Energy management and optimal scheduling method for offshore wind power plant

Abstract

The invention discloses an energy management and optimal scheduling method for an offshore wind plant, and belongs to the technical field of offshore wind plant power scheduling. Comprising the following steps: S1, acquiring offshore wind power plant environment data, and analyzing the offshore wind power plant environment data to obtain a wind power plant operation state evaluation threshold value; s2, acquiring operation state data of the offshore wind plant, comparing the operation state data of the offshore wind plant with an operation state evaluation threshold value of the wind plant, and judging whether the offshore wind plant has power loss or not; s3, acquiring health state data of the wind power plant equipment, and judging whether the wind power plant equipment has a fault after the wind power plant energy management optimization scheme is determined based on the health state data of the wind power plant equipment; by acquiring and analyzing the environment data and the operation state data in real time, the operation state of the wind power plant can be accurately evaluated, the stability of power supply is ensured, the power generation income and the power transmission loss are optimized and balanced, and the economic benefit maximization of the wind power plant is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of power dispatching of offshore wind farms, and in particular relates to an energy management and optimization dispatching method for offshore wind farms. Background Art

[0002] An offshore wind farm is a power generation facility that utilizes offshore wind resources to convert wind energy into electricity through wind turbines. Due to the relatively abundant and stable offshore wind resources, offshore wind farms have greater development potential than onshore wind farms. Offshore wind farms are typically located in waters far offshore, where wind resources are abundant and relatively unaffected by topography and buildings. Wind turbines are typically deployed on offshore platforms, and the generated electricity is transmitted to the onshore power grid via submarine cables. With the increasing global demand for clean energy, offshore wind power has become an important direction for wind power generation. Offshore wind farms not only provide a large amount of renewable electricity, but also play an important role in promoting the transformation of the energy structure.

[0003] Electricity demand is often volatile, especially during different time periods and seasons. Wind farms need to coordinate their output with grid demand fluctuations to avoid power surpluses or shortages.

[0004] Traditional energy management and scheduling methods often rely on fixed models and preset operating parameters, which makes it difficult to flexibly respond to dynamic changes in wind farm operations. Summary of the Invention

[0005] The purpose of the present invention is to address the problem that traditional energy management and scheduling methods often rely on fixed models and preset operating parameters, making it inconvenient to flexibly respond to dynamic changes in wind farm operations. This invention proposes an energy management and optimized scheduling method for offshore wind farms. By acquiring and analyzing environmental data and operating status data in real time, the present invention can accurately assess the operating status of the wind farm, promptly detect power losses, ensure the stability of the power supply, and optimize the balance between power generation revenue and power transmission losses, thereby ensuring the maximization of the economic benefits of the wind farm. This solves the problem that traditional energy management and scheduling methods often rely on fixed models and preset operating parameters, making it inconvenient to flexibly respond to dynamic changes in wind farm operations.

[0006] To solve the above technical problems, the present invention provides an energy management and optimization scheduling method for an offshore wind farm, comprising the following steps:

[0007] S1. Obtaining and analyzing offshore wind farm environmental data to obtain wind farm operating status assessment thresholds;

[0008] S2. Acquire operating status data of the offshore wind farm, compare the operating status data of the offshore wind farm with a wind farm operating status assessment threshold, and determine whether there is power loss in the offshore wind farm;

[0009] If there is no power loss, continue to determine whether there is power loss in the offshore wind farm based on the offshore wind farm operating status data and the wind farm operating status assessment threshold;

[0010] If there is power loss, the wind farm energy management optimization plan is determined with the optimization goals of maximizing wind farm power generation revenue, minimizing power transmission losses, and meeting the power load demand within the offshore wind farm;

[0011] S3. Obtaining health status data of wind farm equipment, and determining whether there is a fault in the wind farm equipment after determining the wind farm energy management optimization plan based on the health status data of the wind farm equipment;

[0012] If it is determined that there is a fault, a fault warning is issued;

[0013] If it is determined that no fault exists, the health status data of the wind farm equipment is continued to be obtained.

[0014] Preferably, the S1 includes:

[0015] S11, obtaining offshore wind farm environmental parameter data, wherein the offshore wind farm environmental parameter data includes: parameterized wind speed data, parameterized wind direction data, and parameterized line temperature data;

[0016] S12. Determining a wind farm environmental assessment coefficient based on offshore wind farm environmental data and offshore wind farm environmental parameter data, wherein the offshore wind farm environmental data includes wind speed data, wind direction data, and line temperature data;

[0017] S13. Determining a wind farm environmental assessment coefficient based on offshore wind farm environmental data and offshore wind farm environmental parameter data, wherein the offshore wind farm environmental data includes wind speed data, wind direction data, and line temperature data;

[0018] S14. Store the wind farm environmental assessment coefficient as a designated tag, compare the designated tag with each set tag stored in the database one by one, determine the set tag that is the same as the designated tag, and obtain the wind farm operating status assessment threshold corresponding to the set tag stored in the database.

[0019] Preferably, determining whether there is power loss in the offshore wind farm in S2 specifically includes:

[0020] Sa. Obtaining offshore wind farm operating status parameter data, wherein the offshore wind farm operating status parameter data includes parameter power output data, parameter load demand data, and parameter wind farm power generation;

[0021] Sb. Obtaining permissible deviation data of the operating status of an offshore wind farm, wherein the permissible deviation data of the operating status of the offshore wind farm includes a permissible deviation value of power output data, a permissible deviation value of load demand data, and a permissible deviation value of wind farm power generation;

[0022] Sc, determining an offshore wind farm operating status assessment coefficient based on offshore wind farm operating status data, offshore wind farm operating status parameter data, and offshore wind farm operating status allowable deviation data, wherein the offshore wind farm operating status data includes power output data, load demand data, and wind farm power generation;

[0023] Sd, comparing the offshore wind farm operation status assessment coefficient with the wind farm operation status assessment threshold, and determining whether the offshore wind farm operation status assessment coefficient is greater than the wind farm operation status assessment threshold;

[0024] If the offshore wind farm operating status assessment coefficient is judged to be greater than the wind farm operating status assessment threshold, it is judged that there is no power loss;

[0025] If it is determined that the offshore wind farm operating status assessment coefficient is not greater than the wind farm operating status assessment threshold, it is determined that there is power loss.

[0026] Preferably, obtaining the offshore wind farm operating status allowable deviation data specifically includes:

[0027] Sa. Acquire operating state deviation impact data, wherein the operating state deviation impact data includes blade surface roughness and blade rotation speed;

[0028] Sb. Obtaining an operating state deviation impact matching data set stored in a database, wherein the operating state deviation impact matching data set includes a plurality of operating state deviation impact matching data, wherein the operating state deviation impact matching data includes a blade surface roughness matching value and a blade speed matching value;

[0029] Sc. comparing the operation state deviation impact data with each operation state deviation impact matching data stored in the database one by one to determine each operation state comparison value;

[0030] Sd, determining the operating state deviation impact matching data corresponding to the minimum operating state comparison value, and obtaining the corresponding offshore wind farm operating state allowable deviation data from the database based on the operating state deviation impact matching data.

[0031] Preferably, the calculation formula of the offshore wind farm operating status assessment coefficient is:

[0032]

[0033] Specifically, JB is the operating status assessment coefficient of the offshore wind farm, sA is the power output data, cA is the parameterized power output number, ΔsA is the allowable deviation value of the power output data, sS is the load demand data, cS is the parameterized load demand data, ΔsS is the allowable deviation value of the load demand data, sD is the wind farm power generation, cD is the parameterized wind farm power generation, and ΔsD is the allowable deviation value of the wind farm power generation.

[0034] Preferably, in S2, the optimization objectives are to maximize the power generation revenue of the wind farm, minimize the power transmission loss, and meet the electricity load demand in the offshore wind farm. The specific analysis process is: obtain the objective function of maximizing the power generation revenue and minimizing the power transmission loss, and determine the wind farm energy management optimization plan based on the genetic algorithm while meeting the electricity load demand constraints, wind turbine operation constraints, power transmission system constraints and balance constraints in the offshore wind farm.

[0035] Preferably, in S3, the power generation revenue maximization objective function is specifically expressed as:

[0036]

[0037] Where, P i is the actual active power output of the i-th wind turbine, C is the grid electricity price, C OM，i is the unit time operation and maintenance cost of the i-th wind turbine, t is the time interval, i is the number of the wind turbine, i = 1, 2, ..., N, N is the total number of wind turbines;

[0038] The objective function of minimizing power transmission loss is specifically expressed as:

[0039]

[0040] Where Ω is the set of transmission lines, r aj is the resistance of circuit aj, S aj is the power transmission capacity of the transmission line, and aj is the line connecting nodes a and j.

[0041] Preferably, in S3, judging whether there is a fault in the wind farm equipment after determining the wind farm energy management optimization plan based on the health status data of the wind farm equipment is specifically as follows:

[0042] Sa. Obtaining wind farm equipment health status parameter data, wherein the wind farm equipment health status parameter data includes a parameterized generator winding temperature, a parameterized gearbox vibration amplitude, and a parameterized line leakage current;

[0043] Sb. Obtaining wind farm equipment health status allowable deviation data, wherein the wind farm equipment health status allowable deviation data includes a generator winding temperature allowable deviation value, a gearbox vibration amplitude allowable deviation value, and a line leakage current allowable deviation value;

[0044] Sc. determining a wind farm equipment health status assessment coefficient based on the wind farm equipment health status data, wind farm equipment health status parameter data, and wind farm equipment health status allowable deviation data, wherein the wind farm equipment health status data includes generator winding temperature, gearbox vibration amplitude, and line leakage current;

[0045] Sd, judging whether the wind farm equipment health status assessment coefficient is greater than the wind farm equipment health status assessment threshold stored in the database;

[0046] If the wind farm equipment health status assessment coefficient is greater than the wind farm equipment health status assessment threshold stored in the database, it is determined that a fault exists;

[0047] If the wind farm equipment health status assessment coefficient is not greater than the wind farm equipment health status assessment threshold stored in the database, it is determined that no fault exists.

[0048] Preferably, the step of obtaining the wind farm equipment health status allowable deviation data specifically includes the following steps:

[0049] Sa. Obtaining equipment health deviation impact data, wherein the equipment health deviation impact data includes external ambient temperature, load impact change, and ambient humidity;

[0050] Sb. Obtaining a device health deviation impact matching data set stored in a database, wherein the device health deviation impact matching data set includes a plurality of device health deviation impact matching data, wherein the device health deviation impact matching data includes an external ambient temperature matching value, a load impact change matching value, and an ambient humidity matching value;

[0051] Sc. Compare the equipment health deviation impact data with the health deviation impact matching data of each equipment stored in the database one by one to determine the health status comparison value of each equipment;

[0052] Sd, determining the equipment health deviation impact matching data corresponding to the minimum health status comparison value, and obtaining the corresponding wind farm equipment health status allowable deviation data from the database based on the equipment health deviation impact matching data.

[0053] Preferably, the wind farm equipment health status assessment coefficient is specifically expressed as follows:

[0054]

[0055] Where, JC is the health status assessment coefficient of wind farm equipment, sR is the generator winding temperature, cR is the parameter generator winding temperature, ΔsR is the allowable deviation of the generator winding temperature, sT is the gearbox vibration amplitude, cT is the parameter gearbox vibration amplitude, ΔsT is the allowable deviation of the gearbox vibration amplitude, sY is the line leakage current, cY is the parameter line leakage current, and ΔsY is the allowable deviation of the line leakage current.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] 1. By acquiring and analyzing environmental and operational data in real time, this solution accurately assesses the operational status of wind farms, promptly identifies power losses, ensures power supply stability, and optimizes the balance between power generation revenue and power transmission losses, maximizing the economic benefits of wind farms. This addresses the problem that traditional energy management and scheduling methods often rely on fixed models and preset operating parameters, making them inflexible in responding to dynamic changes in wind farm operations.

[0058] 2. In this solution, different types of wind turbines have different wind speed-power conversion curves, meaning that the wind turbine's power generation capacity varies with wind speed. By monitoring wind speed, the power generation capacity of each wind turbine can be predicted, thereby optimizing power generation scheduling. The stability of wind direction affects the long-term power generation efficiency of a wind farm. Frequent changes in wind direction can also affect power generation efficiency. The temperature of power transmission lines directly affects the power transmission capacity. Excessive line temperature leads to increased power loss. When the temperature of power transmission lines rises, the resistance of the wires also increases, resulting in increased power loss during power transmission, affecting power generation efficiency. By comparing tags, the similarity between the current operating status and the standard status can be quickly determined. By comparing and finding identical tags, the wind farm operating status assessment threshold for a specific environment can be obtained. The wind farm operating status assessment threshold is used to determine whether the wind farm is currently experiencing power loss.

[0059] 3. This proposal proposes a wind farm environmental assessment coefficient. Each term in the formula represents the absolute value of the difference between actual environmental data and reference data, uniformly treating positive and negative errors so that all deviations have the same impact on the assessment coefficient. After obtaining the absolute deviation of each parameter, the formula directly accumulates them and performs a natural logarithm transformation on the accumulated result. The purpose is to smooth the impact of the differences so that large deviations do not cause drastic fluctuations in the assessment coefficient. Through a comprehensive assessment of wind speed, wind direction, and line temperature, the operational stability of the wind farm under current environmental conditions can be measured. It can reveal whether the wind farm is affected by environmental factors, help adjust and optimize the scheduling plan, and improve the overall operational efficiency and reliability of the wind farm.

[0060] 4. This solution compares actual data with preset parameter data and combines it with the deviation tolerance range to judge the operating status of the wind farm, timely discover power loss or potential efficiency decline problems, improve the operating efficiency of the wind farm, help optimize the power generation scheduling of the wind farm, and minimize power loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 This is a flow chart of the energy management and optimization scheduling method for offshore wind farms according to the present invention. DETAILED DESCRIPTION

[0062] Example 1: Figure 1 As shown, a method for energy management and optimal scheduling of offshore wind farms includes the following steps: obtaining offshore wind farm environmental data, analyzing the offshore wind farm environmental data, and obtaining a wind farm operating status assessment threshold; the specific analysis process is: obtaining offshore wind farm environmental parameter data, the offshore wind farm environmental parameter data including: parameter wind speed data, parameter wind direction data and parameter line temperature data; determining a wind farm environmental assessment coefficient based on the offshore wind farm environmental data and the offshore wind farm environmental parameter data, the offshore wind farm environmental data including wind speed data, wind direction data and line temperature data; storing the wind farm environmental assessment coefficient as a designated label, comparing the designated label with each set label stored in a database one by one, determining the set label that is the same as the designated label, and obtaining the wind farm operating status assessment threshold corresponding to the set label stored in the database.

[0063] In this embodiment, different types of wind turbines have different wind speed-power conversion curves, that is, the power generation capacity of the wind turbine changes with the change of wind speed. By monitoring the wind speed, the power generation of each wind turbine can be predicted, and then the power generation scheduling can be optimized. The stability of wind direction affects the long-term power generation efficiency of the wind farm. If the wind direction changes frequently, it will affect the power generation efficiency. The temperature of the power transmission line directly affects the power transmission capacity. Excessive line temperature will lead to increased power loss. When the temperature of the power transmission line rises, the resistance of the wire will also increase, which will lead to increased power loss during the power transmission process and affect the power generation efficiency. By comparing the labels, the similarity between the operating status of the current environment and the standard status can be quickly determined. By comparing and finding the same labels, the wind farm operating status assessment threshold under a specific environment can be obtained. The wind farm operating status assessment threshold is used to determine whether the wind farm is currently in a state of power loss.

[0064] The calculation formula for the wind farm environmental assessment coefficient is:

[0065] JB=ln(|sQ-cQ|+|sW-cW|+|sE-cE|+1);

[0066] Where, JB is the wind farm environmental assessment coefficient, sQ is the wind speed data, cQ is the reference wind speed data, sW is the wind direction data, cW is the reference wind direction data, sE is the line temperature data, and cE is the reference line temperature data.

[0067] Each term in the formula represents the absolute value of the difference between the actual environmental data and the reference data, uniformly treating positive and negative errors so that all deviations have the same impact on the rating coefficient. After obtaining the absolute deviation of each parameter, the formula directly accumulates them and performs a natural logarithmic transformation on the accumulated result. The purpose is to smooth the impact of the differences so that large deviations do not cause drastic fluctuations in the rating coefficient. Through a comprehensive assessment of wind speed, wind direction, and line temperature, the operational stability of the wind farm under current environmental conditions can be measured, revealing whether the wind farm is affected by environmental factors, helping to adjust and optimize the scheduling plan and improve the overall operational efficiency and reliability of the wind farm.

[0068] Obtaining offshore wind farm operating status data, comparing the offshore wind farm operating status data with a wind farm operating status assessment threshold, and determining whether the offshore wind farm has power loss; the specific analysis process is as follows: obtaining offshore wind farm operating status parameter data, which includes parameterized power output data, parameterized load demand data, and parameterized wind farm power generation; obtaining offshore wind farm operating status allowable deviation data, which includes allowable deviation values ​​for power output data, allowable deviation values ​​for load demand data, and allowable deviation values ​​for wind farm power generation;

[0069] An offshore wind farm operating status assessment coefficient is determined based on offshore wind farm operating status data, offshore wind farm operating status parameter data and offshore wind farm operating status allowable deviation data, where the offshore wind farm operating status data includes power output data, load demand data and wind farm power generation; the offshore wind farm operating status assessment coefficient is compared with the wind farm operating status assessment threshold to determine whether the offshore wind farm operating status assessment coefficient is greater than the wind farm operating status assessment threshold; if it is determined that the offshore wind farm operating status assessment coefficient is greater than the wind farm operating status assessment threshold, it is determined that there is no power loss; if it is determined that the offshore wind farm operating status assessment coefficient is not greater than the wind farm operating status assessment threshold, it is determined that.

[0070] In this implementation plan, by comparing actual data with preset parameter data and combining the deviation tolerance range, it is used to judge the operating status of the wind farm, timely discover power loss or potential efficiency decline problems, improve the operating efficiency of the wind farm, help optimize the power generation scheduling of the wind farm, and minimize power loss.

[0071] The calculation formula for the offshore wind farm operating status assessment coefficient is:

[0072]

[0073] Specifically, JB is the operating status assessment coefficient of the offshore wind farm, sA is the power output data, cA is the parameterized power output number, ΔsA is the allowable deviation value of the power output data, sS is the load demand data, cS is the parameterized load demand data, ΔsS is the allowable deviation value of the load demand data, sD is the wind farm power generation, cD is the parameterized wind farm power generation, and ΔsD is the allowable deviation value of the wind farm power generation.

[0074] By comprehensively considering the errors of three key parameters: power output, load demand and wind farm power generation, a comprehensive operating status assessment coefficient is provided. It can quantify whether the operating status of the wind farm is normal, promptly identify potential problems, optimize energy management, improve the power generation efficiency and economic benefits of the wind farm, and reduce the operational risks caused by power loss problems, ensuring efficient energy utilization and equipment stability.

[0075] The operating state allowable deviation data of the offshore wind farm is obtained, and the specific analysis process is as follows: obtaining the operating state deviation impact data, the operating state deviation impact data includes the blade surface roughness and the blade speed; obtaining the operating state deviation impact matching data set stored in the database, the operating state deviation impact matching data set includes multiple operating state deviation impact matching data, and the operating state deviation impact matching data includes the blade surface roughness matching value and the blade speed matching value; comparing the operating state deviation impact data with each operating state deviation impact matching data stored in the database one by one to determine each operating state comparison value; determining the operating state deviation impact matching data corresponding to the minimum operating state comparison value, and obtaining the corresponding offshore wind farm operating state allowable deviation data from the database based on the operating state deviation impact matching data.

[0076] In this implementation scheme, there are many variables in the operation of the wind farm, which will cause differences between the actual operating status and the ideal expectation. In order to accurately evaluate the performance of the wind farm in actual operation, some deviations need to be allowed, otherwise any small deviation will lead to excessive fluctuations or misjudgments of the operating status assessment coefficient. The surface roughness of the blade directly affects the aerodynamic performance of the wind turbine, affecting the efficiency and output power of the wind turbine, so a certain deviation range can be allowed to cope with such changes. The blade speed is a parameter that reflects the working status of the wind turbine. The speed is closely related to factors such as wind speed, load demand, and the response of the wind turbine control system. In actual operation, the wind turbine speed may deviate slightly due to environmental changes, load fluctuations, system adjustments and other factors. Allowing a certain deviation can effectively reflect the flexibility and adaptability of the wind farm under different working conditions.

[0077] The calculation formula for the running status comparison value is:

[0078] BA=|sF-cF|+|sG-cG|;

[0079] Where BA is the operating status comparison value, sF is the blade surface roughness, cF is the blade surface roughness, sG is the blade speed, and cG is the blade speed matching value.

[0080] Variations in blade surface roughness and blade speed can affect wind farm operation, leading to deviations during operation. The operating status comparison value determines whether the deviation is within an acceptable range, identifies the operating status data corresponding to the smallest deviation, and thus determines the most appropriate allowable deviation value for the operating status. This ensures that the wind farm can flexibly adapt to various operating conditions while avoiding unnecessary adjustments or downtime due to excessive fluctuations or misjudgments, thereby improving the operational efficiency and stability of the wind farm.

[0081] If power loss is detected, the wind farm energy management optimization plan is determined with the optimization objectives of maximizing wind farm power generation revenue, minimizing power transmission losses, and meeting the power load demand within the offshore wind farm;

[0082] Obtain the objective function of maximizing power generation revenue:

[0083]

[0084] Where, P i is the actual active power output of the i-th wind turbine, C is the grid electricity price, C OM，i is the unit time operation and maintenance cost of the i-th wind turbine, t is the time interval, i is the number of the wind turbine, i = 1, 2, ..., N, N is the total number of wind turbines.

[0085] The objective function for maximizing power generation revenue aims to maximize the wind farm's total power generation revenue. This revenue is calculated as the product of each wind turbine's actual power generation and the electricity price, minus the operating cost, multiplied by the time interval. This ensures the wind farm achieves maximum economic benefits over the long term. The objective function is maximized by adjusting the operating status of each wind turbine.

[0086] Obtain the power transmission loss minimization objective function:

[0087]

[0088] Where Ω is the set of transmission lines, r aj is the resistance of circuit aj, S aj is the power transmission capacity of the transmission line, and aj is the line connecting nodes a and j.

[0089] Power transmission losses are proportional to the resistance of the transmission line and the square of the power transferred. Reducing these losses helps improve system efficiency and reduce grid operating costs. By selecting appropriate transmission lines and power distribution strategies, energy losses during power transmission can be minimized.

[0090] Obtain the constraints that meet the electricity load demand in the offshore wind farm:

[0091]

[0092] Where, P L is the total electricity load demand in the offshore wind farm.

[0093] Power transmission losses are proportional to the resistance of the transmission line and the square of the power transferred. Reducing these losses helps improve system efficiency and reduce grid operating costs. By selecting appropriate transmission lines and power distribution strategies, energy losses during power transmission can be minimized.

[0094] Obtain constraints, including wind turbine operation constraints, power transmission system constraints, and balance constraints; determine the wind farm energy management optimization plan based on a genetic algorithm under the objective function of maximizing power generation revenue, minimizing power transmission loss, and satisfying the power load demand constraints and constraints within the offshore wind farm.

[0095] In this implementation, a genetic algorithm is an optimization method that simulates natural selection and heredity. Its core concept is to find the global optimal or near-optimal solution by gradually improving the solution by simulating the biological evolutionary process, including operations such as selection, crossover, and mutation. In the first step of the genetic algorithm, an initial population is randomly generated. Each individual represents a possible solution, typically represented by a chromosome, a set of parameters. For wind farm energy management problems, each individual's chromosome contains the wind turbine's power output, its operating status, power transmission, and losses. Each individual is evaluated based on an objective function to determine its fitness. The fitness value represents the individual's relative performance within the solution space; a higher fitness value indicates a solution closer to the optimal solution. Maximizing power generation revenue, minimizing transmission losses, and load demand constraints can all serve as the basis for fitness assessment. Based on the individual's fitness value, the best individuals are then selected as parents, and crossover and mutation are then performed. In these selection methods, individuals with higher fitness values ​​are more likely to be selected, ensuring that superior solutions are passed on to the next generation.

[0096] Partial genes from parent individuals are exchanged to create offspring individuals. Through crossover, the new solution inherits the advantages of the parent, potentially forming a better solution. For example, in a wind farm optimization problem, the crossover operation exchanges partial information about the power output and power transmission strategies of two parent wind turbines to generate a new solution. The genes of some individuals are then randomly altered to increase population diversity and avoid being trapped in local optima. While the probability of mutation is typically low, it effectively explores the search space and prevents the algorithm from converging prematurely. For example, the power output or power transmission of certain wind turbines can be randomly adjusted to optimize the performance of the new individuals under certain constraints. After the crossover and mutation operations, new offspring individuals are generated. Based on their fitness values, individuals with higher fitness are selected to advance to the next generation, replacing those with lower fitness. This process typically employs an elitist strategy, retaining the individuals with the highest fitness to ensure that the optimal solution is not lost.

[0097] The iterative process of a genetic algorithm continues until a preset termination condition is reached. Common termination conditions include: 1. The maximum number of iterations is reached; 2. The fitness value reaches a predetermined threshold; 3. The improvement in the solution is less than a set threshold, indicating that the algorithm has converged.

[0098] The termination condition adopted in this implementation is reaching the maximum number of iterations.

[0099] Fan operation constraints:

[0100] Power output limit: P i,min ≤P i ≤P i,max , Q i,min ≤Q i ≤Q i,max ;

[0101] Where, P i，min is the minimum active power output of the i-th wind turbine, P i，max is the maximum active power output of the i-th wind turbine, Q i，min is the minimum reactive power output of the i-th wind turbine, Q i is the actual reactive power output of the i-th wind turbine, Q i，max is the maximum reactive power output of the i-th wind turbine;

[0102] Constraints ensure that each wind turbine's power output remains within a certain range. Due to the physical limitations of wind turbine operation, each turbine's power output must meet its design capacity, influenced by climatic conditions and system stability. The turbine's maximum active and reactive power limits represent its operating range, while the minimum power limit ensures that the turbine does not operate at extremely low output, thereby preventing inefficient or unstable operation.

[0103] Start-stop constraint: When x i =1, P i ≥P i，min , when x i =0, P i =0, ensuring that the fan has power output only when in operation, and the output power is not less than the minimum operating power;

[0104] Where x i is the operating status of the i-th fan, 1 means running, 0 means stopped;

[0105] The start-stop constraint ensures that the wind turbine does not generate any power output when it is stopped; when the wind turbine is started, its output power must not fall below its minimum active power output. This constraint prevents the wind turbine from generating any power output when it is stopped, and also prevents the wind turbine from starting with a power output below its minimum design operating requirement.

[0106] Power transmission system constraints:

[0107] Line power limit: S aj，min ≤S aj ≤S aj，max ;

[0108] Where S aj，min is the minimum power transmission of line aj, S aj，max is the maximum power transmission of line aj;

[0109] This ensures that the power transmission capacity of each transmission line will not exceed its physical capacity limit, nor fall below the minimum power requirement. This ensures that the power system will not experience line overload or low transmission capacity during transmission, maintaining system stability and security.

[0110] Voltage constraint: V j，min ≤V j ≤V j，max ;

[0111] Where V j，min is the minimum allowable voltage at node j, V j is the actual voltage at node j, V j，max is the maximum allowable voltage at node j.

[0112] Voltage constraints ensure that the voltage level at each node in the power system does not exceed its permitted safety range. Excessive voltage can damage electrical equipment, while excessively low voltage can cause unstable or even malfunctioning equipment, so maintaining voltage within a safe range is crucial.

[0113] Power balance constraints:

[0114]

[0115] This constraint represents power balance, meaning the total power generated by the wind farm (the sum of the power output of all wind turbines) equals the sum of the power transmitted by the transmission lines and the power load demand within the wind farm. This ensures a balanced power supply and avoids power shortages or surpluses.

[0116] Obtaining wind farm equipment health status data, and judging whether there is a fault in the wind farm equipment after determining the wind farm energy management optimization plan based on the wind farm equipment health status data; the specific analysis process is as follows: obtaining wind farm equipment health status parameter data, which includes parameterized generator winding temperature, parameterized gearbox vibration amplitude, and parameterized line leakage current; obtaining wind farm equipment health status allowable deviation data, which includes the allowable deviation value of generator winding temperature, the allowable deviation value of gearbox vibration amplitude, and the allowable deviation value of line leakage current;

[0117] The wind farm equipment health status assessment coefficient is determined based on the wind farm equipment health status data, the wind farm equipment health status parameter data and the wind farm equipment health status allowable deviation data, where the wind farm equipment health status data includes the generator winding temperature, the gearbox vibration amplitude and the line leakage current; it is judged whether the wind farm equipment health status assessment coefficient is greater than the wind farm equipment health status assessment threshold stored in the database; if the wind farm equipment health status assessment coefficient is greater than the wind farm equipment health status assessment threshold stored in the database, it is judged that a fault exists; if the wind farm equipment health status assessment coefficient is not greater than the wind farm equipment health status assessment threshold stored in the database, it is judged that no fault exists.

[0118] In this implementation scheme, the generator winding temperature refers to the change in the winding temperature inside the wind turbine generator. The winding temperature is an important indicator reflecting the motor load and operating status. The increase in temperature will cause the generator to overload, and excessive temperature will cause the winding insulation to be damaged, which will lead to motor failure. The gearbox vibration amplitude refers to the vibration intensity of mechanical components such as gears and bearings in the wind turbine gearbox during rotation. Line leakage current refers to the phenomenon that in the wind farm electrical system, current is lost through the ground or other abnormal channels due to insulation damage, wire aging or other electrical faults. By monitoring the equipment generator winding temperature, gearbox vibration amplitude, and line leakage current, the health status of the equipment can be obtained in real time, and potential faults can be discovered in a timely manner, which can avoid sudden shutdowns of equipment due to faults and improve the operational reliability of the wind farm.

[0119] The calculation formula of the wind farm equipment health status assessment coefficient is:

[0120]

[0121] Where, JC is the health status assessment coefficient of wind farm equipment, sR is the generator winding temperature, cR is the parameter generator winding temperature, ΔsR is the allowable deviation of the generator winding temperature, sT is the gearbox vibration amplitude, cT is the parameter gearbox vibration amplitude, ΔsT is the allowable deviation of the gearbox vibration amplitude, sY is the line leakage current, cY is the parameter line leakage current, and ΔsY is the allowable deviation of the line leakage current.

[0122] The wind farm equipment health assessment coefficient reflects the operational status and health of wind farm equipment. It is crucial to the reliability and efficiency of wind farm equipment. Changes in generator winding temperature, gearbox vibration amplitude, and line leakage current can signal equipment failure or performance degradation. Therefore, a certain degree of tolerance is permitted to avoid misjudgment due to normal fluctuations. This assessment coefficient provides a basis for wind farm maintenance, optimization, and early warning, enabling timely detection of potential failures and ensuring the efficient and safe operation of wind farm equipment.

[0123] Obtain the allowable deviation data of the health status of wind farm equipment. The specific analysis process is: obtain the equipment health deviation impact data, which includes the external ambient temperature, load impact change and ambient humidity; obtain the equipment health deviation impact matching data set stored in the database, which includes multiple equipment health deviation impact matching data, and the equipment health deviation impact matching data includes the external ambient temperature matching value, the load impact change matching value and the ambient humidity matching value; compare the equipment health deviation impact data with each equipment health deviation impact matching data stored in the database one by one to determine each health status comparison value; determine the equipment health deviation impact matching data corresponding to the minimum health status comparison value, and obtain the corresponding wind farm equipment health status allowable deviation data from the database based on the equipment health deviation impact matching data.

[0124] In this implementation, the health status of wind farm equipment is affected by a variety of external factors. The ambient temperature has a significant impact on the measurement of generator winding temperature. Excessively high temperatures can cause the generator winding temperature to rise. Factors such as sudden changes in wind speed at a wind farm or load changes when wind turbines start or stop can cause shock changes in the gearbox load. This can lead to mechanical wear or other transient faults in the equipment, affecting the health status assessment. Ambient humidity has a significant impact on the insulation performance of the line, resulting in insulation degradation, short circuits, or other electrical faults. Therefore, the deviation is set to account for changes in the equipment within the normal operating range. Changes caused by these factors can be tolerated to avoid misjudgments.

[0125] The calculation formula for the health status comparison value is:

[0126]

[0127] Where CA is the healthy state comparison value, sB is the external ambient temperature, cB is the external ambient temperature matching value, sN is the load shock change, cN is the load shock change matching value, sM is the ambient humidity, and cM is the ambient humidity matching value. The load shock change is expressed as (load value after shock - load value before shock) / load value before shock × 100%.

[0128] Through health status comparison values, wind farms can accurately determine whether the equipment is within a reasonable health deviation range, thereby providing a basis for equipment maintenance, early warning and optimization, and ensuring the long-term stable operation of wind farm equipment.

Claims

1. A method for energy management and optimization scheduling of offshore wind farms, characterized in that: The steps include: S1. Obtaining and analyzing offshore wind farm environmental data to obtain wind farm operating status assessment thresholds; S2. Acquire operating status data of the offshore wind farm, compare the operating status data of the offshore wind farm with a wind farm operating status assessment threshold, and determine whether there is power loss in the offshore wind farm; If there is no power loss, continue to determine whether there is power loss in the offshore wind farm based on the offshore wind farm operating status data and the wind farm operating status assessment threshold; If there is power loss, the wind farm energy management optimization plan is determined with the optimization goals of maximizing wind farm power generation revenue, minimizing power transmission losses, and meeting the power load demand within the offshore wind farm; S3. Obtaining health status data of wind farm equipment, and determining whether there is a fault in the wind farm equipment after determining the wind farm energy management optimization plan based on the health status data of the wind farm equipment; If it is determined that there is a fault, a fault warning is issued; If it is determined that no fault exists, the health status data of the wind farm equipment is continued to be obtained.

2. The energy management and optimization scheduling method for an offshore wind farm according to claim 1, characterized in that: Said S1 comprises: S11, obtaining offshore wind farm environmental parameter data, wherein the offshore wind farm environmental parameter data includes: parameterized wind speed data, parameterized wind direction data, and parameterized line temperature data; S12. Determining a wind farm environmental assessment coefficient based on offshore wind farm environmental data and offshore wind farm environmental parameter data, wherein the offshore wind farm environmental data includes wind speed data, wind direction data, and line temperature data; S13. Determining a wind farm environmental assessment coefficient based on offshore wind farm environmental data and offshore wind farm environmental parameter data, wherein the offshore wind farm environmental data includes wind speed data, wind direction data, and line temperature data; S14. Store the wind farm environmental assessment coefficient as a designated tag, compare the designated tag with each set tag stored in the database one by one, determine the set tag that is the same as the designated tag, and obtain the wind farm operating status assessment threshold corresponding to the set tag stored in the database.

3. The energy management and optimization scheduling method for an offshore wind farm according to claim 1, characterized in that: Determining whether there is power loss in the offshore wind farm in S2 specifically includes: Sa. Obtaining offshore wind farm operating status parameter data, wherein the offshore wind farm operating status parameter data includes parameter power output data, parameter load demand data, and parameter wind farm power generation; Sb. Obtaining permissible deviation data of the operating status of an offshore wind farm, wherein the permissible deviation data of the operating status of the offshore wind farm includes a permissible deviation value of power output data, a permissible deviation value of load demand data, and a permissible deviation value of wind farm power generation; Sc, determining an offshore wind farm operating status assessment coefficient based on offshore wind farm operating status data, offshore wind farm operating status parameter data, and offshore wind farm operating status allowable deviation data, wherein the offshore wind farm operating status data includes power output data, load demand data, and wind farm power generation; Sd, comparing the offshore wind farm operation status assessment coefficient with the wind farm operation status assessment threshold, and determining whether the offshore wind farm operation status assessment coefficient is greater than the wind farm operation status assessment threshold; If the offshore wind farm operating status assessment coefficient is judged to be greater than the wind farm operating status assessment threshold, it is judged that there is no power loss; If it is determined that the offshore wind farm operating status assessment coefficient is not greater than the wind farm operating status assessment threshold, it is determined that there is power loss.

4. The energy management and optimization scheduling method for an offshore wind farm according to claim 3, characterized in that: The obtaining of the allowable deviation data of the operating status of the offshore wind farm specifically includes: Sa. Acquire operating state deviation impact data, wherein the operating state deviation impact data includes blade surface roughness and blade rotation speed; Sb. Obtaining an operating state deviation impact matching data set stored in a database, wherein the operating state deviation impact matching data set includes a plurality of operating state deviation impact matching data, wherein the operating state deviation impact matching data includes a blade surface roughness matching value and a blade speed matching value; Sc. comparing the operation state deviation impact data with each operation state deviation impact matching data stored in the database one by one to determine each operation state comparison value; Sd, determining the operating state deviation impact matching data corresponding to the minimum operating state comparison value, and obtaining the corresponding offshore wind farm operating state allowable deviation data from the database based on the operating state deviation impact matching data.

5. The energy management and optimization scheduling method for offshore wind farms according to claim 4, characterized in that: The calculation formula of the offshore wind farm operating status assessment coefficient is: Specifically, JB is the operating status assessment coefficient of the offshore wind farm, sA is the power output data, cA is the parameterized power output number, ΔsA is the allowable deviation value of the power output data, sS is the load demand data, cS is the parameterized load demand data, ΔsS is the allowable deviation value of the load demand data, sD is the wind farm power generation, cD is the parameterized wind farm power generation, and ΔsD is the allowable deviation value of the wind farm power generation.

6. The energy management and optimization scheduling method for offshore wind farms according to claim 1, characterized in that: In S2, the optimization objectives are to maximize the power generation revenue of the wind farm, minimize the power transmission loss, and meet the electricity load demand in the offshore wind farm. The specific analysis process is: obtain the objective function of maximizing power generation revenue and minimizing power transmission loss, and determine the wind farm energy management optimization plan based on the genetic algorithm while meeting the electricity load demand constraints, wind turbine operation constraints, power transmission system constraints, and balance constraints in the offshore wind farm.

7. The energy management and optimization scheduling method for offshore wind farms according to claim 6, characterized in that: In S3, the objective function of maximizing power generation revenue is specifically expressed as: Where, P i is the actual active power output of the i-th wind turbine, C is the grid electricity price, C OM，i is the unit time operation and maintenance cost of the i-th wind turbine, t is the time interval, i is the number of the wind turbine, i = 1, 2, ..., N, N is the total number of wind turbines; The objective function of minimizing power transmission loss is specifically expressed as: Where Ω is the set of transmission lines, r aj is the resistance of circuit aj, S aj is the power transmission capacity of the transmission line, and aj is the line connecting nodes a and j.

8. The energy management and optimization scheduling method for an offshore wind farm according to claim 1, characterized in that: In S3, after determining the wind farm energy management optimization plan based on the health status data of the wind farm equipment, it is determined whether there is a fault in the wind farm equipment, specifically: Sa. Obtaining wind farm equipment health status parameter data, wherein the wind farm equipment health status parameter data includes a parameterized generator winding temperature, a parameterized gearbox vibration amplitude, and a parameterized line leakage current; Sb. Obtaining wind farm equipment health status allowable deviation data, wherein the wind farm equipment health status allowable deviation data includes a generator winding temperature allowable deviation value, a gearbox vibration amplitude allowable deviation value, and a line leakage current allowable deviation value; Sc. determining a wind farm equipment health status assessment coefficient based on the wind farm equipment health status data, wind farm equipment health status parameter data, and wind farm equipment health status allowable deviation data, wherein the wind farm equipment health status data includes generator winding temperature, gearbox vibration amplitude, and line leakage current; Sd, judging whether the wind farm equipment health status assessment coefficient is greater than the wind farm equipment health status assessment threshold stored in the database; If the wind farm equipment health status assessment coefficient is greater than the wind farm equipment health status assessment threshold stored in the database, it is determined that a fault exists; If the wind farm equipment health status assessment coefficient is not greater than the wind farm equipment health status assessment threshold stored in the database, it is determined that no fault exists.

9. The energy management and optimization scheduling method for offshore wind farms according to claim 8, characterized in that: The method of obtaining the wind farm equipment health status allowable deviation data specifically includes the following steps: Sa. Obtaining equipment health deviation impact data, wherein the equipment health deviation impact data includes external ambient temperature, load impact change, and ambient humidity; Sb. Obtaining a device health deviation impact matching data set stored in a database, wherein the device health deviation impact matching data set includes a plurality of device health deviation impact matching data, wherein the device health deviation impact matching data includes an external ambient temperature matching value, a load impact change matching value, and an ambient humidity matching value; Sc. Compare the equipment health deviation impact data with the health deviation impact matching data of each equipment stored in the database one by one to determine the health status comparison value of each equipment; Sd, determining the equipment health deviation impact matching data corresponding to the minimum health status comparison value, and obtaining the corresponding wind farm equipment health status allowable deviation data from the database based on the equipment health deviation impact matching data.

10. The energy management and optimization scheduling method for offshore wind farms according to claim 9, characterized in that: The wind farm equipment health status assessment coefficient is specifically expressed as follows: Where, JC is the health status assessment coefficient of wind farm equipment, sR is the generator winding temperature, cR is the parameter generator winding temperature, ΔsR is the allowable deviation of the generator winding temperature, sT is the gearbox vibration amplitude, cT is the parameter gearbox vibration amplitude, ΔsT is the allowable deviation of the gearbox vibration amplitude, sY is the line leakage current, cY is the parameter line leakage current, and ΔsY is the allowable deviation of the line leakage current.

Images