Risk early warning method and device based on new energy output fluctuation and storage medium

Abstract

The invention relates to a risk early warning method and device based on new energy output fluctuation and a storage medium, which are applied to the technical field of power system dispatching, and comprise the following steps: obtaining the output deviation level of a generator set under a dispatching output plan through historical data, quantifying behavior deviation and incorporating the behavior deviation into a risk model, the risk assessment result is closer to the physical reality and market environment, and the accuracy and reliability of imbalance risk early warning are remarkably improved; accurate risk early warning is provided before a scheduling plan is executed, so that scheduling personnel can identify potential system imbalance risks in advance and have sufficient time to take preventive control measures, and therefore, occurrence of large-scale imbalance events can be effectively avoided, and safe and stable operation of a power grid can be guaranteed; accurate risk early warning helps to reduce unnecessary standby capacity configuration and emergency control cost, avoids sharp fluctuation of spot market price caused by large-scale output deviation at the same time, and helps to maintain stable and economical and efficient operation of the power market.

Description

Technical Field

[0001] This invention relates to the field of power system dispatching technology, specifically to a risk warning method, device, and storage medium based on fluctuations in renewable energy output. Background Technology

[0002] As the penetration rate of new energy sources such as wind power and photovoltaics in the power system continues to increase, their inherent intermittency and volatility pose significant challenges to the real-time balance of the power grid. To mitigate fluctuations in new energy output, traditional adjustable power sources such as thermal power units need to frequently and deeply adjust their output. However, the actual adjustment capability of generator units is not only limited by technical factors such as their physical ramp-up rate and operating status, but their adjustment willingness is also significantly affected by economic factors such as spot market electricity prices. This leads to the actual output of the units often deviating from the dispatch plan.

[0003] In existing technologies, risk assessment methods typically employ stochastic optimization models to address the uncertainties in renewable energy output or load forecasting, focusing primarily on external randomness caused by natural factors. However, these methods generally neglect the behavioral uncertainties of generator units themselves due to technological limitations and economic drivers; that is, they fail to effectively quantify and predict the deviation between the actual response of the units and the planned response after the dispatch schedule is issued. This neglect of unit behavioral deviations leads to a disconnect between the risk assessment model and actual operating conditions, making it difficult to accurately predict the truly potential system imbalance risks. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a risk warning method, device and storage medium based on the fluctuation of new energy output, which aims to solve the problem in the prior art that the risk assessment of system imbalance is inaccurate and the warning is not timely because the behavioral deviation of generator sets is not fully considered when conducting risk assessment of power systems.

[0005] According to a first aspect of the present invention, a risk warning method based on fluctuations in new energy output is provided, the method comprising: Acquire data on new energy output, spot market boundary data, and constraints; Based on the aforementioned new energy output data, spot market boundary data, and constraints, a scheduling output plan for generator units is generated. Based on historical data, determine the output deviation level of the generator units under the aforementioned scheduling output plan; Based on the output deviation level and the power system operation data, the system imbalance risk index is calculated using a probabilistic risk assessment model. The system imbalance risk index is compared with a preset risk threshold, and risk warning information is output based on the comparison result.

[0006] Preferably, The power output plan for generating generator sets includes: Based on the new energy output data, spot market boundary data, and constraints, the Safety Constrained Economic Scheduling (SCED) program is used to calculate the scheduled output plan with the goal of minimizing system operating costs, while meeting the constraints.

[0007] Preferably, The determination of the generator unit output deviation level under the dispatch output plan based on historical data includes: The output deviation level is obtained based on historical real-time market clearing prices, historical winning bid output of the unit, and historical actual output of the unit.

[0008] Preferably, The method of obtaining the output deviation level based on historical real-time market clearing prices, historical winning bid output of the unit, and historical actual output of the unit includes: For each generator set in the current scheduling plan, based on the current market and operating conditions, similar historical scenarios are selected from the historical database according to preset filtering conditions. Obtain the historical winning bid output and corresponding historical actual output data of the unit in similar historical scenarios; The historical deviation value of the unit is obtained by calculating the difference between the historical bid output and the actual output for each pair of historical outputs. By statistically analyzing the historical deviation values ​​of the unit, an expected deviation value is obtained; Obtain the expected deviation values ​​of all generator sets to obtain the overall system's generator output deviation level.

[0009] Preferably, The probabilistic risk assessment model is a stochastic programming model, and the objective function of the stochastic programming model is to minimize the expected cost or the expected imbalance. The probabilistic risk assessment model is based on the Monte Carlo simulation method.

[0010] Preferably, The steps for calculating the system imbalance risk index include: Identify the uncertainties in the system, including boundary variables and the output deviation level of the generator set; For uncertain factors, a probability distribution model is fitted to them based on historical data; Based on probability distribution, a large set of random scenarios is generated through random sampling and other methods. Each scenario represents a possible realization of all uncertain factors in the system during a future scheduling period. For each random scenario, the total imbalance of that random scenario is calculated, and the total imbalance is the system imbalance risk index.

[0011] Preferably, The calculation of the total imbalance for each random scenario includes: Identify the uncertainties in each random scenario and calculate the variance of each uncertainty. The total imbalance of the random scenario is obtained by weighted summation of the variances of each uncertain factor.

[0012] According to a second aspect of the present invention, a risk warning device based on fluctuations in new energy output is provided, the device comprising: Real-time data acquisition module: used to acquire new energy output data, spot market boundary data, and constraints; Dispatch output plan acquisition module: used to generate a dispatch output plan for generator sets based on the new energy output data, spot market boundary data and constraints; Output deviation acquisition module: used to determine the output deviation level of the generator set under the scheduling output plan based on historical data; Imbalance Risk Indicator Acquisition Module: Used to calculate the system imbalance risk index based on the output deviation level and the power system operation data through a probabilistic risk assessment model; Risk warning module: used to compare the system imbalance risk index with a preset risk threshold, and output risk warning information based on the comparison result.

[0013] According to a third aspect of the present invention, a storage medium is provided, the storage medium storing a computer program, which, when executed by a host controller, implements the steps of the above-described method.

[0014] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: This application obtains the output deviation level of generator units under the dispatch output plan through historical data. By quantifying the behavioral deviation and incorporating it into the risk model, the risk assessment results are closer to the physical reality and market environment, significantly improving the accuracy and reliability of imbalance risk early warning. By providing accurate risk warnings before the execution of the dispatch plan, dispatchers can identify potential system imbalance risks in advance and have sufficient time to take preventive control measures, thereby effectively avoiding the occurrence of large-scale imbalance events and ensuring the safe and stable operation of the power grid. Accurate risk warnings help reduce unnecessary reserve capacity configuration and emergency control costs, while avoiding drastic fluctuations in spot market prices caused by large-scale output deviations, thus contributing to the stability and economical and efficient operation of the electricity market.

[0015] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0017] Figure 1 This is a flowchart illustrating a risk warning method based on fluctuations in new energy output, according to an exemplary embodiment. Figure 2 This is a schematic diagram of a system architecture according to another exemplary embodiment; Figure 3 This is a schematic diagram of a risk warning device based on fluctuations in new energy output, according to another exemplary embodiment. In the attached diagram: 1-Real-time data acquisition module; 2-Scheduling output plan acquisition module; 3-Output deviation acquisition module; 4-Imbalance risk indicator acquisition module; 5-Risk early warning module; 10-Data layer; 20-Core calculation module; 21-Data acquisition module; 22-Scheduling plan module; 23-Deviation modeling module; 24-Risk assessment module; 25-Early warning release module; 30-User interaction interface. Detailed Implementation

[0018] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0019] Example 1 Figure 1 This is a flowchart illustrating a risk warning method based on fluctuations in new energy output, according to an exemplary embodiment. Figure 1 As shown, the method includes: S1, obtain new energy output data, spot market boundary data, and constraints; S2, Based on the new energy output data, spot market boundary data and constraints, generate a scheduling output plan for the generator sets; S3, Based on historical data, determine the output deviation level of the generator units under the dispatch output plan; S4. Based on the output deviation level and the power system operation data, the system imbalance risk index is calculated using a probabilistic risk assessment model. S5, compare the system imbalance risk index with the preset risk threshold, and output risk warning information based on the comparison result; Understandably, as shown in the attached document Figure 2 As shown, the method of this application can be executed by an early warning device or system deployed on a power dispatch center server. The system can be logically divided into a data layer 10, a core computing module 20, and a user interface 30. Data Layer 10 serves as the system's data foundation and is responsible for interacting with external data sources. Specifically, Data Layer 10 connects to the power system's real-time monitoring and data acquisition system (i.e., SCADA system), meteorological information databases, and power market databases through standard interface protocols, thereby acquiring various types of power system operation data required for risk assessment. The core computing module 20, serving as the central processing unit for executing the method of this application, integrates a series of functional modules to complete the entire risk warning process. Specifically, the core computing module 20 includes: a data acquisition module 21 for responding to instructions and capturing, cleaning, and integrating the required data from the data layer 10; a scheduling plan module 22 for running optimization algorithms based on the acquired data to generate a benchmark scheduling output plan for generator units; a deviation modeling module 23 for analyzing historical data to establish and apply models to predict the possible output deviation levels of each unit under the current scheduling plan; a risk assessment module 24 for comprehensively considering various uncertainties, including unit output deviations, and running probabilistic evaluation algorithms to calculate system imbalance risk indicators; and a warning release module 25 for generating and releasing risk warning information based on a comparison of the risk assessment results with preset thresholds. The user interface 30 is typically deployed on the dispatcher's workstation as a window for human-computer interaction. After the early warning release module 25 generates early warning information, this information will be presented to the power dispatcher in a visual manner (e.g., highlighted alarms, pop-up prompts, or risk dashboards) through the user interface 30, thereby providing decision support for the dispatcher.

[0020] The following will combine Figure 1 The flowchart shown describes the specific steps of this embodiment: Step S1: Acquire new energy output data, spot market boundary data, and constraints. It is understood that this step is performed by the data acquisition module 21. In a specific application scenario, to assess the risk for a future scheduling period (e.g., 15 minutes or 30 minutes), the data acquisition module 21 needs to acquire a series of basic data from the data layer 10, which includes at least: Power output data from renewable energy units: For example, the power output forecast curves for all wind farms and photovoltaic power stations within a specific regional power grid for the next 15 minutes. These forecast data are typically generated by combining meteorological forecasting models with the operating status of the units.

[0021] Boundary data for the electricity spot market includes, but is not limited to, tie-line switching programs, demand in various ancillary service markets, and real-time market price signal forecasts.

[0022] Various constraints exist for power grid operation, including physical and economic constraints. Physical constraints include power balance, upper and lower limits of generator output, limits on ramp and sag rates per unit time, minimum start-up and shutdown times, and the transmission power limits of lines and transformers determined by the grid topology (i.e., network security constraints). Economic constraints are mainly reflected in the price quotes submitted by each generating unit to the electricity market.

[0023] Step S2: Based on the new energy output data, spot market boundary data, and constraints, a generator set dispatch output plan is generated; this step is executed by the dispatch planning module 22. After acquiring comprehensive operational data, the dispatch planning module 22 runs a safety-constrained economic dispatch program. This program is essentially a large-scale optimization problem-solving process with the objective function of minimizing the total system operating cost, aiming to find a generator set output combination that minimizes the total power generation cost to meet the system's total load demand. Simultaneously, a series of strict constraints must be satisfied during the solution process; these constraints are the various constraints collected in step S1, mainly including: System power balance constraint: The total output of all generator sets plus the net input power of tie lines, after deducting network losses, must equal the total system load.

[0024] Unit operation constraints: The planned output of each unit must be between its upper and lower limits, and the change in output between adjacent scheduling periods cannot exceed its maximum ramp or ramp rate.

[0025] Network security constraints: Through power flow calculations, ensure that under the generated scheduling plan, no line or transformer in the power grid exceeds its safe transmission limit.

[0026] By solving this optimization problem, the scheduling planning module 22 calculates the specific output value allocated to each generator unit in the upcoming scheduling period. These output values ​​together constitute the real-time market scheduling output curve of the generator units, which serves as the benchmark for subsequent analysis, i.e., the scheduling output plan.

[0027] Step S3: Based on historical data, determine the output deviation level of the generator units under the dispatch output plan. As a technical feature of this application, this step is performed by the deviation modeling module 23 to quantify the deviation between the actual response of the generator units and the dispatch instructions. To this end, the deviation modeling module 23 accesses the historical database stored in the data layer 10, which stores power grid operation records over a considerable period of time (e.g., the past year). In this embodiment, a method based on historical statistical analysis is used to determine the output deviation level. Specifically, for each generator unit in the current dispatch plan, the deviation modeling module 23 filters similar scenarios from the historical database based on the current market and operating conditions. The filtering criteria may include the range of historical real-time market clearing prices and the percentage of the unit's winning bid output to its rated capacity (i.e., load factor). Subsequently, for these filtered historical moments, the module extracts the historical winning bid output and the corresponding historical actual output data of the unit. By calculating the difference between each pair of historical winning bid output and actual output, a series of historical deviation values ​​can be obtained. Finally, by statistically analyzing these historical deviation values ​​(e.g., calculating their mean or median), an expected deviation value or deviation rate is derived. This statistical result is used as the expected output deviation level of the unit under the current dispatch output plan. This process is repeated for all generator units to obtain the unit output deviation level of the entire system.

[0028] Step S4: Based on the output deviation level and the power system operation data, the system imbalance risk index is calculated using a probabilistic risk assessment model. This step is performed by the risk assessment module 24, and its goal is to comprehensively quantify the impact of various uncertainties on system balance. In one embodiment of this application, an assessment method based on stochastic programming can be used. First, it is necessary to identify the uncertainties in the system. In this application, in addition to the traditionally considered boundary variables (new energy output fluctuations, system load fluctuations, equipment failures, etc.), the output deviation level of each generator unit determined in step S3 is also considered as a core uncertainty factor. For these uncertainties, the risk assessment module 24 will fit a probability distribution model for them based on historical data. For example, it can be assumed that the new energy output error and load prediction error follow a normal distribution with a mean of 0, and their standard deviation is calculated based on historical prediction error data; while for the generator unit output deviation, the expected value of its probability distribution is the deviation level calculated in step S3. Next, based on these probability distributions, a large set of random scenarios (e.g., 1000 scenarios) is generated through random sampling, where each scenario represents a possible realization of all uncertainties in the system within a future scheduling period. Then, for each random scenario s, the total imbalance that the system may experience is calculated. In this embodiment, the system imbalance risk index is defined as the total imbalance. Its calculation method is as follows: First, the variance of each factor is calculated to measure the fluctuation of that factor in the scenario. The specific calculation formula is: ( i =1…C) In the formula, It is the first i The variance of the uncertain factors It is the variance operator. It is the first i One factor in all scenarios s The set of values ​​below; through this formula, the fluctuation of all uncertain factors (such as wind power output uncertainty, photovoltaic power output uncertainty, load forecast uncertainty and output deviation of each generator unit) can be uniformly measured by variance.

[0029] Secondly, by weighted summing of the variances of each factor, the total imbalance in this scenario is obtained. The calculation formula is as follows:

[0030] in, It is the first iThe weighting coefficients of each factor are pre-set by scheduling experts based on experience or through sensitivity analysis to reflect the importance of different factors to the system balance. Through weighted summation, uncertainties from multiple dimensions can be integrated into a single, comprehensive system imbalance risk indicator. ; Based on imbalance risk indicators Calculate the probability of selecting this scenario (usually using an exponential or linear mapping) for subsequent sampling or risk assessment.

[0031] Step S5: Compare the system imbalance risk index with a preset risk threshold, and output risk warning information based on the comparison result. This step is executed by the warning release module 25, which calculates the system imbalance risk index (i.e., the total imbalance) obtained in step S4. (and a preset system imbalance tolerance threshold) A comparison is then performed. It should be noted that this threshold represents the maximum level of imbalance the system can withstand without triggering emergency control or causing stability problems. Its value can be set according to the grid size and safety margin; for example, in this embodiment, it can be set to 5 megawatt-hours. The logical condition for the comparison is to determine... Does this hold true? If the total imbalance in any evaluation scenario... Exceeding the threshold If the system determines that there is an imbalance risk, the early warning module 25 will immediately generate a risk warning signal. This signal is sent to the user interface 30 via the network, allowing the dispatcher to see a clear warning message on the workstation. For example, the relevant area or unit icon on the interface will turn red, and a pop-up window will display the expected risk level, the magnitude of the imbalance, and the main factors that may cause the risk. Conversely, if the determination result is negative, the process ends and no warning is generated.

[0032] Through the above steps, this embodiment can identify the risk of system imbalance that may be caused by the superposition of factors such as unit behavior deviation and new energy fluctuations before the actual issuance and execution of the dispatch plan. This provides valuable time for dispatchers to take preventive control measures, thereby significantly improving the safety of power grid operation.

[0033] Example 2 As an optional implementation, this embodiment discloses a variation of Embodiment 1. The main difference between this variation and Embodiment 1 is that a more refined machine learning modeling method is used in step S3, "determining the plan deviation level," aiming to improve the accuracy of output deviation level prediction. It is understood that the principles and processes of other steps in this embodiment, such as data acquisition (S1), plan generation (S2), risk assessment (S4), and early warning issuance (S5), can be found in the description of Embodiment 1, and will not be repeated here.

[0034] In this embodiment, the deviation modeling module 23 constructs and trains a machine learning model (e.g., a multiple linear regression model) to predict the unit's output deviation. Specifically: The model construction and training process is as follows: First, a training dataset is prepared from a historical database, where each sample corresponds to the unit's operating status at a historical moment. For each sample, the following features are extracted as model inputs (independent variables): historical real-time market clearing price, the percentage of planned unit output to its rated capacity (load factor), and the rate of planned unit adjustments. Simultaneously, the difference between the unit's "actual output" and "bid-winning output" at that moment is extracted as the model output (dependent variable), i.e., the target value to be predicted—output deviation. Using the massive historical data accumulated in the past as a training set, the multiple linear regression model is trained to find an optimal set of regression coefficients, enabling the model to learn the quantitative relationship between the above input features and the output results.

[0035] Accordingly, the application process of the model is as follows: After completing step S2 and generating a new dispatch output plan, for each generator unit in the power grid, the deviation modeling module 23 extracts its parameters under the current plan: the real-time market clearing price to be executed, the load factor calculated based on the planned output, and the adjustment rate required by the planned output. Subsequently, this set of parameters is input into the trained multiple linear regression model. Based on the learned internal rules, the model directly calculates and outputs a predicted output deviation value. Compared with the statistical average value in Example 1, this predicted value can more dynamically and accurately reflect the behavioral tendency of the unit under the current specific operating conditions and market environment. Finally, this more accurate output deviation level predicted by the machine learning model will be passed to the risk assessment module 24 for the probabilistic risk assessment in the subsequent step S4, thereby making the final output system imbalance risk index more reliable and the early warning result more sensitive and accurate in responding to market changes.

[0036] Example 3 Alternatively, in another embodiment, this application also discloses another variation of Embodiment 1. Its core idea is consistent with Embodiment 1, namely, both consider the unit's output deviation level. The difference lies in that, in step S4, "performing a probabilistic risk assessment," this embodiment uses a Monte Carlo simulation method instead of the stochastic programming algorithm in Embodiment 1 as another specific implementation of the probabilistic risk assessment model. This indicates that the technical solution proposed in this application can be combined with various probability calculation tools. The implementation methods of steps S1, S2, S3, and S5 can refer to Embodiment 1 or Embodiment 2.

[0037] In this embodiment, the Monte Carlo simulation risk assessment process executed by the risk assessment module 24 is as follows: Random sampling and scenario generation: First, a probability distribution model is established for all uncertainties in the system (including new energy output prediction error, system load prediction error, and output deviation level of each generator unit).

[0038] Subsequently, the risk assessment module 24 starts the Monte Carlo simulator and performs large-scale independent random sampling (e.g., 10,000 simulations) based on these probability distribution models. Each simulation randomly selects a specific value for each uncertainty factor, thus forming an independent stochastic scenario of the future system state.

[0039] System imbalance calculation: For each generated scenario, the risk assessment module 24 calculates the net system imbalance under that scenario. The calculation formula is: Net system imbalance = (Actual total output of all generator sets) - (Actual value of total system load). Wherein, "Actual total output" equals "Dispatch plan output" plus the "Output deviation value" sampled under that scenario; "Actual total load" equals "Predicted load value" plus the "Load prediction error value" sampled under that scenario.

[0040] Risk Statistics and Indicator Output: After calculating the net imbalance for all scenarios, the risk assessment module 24 performs a comprehensive statistical analysis of these results to output a system imbalance risk indicator. This indicator can take various forms, such as: a. Probability of exceeding the standard: The number of scenarios where the absolute value of the net imbalance exceeds a preset threshold (e.g., 20 MW) is counted, and the ratio of this number to the total number of scenarios is the probability of exceeding the risk standard.

[0041] b. Value at Risk (VaR): The value at a certain confidence level (e.g., 95%) after sorting all the unbalanced values.

[0042] c. Expected imbalance: Calculate the mathematical expectation of all imbalance values ​​to reflect the average trend of system imbalance.

[0043] After the calculation is completed, the early warning module 25 compares these statistical results (especially the probability of exceeding the risk limit) with a preset risk threshold (for example, an acceptable exceedance probability threshold of 1%). If the calculated probability is greater than the threshold, a risk warning is triggered. On the user interface 30, a probability distribution histogram of the imbalance can also be displayed to the dispatcher, providing them with richer and more intuitive decision-making basis.

[0044] Example 4 This embodiment is also a variation of Embodiment 1. Based on the stochastic programming framework of Embodiment 1, it optimizes the risk measurement method and risk judgment criteria in step S4 to manage and avoid low-probability, high-impact extreme risk events. The implementation methods of steps S1, S2, S3, and S5 can refer to Embodiment 1 or Embodiment 2.

[0045] In this embodiment, the probabilistic risk assessment model used by the risk assessment module 24 is still a stochastic programming model, but its core risk indicator has been changed to Conditional Value at Risk (VaR), replacing the total imbalance based on variance-weighted sum in Embodiment 1. It should be noted that VaR is an advanced risk management metric. That is, VaR aims to quantify the conditional expected value of loss after a certain confidence level of risk value (i.e., within the "tail risk" region).

[0046] The specific workflow of risk assessment module 24 is as follows: Model Construction (Based on Conditional Value at Risk): The stochastic programming model constructed by the risk assessment module 24 has the objective function of minimizing the conditional value at risk of the system's imbalance cost. For example, setting a confidence level α of 95%, the model's objective function is to minimize the average imbalance cost of the top 5% of scenarios with the highest costs across all stochastic scenarios. The imbalance cost can be calculated by multiplying the imbalance amount by a penalty electricity price.

[0047] Risk Assessment and Judgment: After solving the model, an optimal conditional risk value is obtained. Subsequently, in step S5, the early warning issuance module 25 compares the calculated conditional risk value (e.g., 80,000 yuan) with a preset risk tolerance cost (e.g., 50,000 yuan). If the calculated conditional risk value exceeds the preset risk tolerance cost, it is determined that the system has an unacceptable extreme risk.

[0048] Early Warning Information Output: When an early warning is triggered, the user interface 30 not only alerts the user to the risk but also conveys deeper information to the dispatcher, such as: "At a 95% confidence level, the system faces a conditional risk value of 80,000 yuan, exceeding the tolerance limit of 50,000 yuan. This means that in the event of an extreme imbalance, the average economic loss is expected to reach 80,000 yuan." This information gives the dispatcher a clearer and more quantifiable understanding of the severity of the risk, thereby prompting them to take more decisive and forceful preventative measures. By using conditional risk value as a risk indicator, the early warning method in this embodiment can more effectively identify and manage tail risks, and is particularly suitable for power grid operation scenarios with extremely high requirements for safe and stable operation.

[0049] Example 5 Figure 3This is a schematic diagram of a risk warning device based on fluctuations in new energy output, according to another exemplary embodiment. The device includes: Real-time data acquisition module 1: used to acquire new energy output data, spot market boundary data, and constraints; Dispatch output plan acquisition module 2: used to generate a dispatch output plan for generator sets based on the new energy output data, spot market boundary data and constraints; Output deviation acquisition module 3: used to determine the output deviation level of the generator set under the scheduling output plan based on historical data; Imbalance Risk Indicator Acquisition Module 4: Used to calculate the system imbalance risk index based on the output deviation level and the power system operation data through a probabilistic risk assessment model; Risk warning module 5: It is used to compare the system imbalance risk index with the preset risk threshold and output risk warning information based on the comparison result.

[0050] Example 6 This embodiment provides a storage medium storing a computer program, which, when executed by a host controller, implements the various steps in the above method. It is understood that the storage medium mentioned above can be a read-only memory, a hard disk, or an optical disk, etc.

[0051] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.

[0052] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.

[0053] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0054] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0055] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0056] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0057] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.

[0058] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0059] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A risk early warning method based on fluctuations in new energy output, characterized in that, The method includes: Acquire data on new energy output, spot market boundary data, and constraints; Based on the aforementioned new energy output data, spot market boundary data, and constraints, a scheduling output plan for generator units is generated. Based on historical data, determine the output deviation level of the generator units under the aforementioned scheduling output plan; Based on the output deviation level and the power system operation data, the system imbalance risk index is calculated using a probabilistic risk assessment model. The system imbalance risk index is compared with a preset risk threshold, and risk warning information is output based on the comparison result.

2. The method according to claim 1, characterized in that, The power output plan for generating generator sets includes: Based on the new energy output data, spot market boundary data, and constraints, the Safety Constrained Economic Scheduling (SCED) program is used to calculate the scheduled output plan with the goal of minimizing system operating costs, while meeting the constraints.

3. The method according to claim 2, characterized in that, The determination of the generator unit output deviation level under the dispatch output plan based on historical data includes: The output deviation level is obtained based on historical real-time market clearing prices, historical winning bid output of the unit, and historical actual output of the unit.

4. The method according to claim 3, characterized in that, The method of obtaining the output deviation level based on historical real-time market clearing prices, historical winning bid output of the unit, and historical actual output of the unit includes: For each generator set in the current scheduling plan, based on the current market and operating conditions, similar historical scenarios are selected from the historical database according to preset filtering conditions. Obtain the historical winning bid output and corresponding historical actual output data of the unit in similar historical scenarios; The historical deviation value of the unit is obtained by calculating the difference between the historical bid output and the actual output for each pair of historical outputs. By statistically analyzing the historical deviation values ​​of the unit, an expected deviation value is obtained; Obtain the expected deviation values ​​of all generator sets to obtain the overall system's generator output deviation level.

5. The method according to claim 4, characterized in that, The probabilistic risk assessment model is a stochastic programming model, and the objective function of the stochastic programming model is to minimize the expected cost or the expected imbalance. The probabilistic risk assessment model is based on the Monte Carlo simulation method.

6. The method according to claim 5, characterized in that, The steps for calculating the system imbalance risk index include: Identify the uncertainties in the system, including boundary variables and the output deviation level of the generator set; For uncertain factors, a probability distribution model is fitted to them based on historical data; Based on probability distribution, a large set of random scenarios is generated through random sampling and other methods. Each scenario represents a possible realization of all uncertain factors in the system during a future scheduling period. For each random scenario, the total imbalance of that random scenario is calculated, and the total imbalance is the system imbalance risk index.

7. The method according to claim 6, characterized in that, The calculation of the total imbalance for each random scenario includes: Identify the uncertainties in each random scenario and calculate the variance of each uncertainty. The total imbalance of the random scenario is obtained by weighted summation of the variances of each uncertain factor.

8. A risk early warning device based on fluctuations in new energy output, characterized in that, The device includes: Real-time data acquisition module: used to acquire new energy output data, spot market boundary data, and constraints; Dispatch output plan acquisition module: used to generate a dispatch output plan for generator sets based on the new energy output data, spot market boundary data and constraints; Output deviation acquisition module: used to determine the output deviation level of the generator set under the scheduling output plan based on historical data; Imbalance Risk Indicator Acquisition Module: Used to calculate the system imbalance risk index based on the output deviation level and the power system operation data through a probabilistic risk assessment model; Risk warning module: used to compare the system imbalance risk index with a preset risk threshold, and output risk warning information based on the comparison result.

9. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by the main controller, implements each step of the risk warning method based on the fluctuation of new energy output as described in any one of claims 1-7.

Images