mode is initiated. Guided by minimizing power deviation, the charging and discharging strategies of the energy storage system in the new energy power plant are specifically optimized. This fully leverages the power regulation and fluctuation mitigation capabilities of the energy storage system. By scientifically adjusting the charging and discharging strategy, significant fluctuations in the power plant's generation power are offset, reducing power deviation from a practical control perspective. This effectively lowers the risk of deviation assessments caused by power fluctuations, while making the control actions of the energy storage system more targeted, improving the utilization efficiency of energy storage resources, and ensuring the stability of the power plant's generation power.

[0019] In an alternative implementation, if no dominant influencing factor is identified, the method further includes: In normal mode, a multi-objective optimization algorithm is used to optimize the charging and discharging strategy of the energy storage system in the new energy power station.

[0020] The new energy power plant optimization control method based on the analysis of key factors in deviation assessment provided by this invention enables a normal mode for power plant operation scenarios where no dominant influencing factors have been identified. In this mode, a multi-objective optimization algorithm is used to optimize the charging and discharging strategy of the energy storage system. Unlike single-objective control strategies, multi-objective optimization can take into account multiple core needs such as power plant deviation assessment and control, efficient utilization of energy storage resources, and revenue from normal operation of the power plant. It avoids the one-sidedness of single-objective optimization and makes the energy storage charging and discharging strategy under normal conditions more in line with the overall operation goals of the power plant. This improves the utilization efficiency of the energy storage system under normal operation scenarios and ensures the stability and economy of the overall operation of the power plant.

[0021] Secondly, this invention provides an optimization control device for new energy power stations based on the analysis of key factors in deviation assessment. The device includes: The data acquisition module is used to acquire real-time operating data of the new energy power stations to be optimized; The module for determining the dominant influencing factors is used to calculate the characteristic values ​​of each key factor from the real-time operating data in a preset order, and to diagnose the characteristic values ​​based on the judgment conditions of each key factor. The first key factor that meets the judgment conditions is determined as the dominant influencing factor. The key factors and the judgment conditions of each key factor are determined based on the historical operating data and historical deviation assessment data of the new energy power station to be optimized. The scheduling strategy determination module is used to determine the corresponding operating mode based on the dominant influencing factors, and to determine the scheduling strategy of the new energy power station to be optimized according to the operating mode. The optimization control module is used to send control commands corresponding to the scheduling strategy to the new energy power stations to be optimized, so that the new energy power stations to be optimized can execute the control commands.

[0022] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the above-described first aspect or any corresponding embodiment of the new energy power station optimization control method based on the analysis of key factors of deviation assessment. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first type of the optimization control method for new energy power stations based on the analysis of key factors of deviation assessment according to an embodiment of the present invention. Figure 3 This is an operational status data diagram based on a specific application embodiment of the optimization control method for new energy power stations based on the analysis of key factors in deviation assessment; Figure 4 This is a comparison chart of deviation assessment electricity costs based on a specific application example of the optimized control method for new energy power plants based on the analysis of key factors in deviation assessment. Figure 5 This is a structural block diagram of a new energy power station optimization control device based on the analysis of key factors of deviation assessment according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0028] As an optional application scenario of this invention, the specific application environment architecture or specific hardware architecture on which the new energy power station optimization control method based on the analysis of key factors of deviation assessment depends is described here. For example... Figure 1 As shown, the architecture system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0029] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0030] According to an embodiment of the present invention, an embodiment of an optimization control method for new energy power stations based on the analysis of key factors of deviation assessment is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This embodiment provides an optimized control method for new energy power plants based on the analysis of key factors in deviation assessment, which can be used on the aforementioned mobile terminals, such as mobile phones and tablets. Figure 2 This is a flowchart of a new energy power station optimization control method based on the analysis of key factors in deviation assessment according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Obtain real-time operation data of the new energy power station to be optimized.

[0032] In one optional embodiment, the real-time operation data of the renewable energy power station to be optimized is continuously collected with a basic time resolution of 15 minutes, including power data such as actual power generation, short-term forecast power, and ultra-short-term forecast power; market price information such as day-ahead clearing price and real-time clearing price is obtained through the power trading platform interface; meteorological parameters such as irradiance, temperature, humidity, and wind speed are obtained from the power station's self-built meteorological monitoring equipment or professional meteorological service agencies; at the same time, the operating parameters of the energy storage system, such as the state of charge and charging / discharging power limits, are monitored in real time; and grid operation information such as power load and reserve capacity are obtained through other channels.

[0033] Furthermore, the real-time running data is processed for missing values, outlier identification and correction, and standardization for different data types based on spatiotemporal interpolation.

[0034] Step S202: Calculate the feature values ​​of each key factor from the real-time running data according to a preset order, and diagnose the feature values ​​based on the judgment conditions of each key factor, and determine the first key factor that meets the judgment conditions as the dominant influencing factor.

[0035] In one optional embodiment, the key factors and the criteria for determining each key factor are determined based on the historical operating data and historical deviation assessment data of the new energy power station to be optimized.

[0036] Specifically, the process begins by analyzing historical operational data and historical deviation assessment data of the stations to identify key factors related to deviation assessment and set corresponding judgment conditions. Then, real-time operational data is quantitatively calculated in a preset order to obtain the characteristic values ​​of each key factor. In accordance with the judgment conditions, compliance diagnosis is performed one by one, and the first key factor that meets the judgment conditions is identified as the dominant influencing factor.

[0037] Step S203: Determine the corresponding operation mode based on the dominant influencing factors, and determine the scheduling strategy for the new energy power station to be optimized according to the operation mode.

[0038] In one optional embodiment, the operating modes include an economic mode, a predictive correction mode, a priority tracking mode, and a normal mode. A pre-established correlation between dominant influencing factors and suitable operating modes is established. Based on the diagnosed dominant influencing factors and their corresponding operating modes, and combined with the control logic of the operating mode, specific scheduling strategies are formulated for the control targets of the new energy power plants.

[0039] Step S204: The control command corresponding to the scheduling strategy is sent to the new energy power station to be optimized so that the new energy power station to be optimized can execute the control command.

[0040] In one optional embodiment, the established scheduling strategy is transformed into standardized control commands that can be identified and executed by each execution device in the new energy power station. Through the control execution link of the power station, the control commands are accurately sent to the corresponding execution units.

[0041] Specifically, in terms of energy storage control, a detailed charging and discharging plan is generated based on the selected control mode, including parameters such as power setpoint, duration, and SOC control range. The control system adopts a hierarchical adjustment strategy, first responding quickly to power changes through feedforward control, and then eliminating steady-state errors through feedback control. For AGC system control, the power setpoint is dynamically adjusted, appropriately relaxing tracking requirements in economic mode and strictly executing the planned curve in priority tracking mode. For predictive model optimization, the module generates parameter adjustment instructions to guide the predictive system in online learning and model updates. Furthermore, a comprehensive safety protection mechanism is established, monitoring equipment operating status in real time to ensure control commands are executed within safety constraints. When equipment abnormalities or operational risks are detected, the system automatically switches to safety mode, prioritizing equipment safety.

[0042] The new energy power plant optimization control method provided in this embodiment, based on the analysis of key factors in deviation assessment, determines key factors and judgment conditions based on the power plant's historical operation and deviation assessment data. This ensures that the selection of key factors and the setting of judgment conditions are aligned with the actual operating characteristics of the power plant, overcoming the insufficient adaptability of generalized standards and making subsequent factor diagnosis more targeted. It diagnoses the first dominant influencing factor that meets the conditions in a preset order, accurately and quickly locating the core factors currently affecting deviation assessment, avoiding ambiguity caused by multiple factors, and making subsequent control more targeted. Furthermore, it matches the corresponding operating mode and formulates a scheduling strategy based on the dominant influencing factor, ensuring that the scheduling strategy is highly adapted to the current core operating status of the power plant, overcoming the limitations of a single control mode, and making the strategy formulation more in line with actual management and control needs. Finally, it issues the control commands corresponding to the scheduling strategy to the power plant and promotes their execution, transforming the formulated adaptive scheduling strategy into the actual control actions of the power plant.

[0043] In some optional implementations, the step of determining key factors based on historical operating data and historical deviation assessment data of the renewable energy power station to be optimized includes: Step a1: Based on the historical operating data of the new energy power station to be optimized in different time periods, calculate the characteristic values ​​of each candidate factor in different prediction time periods.

[0044] In one optional embodiment, a sliding time window mechanism is employed to extract historical operating data of the renewable energy power plants to be optimized within different time periods, and to calculate the characteristic values ​​of each candidate factor within different prediction time periods. For example, in terms of deviation electricity price analysis, the module focuses on analyzing indicators such as short-term prediction error, real-time electricity price difference, and power volatility. In terms of performance-based electricity price analysis, the module focuses on indicators such as ultra-short-term prediction accuracy, meteorological data deviation, and power volatility. The module uses a sliding time window mechanism to extract the characteristic values ​​of data changes for various indicators, such as derived indicators such as the standard deviation, variance, extreme value difference, and electricity price volatility of power fluctuations within a historical hour.

[0045] Step a2: Based on the characteristic values ​​of each candidate factor in different prediction time periods and the historical deviation assessment data in different prediction time periods, calculate the correlation coefficient between each candidate factor and the historical deviation assessment data.

[0046] In one optional embodiment, the feature values ​​of candidate factors within the same prediction time period are precisely mapped to historical deviation assessment data. For each candidate factor, the correlation coefficient between its feature value within that prediction time period and the corresponding historical deviation assessment data is calculated separately. The correlation coefficient is a numerical indicator that quantifies the degree of linear association between two sets of data. Calculating the correlation coefficients for the corresponding data for different prediction time periods can accurately reflect the degree of association between each candidate factor and the station deviation assessment at a specific prediction stage.

[0047] Specifically, correlation analysis is performed on historical operating data, and Pearson correlation coefficients are calculated in the analysis of deviation electricity costs and assessment electricity costs to determine the degree of influence of each factor on deviation assessment costs.

[0048] Step a3: Select key factors from candidate factors based on correlation coefficients.

[0049] In one optional embodiment, the magnitude of the correlation coefficient is used as the quantitative judgment basis. Combined with the analysis requirements of deviation assessment, candidate factors that are significantly correlated with the electricity deviation assessment data are screened out, while candidate factors that are weakly correlated and have no substantial impact on deviation assessment are eliminated.

[0050] The new energy power plant optimization control method based on the analysis of key factors for deviation assessment provided in this embodiment calculates the characteristic values ​​of each candidate factor for different prediction time periods using historical operating data of the new energy power plant at different time periods. This allows the characteristic values ​​of the candidate factors to match the operating patterns and deviation assessment dimensions of the power plant at different power prediction stages, enabling the characteristic values ​​to truly reflect the actual state of the candidate factors at the corresponding stages. Furthermore, by combining the characteristic values ​​of the candidate factors with historical deviation assessment data in different prediction time periods, correlation coefficients are calculated to accurately quantify the degree of correlation between each candidate factor and the power plant deviation assessment at a specific prediction stage, which aligns with the actual needs of the power plant's deviation electricity charges and assessment electricity charges in different dimensions. Based on the correlation coefficients, key factors are screened from the candidate factors, effectively eliminating candidate factors with weak correlation to deviation assessment, ensuring that the screened key factors are the core factors that truly affect the power plant deviation assessment.

[0051] In some optional implementations, the historical deviation assessment data includes historical electricity deviation assessment data and historical power deviation assessment data. The historical power deviation assessment data is determined based on the power deviation between the actual power generation and the day-ahead declared power generation of the new energy power plants to be optimized in different forecast periods, as well as the real-time electricity price.

[0052] In one optional embodiment, since the deviation assessment of new energy power plants is divided into electricity deviation assessment and power prediction deviation assessment, historical deviation assessment data is divided into historical electricity deviation assessment data and historical power deviation assessment data. The historical electricity deviation assessment data is the deviation between the actual electricity consumption and the declared electricity consumption for the current day. Furthermore, the penalty settlement for this deviation is related to the real-time electricity price. Therefore, calculating the historical electricity deviation assessment data by combining the aforementioned deviation amount and the real-time electricity price aligns with the actual accounting rules for electricity deviation assessment.

[0053] Historical power deviation assessment data is determined based on the deviation between the predicted power and the actual power of the new energy power plants to be optimized in different prediction time periods.

[0054] The new energy power plant optimization control method based on the analysis of key factors in deviation assessment provided in this embodiment divides historical deviation assessment data into historical electricity deviation assessment data and historical power deviation assessment data. This aligns with the actual situation of new energy power plant deviation assessment, which is divided into two core dimensions: electricity deviation and power prediction deviation. It also matches the assessment classification of deviation electricity fees and power prediction assessment electricity fees. The calculation method of historical electricity deviation assessment data strictly follows the actual accounting rules of electricity deviation assessment, which uses the amount of electricity deviation combined with real-time electricity prices for punitive settlement. Historical power deviation assessment data is determined based on the deviation between predicted power and actual power in different prediction time periods, matching the judgment logic of power prediction assessment, which is centered on the accuracy of power prediction.

[0055] In some optional implementations, key factors include real-time electricity price difference indicators, prediction error indicators, and power fluctuation indicators. Characteristic values ​​for each key factor are calculated from real-time operating data in a preset order. Based on the judgment conditions for each key factor, the characteristic values ​​are diagnosed, and the first key factor that meets the judgment conditions is identified as the dominant influencing factor, including: Step b1: Calculate the characteristic value of the real-time electricity price difference index at different times based on the absolute value of the difference between the real-time electricity price and the day-ahead electricity price in the real-time data.

[0056] Step b2: If the characteristic value of the real-time electricity price difference index exceeds the first preset threshold and the duration exceeds the first preset duration, the real-time electricity price difference index is determined as the dominant influencing factor.

[0057] In an optional embodiment, when the characteristic value of the real-time electricity price difference index exceeds the first preset threshold and the duration exceeds the first preset duration, it indicates that the electricity price difference has undergone a continuous and significant change, which directly affects the net revenue calculation of the site deviation assessment. In this case, the real-time electricity price difference index is determined as the dominant influencing factor.

[0058] Step b3: If the real-time electricity price difference index does not meet the corresponding judgment conditions, calculate the characteristic value of the prediction error index based on the absolute value of the difference between the actual power generation and the predicted power. If the characteristic value of the prediction error index exceeds the second preset threshold and the duration exceeds the second preset duration, the prediction error index is determined as the dominant influencing factor.

[0059] In an optional embodiment, if the real-time electricity price difference index does not meet the corresponding judgment condition, the characteristic value of the prediction error index is calculated based on the absolute value of the difference between the actual power generation and the predicted power. When the characteristic value of the prediction error index exceeds the second preset threshold and the duration exceeds the second preset duration, it indicates that the prediction error is continuously too large, which directly affects the net revenue calculation of the station deviation assessment. At this time, the prediction error index is determined as the dominant influencing factor.

[0060] Step b4: If the real-time electricity price difference index and the prediction error index do not meet their respective judgment conditions, calculate the characteristic value of the power fluctuation index based on the power fluctuation amplitude within the preset time window. If the characteristic value of the power fluctuation index exceeds the third preset threshold and the duration exceeds the third preset duration, the power fluctuation index is determined as the dominant influencing factor.

[0061] In one optional embodiment, a preset time window is first defined and the continuous actual power generation data of new energy power plants within the window is extracted to form a power data sequence; then, based on the sequence, the statistical index of energy fluctuation amplitude is calculated, namely extreme value difference, variance or standard deviation, and the result is the characteristic value of the power fluctuation index. The window slides and scrolls according to a set step size to calculate and update the characteristic value.

[0062] When the characteristic value of the power fluctuation index exceeds the third preset threshold and the duration exceeds the third preset duration, it indicates that the power fluctuation is severe and directly affects the net revenue calculation of the site deviation assessment. In this case, the power fluctuation index is identified as the dominant influencing factor.

[0063] The new energy power plant optimization control method provided in this embodiment, based on the analysis of key factors in deviation assessment, identifies three core key factors: real-time electricity price difference, prediction error, and power fluctuation. It calculates characteristic values ​​for each indicator in a preset order and performs judgments according to their respective judgment conditions, avoiding the logical confusion of parallel judgments of multiple factors and ensuring the hierarchical and orderly nature of the diagnosis of dominant influencing factors. A dedicated characteristic value calculation method is designed for each indicator, allowing the characteristic values ​​to accurately and objectively quantify the actual state of each indicator, providing a reliable quantitative basis for judgment. This avoids misjudgment of dominant factors, improves the accuracy of diagnostic results, and lays a precise foundation for subsequent rapid matching and adaptation of operating modes, ensuring the efficiency of real-time control of the power plant.

[0064] In some optional implementations, step S203 above includes: If the real-time electricity price difference is the dominant influencing factor, the economic mode is activated. The net revenue of different discharge strategies is calculated using a pre-established revenue-penalty analysis model. When the net revenue is positive, the energy storage system in the new energy power station to be optimized performs a discharge operation. The net revenue is determined based on the revenue generated by the discharge strategy and the difference between the power deviation assessment data.

[0065] In one optional embodiment, the real-time electricity price difference directly determines the market arbitrage space and the cost of power deviation assessment at the power station. In this case, the core objective of operation control is to maximize economic benefits and balance electricity price gains with assessment penalties, thus triggering an economic mode. This mode calculates the economics of different charging and discharging strategies by establishing a revenue-penalty analysis model. When the real-time electricity price exceeds the day-ahead price by a threshold and the energy storage system has adjustment capabilities, the system will appropriately relax power point tracking requirements. Within an acceptable deviation range, the system will instruct the energy storage system to discharge during high-price periods to generate profit. The decision-making process comprehensively considers the discharge revenue from high real-time electricity prices minus potential deviation assessment penalty costs; discharge operations are only executed when the net revenue is positive.

[0066] The new energy power station optimization control method based on the analysis of key factors in deviation assessment provided in this embodiment starts the economic mode for scenarios where the real-time electricity price difference index is the dominant influencing factor. It calculates the net revenue of different discharge strategies through a pre-established revenue-penalty analysis model, and incorporates the market revenue generated by energy storage discharge and the cost brought by the power deviation assessment into the same accounting system. This achieves a comprehensive quantitative evaluation of revenue and assessment costs, avoiding the actual revenue loss caused by only considering the discharge revenue and ignoring the assessment penalty. The net revenue is positive as the criterion for the energy storage system to perform discharge operation, avoiding the loss of revenue or increase in assessment costs caused by blind discharge operation.

[0067] In some optional implementations, step S203 above includes: If the prediction error index is the dominant influencing factor, the prediction correction mode is activated. The predicted power is calculated using the pre-established power prediction model, and the model parameters of the power prediction model are corrected to obtain the corrected predicted power result.

[0068] In one optional embodiment, prediction error is the core cause of power deviation assessment. Therefore, the core objective of operation control is to improve prediction accuracy and reduce prediction deviation from the source, thus initiating a prediction correction mode. This mode analyzes historical error patterns, establishes a prediction model parameter correction mechanism, and triggers the online learning function of the prediction model. It uses the latest measured data to perform rolling optimization of model parameters and adaptively corrects the prediction results. For systematic deviations, the module generates correction coefficients to smooth subsequent prediction curves; for random errors, it adjusts the confidence interval of the prediction model to improve the reliability of the prediction results.

[0069] The new energy power plant optimization control method based on the analysis of key factors for deviation assessment provided in this embodiment activates a prediction correction mode for scenarios where prediction error is the dominant influencing factor. This allows the power plant's control actions to precisely focus on power prediction deviation. The predicted power is calculated using a pre-established power prediction model, and the model parameters of the power prediction model are corrected to obtain the corrected predicted power result. This method optimizes the model from the core influencing level of power prediction, rather than simply correcting the predicted value. It can fundamentally improve the accuracy of power prediction and effectively reduce the deviation assessment risk caused by excessive prediction error. At the same time, the corrected predicted power result can provide a more realistic power reference for the subsequent power generation scheduling of the power plant, further enhancing the scientificity and rationality of the power plant scheduling strategy.

[0070] In some optional implementations, step S203 above includes: If power fluctuation is the dominant influencing factor, the priority tracking mode is activated to optimize the charging and discharging strategy of the energy storage system in the new energy power station with the goal of minimizing power deviation.

[0071] In one optional embodiment, excessive power fluctuations can directly lead to a significant deviation between actual and predicted power, causing power overruns and performance risks. In this case, the core objective of operational control is to smooth out fluctuations and minimize power deviations; therefore, a priority tracking mode is activated. This mode elevates the control priority of the energy storage system to the highest level, ensuring power tracking accuracy to the fullest extent. In this mode, the system utilizes its energy storage capacity to the fullest extent to smooth out power fluctuations and minimize the deviation between actual and planned power. The energy storage system's charging and discharging strategy aims to minimize power deviations, responding quickly to power changes to ensure power tracking accuracy and reduce performance costs caused by power fluctuations to the greatest extent possible.

[0072] The new energy power plant optimization control method provided in this embodiment, based on the analysis of key factors for deviation assessment, initiates a priority tracking mode for scenarios where power fluctuation is the dominant influencing factor. Guided by minimizing power deviation, it optimizes the charging and discharging strategies of the energy storage system in the new energy power plant, fully leveraging the power regulation and fluctuation mitigation capabilities of the energy storage system. By scientifically adjusting the charging and discharging strategies, it offsets large fluctuations in the power generation of the power plant, reducing power deviation from the actual control level. This effectively reduces the risk of deviation assessment caused by power fluctuations, while making the control actions of the energy storage system more targeted, improving the utilization efficiency of energy storage regulation resources, and ensuring the stability of the power generation of the power plant.

[0073] In some alternative implementations, if no dominant influencing factor is identified, the optimization control method for new energy power plants based on the analysis of key factors in deviation assessment also includes: In normal mode, a multi-objective optimization algorithm is used to optimize the charging and discharging strategy of the energy storage system in the new energy power station.

[0074] In an optional embodiment, the normal mode employs a multi-objective optimization algorithm to seek a balance among multiple objectives such as assessment costs, equipment wear and tear, and operating costs.

[0075] The new energy power station optimization control method based on the analysis of key factors for deviation assessment provided in this embodiment enables the normal mode for power station operation scenarios where no dominant influencing factors are identified. In this mode, a multi-objective optimization algorithm is used to optimize the charging and discharging strategy of the energy storage system. Unlike the single-objective control strategy, the multi-objective optimization can take into account multiple core needs such as power station deviation assessment and control, efficient utilization of energy storage resources, and normal operation benefits of the power station. It avoids the one-sidedness of single-objective optimization and makes the energy storage charging and discharging strategy under normal conditions more in line with the overall operation goals of the power station. This improves the utilization efficiency of the energy storage system under normal operation scenarios and ensures the stability and economy of the overall operation of the power station.

[0076] As a specific application embodiment of the present invention, in-depth analysis was conducted on the annual operating data of a 100MW photovoltaic power station. First, the data acquisition time resolution was 15 minutes, totaling 35,040 data points. Through correlation analysis and multiple linear regression, key factors affecting deviation electricity charges and assessment electricity charges were identified, and corresponding patterns were determined. The results are shown in Tables 1 and 2.

[0077] Table 1 Key Influencing Factors and Pattern Diagnosis of Deviation Electricity Charges

[0078] Table 2 Key Influencing Factors and Pattern Diagnosis for Electricity Fee Assessment

[0079] Furthermore, a 7-day test was conducted, and the operational status data is as follows: Figure 3 As shown, the control cycle is 15 minutes. Figure 3 The system incorporates power curves and predictions, and designs four typical operating scenarios: a sunny day mode with stable output and high prediction accuracy; a cloudy day mode with large output fluctuations and significant prediction errors; a rainy day mode with stable output and low power levels; and a fluctuating electricity price mode. The energy storage system is configured with 5 MW / 20 MWh, and its performance is compared with traditional control modes. Based on historical data analysis, the following operating mode trigger thresholds are set: an electricity price difference threshold of 100 yuan / MWh (exceeding this value triggers the economic mode, initiating the energy storage system to discharge); a prediction error threshold of 8 MW (exceeding this threshold triggers the prediction correction mode); and a power fluctuation threshold of 15 MW (exceeding this threshold triggers the tracking mode, enabling power generation curve tracking). Analysis of the operating modes shows that the system operates in normal mode 81.7% of the time, activates the prediction correction mode 16.4% of the time, and the economic mode and priority tracking mode account for 1.2% and 0.7% respectively, reflecting a control characteristic that prioritizes robust operation with targeted intervention as a supplement.

[0080] In terms of economic benefits, deviation assessment of electricity charges is, for example... Figure 4 As shown, the total cost of the traditional control strategy is -36,602.61 yuan (negative values ​​represent net profit), while the total cost of this invention is 5,803.28 yuan. Specific analysis shows that the improvement in deviation electricity costs is particularly significant, decreasing from -49,830.84 yuan to -4,849.54 yuan, a reduction of 90.3%; the assessment electricity cost also decreased from 13,228.22 yuan to 10,652.82 yuan, a reduction of 19.5%.

[0081] The above data fully demonstrates that by intelligently identifying key influencing factors and dynamically switching control modes, this invention effectively utilizes price differences to generate profits in the economic mode, significantly reduces assessment costs in the predictive correction mode, and prioritizes tracking accuracy during power fluctuations, thereby achieving a substantial improvement in overall economic benefits and providing an effective technical solution for the intelligent operation of new energy power plants.

[0082] This embodiment also provides a new energy power station optimization control device based on the analysis of key factors in deviation assessment. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0083] This embodiment provides an optimized control device for new energy power stations based on the analysis of key factors in deviation assessment, such as... Figure 5 As shown, it includes: The data acquisition module 501 is used to acquire real-time operating data of the new energy power stations to be optimized.

[0084] The dominant influencing factor determination module 502 is used to calculate the characteristic values ​​of each key factor from the real-time operating data according to a preset order, and to diagnose the characteristic values ​​based on the judgment conditions of each key factor. The first key factor that meets the judgment conditions is determined as the dominant influencing factor. The key factors and the judgment conditions of each key factor are determined based on the historical operating data and historical deviation assessment data of the new energy power station to be optimized.

[0085] The scheduling strategy determination module 503 is used to determine the corresponding operating mode based on the dominant influencing factors, and to determine the scheduling strategy of the new energy power station to be optimized according to the operating mode.

[0086] The optimization control module 504 is used to send the control commands corresponding to the scheduling strategy to the new energy power stations to be optimized, so that the new energy power stations to be optimized can execute the control commands.

[0087] The new energy power station optimization control device based on deviation assessment key factor analysis provided in this embodiment of the invention can execute the new energy power station optimization control method based on deviation assessment key factor analysis provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0088] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0089] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0090] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0091] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the new energy power station optimization control method based on deviation assessment key factor analysis according to embodiments of the present invention.

[0092] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0093] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that the computer, processor, microprocessor controller, or programmable hardware includes storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the new energy power station optimization control method based on the analysis of key factors in deviation assessment shown in the above embodiments is implemented.

[0094] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0095] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for optimizing the control of new energy power plants based on the analysis of key factors in deviation assessment, characterized in that, The method includes: Obtain real-time operational data of the new energy power stations to be optimized; The feature values ​​of each key factor are calculated from the real-time operating data in a preset order, and the feature values ​​are diagnosed based on the judgment conditions of each key factor. The first key factor that meets the judgment conditions is identified as the dominant influencing factor. The key factors and the judgment conditions of each key factor are determined based on the historical operating data and historical deviation assessment data of the new energy power station to be optimized. The corresponding operating mode is determined based on the dominant influencing factors, and the scheduling strategy of the new energy power station to be optimized is determined according to the operating mode. The control command corresponding to the scheduling strategy is sent to the new energy power station to be optimized, so that the new energy power station to be optimized executes the control command.

2. The method according to claim 1, characterized in that, The steps for determining the key factors based on the historical operating data and historical deviation assessment data of the new energy power stations to be optimized include: Based on the historical operating data of the new energy power station to be optimized in different time periods, the characteristic values ​​of each candidate factor in different prediction time periods are calculated respectively. Based on the characteristic values ​​of each candidate factor in different prediction time periods and the historical deviation assessment data in different prediction time periods, the correlation coefficient between each candidate factor and the historical deviation assessment data is calculated respectively. The key factors are selected from the candidate factors based on the correlation coefficient.

3. The method according to claim 1, characterized in that, The historical deviation assessment data includes historical electricity deviation assessment data and historical power deviation assessment data. The historical power deviation assessment data is determined based on the power deviation between the actual power generation and the reported power generation of the new energy power station to be optimized in different prediction time periods, as well as the real-time electricity price. The historical power deviation assessment data is determined based on the deviation between the predicted power and the actual power of the new energy power station to be optimized in different prediction time periods.

4. The method according to claim 1, characterized in that, The key factors include real-time electricity price difference indicators, prediction error indicators, and power fluctuation indicators. The characteristic values ​​of each key factor are calculated from the real-time operating data according to a preset order. Based on the judgment conditions of each key factor, the characteristic values ​​are diagnosed, and the first key factor that meets the judgment conditions is identified as the dominant influencing factor, including: The characteristic value of the real-time electricity price difference index at different times is calculated based on the absolute value of the difference between the real-time electricity price and the day-ahead electricity price in the real-time data. If the characteristic value of the real-time electricity price difference index exceeds the first preset threshold and the duration exceeds the first preset duration, the real-time electricity price difference index is determined as the dominant influencing factor. If the real-time electricity price difference index does not meet the corresponding judgment condition, the characteristic value of the prediction error index is calculated based on the absolute value of the difference between the actual power generation and the predicted power. If the characteristic value of the prediction error index exceeds the second preset threshold and the duration exceeds the second preset duration, the prediction error index is determined as the dominant influencing factor. If the real-time electricity price difference index and the prediction error index do not meet their respective judgment conditions, the characteristic value of the power fluctuation index is calculated based on the power fluctuation amplitude within the preset time window. If the characteristic value of the power fluctuation index exceeds the third preset threshold and the duration exceeds the third preset duration, the power fluctuation index is determined as the dominant influencing factor.

5. The method according to claim 1, characterized in that, Based on the dominant influencing factors, the corresponding operating mode is determined, and the scheduling strategy for the new energy power station to be optimized is determined according to the operating mode, including: If the real-time electricity price difference is the dominant influencing factor, the economic mode is activated. The net revenue of different discharge strategies is calculated using a pre-established revenue-penalty analysis model. When the net revenue is positive, the energy storage system in the new energy power station to be optimized performs a discharge operation. The net revenue is determined based on the difference between the revenue generated by the discharge strategy and the power deviation assessment data.

6. The method according to claim 1, characterized in that, Based on the dominant influencing factors, the corresponding operating mode is determined, and the scheduling strategy for the new energy power station to be optimized is determined according to the operating mode, including: If the prediction error index is the dominant influencing factor, the prediction correction mode is activated. The predicted power is calculated using the pre-established power prediction model, and the model parameters of the power prediction model are corrected to obtain the corrected predicted power result.

7. The method according to claim 1, characterized in that, Based on the dominant influencing factors, the corresponding operating mode is determined, and the scheduling strategy for the new energy power station to be optimized is determined according to the operating mode, including: If the power fluctuation index is the dominant influencing factor, the priority tracking mode is activated to optimize the charging and discharging strategy of the energy storage system in the new energy power station to be optimized, with the goal of minimizing the power deviation.

8. The method according to claim 1, characterized in that, If no dominant influencing factor is identified, the method further includes: In normal mode, a multi-objective optimization algorithm is used to optimize the charging and discharging strategy of the energy storage system in the new energy power station to be optimized.

9. A new energy power station optimization control device based on the analysis of key factors in deviation assessment, characterized in that, The device includes: The data acquisition module is used to acquire real-time operating data of the new energy power stations to be optimized; The dominant influencing factor determination module is used to calculate the characteristic values ​​of each key factor from the real-time operating data in a preset order, and to diagnose the characteristic values ​​based on the judgment conditions of each key factor. The first key factor that meets the judgment conditions is determined as the dominant influencing factor. The key factors and the judgment conditions of each key factor are determined based on the historical operating data and historical deviation assessment data of the new energy power station to be optimized. The scheduling strategy determination module is used to determine the corresponding operating mode based on the dominant influencing factors, and to determine the scheduling strategy of the new energy power station to be optimized according to the operating mode. The optimization control module is used to send the control command corresponding to the scheduling strategy to the new energy power station to be optimized, so that the new energy power station to be optimized executes the control command.

10. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the new energy power station optimization control method based on the analysis of key factors for deviation assessment as described in any one of claims 1 to 8.

Images