Power plant unit maintenance optimization method considering multiple uncertain factors of power market

Abstract

The invention relates to a power plant unit maintenance optimization method considering multiple uncertain factors of a power market, and belongs to the technical field of power system operation management. The method comprises the following steps: firstly, obtaining spot market electricity price and new energy output data in each time period of a historical year in a power plant; a random scene set considering spot market electricity price and new energy output is established based on historical data, time-varying features are described through data segmentation, state space division and a non-uniform Markov model, and the random scene set is generated by using a Monte Carlo method; and finally, taking maximization of the total expected income of the power plant as an objective function, constructing an optimization model in combination with preset constraint conditions of the unit, inputting the random scene set into the optimization model for solving, and outputting an optimized unit operation and maintenance strategy which comprises maintenance plans of wind power, photovoltaic and thermal power units and corresponding output plans. Multiple uncertain factors in the power market can be effectively handled, and the operation and maintenance benefits of a power plant are improved.

Description

Technical Field

[0001] This application relates to the field of power market strategy optimization, and in particular to a method, system, computer equipment, and computer-readable storage medium for optimizing power plant unit maintenance considering multiple uncertainties in the power market. Background Technology

[0002] Currently, optimization methods for unit maintenance in the electricity market environment mainly focus on maintenance plan formulation under deterministic environmental assumptions. Traditional maintenance optimization methods are usually based on deterministic market environments and load forecasts, failing to fully consider the various uncertainties in the electricity market, especially the impact of spot market price fluctuations and the randomness of renewable energy output on maintenance decisions. As the proportion of renewable energy installed capacity continues to increase, the intermittency and volatility of its output bring greater challenges to the maintenance decisions of power generation companies.

[0003] In the electricity spot market environment, the volatility of market electricity prices has significantly increased, which has a significant impact on the maintenance decisions of power generation companies. CN111210144A discloses a power generation risk management method and system for the electricity spot market. This method obtains multiple price scenarios based on Monte Carlo simulation and constructs a power plant profit model and risk model to obtain the optimal bidding strategy. However, this method mainly focuses on day-ahead market bidding decisions and does not effectively combine unit maintenance plans with market electricity price fluctuations.

[0004] The uncertainty of renewable energy output is another important factor affecting maintenance decisions. CN112529249B proposes a virtual power plant optimization scheduling and trading management method that takes into account green certificate trading. It uses a truncated general distribution model to fit renewable energy output and constructs a scheduling model with the optimization objective of maximizing virtual power plant profits. CN108960510B discloses a virtual power plant optimization trading strategy device based on two-stage stochastic programming, considering the impact of the uncertainty of clean energy output and market electricity prices on the virtual power plant's participation in market bidding strategies. Although these methods consider the uncertainty of renewable energy output, they mainly focus on short-term scheduling optimization and do not incorporate medium- and long-term maintenance plans into the overall optimization framework.

[0005] However, existing technologies have the following shortcomings: First, existing maintenance optimization methods are mostly based on deterministic market environment assumptions, failing to fully consider the impact of random factors such as electricity price fluctuations and changes in renewable energy output on maintenance decisions. Second, existing methods lack a systematic consideration of medium- and long-term contract delivery constraints, making it difficult to balance the relationship between maintenance plans and market contract performance. Third, existing methods fail to effectively establish a set of random scenarios covering the characteristics of different periods throughout the year, resulting in insufficient adaptability of maintenance optimization results to the actual market environment. Finally, existing methods fail to take maximizing the overall revenue of power plants as the core objective, making it difficult to achieve synergistic optimization of maintenance plans and market participation strategies. These problems often lead to power generation companies facing the dilemma of insufficient adaptability between maintenance strategies and the market environment in actual operation, resulting in decreased unit utilization or loss of market revenue.

[0006] Therefore, there is an urgent need for a power plant unit maintenance optimization method that can take into account the many uncertainties in the electricity market, so as to improve the operational efficiency of power generation companies in complex market environments. Summary of the Invention

[0007] This application provides a method, system, computer equipment, and computer-readable storage medium for optimizing the maintenance of power plant units that takes into account multiple uncertainties in the electricity market, in order to at least solve the problem in the related art of urgently needing a method for optimizing the maintenance of power plant units that can take into account multiple uncertainties in the electricity market.

[0008] In a first aspect, embodiments of this application provide a method for optimizing the overhaul of power plant units considering multiple uncertainties in the electricity market, deployed in a power plant operation and maintenance support management system, the method comprising: Acquire historical data from the power plant, including spot market electricity prices and renewable energy output for various time periods within a historical year; Based on the aforementioned historical data, a set of random scenarios is established that considers spot market electricity prices and renewable energy output, covering the characteristics of different time periods throughout the year; The objective function is to maximize the total expected revenue of the power plant. An optimization model is constructed in combination with the preset constraints of the unit. The random scenario set is input into the optimization model for solution and optimization, and the optimized unit operation and maintenance strategy is output.

[0009] In some embodiments, a set of random scenarios, based on the historical data and considering spot market electricity prices and renewable energy output, covering characteristics of different time periods throughout the year, includes: The historical data is segmented and optimized to obtain multiple state spaces at different time scales and their corresponding state probabilities. Based on the state space and its corresponding probabilities, a general generating function is used for modeling, and a non-uniform Markov model is used to describe the time-varying characteristics of spot market electricity prices and new energy output in the modeling results, resulting in a time-varying state transition matrix. The initial state space of each dataset is generated using the Monte Carlo method. Based on the initial state space and the state transition matrix, an uncertain random scenario set of spot market electricity price and renewable energy output is obtained.

[0010] In some embodiments, the historical data is segmented and optimized to obtain multiple state spaces at different time scales, and their corresponding state probabilities include: The historical data is divided into multiple datasets according to a preset time scale; Discretize the value range of the coupling between new energy output and spot market electricity price for each dataset to divide the dataset into multiple state spaces; The state probabilities corresponding to each state space are calculated based on historical data. Each state space represents a fixed range of new energy output or spot market electricity price.

[0011] In some embodiments, the factors influencing the objective function include: power plant participation in the spot market, annual transaction volume breakdown, unit maintenance costs, and contract volume deviation.

[0012] In some embodiments, the objective function is expressed by the following formula:

[0013] In the formula, It is the contract for difference (CFD) revenue of the power plant. It is a power plant in the scene Below the m Months in t Contract for Difference (CFD) returns over time The scene where it occurs ω The probability is calculated using Monte Carlo scene generation. This refers to the maintenance costs of wind turbine units within the power plant. It is a penalty for the deviation between the actual power generation and the annual transaction contract delivery curve. The power plant was at the m Months in t The annual contract curve over a given time period is given by a known input. It is a scene ω Next m Months in t The total electricity volume curve in the spot market over time. It is the first m Months in tAnnual contract price over time , and These represent the total number of wind turbine units, the total number of photovoltaic units, and the total number of thermal power units, respectively. This represents the total number of days in the m-th month. It is a scene ω Next w Each wind turbine unit t Predicted output power over time It is a scene ω Next p A photovoltaic unit in t Predicted output power over time.

[0014] In some embodiments, the preset constraints include operating constraints for new energy units and operating constraints for thermal power units; The unit maintenance strategies output by the optimization model include: wind turbine maintenance plans and their corresponding wind turbine output plans, photovoltaic unit maintenance plans and their corresponding output plans, and thermal power unit maintenance plans and their corresponding output plans.

[0015] In some embodiments, the method further includes configuring a penalty mechanism for market contract delivery default during the construction of the optimization model.

[0016] Secondly, embodiments of this application provide a power plant unit maintenance optimization system that considers multiple uncertainties in the electricity market, deployed within a power plant operation and maintenance support management system. The system includes: an acquisition module, a scenario set generation module, and an optimization module, wherein: The acquisition module is used to acquire historical data within the power plant, wherein the historical data includes spot market electricity prices and renewable energy output for various time periods within a historical year; The scenario set generation module is used to establish a random scenario set based on the historical data, taking into account spot market electricity prices and renewable energy output, and covering the characteristics of different time periods throughout the year; The optimization module takes maximizing the total expected revenue of the power plant as the objective function, constructs an optimization model in combination with the preset constraints of the unit, inputs the random scenario set into the optimization model for solution optimization, and outputs an optimized unit operation and maintenance strategy.

[0017] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect above.

[0019] The beneficial effects of this invention are as follows: 1. By conducting multiple uncertainty analysis and modeling of spot market electricity prices and renewable energy output, a general generating function is used to characterize the multi-state matrix and probability of wind and solar power output and market electricity prices. A non-uniform Markov model considering seasonal differences is established. Through Monte Carlo sampling, a set of uncertain scenarios for spot market electricity and renewable energy output covering different seasonal characteristics is generated, which effectively captures the stochastic characteristics of the market environment and provides a reliable data foundation for subsequent optimization decisions.

[0020] 2. By constructing a stochastic optimization maintenance decision model for power plants, with the objective function of maximizing the total power generation revenue of the power plant, the model integrates physical constraints such as maintenance constraints of thermal power and wind turbine units, and output operation constraints of each unit. At the same time, it embeds a market contract delivery default penalty mechanism, thereby achieving systematic optimization of the entire power plant operation process and effectively coordinating unit maintenance, contract delivery constraints and market risk management.

[0021] 3. The optimization method for power plant unit maintenance plans established in this application, which considers multiple uncertainties in the electricity market, establishes maintenance strategies for wind turbines and thermal power units by means of stochastic optimization to meet the delivery of electricity contracts. This solves the problem of insufficient adaptability of maintenance strategies to the market environment, maximizes the market revenue of power plants under multiple uncertainties, avoids the problems of decreased unit utilization or loss of market revenue, and provides strong support for the operational decision-making of power generation enterprises in the electricity market environment. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a flowchart of a power plant unit maintenance optimization method considering multiple uncertainties in the electricity market, according to an embodiment of this application; Figure 2 This is a structural block diagram of a power plant unit maintenance optimization system that takes into account multiple uncertainties in the electricity market, according to this application. Figure 3 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0024] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0025] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0026] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0027] This application provides an optimization method for power plant unit maintenance that considers multiple uncertainties in the electricity market, and it is deployed in the power plant operation and maintenance support management system. Figure 1 This is a flowchart of a power plant unit maintenance optimization method considering multiple uncertainties in the electricity market, according to an embodiment of this application. Figure 1 As shown, the process includes the following steps: S101, Obtain historical data from the power plant, including spot market electricity prices and renewable energy output for various time periods within the historical year; S102, based on historical data, establishes a set of random scenarios that consider spot market electricity prices and renewable energy output, covering the characteristics of different time periods throughout the year; S103 takes maximizing the total expected revenue of the power plant as the objective function and constructs an optimization model in combination with the preset constraints of the unit. The random scenario set is input into the optimization model for solution optimization, and the optimized unit operation and maintenance strategy is output.

[0028] In this embodiment, the specific steps for establishing a set of random scenarios based on historical data, considering spot market electricity prices and renewable energy output, and covering the characteristics of different time periods throughout the year, include: S1, through segmentation and optimization of historical data, yields multiple state spaces at different time scales and their corresponding state probabilities; S2, based on the state space and its corresponding probabilities, uses a general generating function for modeling, and uses a non-uniform Markov model to describe the time-varying characteristics of spot market electricity prices and renewable energy output in the modeling results, and obtains a time-varying state transition matrix; S3 generates the initial state space of each dataset using the Monte Carlo method. Based on the initial state space and the state transition matrix, it obtains a set of uncertain random scenarios for spot market electricity prices and renewable energy output.

[0029] In this embodiment, the specific steps of segmenting historical data and performing optimization processing to obtain multiple state spaces at different time scales and their corresponding state probabilities include: S1 divides historical data into multiple datasets according to a preset time scale; S2, discretize the value range of the coupling between new energy output and spot market electricity price for each dataset, so as to divide the dataset into multiple state spaces; S3 calculates the state probabilities corresponding to each state space based on historical data. Each state space represents a fixed range of new energy output or spot market electricity price.

[0030] In this embodiment, the preset constraints include the operating constraints of new energy units and the operating constraints of thermal power units; the unit maintenance strategies output by the optimization model include: wind turbine maintenance plans and their corresponding wind turbine output plans, photovoltaic unit maintenance plans and their corresponding output plans, and thermal power unit maintenance plans and their corresponding output plans.

[0031] The method of this embodiment will be described in detail below: First, the power plant's operation and maintenance support management system acquires historical data from within the power plant. This historical data includes spot market electricity prices and renewable energy output for various time periods within a historical year. Specifically, the historical data can include records from the past 3-5 years, recorded hourly, including hourly spot market electricity prices and actual renewable energy output (such as wind and solar power). Historical data can be acquired through the power plant's internal data acquisition system, or from electricity market trading platforms and grid dispatch centers.

[0032] Furthermore, based on the acquired historical data, a set of random scenarios is established that considers spot market electricity prices and renewable energy output, covering the characteristics of different time periods throughout the year. The specific implementation method for this step is as follows: First, the historical data is divided into multiple datasets according to a preset time scale. The preset time scale can be a season (spring, summer, autumn, winter), month, weekday / non-working day, daytime / nighttime, etc. For example, the data for the whole year can be divided into datasets for 12 months, and each month's dataset can be further divided into weekday and non-working day categories. Each category can be further divided into daytime (6:00-18:00) and nighttime (18:00-6:00 the next day) time periods, thus forming 48 datasets with different time scales.

[0033] Then, the range of values ​​for coupling renewable energy output and spot market electricity prices is discretized for each dataset to divide the dataset into multiple state spaces. For example, renewable energy output can be divided into 5 intervals according to the percentage of rated capacity: 0-20%, 20%-40%, 40%-60%, 60%-80%, and 80%-100%; spot market electricity prices can be divided into 5 intervals according to price level: low price (0-200 yuan / MWh), relatively low price (200-300 yuan / MWh), medium price (300-400 yuan / MWh), relatively high price (400-500 yuan / MWh), and high price (above 500 yuan / MWh). In this way, the combination of renewable energy output and spot market electricity prices can form 5×5=25 state spaces.

[0034] In a specific example, the annual overall data is divided into monthly time scales, and the range of values ​​for the coupling between renewable energy output and spot electricity market prices in different months is discretized and divided into... A state space, each state Represents a fixed range of new energy output or market price, as defined in (1). In the formula: This represents the operating status of the k-th power plant in the m-th month. and These represent the upper and lower bounds of photovoltaic power output in the k-th state during the m-th month, respectively. Characterizing photovoltaic operating state variables, and These represent the upper and lower bounds of wind power output in the k-th state during the m-th month, respectively. Characterizing wind power operating state variables, and Let these represent the upper and lower bounds of the spot electricity price in the k-th state during the m-th month, respectively. State variables characterizing the spot electricity price level.

[0035] To calculate the probability of different states occurring, the frequency of new energy output or market prices is statistically analyzed based on historical data; therefore, the state probabilities are... Represented as: In the formula, Indicates the first m Historical data for the past month fell within the range The number of samples, Indicates the first in history m Total number of samples over the months.

[0036] The uncertainty is modeled using a multi-state model and a general generating function method, as shown in (3)-(6). Then, a non-uniform Markov model is used to characterize the time-varying features of these uncertainties. In the formula, For the first m A general generating function model for monthly renewable energy generation / market price at time t; For the first m The state probability of renewable energy generation / market price at time t in state i; K is the number of states of renewable energy generation / market price; For the first m The probability of a monthly renewable energy generation / market price transitioning from state i to state j at time t. In the formula, It is a scene ω Next m Months in t Spot market electricity prices at that time It is a scene ω Next w Each wind turbine unit t Predicted power generation rate over time It is a scene ω Next p A photovoltaic unit in t Predicted power generation rate over time This is the initial state space input.

[0037] Finally, the initial state space for each dataset is generated using the Monte Carlo method. Based on the initial state space and the state transition matrix, a set of uncertain random scenarios for spot market electricity prices and renewable energy output is obtained. Specifically, for each time scale dataset, the initial state is first randomly generated based on the probability distribution of each state space at that time scale, and then the state sequence for subsequent time points is generated based on the state transition matrix. This process is repeated multiple times (e.g., 1000 times) to generate a large number of random scenarios, forming a set of random scenarios. Each scenario contains the predicted values ​​for spot market electricity prices and renewable energy output for 8760 hours throughout the year.

[0038] After obtaining the random scenario set, the objective function is to maximize the total expected revenue of the power plant. An optimization model is constructed in combination with the preset constraints of the unit. The random scenario set is input into the optimization model for solution optimization, and the optimized unit operation and maintenance strategy is output.

[0039] Furthermore, the objective function considers factors such as power plant participation in the spot market, annual transaction volume breakdown, unit maintenance costs, and contract volume deviations. In this objective function, the power plant's total expected revenue equals the contract for difference (CFD) revenue minus maintenance costs and penalties for contract volume deviations. The CFD revenue is a weighted sum of CFD revenues across various scenarios, months, and time points, with the weights representing the probability of each scenario occurring.

[0040] In a specific example, the objective function is to maximize the expected market returns of the power plant under various uncertainty scenarios, as shown in (7) - (13), which takes into account the power plant's participation in the spot market, the annual transaction volume breakdown, unit maintenance costs, and contract volume deviations.

[0041] In the formula, It is the contract for difference (CFD) revenue of the power plant. It is a power plant in the scene Below the m Months in t Contract for Difference (CFD) returns over time The scene where it occurs ω The probability is calculated using Monte Carlo scene generation. This refers to the maintenance costs of wind turbine units within the power plant. It is a penalty for the deviation between the actual power generation and the annual transaction contract delivery curve. The power plant was at the m Months in t The annual contract curve over a given time period is given by a known input. It is a scene ω Next m Months in t The total electricity volume curve in the spot market over time. It is the first m Months in t Annual contract price over time , and These represent the total number of wind turbine units, the total number of photovoltaic units, and the total number of thermal power units, respectively. This represents the total number of days in the m-th month. It is a scene ω Next w Each wind turbine unit tPredicted output power over time It is a scene ω Next p A photovoltaic unit in t Predicted output power over time. In the formula, The 01 variables represent the maintenance decisions for wind turbine units; Indicates wind turbine w In time t Start maintenance; Indicates wind turbine w The cost of a single maintenance operation; A binary variable representing a decision to overhaul a photovoltaic unit; Indicates photovoltaic unit p In time t Start maintenance; Indicates photovoltaic unit p The cost of a single maintenance operation; Indicates thermal power unit g The cost of a single maintenance operation; It is a binary variable for thermal power unit maintenance decisions; Indicates time t Start working on thermal power units g Maintenance is being carried out. In the formula, For the scene ω Next m The deviation in electricity volume from the monthly delivery contract. The allowable percentage for the deviation in electricity volume from the contract delivery. This represents the time set corresponding to the m-th month. This represents the penalty coefficient for deviations in the annual transaction contract evaluation.

[0042] Furthermore, the preset constraints include operating constraints for new energy units and operating constraints for thermal power units. The operating constraints for new energy units include: The upper limit of wind turbine output is affected by wind speed and cannot exceed the theoretical maximum output at a given wind speed; the upper limit of photovoltaic turbine output is affected by sunlight intensity and cannot exceed the theoretical maximum output under a given sunlight condition; the output of new energy units is zero during maintenance; the maintenance time of new energy units must meet equipment maintenance requirements, such as at least one preventive maintenance per year, with a maintenance time of not less than the specified minimum time; the maintenance time of new energy units should avoid periods of abundant resources as much as possible.

[0043] The operating constraints of thermal power units include: The output of thermal power units must be between their minimum technical output and maximum rated output; the output of thermal power units must be zero during maintenance; the start-up, shutdown, and ramp-up rates of thermal power units must meet technical requirements, specifically including: the output power of the thermal power unit must be between the minimum and maximum output power; the rate of increase or decrease in the unit's power generation must not exceed its specified ramp-up or ramp-down capacity; and the unit must meet the requirements for minimum continuous operating time and minimum continuous shutdown time during normal operation and shutdown. The maintenance time of thermal power units must meet equipment maintenance requirements, for example, by determining the maintenance cycle based on operating hours or the number of start-ups and shutdowns; the maintenance time of thermal power units should consider the system's reserve capacity requirements to avoid insufficient system reserve due to simultaneous maintenance of multiple units.

[0044] In a specific example, the model proposed in this embodiment takes into account the operational constraints of wind turbines, photovoltaic generators, and thermal power units.

[0045] a) Wind turbine operation: The operating constraints of the wind turbine are shown in formulas (14)-(19). Specifically, the upper and lower limits of the power generation of the wind turbine are shown in (14), the constraints of maintenance and operation decisions are shown in (15), constraint (16) stipulates that a certain interval should be ensured between consecutive maintenance, constraint (17) stipulates that the total number of maintenance for each unit should meet the requirements, the constraint of the maximum number of maintenance for the wind turbine is shown in (18), which can be carried out in the same period, and the continuity of the operating status during the maintenance period is shown in (19).

[0046] In the formula, Indicates wind turbine w The time interval between two consecutive maintenance periods; Indicates wind turbine w The capacity; Indicates wind turbine w exist t A binary variable representing the running state at all times. This indicates that the system is operating normally. Indicates wind turbine w Total number of maintenance operations required; This indicates the minimum number of wind turbine units that can operate simultaneously under maximum maintenance resources. For wind turbines w The time required for a single maintenance.

[0047] b) Operation of photovoltaic power generation equipment: The constraints on photovoltaic power generation are similar to those on wind turbines, as shown in (20)-(25). In the formula, Indicates photovoltaic unit p The time interval between two consecutive maintenance periods; Indicates photovoltaic unit p The capacity; Indicates photovoltaic unit p The binary variable representing the running state at time t. This indicates that the system is operating normally. Indicates photovoltaic unit p Total number of maintenance operations required; This indicates the minimum number of photovoltaic units that can operate simultaneously under maximum maintenance resources. For photovoltaic units p The time required for a single maintenance.

[0048] c) Operation of thermal power units: The constraints of thermal power units are shown in (26)-(35). The upper and lower limits of the output of thermal power units are shown in (26). The constraints of the climbing ability are shown in (27). Constraints (28)-(32) explain the start-up and shutdown constraints. Constraints (33)-(35) explain the maintenance constraints of thermal power units. In the formula, Indicates thermal power unit g exist t A binary variable representing the start or stop status at any given time. and They represent thermal power units g Its ability to climb hills, both upwards and downwards. and They represent thermal power units g The minimum and maximum output power. and Indicates thermal power unit g In time t Start-up and shutdown periods and This represents the shortest start-up and shutdown time for thermal power units. This indicates the minimum continuous operating time of the unit. This indicates the minimum continuous downtime of a thermal power unit. This indicates the time interval between two consecutive maintenance periods of a thermal power unit. Indicates thermal power unit g Total number of maintenance required. Indicates thermal power unit g The time required for one maintenance.

[0049] In summary, the main output variable of this model is the wind turbine maintenance plan. Photovoltaic unit maintenance plan Thermal power unit maintenance plan And the wind turbine output plan under these maintenance programs Photovoltaic unit output plan Thermal power unit output plan .

[0050] The optimization model, by solving the above objective function and constraints, outputs optimized unit operation and maintenance strategies, including: Wind turbine maintenance plan and its corresponding power output plan: clearly define the maintenance schedule for each wind turbine throughout the year, as well as the expected power output during non-maintenance periods; Photovoltaic turbine maintenance plan and its corresponding power output plan: clearly define the maintenance schedule for each photovoltaic turbine throughout the year, as well as the expected power output during non-maintenance periods; Thermal power turbine maintenance plan and its corresponding power output plan: clearly define the maintenance schedule for each thermal power turbine throughout the year, as well as the expected power output during non-maintenance periods.

[0051] In this way, power plants can formulate optimal unit maintenance strategies based on the uncertainties of spot market electricity prices and renewable energy output, thereby maximizing the total expected revenue of the power plant while ensuring reliable equipment operation.

[0052] Example 2

[0053] This application provides a power plant unit maintenance optimization system that considers multiple uncertainties in the electricity market, and it is deployed in the power plant operation and maintenance support management system. Figure 2 This is a structural block diagram of a power plant unit maintenance optimization system that considers multiple uncertainties in the electricity market, according to this application. Figure 2 As shown, the system includes: an acquisition module 20, a scene set generation module 21, and an optimization module 22, wherein: The acquisition module 20 is used to acquire historical data within the power plant, including spot market electricity prices and renewable energy output for various time periods within a historical year. The scenario set generation module 21 is used to establish a random scenario set based on historical data, taking into account spot market electricity prices and renewable energy output, and covering the characteristics of different time periods throughout the year; The optimization module 22 takes maximizing the total expected revenue of the power plant as the objective function and constructs an optimization model in combination with the preset constraints of the unit. It inputs a random scenario set into the optimization model for solution optimization and outputs an optimized unit operation and maintenance strategy.

[0054] The system of this embodiment will now be described in detail: This system, deployed within the power plant operation and maintenance support management system, is a power plant unit maintenance optimization system that considers the many uncertainties in the electricity market. The system consists of three main modules: an acquisition module 20, a scenario set generation module 21, and an optimization module 22.

[0055] The acquisition module 20 acquires historical data from the power plant. This historical data includes spot market electricity prices and renewable energy output for various time periods within a historical year. Specifically, the acquisition module 20 can extract historical data from the power plant's database system via a data interface, or obtain relevant data from the electricity market trading platform and the power grid dispatch center via a network interface. The acquisition module 20 is also responsible for preprocessing the raw data, including data cleaning, outlier handling, and missing value imputation, to ensure the quality of the data used in subsequent analysis.

[0056] The scenario set generation module 21 is responsible for establishing a random scenario set based on historical data, considering spot market electricity prices and renewable energy output, and covering the characteristics of different time periods throughout the year. This module first divides the historical data into multiple datasets according to a preset time scale. Then, it discretizes the value range of the coupling between renewable energy output and spot market electricity prices in each dataset to divide the dataset into multiple state spaces, and calculates the state probability corresponding to each state space based on the historical data. Next, based on the state spaces and their corresponding probabilities, the module uses a general generating function to model the data, and uses a non-uniform Markov model to describe the time-varying characteristics of spot market electricity prices and renewable energy output in the modeling results, obtaining a time-varying state transition matrix. Finally, the module generates the initial state space of each dataset using the Monte Carlo method, and obtains the uncertain random scenario set of spot market electricity prices and renewable energy output based on the initial state space and the state transition matrix.

[0057] Optimization module 22 is responsible for constructing an optimization model with the objective function of maximizing the total expected revenue of the power plant, combined with the preset constraints of the units. It inputs a set of random scenarios into the optimization model for solution optimization and outputs optimized unit operation and maintenance strategies. This module first constructs the objective function, considering factors such as the power plant's participation in the spot market, the annual transaction volume breakdown, unit maintenance costs, and contract volume deviations. Then, the module sets preset constraints, including operational constraints for both renewable energy units and thermal power units. During the construction of the optimization model, the module also configures a penalty mechanism for market contract delivery defaults. Finally, the module inputs the set of random scenarios into the optimization model and solves the optimization problem using algorithms (such as mixed-integer linear programming and genetic algorithms), outputting optimized unit operation and maintenance strategies, including wind turbine maintenance plans and their corresponding wind turbine output plans, photovoltaic unit maintenance plans and their corresponding output plans, and thermal power unit maintenance plans and their corresponding output plans.

[0058] The workflow of this system is as follows: First, the acquisition module 20 retrieves historical data from the power plant's database system or external data sources, including spot market electricity prices and renewable energy output for various time periods within historical years. The acquisition module preprocesses the raw data to ensure data quality.

[0059] Then, the scenario set generation module 21 receives the preprocessed historical data and, through a series of data analysis and modeling steps, generates a set of uncertain random scenarios related to spot market electricity prices and renewable energy output. These scenario sets cover the characteristics of different periods throughout the year and can reflect the uncertainty of spot market electricity prices and renewable energy output.

[0060] Finally, the optimization module 22 receives a set of random scenarios and, combined with the power plant's unit characteristics and operational constraints, constructs an optimization model aimed at maximizing total expected revenue. The optimization module solves this model using a solution algorithm, outputting optimized unit operation and maintenance strategies. These strategies include maintenance schedules for each unit and output plans during non-maintenance periods, helping the power plant maximize total expected revenue while ensuring reliable equipment operation.

[0061] The advantages of this system are: The optimization results are more consistent with reality by taking into account various uncertainties in the electricity market, especially the uncertainties in spot market electricity prices and renewable energy output. By establishing a set of random scenarios covering the characteristics of different time periods throughout the year, the time-varying characteristics of the electricity market can be described more accurately. With the goal of maximizing the total expected revenue of the power plant, while taking into account the unit's operational constraints and market contract delivery requirements, a balance between economy and reliability is achieved. The output optimized unit operation and maintenance strategy is highly practical and can directly guide the power plant's unit maintenance arrangements and operation plan formulation.

[0062] It should be noted that both Example 1 and Example 2 are methods for optimizing the maintenance of power plant units that take into account the many uncertainties in the electricity market.

[0063] In one embodiment, Figure 3 This is a schematic diagram of the internal structure of an electronic device according to an embodiment of this application, such as... Figure 3 As shown, an electronic device is provided, which can be a server, and its internal structure diagram can be as follows. Figure 3As shown, the electronic device includes a processor, a network interface, internal memory, and non-volatile memory connected via an internal bus. The non-volatile memory stores the operating system, computer programs, and a database. The processor provides computing and control capabilities, the network interface communicates with external terminals via a network, the internal memory provides an environment for the operation of the operating system and computer programs, and the computer programs, when executed by the processor, implement a power plant unit maintenance optimization method that considers multiple uncertainties in the electricity market. The database stores data.

[0064] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0065] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0066] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification. The above embodiments only illustrate several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for unit maintenance optimization of power plants considering multiple uncertain factors of power market, characterized in that, The method is deployed in a power plant operation and maintenance guarantee control system, and the method comprises: acquiring historical data in a power plant, wherein the historical data comprises spot market electricity prices and new energy output in each time period in a historical year; establishing a random scenario set considering spot market electricity prices and new energy output and covering characteristics of different time periods throughout the year based on the historical data; constructing an optimization model with a total expected income of the power plant as an objective function and combining preset constraint conditions of the unit, inputting the random scenario set into the optimization model for solving and optimization, and outputting an optimized unit operation and maintenance strategy.

2. The method of claim 1, wherein, The method of establishing a random scenario set considering spot market electricity prices and new energy output and covering characteristics of different time periods throughout the year based on the historical data comprises: splitting the historical data and performing optimization processing to obtain a plurality of state spaces of different time scales and corresponding state probabilities thereof; based on the state spaces and corresponding probabilities thereof, modeling by using a general generating function, and describing time-varying characteristics of spot market electricity prices and new energy output in the modeling result by using a non-uniform Markov model to obtain a time-varying state transition matrix; generating an initial state space of each data set by using a Monte Carlo method, and obtaining an uncertain random scenario set of spot market electricity prices and new energy output according to the initial space state and the state transition matrix.

3. The method of claim 2, wherein, The method of splitting the historical data and performing optimization processing to obtain a plurality of state spaces of different time scales and corresponding state probabilities thereof comprises: dividing the historical data into a plurality of data sets according to a preset time scale; discretizing the value range of new energy output and spot market electricity prices of each data set to divide the data set into a plurality of state spaces; calculating state probabilities corresponding to each state space based on historical data, wherein a state space represents a fixed range of new energy output or spot market electricity prices.

4. The method of claim 1, wherein, Influencing factors of the objective function include: power plant participation in the spot market, annual transaction electricity quantity decomposition, unit maintenance cost, and contract electricity quantity deviation.

5. The method of claim 4, wherein, The objective function is specifically calculated in the following manner to maximize: summing up expected total incomes under all uncertain scenarios, wherein the total income under a single scenario is determined by subtracting the unit maintenance cost and the penalty corresponding to the contract electricity quantity deviation from the spread contract income under the scenario; the spread contract income further comprises annual contract income and spot market income, the annual contract income is obtained from the annual contract price and the agreed delivery electricity quantity on the annual contract curve, and the spot market income is obtained from the difference between the total output of all units and the annual contract agreed delivery electricity quantity under the spot market real-time electricity price in the scenario; the unit maintenance cost is the cumulative sum of the single maintenance cost of each maintenance of all units in the entire cycle, and the penalty corresponding to the contract electricity quantity deviation is calculated by using a preset penalty coefficient for the part of electricity quantity exceeding the preset allowed range when the monthly delivery electricity quantity deviates from the contract electricity quantity.

6. The method of claim 1, wherein, The preset constraint conditions include operation constraints of new energy units and operation constraints of thermal power units. The optimization model outputted unit maintenance strategy includes: wind turbine maintenance plan and corresponding wind turbine output plan, photovoltaic unit maintenance plan and corresponding output plan, thermal power unit maintenance plan and corresponding output plan.

7. A power plant unit maintenance optimization system considering multiple uncertain factors of power market, characterized in that, The system is deployed in a power plant operation and maintenance guarantee control system, and the system includes an acquisition module, a scenario set generation module, and an optimization module. The acquisition module is configured to acquire historical data in the power plant, wherein the historical data includes spot market electricity prices and new energy output in each time period in a historical year. The scenario set generation module is configured to establish a random scenario set considering spot market electricity prices and new energy output and covering different time period characteristics throughout the year based on the historical data. The optimization module takes maximizing total expected revenue of the power plant as an objective function, constructs an optimization model in combination with preset constraint conditions of the units, inputs the random scenario set into the optimization model for solving and optimization, and outputs an optimized unit operation and maintenance strategy.

8. The system of claim 7, wherein, The preset constraint conditions include operation constraints of new energy units and operation constraints of thermal power units. The optimization model outputted unit maintenance strategy includes: wind turbine maintenance plan and corresponding wind turbine output plan, photovoltaic unit maintenance plan and corresponding output plan, thermal power unit maintenance plan and corresponding output plan.

9. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1 to 7.

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

Images