Distributed power grid power generation equipment optimization scheduling method and system

Abstract

The invention discloses a distributed power grid power generation equipment optimization scheduling method and system, and the method comprises the steps: firstly obtaining historical operation state data and real-time operation state data of a distributed power generation network, then taking one piece of distributed power generation equipment as target distributed power generation equipment, and determining an initial output range and an actual output range of the target distributed power generation equipment; and finally, determining the actual output range of the plurality of distributed power generation devices, constructing an output optimization scheduling model, determining an optimization objective function and constraint conditions, solving the output optimization scheduling model, outputting an optimal scheduling scheme, and adjusting the output of the distributed power generation devices. According to the method, the target distributed power generation equipment is evaluated and scored by integrating historical and real-time data so as to accurately determine the actual output range of the equipment, and the scheduling scheme is ensured to better fit the actual operation condition by constructing the optimization model and determining the appropriate target and constraint, so that the operation efficiency and stability of a power grid are improved.

Description

Technical Field

[0001] The present invention relates to a dispatching means for power generation equipment, belonging to the field of microgrid optimization, and particularly relates to an optimized dispatching method and system for distributed grid power generation equipment. Background Art

[0002] With the development of new energy technologies, the demand for energy is increasing, while the consumption of traditional fossil energy is continuously increasing. However, the energy crisis and environmental pollution problems brought by traditional energy also need to be solved urgently. In order to make full use of green and clean renewable energy and reduce the share of traditional energy, distributed generation technology has been developed.

[0003] Distributed generation is a small-module decentralized power generation unit. Distributed generation has many advantages, such as reducing system losses, reducing environmental pollution, and improving power quality, etc. Distributed generation technology combines with the power system to form distributed power generation. In order to better dispatch distributed power generation, an information interaction platform between distributed power generation and the power grid is established to monitor and analyze the operation status of the power grid in real time, and adjust the output of distributed power generation accordingly, so as to achieve collaborative optimization with the power grid. In the existing optimized dispatching solutions for distributed power generation equipment, it is usually based on the subjective experience of relevant technical personnel, and the correctness of subjective experience depends on the technical ability of technical personnel, resulting in a large deviation between the dispatching result and the objective situation, with low accuracy. Moreover, due to the dispersion of distributed power generation equipment, the efficiency of manual evaluation is not high, which is not conducive to the stable operation of distributed power generation equipment. Summary of the Invention

[0004] The purpose of the present invention is to overcome the above-mentioned defects and problems in the prior art, and provide an efficient and accurate optimized dispatching method and system for distributed grid power generation equipment.

[0005] To achieve the above purpose, the technical solution of the present invention is: an optimized dispatching method for distributed grid power generation equipment, including:

[0006] S1. Obtain the historical operation status data and real-time operation status data of the distributed power generation network;

[0007] S2. Based on the historical operation status data and real-time operation status data, taking a distributed power generation equipment in the distributed power generation network as the target distributed power generation equipment, determine the initial output range and actual output range of the target distributed power generation equipment;

[0008] The determination of the actual output range of the target distributed power generation equipment includes any one of the first scheme and the second scheme:

[0009] The steps of the first scheme are as follows:

[0010] A21. Determine the first and second evaluation scores of the target distributed power generation equipment based on the historical operation data and current working environmental data of the target distributed power generation equipment;

[0011] A22. Obtain the equipment status and maintenance data of the target distributed power generation equipment, and determine the third evaluation score of the target distributed power generation equipment;

[0012] A23. Assign corresponding weights to the first evaluation score, the second evaluation score, and the third evaluation score, and calculate the total evaluation score; the expression of the total evaluation score is as follows:

[0013] T = H * w H + E * w E + S * w S ;

[0014] w H + w E + w S = 1;

[0015] Where: T is the total evaluation score, H is the first evaluation score, w H is the weight corresponding to the first evaluation score, E is the second evaluation score, w E is the weight corresponding to the second evaluation score, S is the third evaluation score, w S is the weight corresponding to the third evaluation score;

[0016] A24. Based on the total evaluation score, and set the mapping function α = T / 100 to adjust the initial output range of the target distributed power generation equipment to obtain the actual output range of the target distributed power generation equipment;

[0017] The actual output range is as follows:

[0018] P 实际 = [α × P min , α × P max ;

[0019] Where: α is the mapping function, P min is the minimum value of the initial output range, P max is the maximum value of the initial output range;

[0020] The steps of the second solution are as follows:

[0021] B21. Based on the historical operation data of the target distributed power generation equipment, analyze the output stability evaluation results of the target distributed power generation equipment under different environmental parameter conditions, and determine the output stability evaluation result of the target distributed power generation equipment under the current environmental parameters according to the current environmental parameters of the target distributed power generation equipment;

[0022] Based on the output stability evaluation result of the target distributed generation device under the current environmental parameters, adjust the initial output range of the target distributed generation device to determine the actual output range of the target distributed generation device;

[0023] S3. Determine the actual output ranges of multiple distributed generation devices in the distributed generation network, construct an output optimization scheduling model, and determine the optimization objective function and constraint conditions; solve the output optimization scheduling model, output the optimal scheduling plan, and adjust the output of the distributed generation device based on the optimal scheduling plan.

[0024] In the step A21, the steps for obtaining the first and second evaluation scores specifically include:

[0025] A211. Based on the historical operation data and the current working environmental data of the target distributed generation device, and perform preprocessing;

[0026] The historical operation data includes actual output, operation time, and load change; the current working environmental data includes light intensity, temperature, and humidity;

[0027] A212. Respectively determine the key indicators in the historical operation data and the current working environmental data, and calculate the evaluation index scores of each key indicator based on the fuzzy comprehensive evaluation method; the expression of the evaluation index score is as follows:

[0028]

[0029] Where: F is the evaluation index score, w i is the weight of the i-th evaluation index, s i is the score value of the i-th evaluation index, and n is the total number of evaluation indexes;

[0030] A213. Sum up the evaluation index scores of each key indicator corresponding to the historical operation data to obtain the first evaluation score; sum up the evaluation index scores of each key indicator corresponding to the current working environmental data to obtain the second evaluation score.

[0031] In the step A22, the steps for obtaining the third evaluation score specifically include:

[0032] A221. Define the key dimensions affecting the comprehensive performance of the target distributed generation device, and perform preprocessing; the key dimensions include operation efficiency, failure rate, maintenance cost, maintenance response time, and equipment age;

[0033] A222. Assign weights based on the importance of each key dimension to the comprehensive performance; calculate the score value of each key dimension;

[0034] Based on the scoring values corresponding to each key dimension and their respective weights, calculate the third evaluation score; the expression for the third evaluation score is as follows:

[0035] CES = (S E × a 1 ) + (S FR × a 2 ) + (S MC × a 3 ) + (S MRT × a 4 ) + (S Age × a 5 );

[0036] Where: CES is the third evaluation score, S E , S FR , S MC , S MRT , S Age are the scoring values of operating efficiency, failure rate, maintenance cost, maintenance response time, and equipment age respectively, and a 1 , a 2 , a 3 , a 4 , a 5 are all weights.

[0037] The scoring value S E of the operating efficiency is as follows:

[0038] If the actual operating efficiency E actual is greater than or equal to the benchmark operating efficiency E base , then S E = 100;

[0039] If the actual operating efficiency E actual is less than the benchmark operating efficiency E base , then calculate according to the following formula:

[0040]

[0041] Where: E base is the benchmark operating efficiency, E actual is the actual operating efficiency, and E min is the minimum value of the operating efficiency;

[0042] The scoring value S FR of the failure rate is as follows:

[0043]

[0044] Where: F Ractual is the actual failure rate, F Rtarget is the target failure rate, and ∈ is a positive number to avoid division by zero;

[0045] The scoring value S of the maintenance cost MC is as follows:

[0046]

[0047] Where: MC actual is the actual cost, MC budget is the budgeted cost, and δ is the adjustment factor;

[0048] The scoring value S of the maintenance response time MRT is as follows:

[0049]

[0050] Where: MRT actual is the actual response time, MRT target is the target response time, and γ is the adjustment factor;

[0051] The scoring value S of the equipment age Age is as follows:

[0052]

[0053] Where: Age actual is the actual equipment age, Age life is the preset equipment life.

[0054] The step B21 specifically includes:

[0055] B211. Collect the environmental parameters and output conditions of the target distributed generation equipment, and evaluate the correlation between the output and different numerical conditions of the same type of environmental parameters based on statistical methods;

[0056] B212. Determine the output stability index of the target distributed generation equipment under different environmental parameter conditions based on the historical operation data of the target distributed generation equipment; the output stability index includes output volatility, output standard deviation, and output coefficient of variation;

[0057] B213. Divide the output stability of the target distributed generation equipment based on the output stability index, and determine the output stability evaluation result of the target distributed generation equipment; the output stability evaluation result includes any one of the following:

[0058] First, stable: 80% of the output stability indicators are normal;

[0059] Second, less stable: at least one stability indicator is abnormal;

[0060] Third, extremely unstable: 80% of the output stability indicators are abnormal.

[0061] The step B22 specifically includes:

[0062] B221. Determine the corresponding weighting parameter based on the output stability evaluation result of the target distributed generation device under the current environmental parameters;

[0063] B222. Calculate the actual output range of the target distributed generation device based on the weighting parameter and the initial output range of the target distributed generation device; its expression is as follows:

[0064] P 实际 =P 初始 ×w;

[0065] Where: P 实际 is the actual output range, P 初始 is the initial output range, and w is the weighting parameter.

[0066] The output optimization scheduling model aims to minimize the total operating cost and is subject to constraints such as supply-demand balance constraints, equipment capacity constraints, energy storage system state constraints, upper and lower limits of the energy storage system state, diesel generator start-stop constraints, and power grid network security constraints;

[0067] The objective function of the optimization scheduling model is as follows:

[0068]

[0069] Where: T is the total number of time periods, C pv，t , C WT，t are the power generation costs of photovoltaic and wind power respectively, C BESS，t is the charge and discharge cost of the energy storage system, C DG，t is the operating cost of the diesel generator, C grid，t is the grid interaction cost, λ is the environmental cost coefficient, and P DG，t is the output power of the diesel generator at time t.

[0070] The expression of the supply-demand balance constraint is as follows:

[0071]

[0072] Where: P load，t is the load power at time t, P BESS，dit , P BESS_chg，t are the discharge and charge powers of the energy storage system respectively, P grid_in，t , P grid_out，t are the power purchase and power sale powers respectively;

[0073] The equipment capacity limitations include: the output of photovoltaic and wind power generation is restricted by natural conditions; the charge-discharge power and state of the energy storage system are restricted by capacity and charge-discharge rate; the output power of the diesel generator is restricted by the rated power;

[0074] The expression for the state limitation of the energy storage system is as follows:

[0075]

[0076] Where: SOC t is the state of the energy storage system at time t, and η chg , η dis are the charge and discharge efficiencies of the energy storage system respectively, and Δt is the time step;

[0077] The expressions for the upper and lower limits of the state of the energy storage system are as follows:

[0078] SOC min ≤SOC t ≤SOC max ;

[0079] Where: SOC min , SOC max are the upper and lower limits of the state of the energy storage system respectively;

[0080] The start-stop limitations of the diesel generator include minimum running time and minimum shutdown time limitations;

[0081] The grid network security limitations include limitations on voltage and frequency within the allowable range.

[0082] The cost C pv，t of photovoltaic power generation has no fuel cost, and it is simplified to a fixed operation and maintenance cost C pv，t = FixedCost PV or the cost is zero C pv，t = 0;

[0083] The cost C WT，t of wind power generation has no fuel cost, and it is simplified to a fixed operation and maintenance cost C WT，t = FixedCost WT or the cost is zero C WT，t = 0;

[0084] The charge-discharge cost of the energy storage system includes investment cost, operation and maintenance cost, replacement cost, and efficiency loss; its expression is as follows:

[0085]

[0086] Where: C inv is the initial investment cost of the energy storage system, L BESSFor the service life of the energy storage system, C O&M For the annual operation and maintenance cost of the energy storage system, C rep For the replacement cost that may occur during the life cycle of the energy storage system, C eff_loss Costs incurred due to efficiency losses during the charge and discharge processes of the energy storage system;

[0087]

[0088] Where: P BESS_dis，t Is the discharge power of the energy storage system, η chg 、η dis Are the charge and discharge efficiencies of the energy storage system respectively, Cost per kWh discharged is the discharge cost per kilowatt-hour, and Subsidy per kWh charged is the generation subsidy per kilowatt-hour;

[0089] The operating cost C of the diesel generator DG，t Includes fuel costs; its expression is as follows:

[0090] C DG，t =P DG，t ·Δt·Fuel Price per kWh;

[0091] Where: P DG，t Is the power generation power of the diesel generator, and Fuel Price per kWh is the fuel cost per kilowatt-hour of power generation;

[0092] The grid interaction cost C grid，t Includes the purchased electricity quantity, sold electricity quantity, and electricity price; its expression is as follows:

[0093]

[0094] Where: P grid_in，t ·Δt is the purchased electricity quantity, P grid_out，t ·Δt is the sold electricity quantity, Buyback Price per kWh is the purchase cost per kilowatt-hour, and Selling Price per kWh is the selling cost per kilowatt-hour.

[0095] A distributed grid power generation equipment optimal scheduling system, which is applied to the above method. The system includes:

[0096] A data acquisition module for acquiring historical operation status data and real-time operation status data of the distributed power generation network;

[0097] An actual output range determination module, configured to determine an initial output range and an actual output range of a target distributed power generation device in a distributed power generation network based on historical operation status data and real-time operation status data, with one distributed power generation device in the distributed power generation network as the target distributed power generation device;

[0098] Determining the actual output range of the target distributed power generation device includes any one of a first scheme and a second scheme:

[0099] The steps of the first scheme are as follows:

[0100] A21. Determine first and second evaluation scores of the target distributed power generation device based on the historical operation data and the current working environment data of the target distributed power generation device;

[0101] A22. Obtain the device status and maintenance data of the target distributed power generation device, and determine the third evaluation score of the target distributed power generation device;

[0102] A23. Assign corresponding weights to the first evaluation score, the second evaluation score, and the third evaluation score, and calculate the total evaluation score; the expression of the total evaluation score is as follows:

[0103] T = H * w H + E * w E + S * w S ;

[0104] w H + w E + w S = 1;

[0105] Where: T is the total evaluation score, H is the first evaluation score, w H is the weight corresponding to the first evaluation score, E is the second evaluation score, w E is the weight corresponding to the second evaluation score, S is the third evaluation score, w S is the weight corresponding to the third evaluation score;

[0106] A24. Based on the total evaluation score, and set the adjustment coefficient α = T / 100 to adjust the initial output range of the target distributed power generation device to obtain the actual output range of the target distributed power generation device;

[0107] The actual output range is as follows:

[0108] P 实际 = [α × P min , × P max ;

[0109] Where: α is a mapping function, P min is the minimum value of the initial output range, P maxis the maximum value of the initial output range;

[0110] The steps of the second solution are as follows:

[0111] B21. Based on the historical operation data of the target distributed generation device, analyze the output stability evaluation results of the target distributed generation device under different environmental parameter conditions, and determine the output stability evaluation result of the target distributed generation device under the current environmental parameters according to the current environmental parameters of the target distributed generation device;

[0112] B22. Based on the output stability evaluation result of the target distributed generation device under the current environmental parameters, adjust the initial output range of the target distributed generation device to determine the actual output range of the target distributed generation device;

[0113] The scheduling optimization module is used to determine the actual output ranges of multiple distributed generation devices in the distributed generation network, construct an output optimization scheduling model; determine the optimization objective function and constraint conditions of the output optimization scheduling model; solve the output optimization scheduling model, and output the optimal scheduling plan.

[0114] Compared with the prior art, the beneficial effects of the present invention are:

[0115] In a method and system for optimizing the scheduling of distributed power grid generation equipment according to the present invention, the method first obtains the historical operation state data and real-time operation state data of the distributed generation network, then takes a distributed generation device as the target distributed generation device, determines the initial output range and actual output range of the target distributed generation device, and finally determines the actual output ranges of multiple distributed generation devices and constructs an output optimization scheduling model. At the same time, determine the optimization objective function and constraint conditions, solve the output optimization scheduling model, output the optimal scheduling plan, and adjust the output of the distributed generation device; in the application of this design, the target distributed generation device is evaluated and scored by integrating historical and real-time data to accurately determine the actual output range of the device, and by constructing an optimization model, determine appropriate objectives and constraints to ensure that the scheduling plan is more in line with the actual operation situation, thereby improving the operation efficiency and stability of the power grid. Description of the Drawings

[0116] Figure 1 is the flowchart of the method steps of the present invention.

[0117] Figure 2 is the schematic diagram of the system structure of the present invention.

[0118] Figure 3 is the schematic diagram of the device structure of the present invention.

[0119] In the figure: data acquisition module 1, actual output range determination module 2, scheduling optimization module 3, processor 4, memory 5, computer program code 51. Specific Embodiment

[0120] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0121] Embodiment 1:

[0122] See Figure 1 , an optimized scheduling method for distributed power grid generation equipment, including:

[0123] S1. Obtain the historical operation status data and real-time operation status data of the distributed power generation network;

[0124] S2. Based on the historical operation status data and real-time operation status data, taking a distributed power generation equipment in the distributed power generation network as the target distributed power generation equipment, determine the initial output range and actual output range of the target distributed power generation equipment;

[0125] The determination of the actual output range of the target distributed power generation equipment includes any one of the first scheme and the second scheme:

[0126] The steps of the first scheme are as follows:

[0127] A21. Based on the historical operation data and current working environment data of the target distributed power generation equipment, determine the first and second evaluation scores of the target distributed power generation equipment;

[0128] Further, the obtaining steps of the first and second evaluation scores specifically include:

[0129] A211. Based on the historical operation data and current working environment data of the target distributed power generation equipment, and perform preprocessing; the historical operation data includes actual output, operation time, and load change; the current working environment data includes light intensity, temperature, and humidity;

[0130] In this embodiment, by installing sensors at key parts (such as generators, inverters, transformers, etc.) of the distributed power generation equipment to collect operation data such as actual output, operation time, and load change, and perform preprocessing work such as removing outliers and filling missing values, and convert the data into a format suitable for analysis, such as time series data or tabular data, etc.

[0131] A212. Respectively determine the key indicators in the historical operation data and current working environment data, and calculate the evaluation index scores of each key indicator based on the fuzzy comprehensive evaluation method; the expression of the evaluation index score is as follows:

[0132]

[0133] Among them: F is the evaluation index score, w i is the weight of the i-th evaluation index, s i is the score value of the i-th evaluation index, and n is the total number of evaluation indexes; the weight w i can be obtained by methods such as the expert scoring method and the analytic hierarchy process.

[0134] In this embodiment, according to the equipment characteristics and analysis requirements, key indicators are determined. Common key indicators include power generation efficiency, equipment failure rate, load response speed, stability, etc.

[0135] The steps for calculating the evaluation index score of each key indicator based on the fuzzy comprehensive evaluation method are as follows:

[0136] For the key indicator to be evaluated, a set of evaluation factors U = {u 1 , u 2 ,..., u n} is formed, and a set of evaluation grades V = {v 1 , v 2 ,..., v m} is set; each grade in the set of evaluation grades corresponds to a fuzzy set, such as "excellent", "good", "medium", "poor", etc.

[0137] For each evaluation factor u i and each evaluation grade v j , a membership function μ ij (x) is determined. This function represents the degree of membership of the evaluation factor u i to the evaluation grade v j at the value x. The determination of the membership function is usually based on expert experience, historical data, or statistical laws (such as statistical analysis methods, fuzzy statistical methods, and fuzzy distribution methods, etc.).

[0138] Obtain the data x i of the key indicator, that is, based on the actual value of the evaluation factor u i , use the membership function to calculate the membership degree μ ij (x i ) of this data to each evaluation grade; and combine the membership degrees of all evaluation factors to each evaluation grade to form a fuzzy relation matrix R = [μ ij .

[0139] According to the importance of each evaluation factor, determine its weight W = [w 1 , w 2 ,..., w n ; w i represents the weight of the i-th evaluation factor and satisfies

[0140] Using the weighted average model Wherein: represents the fuzzy composition operation, such as the maximum-minimum method, the weighted average method, etc., and the comprehensive evaluation result B = [b 1 , b 2 ,..., b m ; b j represents the membership degree of the evaluated factor to the evaluation level v j .

[0141] Finally, according to the specific meanings of the comprehensive evaluation result B and the evaluation level set V, the specific score value is further calculated. This usually requires quantifying the evaluation level set V, that is, assigning a specific score value to each level (which can be reasonably set according to the actual situation and expert experience), and then calculating the final score value through weighted average or other methods.

[0142] For example, if the evaluation level set is V = {"excellent" (90 points), "good" (80 points), "medium" (70 points), "poor" (60 points)}; then according to the membership degree b j in the comprehensive evaluation result B and the corresponding score value, the score value is calculated as follows:

[0143]

[0144] Wherein: the score value is any one of 90 points, 80 points, 70 points, and 60 points.

[0145] Taking the inverter of a certain distributed photovoltaic power station as an example, the power generation efficiency, failure rate, and load response speed are selected as key indicators; through the analysis of historical operation data, it is determined that the power generation efficiency of the inverter is 95%, the failure rate is 0.1%, and the load response speed is 1 second; assuming that the weight of the power generation efficiency is 0.5, the weight of the failure rate is 0.3, and the weight of the load response speed is 0.2; according to the fuzzy evaluation method, the score of the power generation efficiency is 0.9 (full score 1 point), the score of the failure rate is 0.95 (full score 1 point, the lower the failure rate, the higher the score), and the score of the load response speed is 0.8 (full score 1 point, the faster the response speed, the higher the score); substituting them into the evaluation score calculation formula, the first evaluation score of the distributed photovoltaic power station is: F = 0.5×0.9 + 0.3×0.95 + 0.2×0.8 = 0.895.

[0146] Through the above strategy, the historical operation data of distributed generation equipment can be systematically collected, and detailed data analysis and equipment operation status evaluation can be carried out. The first evaluation score can intuitively reflect the performance and operation status of the equipment, providing strong support for the optimal operation and maintenance of the equipment.

[0147] A213. Sum the evaluation scores of each key indicator corresponding to the historical operation data to obtain the first evaluation score; sum the evaluation scores of each key indicator corresponding to the environmental data of the current operation to obtain the second evaluation score.

[0148] Similarly, the method for determining the second evaluation score can be calculated by referring to the method for the first evaluation score.

[0149] Determine the second evaluation score according to the environmental data of the current operation of the target distributed power generation device; where the key indicators include light intensity, temperature, humidity, etc.

[0150] Assume that the light intensity thresholds are L1 (medium-strong boundary) and L2 (strong-weak boundary) respectively, then the membership function can be set as:

[0151]

[0152] Among them: L max is the maximum light intensity that may be achieved;

[0153] Temperature: Assume that the temperature thresholds are T1 (suitable and slightly high boundary) and T2 (slightly high and too high boundary) respectively, then the membership function is similar to that of light intensity.

[0154] Humidity: Assume that the humidity thresholds are H1 (low and medium boundary) and H2 (medium and high boundary) respectively, then the membership function is similar.

[0155] Assume that each evaluation level corresponds to a score interval (such as V 1 corresponds to [90, 100], V 2 corresponds to [70, 89], V 3 corresponds to [0, 69]), then the weighted average can be performed on the membership degrees in the comprehensive evaluation result b to obtain the final score value. For example, if B = [b1, b2, b3], then the score value s i is calculated as follows:

[0156] s i = b 1 × the median of V 1 + b 2 × the median of V 2 + b 3 × the median of V 3 of the median.

[0157] Suppose the measured data of a PV power station on a certain day are as follows: light intensity of 800 W / m², temperature of 25 °C, and humidity of 40%. According to the preset thresholds and membership functions, the membership degrees of each evaluation index to each evaluation level can be calculated, and then the membership matrix R can be obtained; then, combined with the weight vector W, the comprehensive evaluation result B can be obtained through fuzzy comprehensive evaluation; finally, according to the membership degrees in the comprehensive evaluation result B and the preset score intervals, the final score value can be calculated.

[0158] Specifically, in this embodiment, assume the following data and preset conditions:

[0159] Light intensity: the measured value is 800 W / m 2 ; Preset threshold: L1 = 500 W / m 2 (medium-strong boundary), L2 = 1000 W / m 2 (strong-weak boundary), Lmax = 1500 W / m 2 (maximum possible light intensity).

[0160] Temperature: the measured value is 25 °C; Preset threshold: T1 = 20 °C (suitable and slightly high boundary), T2 = 35 °C (slightly high and too high boundary).

[0161] Humidity: the measured value is 40%; Preset threshold: H1 = 50% (low and medium boundary), H2 = 80% (medium and high boundary).

[0162] Weights: W = [0.5, 0.3, 0.2] (weights of light intensity, temperature, and humidity).

[0163] Score interval: V 1 (excellent) corresponds to [90, 100], V 2 (good) corresponds to [70, 89], V 3 (poor) corresponds to [0, 69].

[0164] Calculate the membership degrees of light intensity, temperature, and humidity as follows:

[0165] Light intensity:

[0166] For V 1 (strong): μlight,

[0167] For V 2 (medium): μlight,

[0168] For V 3 (weak): μlight, V 3 (800) = 0 (because the light is strong enough);

[0169] Since the light intensity simultaneously belongs to V 1and V 2 , but usually we take the one with the largest membership degree, that is, V 1 .

[0170] Temperature:

[0171] For V 1 (suitable): μTemperature, V 1 (25) = 1; (because 25°C is within the suitable range);

[0172] For V 2 (on the high side): μTemperature, V 2 (25) = 0;

[0173] For V 3 (too high): μTemperature, V 3 (25) = 0;

[0174] Humidity:

[0175] For V 1 (low): μHumidity, V 1 (40) = 1;

[0176] For V 2 (medium): μTemperature, V 2 (40) = 0;

[0177] For V 3 (high): μTemperature, V 3 (40) = 0;

[0178] Based on the above membership degrees, the membership degree matrix is constructed as follows:

[0179]

[0180] Assume that the weight of light intensity is 0.5, the weight of temperature is 0.3, and the weight of humidity is 0.2, then the comprehensive evaluation result is as follows:

[0181] B = [0.8, 0, 0]

[0182] Since the non-zero elements in the comprehensive evaluation result B only appear in the first position, that is, corresponding to V 1 , then the score can be directly calculated according to this membership degree. However, to handle this problem more rigorously, the midpoint of each grade interval can be considered as the representative value of that interval.

[0183] The midpoints of the score intervals are respectively:

[0184]

[0185] Then, use the membership degrees in the comprehensive evaluation result vector B as weights to perform a weighted average of the scores for each level. However, in this embodiment, since only the membership degree of V 1 is non-zero, the second evaluation score is as follows:

[0186] s i = B 1 × the midpoint of V 1 = 0.8 × 95 = 76

[0187] Although the calculated result in this embodiment is 76, this value does not actually directly fall within the scoring range [90, 100] of V 1 . This is because the product of the membership degree (0.8) and the midpoint of the scoring range (95) is used to obtain a specific score, and this score may not exactly correspond to the division of the original scoring range. In practical applications, if a more accurate reflection of the scoring range is required, the upper limit of the scoring range (or adjusted according to specific circumstances) can also be selected to multiply the membership degree, and then necessary adjustments can be made to ensure that the score falls within the correct range.

[0188] A22. Obtain the device status and maintenance data of the target distributed generation device, and determine the third evaluation score of the target distributed generation device;

[0189] Further, in step A22, the step of obtaining the third evaluation score specifically includes:

[0190] A221. Define the key dimensions affecting the comprehensive performance of the target distributed generation device and perform preprocessing;

[0191] The key dimensions include operating efficiency, failure rate, maintenance cost, maintenance response time, and device age. The preprocessing is to remove outliers and missing values, and perform standardization or normalization processing on the data so that data with different dimensions can be compared.

[0192] The operating efficiency represents the power generation efficiency of the device in the current state and is obtained by directly reading the real-time data of the device monitoring system. The failure rate represents the number or proportion of failures occurring per unit time and is calculated through historical failure records. The maintenance cost represents the average cost of each maintenance and repair and is determined by taking the average maintenance cost over a past period of time. The maintenance response time represents the time interval from the fault report to the start of repair, and the average response time is calculated through the number of faults. The device age represents the length of time since the device was installed and affects the natural degradation of the device performance, and is determined by directly obtaining or calculating from the installation date.

[0193] A222. Assign weights based on the importance of each key dimension to the comprehensive performance; calculate the scoring values of each key dimension. The weights can be determined based on expert opinions, historical data analysis, or a combination of both.

[0194] Further, the scoring value S of the operating efficiency E is as follows:

[0195] Set a benchmark operating efficiency value (such as 90%) as a reference point for efficient operation, and then calculate the score using a piecewise linear or non-linear function based on the comparison between the actual efficiency and the benchmark efficiency. Assume the score range is 0 - 100;

[0196] If the actual operating efficiency E actual is greater than or equal to the benchmark operating efficiency E base , then S E = 100;

[0197] If the actual operating efficiency E actual is less than the benchmark operating efficiency E base , then calculate according to the following formula:

[0198]

[0199] where: E base is the benchmark operating efficiency; E actual is the actual operating efficiency; E min is the lowest operating efficiency value, which is the lowest acceptable operating efficiency value set (such as 80%) to avoid the denominator being zero;

[0200] The scoring value S of the failure rate FR is as follows:

[0201] Set a target failure rate (such as 0.5%) as a reference point for low failure rate; the lower the failure rate, the higher the score; the higher the failure rate, the lower the score; assume the score range is 0 - 100;

[0202]

[0203] where: F Ractual is the actual failure rate; F Rtarget is the target failure rate; ∈ is a very small positive number (such as 0.001) to avoid the denominator from becoming zero; if F Ractual exceeds a certain upper limit (such as 2%), then the score can be directly set to 0 or a very low value.

[0204] The scoring value S of the maintenance cost MC is as follows:

[0205] Set a budget cost or historical average cost as a reference point; the lower the cost, the higher the score; the higher the cost, the lower the score; assume the score range is 0 - 100;

[0206]

[0207] Where: MC actual is the actual cost; MC budget is the budgeted cost; δ is an adjustment factor used to control the impact of cost variance on the score. If the cost is much lower than the budget, the score can be close to or reach 100; if the cost is much higher than the budget, the score will drop rapidly.

[0208] The score value S of the maintenance response time MRT is as follows:

[0209] Set a target response time (such as 2 hours) as a reference point for quick response; the shorter the response time, the higher the score; the longer the response time, the lower the score; assume the score range is 0 - 100;

[0210]

[0211] Where: MRT actual is the actual response time; MRT target is the target response time; γ is an adjustment factor used to control the impact of response time on the score. If the actual response time exceeds a certain upper limit (such as 12 hours), the score can be directly set to 0 or a very low value.

[0212] The score value S of the equipment age Age is as follows:

[0213] Set an equipment life (such as 20 years) as a reference point for equipment aging. The younger the equipment age, the higher the score; the older the equipment age, the lower the score; assume the score range is 0 - 100;

[0214]

[0215] Where: Age actual is the actual equipment age, Age life is the preset equipment life.

[0216] If the equipment age is close to or exceeds the life, the score will drop rapidly. In addition, for some equipment, its performance may drop sharply after reaching a certain life. Therefore, the score here is the regular life score. For equipment reaching special life years, fixed score values can be set, such as 50, 30, 10, etc.

[0217] A223. Calculate the third evaluation score based on the score value of each key dimension and the corresponding weight; the expression of the third evaluation score is as follows:

[0218] CES = (S E × a 1 ) + (S FR×a 2 )+(S MC ×a 3 )+(S MRT ×a 4 )+(S Age ×a 5 );

[0219] Where: CES is the third evaluation score, and S E , S FR , S MC , S MRT , S Age are the score values of operating efficiency, failure rate, maintenance cost, maintenance response time, and equipment age respectively, and a 1 , a 2 , a 3 , a 4 , a 5 are all weights.

[0220] Assume the scores for each dimension are as follows:

[0221] [S E , S FR , S MC , S MRT , S Age = [90, 70, 80, 85, 95];

[0222] Weights [a 1 , a 2 , a 3 , a 4 , a 5 = [0.3, 0.2, 0.2, 0.15, 0.15];

[0223] Then the expression for the third evaluation score is as follows:

[0224] CES = (90 × 0.3) + (70 × 0.2) + (80 × 0.2) + (85 × 0.15) + (90 × 0.15) ≈ 84;

[0225] The higher the CES score, the better the comprehensive performance of the photovoltaic power generation equipment. In this embodiment, the CES score is 84, indicating that the equipment performs well during the given time period, but there is still room for improvement, especially in terms of failure rate and maintenance cost.

[0226] A23. Assign corresponding weights to the first evaluation score, the second evaluation score, and the third evaluation score, and calculate the total evaluation score; the expression for the total evaluation score is as follows:

[0227] T = H*w H +E*w E +S*wS ;

[0228] w H + w E + w S = 1

[0229] Where: T is the total evaluation score, H is the first evaluation score, and w H is the weight corresponding to the first evaluation score, E is the second evaluation score, and w E is the weight corresponding to the second evaluation score, S is the third evaluation score, and w S is the weight corresponding to the third evaluation score;

[0230] The first evaluation score and weight corresponding to the historical operation data are H and w H respectively; the second evaluation score and the second weight corresponding to the environmental factor data are E and w E respectively; the third evaluation score and the third weight corresponding to the equipment status information data are S and w S respectively; the weight parameters w H , w E , w S are artificially set weights, representing the influence degree of each evaluation parameter on the actual output range.

[0231] A24. Based on the total evaluation score, set the adjustment coefficient α = T / 100 to adjust the initial output range of the target distributed generation equipment to obtain the actual output range of the target distributed generation equipment;

[0232] In this embodiment, a mapping relationship is set to determine the adjustment of the initial output range. For example, when T is close to 100, the equipment is in the best state and can approach or reach the maximum output; when T is low, the output may need to be reduced. Set a mapping function f(T) to convert T into an adjustment coefficient α (0 < α ≤ 1) for the initial output range.

[0233] Specifically, the mapping relationship between the mapping function f(T) and the adjustment coefficient α can be determined through historical power generation data, that is, by statistically analyzing the historical power generation data, calculating the total evaluation score and the optimal output range respectively, constructing a data set, and solving the functional relationship between the total evaluation score and the optimal processing range through the data set. It can be solved using a mathematical model or a neural network model to determine the mapping relationship. When the neural network model is selected, the model is trained to converge to obtain the trained neural network model. By inputting the initial output range and the total evaluation score, the actual output range can be obtained through the output. At this time, the mapping relationship exists in the form of a neural network model.

[0234] Taking the solution of the linear mapping relationship by the mathematical model as an example, a simple linear mapping is: α = T / 100;

[0235] The actual output range is as follows:

[0236] P 实际 = [α × P min , α × P max ;

[0237] Where: α is a mapping function, P min is the minimum value of the initial output range, P max is the maximum value of the initial output range;

[0238] In this embodiment, assume that the initial output range of a distributed generation device is [50kW, 100kW]. According to the evaluation scores, the first evaluation score: the historical operation data (H) is 90 points (the device has been operating stably and has a low failure rate in the past period); the second evaluation score for environmental factors (E) is 80 points (the current light intensity is moderate and the temperature is appropriate); the third evaluation score for device status information (S) is 95 points (parameters such as the device temperature and vibration are normal and the maintenance is good). Assume that the device status information has the greatest impact on the output range, and the weight parameters are set as:

[0239] w H = 0.3, w E = 0.3, w S = 0.4;

[0240] Then the total evaluation score is:

[0241] T = 90×0.3 + 80×0.3 + 95×0.4 = 88;

[0242] Using linear mapping to obtain the adjustment coefficient α = 100 / 88 = 0.88;

[0243] Then the actual output range is:

[0244] P 实际 = [0.88×50kW, 0.88×100kW] = [44kW, 88kW];

[0245] Determining the actual output range of the distributed generation device through the evaluation scores and the mapping function is beneficial for subsequent adjustment of the output of the distributed generation device.

[0246] Furthermore, in this solution, to determine the actual output range of the target distributed generation device, a second solution can also be adopted. The specific steps are as follows:

[0247] B21. Analyze the output stability evaluation results of the target distributed power generation equipment under different environmental parameter conditions based on the historical operation data of the target distributed power generation equipment, and determine the output stability evaluation result of the target distributed power generation equipment under the current environmental parameters according to the current environmental parameters of the target distributed power generation equipment.

[0248] Further, step B21 specifically includes:

[0249] B211. Collect the environmental parameters and output conditions of the target distributed power generation equipment, and evaluate the correlation between different numerical conditions of the same type of environmental parameters and the output based on statistical methods.

[0250] For example: Collect the environmental parameters of the target distributed power generation equipment through sensors installed on the target distributed power generation equipment during the target period, collect environmental parameters (such as temperature, humidity, wind speed, light intensity, etc.) and output conditions, and use statistical methods (such as correlation analysis, regression analysis, etc.) to evaluate the correlation between different numerical conditions of the same type of environmental parameters and the output.

[0251] B212. Based on the historical operation data of the target distributed power generation equipment, determine the output stability indicators of the target distributed power generation equipment under different environmental parameter conditions; the output stability indicators include output volatility, output standard deviation, and output coefficient of variation.

[0252] B213. Divide the output stability of the target distributed power generation equipment based on the output stability indicators, and determine the output stability evaluation result of the target distributed power generation equipment; the output stability evaluation result includes any one of the following:

[0253] First, stable: 80% of the output stability indicators are normal; when the distributed power generation equipment shows normal performance in multiple stability indicators, it can be considered that its operation is stable; in this case, the operation strategy of the equipment can be further optimized to improve power generation efficiency and reliability.

[0254] Second, less stable: At least one stability indicator is abnormal; when the distributed power generation equipment shows output fluctuations under certain environmental parameter conditions, that is, when at least one stability indicator is abnormal (but not all are abnormal), possible reasons include equipment failure, drastic changes in environmental parameters, unstable control systems, etc.

[0255] Third, extremely unstable: 80% of the output stability indicators are abnormal; when the distributed power generation equipment shows extremely unstable output in multiple stability indicators, it is an extremely unstable situation.

[0256] Further, step B22 specifically includes:

[0257] B221. Determine the corresponding weighting parameter based on the output stability evaluation result of the target distributed generation device under the current environmental parameters; for the weighting parameter corresponding to the output stability evaluation result, see the following table:

[0258] Output stability evaluation results Weighting parameter Stable 1 Less stable 1.2 Highly unstable 1.4

[0259] B222. Calculate the actual output range of the target distributed generation device based on the weighting parameter and the initial output range of the target distributed generation device; its expression is as follows:

[0260] P 实际 =P 初始 ×w;

[0261] Where: P 实际 is the actual output range, P 初始 is the initial output range, and w is the weighting parameter.

[0262] B22. Adjust the initial output range of the target distributed generation device based on the output stability evaluation result of the target distributed generation device under the current environmental parameters, and determine the actual output range of the target distributed generation device;

[0263] S3. Determine the actual output ranges of multiple distributed generation devices in the distributed generation network, construct an output optimization scheduling model, and determine the optimization objective function and constraint conditions; solve the output optimization scheduling model, output the optimal scheduling plan, and adjust the output of the distributed generation device based on the optimal scheduling plan.

[0264] Further, the output optimization scheduling model aims to minimize the total operating cost, and the constraint conditions include supply-demand balance limit, equipment capacity limit, energy storage system state limit, upper and lower limits of the energy storage system state, diesel generator start-stop limit, and power grid network security limit;

[0265] The objective function of the optimization scheduling model is as follows:

[0266]

[0267] Where: T is the total number of time periods, C pv，t , C WT，t are the power generation costs of photovoltaic and wind power respectively, C BESS，t is the charge-discharge cost of the energy storage system, C DG，t is the operating cost of the diesel generator, C grid，t is the grid interaction cost, λ is the environmental cost coefficient, and P DG，t is the output power of the diesel generator at time t.

[0268] Since photovoltaic power generation usually has no direct fuel cost, its cost mainly comes from equipment depreciation, maintenance, and cleaning, etc. It can be assumed that its cost is zero or a fixed value, and it is simplified to a fixed operation and maintenance cost C pv，t = FixedCost PV or the cost is zero C pv，t = 0;

[0269] Similar to photovoltaic power generation, wind power generation also has no direct fuel cost, and its main cost also comes from equipment depreciation, maintenance, and overhaul. It is simplified to a fixed operation and maintenance cost C WT，t = FixedCost WT or the cost is zero C WT，t = 0;

[0270] The charging and discharging costs of the energy storage system include investment cost, operation and maintenance cost, replacement cost, and efficiency loss; its expression is as follows:

[0271]

[0272] Where: C inv is the initial investment cost of the energy storage system, including costs such as purchase, installation, and commissioning; L BESS is the service life of the energy storage system, usually in years, and is used to calculate the annual depreciation cost of the energy storage system; C O&M is the annual operation and maintenance cost of the energy storage system, including costs such as regular inspections, maintenance, and repairs, and can be estimated based on historical data and experience; C rep is the replacement cost that may occur during the life cycle of the energy storage system. Due to reasons such as technological updates, equipment aging, or damage, some components of the energy storage system may need to be replaced during its service life, and can be estimated based on the cost of replacement components and replacement frequency; C eff_loss is the cost generated due to the efficiency loss during the charging and discharging process of the energy storage system. There will be a certain amount of energy loss during the charging and discharging process of the energy storage system, which will result in a reduction in the actual available energy of the energy storage system, and can be estimated based on the efficiency of the energy storage system, the charging and discharging volume, and the electricity price. Specifically, the energy loss caused by the efficiency loss can be calculated and multiplied by the electricity price to obtain the cost.

[0273]

[0274] Where: P BESS_dis，t is the discharge power of the energy storage system, η chg 、η disThey are the charging and discharging efficiencies of the energy storage system respectively. Cost per kWh discharged is the cost of discharging per kilowatt-hour, and Subsidy per kWh charged is the power generation subsidy per kilowatt-hour. In practice, the subsidy may not exist, or the charging cost may be reflected in other forms (such as grid electricity price differences). If the subsidy and specific costs are ignored, it can be simplified to only consider the cost of efficiency loss.

[0275] The cost of a diesel generator mainly includes fuel cost and operation and maintenance cost. The fuel cost is usually proportional to the power generation and fuel price. If the operation and maintenance cost is ignored, the operating cost C of the diesel generator DG，t is expressed as follows:

[0276] C DG，t = P DG,t ·Δt·Fuel Price per kWh;

[0277] where: P DG，t is the power generation power of the diesel generator, and Fuel Price per kWh is the fuel cost per kilowatt-hour of power generation;

[0278] The grid interaction cost C grid，t depends on the power purchase volume, power sales volume and corresponding electricity prices, including power purchase volume, power sales volume, electricity price; and its expression is as follows:

[0279]

[0280] where: P grid_in，t ·Δt is the power purchase volume, P grid_out，t ·Δt is the power sales volume, Buyback Price per kWh is the power purchase cost per kilowatt-hour, and Selling Price per kWh is the power sales cost per kilowatt-hour.

[0281] Furthermore, the constraint conditions of the output optimization scheduling model include the following:

[0282] The expression of the supply-demand balance limit is as follows:

[0283]

[0284] where: P load，t is the load power at time t, P BESS，dit , P BESS_chg，t are the discharging and charging powers of the energy storage system respectively, and P grid_in，t , P grid_out,t are the power purchase and power sales powers respectively;

[0285] The device capacity limitations include: the output of photovoltaic and wind power generation is restricted by natural conditions; the charge and discharge power and status of the energy storage system are limited by its capacity and charge and discharge rate; the output power of the diesel generator is limited by its rated power; relevant technical manuals can be consulted for details.

[0286] The expression for the state limitation of the energy storage system is as follows:

[0287]

[0288] Where: SOC t is the state of the energy storage system at time t, η chg and η dis are the charging and discharging efficiencies of the energy storage system respectively, and Δt is the time step;

[0289] The expressions for the upper and lower limits of the state of the energy storage system are as follows:

[0290] SOC min ≤SOC t ≤SOC max ;

[0291] Where: SOC min and SOC max are the upper and lower limits of the state of the energy storage system respectively;

[0292] The start-stop limitations of the diesel generator include minimum running time and minimum shutdown time limitations;

[0293] The grid network security limitations include limitations on voltage and frequency within the allowable range.

[0294] After solving the above output optimization scheduling model, the optimal scheduling plan can be output, and the output adjustment instruction is sent to the distributed generation equipment through the intelligent control system, and the output scheduling of the distributed generation is adjusted through the adjustment instruction.

[0295] Optionally, taking the genetic algorithm to solve the optimization scheduling model as an example, according to the output range of each distributed generation equipment, the constraint conditions of the optimization scheduling model can be determined; the objective function is set based on the factors to be considered in the current scheduling (such as maximizing the output and minimizing the cost, etc.), and the genetic algorithm is used to randomly match the output values of multiple distributed generation equipments (randomly taking values within the processing range). At this time, the first scheduling plan is generated, and the fitness value of the first scheduling plan is calculated. Here, the fitness value is the objective function value. At this time, only the fitness value of the first scheduling plan is calculated, and the first scheduling plan is used as the optimal scheduling plan.

[0296] Further, continue to randomly generate the output data of distributed generation equipment, generate the second scheduling plan, calculate the fitness value of the second scheduling plan, and compare the fitness value of the first scheduling plan with that of the second scheduling plan; if the fitness value of the second scheduling plan is higher than that of the first scheduling plan, then update the second scheduling plan as the current optimal scheduling plan. And so on. After completing the output value combinations of each distributed generation equipment within the output range and calculating the fitness values of the corresponding scheduling plans, output the optimal scheduling plan. At this time, the optimal scheduling plan is the first scheduling plan. When solving the optimal scheduling model using the genetic algorithm, a hybrid particle swarm algorithm can be adopted.

[0297] In this embodiment, assume that the real-time load prediction value of a certain regional power grid is 100 MW, the output of other power sources is 60 MW, and the efficiency of the distributed generation equipment is 0.8; according to the calculation formula, the optimal output of distributed generation is:

[0298] Distributed generation output = (100 MW - 60 MW) / 0.8 = 50 MW;

[0299] At this time, the intelligent control system will send an instruction to the distributed generation equipment, requiring its output to be adjusted to 50 MW. At the same time, the system will also monitor the operating state of the power grid in real time and adjust the output of distributed generation as needed to achieve collaborative optimization with the power grid. Among them, if there are multiple distributed generation equipment, assume that we have three distributed generation equipment (DG1, DG2, DG3), the real-time load prediction value of the power grid is 150 MW, the output of other power sources is 80 MW, and we need to meet the remaining 70 MW demand through these three distributed generation equipment.

[0300] Through data collection and prediction, the real-time load prediction value of the power grid is obtained: 150 MW; the output of other power sources: 80 MW; then the remaining demand: 70 MW. Through the capacity evaluation of distributed generation equipment: the output range of DG1 is 0 - 30 MW, and the efficiency is 0.85; the output range of DG2 is 0 - 40 MW, and the efficiency is 0.8; the output range of DG3 is 0 - 25 MW, and the efficiency is 0.9.

[0301] Through the establishment of an optimal scheduling model, set up the objective function: minimize the operating cost (assuming that the cost is related to the output and efficiency), and set the constraint conditions as:

[0302] DG1 output + DG2 output + DG3 output = 70 MW;

[0303] DG1 output ≤ 30 MW;

[0304] DG2 output ≤ 40 MW;

[0305] DG3 output ≤ 25 MW;

[0306] Finally, by solving the optimization problem using an optimization algorithm, the optimal output of each power generation device is obtained as follows:

[0307] Optimal output of DG1: 25 MW (efficiency 0.85);

[0308] Optimal output of DG2: 30 MW (efficiency 0.8);

[0309] Optimal output of DG3: 15 MW (efficiency 0.9);

[0310] According to the optimization results, for output allocation and adjustment: send instructions to DG1 to output 25 MW; send instructions to DG2 to output 30 MW; send instructions to DG3 to output 15 MW. Monitor the operating status of the power grid and equipment in real time and make adjustments as needed.

[0311] If the grid voltage is low, the system can increase the reactive power output of distributed generation to boost the voltage; if the grid frequency is high, the system can reduce the active power output of distributed generation to lower the frequency. These control measures will ensure the stable operation of the power grid and optimize the interaction between distributed generation and the power grid.

[0312] Optionally, based on the optimization results, the impact of distributed generation on the power grid can also be studied; the impact mechanisms of distributed generation on grid voltage, frequency, and power flow can be analyzed; the stability and security after distributed generation is connected to the grid can be evaluated. Appropriate control measures such as reactive power compensation and frequency regulation can be proposed.

[0313] Optionally, specific control measures can be formulated according to the analysis results. For example, when the grid voltage is low, the voltage can be boosted by increasing the reactive power output of distributed generation; when the grid frequency is high, the frequency can be lowered by reducing the active power output of distributed generation. These control measures are implemented through an intelligent control system to ensure the stable operation of the power grid.

[0314] In the embodiment of this application, the optimization model is used to optimize the scheduling model, and the output of multiple distributed generation devices is optimized and adjusted, which can improve the output effect of multiple distributed generation devices.

[0315] Optionally, when multiple distributed generation devices are clustered into multiple groups, the specific scheduling within each distributed generation device in each group constitutes a second scheduling plan, and multiple second scheduling plans constitute the first scheduling plan. For example, when there are three groups, based on the second scheduling plans within each group, that is, three second scheduling plans, the overall scheduling plan, that is, the first scheduling plan, can be obtained.

[0316] If the distributed generation devices within each group are of the same type, the corresponding scheduling objective function can be determined based on the characteristics of the generation type. Different scheduling objective functions can be set separately within each group. Correspondingly, the scheduling of multiple distributed generation devices within each group also has different constraint conditions. The same algorithm (such as a genetic algorithm) used to determine the first scheduling plan can be used to determine the specific scheduling plan for each distributed generation device within the same group in the second scheduling plan. By determining the output value of each distributed generation device, calculating the objective function value, and iteratively searching for the way to maximize the objective function value, the second scheduling plan is determined.

[0317] For example: Suppose there are two distributed generation groups: Group A is a photovoltaic power generation group, and Group B is a wind power generation group.

[0318] Through group classification and characteristic analysis: Group A consists of multiple photovoltaic power stations, and its output is affected by the light intensity, showing large fluctuations. Group B consists of multiple wind turbines, and its output is affected by the wind speed, also showing fluctuations but not completely related to Group A.

[0319] Through prediction and demand matching: The prediction shows that the light intensity will be high within the next 24 hours, and the output potential of Group A is large; while the wind speed is moderate, and the output of Group B is relatively stable. The power demand prediction shows that the power demand is high during the day and low at night. Through priority setting: Since Group A is a renewable energy group and has a large output potential during the day, its priority is set higher than that of Group B. Through optimized scheduling: During the day, Group A is preferentially scheduled to meet the power demand, and the output of Group A is flexibly adjusted according to the demand changes. When the output of Group A is insufficient to meet the demand, Group B is started to make up for it. At night, since the output of Group A is low, the power supply mainly depends on Group B. Through real-time monitoring and adjustment: Through monitoring, it is found that the light intensity suddenly decreases at a certain moment, resulting in a sharp reduction in the output of Group A. At this time, the scheduling plan is adjusted in time to increase the output of Group B to make up for the decrease in the output of Group A.

[0320] Embodiment 2:

[0321] See Figure 2 , an optimized scheduling system for distributed power grid generation devices, which is applied to the method described in Embodiment 1. The system includes:

[0322] A data acquisition module 1 for acquiring the historical operation status data and real-time operation status data of the distributed generation network;

[0323] An actual output range determination module 2 for determining the initial output range and actual output range of the target distributed generation device based on the historical operation status data and real-time operation status data, with a distributed generation device in the distributed generation network as the target distributed generation device;

[0324] Further, for the specific steps of the actual output range determination module 2 to obtain the first and second scenarios, please refer to the corresponding records in Embodiment 1.

[0325] Determining the actual output range of the target distributed power generation equipment includes any one of the first and second scenarios:

[0326] The steps of the first scenario are as follows:

[0327] A21. Based on the historical operation data and current working environment data of the target distributed power generation equipment, determine the first and second evaluation scores of the target distributed power generation equipment;

[0328] A22. Obtain the equipment status and maintenance data of the target distributed power generation equipment, and determine the third evaluation score of the target distributed power generation equipment;

[0329] A23. Assign corresponding weights to the first evaluation score, the second evaluation score, and the third evaluation score, and calculate the total evaluation score; the expression of the total evaluation score is as follows:

[0330] T = H * w H + E * w E + S * w S ;

[0331] w H + w E + w S = 1;

[0332] Where: T is the total evaluation score, H is the first evaluation score, w H is the weight corresponding to the first evaluation score, E is the second evaluation score, w E is the weight corresponding to the second evaluation score, S is the third evaluation score, w S is the weight corresponding to the third evaluation score;

[0333] A24. Based on the total evaluation score, and set the adjustment coefficient α = T / 100 to adjust the initial output range of the target distributed power generation equipment to obtain the actual output range of the target distributed power generation equipment;

[0334] The actual output range is as follows:

[0335] P 实际 = [α × P min , α × P max ;

[0336] Where: α is the mapping function, P min is the minimum value of the initial output range, P max is the maximum value of the initial output range;

[0337] The steps of the second solution are as follows:

[0338] B21. Analyze the output stability evaluation results of the target distributed power generation equipment under different environmental parameter conditions based on the historical operation data of the target distributed power generation equipment, and determine the output stability evaluation results of the target distributed power generation equipment under the current environmental parameters according to the current environmental parameters of the target distributed power generation equipment;

[0339] B22. Adjust the initial output range of the target distributed power generation equipment based on the output stability evaluation results of the target distributed power generation equipment under the current environmental parameters, and determine the actual output range of the target distributed power generation equipment;

[0340] The scheduling optimization module 3 is used to determine the actual output ranges of multiple distributed power generation equipment in the distributed power generation network, construct an output optimization scheduling model; determine the optimization objective function and constraint conditions of the output optimization scheduling model; solve the output optimization scheduling model, and output the optimal scheduling plan.

[0341] Furthermore, for the optimization objective function and constraint conditions of the output optimization scheduling model constructed by the scheduling optimization module 3, please refer to the corresponding records in Embodiment 1.

[0342] Embodiment 3:

[0343] Refer to Figure 3 , an optimized scheduling device for distributed power grid power generation equipment, the device includes a processor 4 and a memory 5;

[0344] The memory 5 is used to store computer program code 51 and transmit the computer program code 51 to the processor 4;

[0345] The processor 4 is used to execute the optimized scheduling method for distributed power grid power generation equipment described in Embodiment 1 according to the instructions in the computer program code 51.

[0346] In this embodiment, there is also a computer-readable storage medium, and computer-executable instructions are stored in the computer-readable storage medium. When the computer-executable instructions are executed on a computer, the optimized scheduling method for distributed power grid power generation equipment described in Embodiment 1 is implemented.

[0347] Generally speaking, the computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. A non-transitory computer-readable storage medium can include any computer-readable medium except for the signal propagating temporarily itself.

[0348] A computer-readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0349] Computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. In particular, the Python language suitable for neural network computing and platform frameworks based on TensorFlow, PyTorch, etc. can be used. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0350] For the above-mentioned devices and non-transitory computer-readable storage media, reference can be made to the specific description of an optimized scheduling method and beneficial effects of a distributed power grid generation device, which will not be elaborated here.

[0351] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for optimizing the dispatching of distributed power grid power generation equipment, characterized in that: include: S1. Obtain historical operation status data and real-time operation status data of the distributed power generation network; S2. Based on the historical operation status data and the real-time operation status data, taking a distributed generation device in the distributed generation network as the target distributed generation device, determining the initial output range and the actual output range of the target distributed generation device; The method of determining the actual output range of the target distributed power generation equipment includes any one of the first solution and the second solution: The steps of the first scheme are as follows: A21. Determine the first and second evaluation scores of the target distributed generation equipment based on the historical operation data and the current working environment data of the target distributed generation equipment; A22. Obtaining equipment status and maintenance data of the target distributed power generation equipment, and determining a third evaluation score of the target distributed power generation equipment; A23. Assign corresponding weights to the first evaluation score, the second evaluation score, and the third evaluation score, and calculate the total evaluation score; the expression of the total evaluation score is as follows: T=H*w H +E*w E +S*w S ; In H +in E +in S =1; Where: T is the total evaluation score, H is the first evaluation score, w H is the weight corresponding to the first evaluation score, E is the second evaluation score, and w E is the weight corresponding to the second evaluation score, S is the third evaluation score, and w S is the weight corresponding to the third evaluation score; A24. Based on the total evaluation score, the initial output range of the target distributed power generation equipment is adjusted by setting an adjustment coefficient a=T / 100 to obtain the actual output range of the target distributed power generation equipment; The actual output range is as follows: P 实际 =[α×P min ,α×P max ]; Where: α is the mapping function, P min is the minimum value of the initial output range, P max is the maximum value of the initial output range; The steps of the second scheme are as follows: B21. Analyze the output stability evaluation results of the target distributed power generation equipment under different environmental parameter conditions based on the historical operation data of the target distributed power generation equipment, and determine the output stability evaluation results of the target distributed power generation equipment under the current environmental parameters according to the current environmental parameters of the target distributed power generation equipment; B22. Based on the output stability evaluation result of the target distributed power generation equipment under the current environmental parameters, the initial output range of the target distributed power generation equipment is adjusted to determine the actual output range of the target distributed power generation equipment; S3. Determine the actual output range of multiple distributed power generation equipment in the distributed power generation network, construct an output optimization scheduling model and determine the optimization objective function and constraints; solve the output optimization scheduling model, output the optimal scheduling plan, and adjust the output of the distributed power generation equipment based on the optimal scheduling plan.

2. The method for optimizing and dispatching distributed power grid power generation equipment according to claim 1, characterized in that: In step A21, the steps of obtaining the first and second evaluation scores specifically include: A211, based on the historical operation data of the target distributed power generation equipment and the current working environment data, and pre-processing; The historical operation data includes actual output, operation time, and load change; the current working environment data includes light intensity, temperature, and humidity; A212. Determine the key indicators in the historical operation data and the current working environment data respectively, and calculate the evaluation index score of each key indicator based on the fuzzy comprehensive evaluation method; the expression of the evaluation index score is as follows: Where: F is the evaluation index score, w i is the weight of the i-th evaluation indicator, s i is the score value of the i-th evaluation indicator, and n is the total number of evaluation indicators; A213. Sum the evaluation index scores of each key indicator corresponding to the historical operation data to obtain a first evaluation score; sum the evaluation index scores of each key indicator corresponding to the current working environment data to obtain a second evaluation score.

3. The method for optimizing and dispatching distributed power grid power generation equipment according to claim 2, characterized in that: The step A22, the step of obtaining the third evaluation score, specifically includes: A221. Define the key dimensions that affect the comprehensive performance of the target distributed generation equipment and perform preprocessing; the key dimensions include operating efficiency, failure rate, maintenance cost, maintenance response time, and equipment age; A222. Assign weights to each key dimension based on its importance to overall performance; calculate the score for each key dimension; A223. Based on the score value of each key dimension and the corresponding weight, a third evaluation score is calculated; the expression of the third evaluation score is as follows: CES=(S E ×a1)+(S FR ×a2)+(S MC ×a3)+(S MRT ×a4)+(S Age ×a5); Among them: CES is the third assessment score, S E , S FR , S MC , S MRT , S Age They are the scoring values ​​of operating efficiency, failure rate, maintenance cost, maintenance response time and equipment age respectively. a1, a2, a3, a4 and a5 are all weights.

4. The method for optimizing the dispatching of distributed power grid power generation equipment according to claim 3, characterized in that: The operating efficiency score S E as follows: If the actual operating efficiency E actual Greater than or equal to the benchmark operating efficiency E base , then S E =100; If the actual operating efficiency E actual Less than the benchmark operating efficiency E base , then calculate according to the following formula: Where: E base is the benchmark operating efficiency, E actual is the actual operating efficiency, E min It is the minimum value of operating efficiency; The score value S of the failure rate FR as follows: Among them: F Ractual is the actual failure rate, F Rtarget is the target failure rate, ∈ is a positive number to avoid the denominator returning to zero; The maintenance cost score S MC as follows: Among them: MC actual is the actual cost, MC budget is the budget cost, δ is the adjustment factor; The score value S of the maintenance response time MRT as follows: Among them: MRT actual is the actual response time, MRT target is the target response time, γ is the adjustment factor; The rating value S of the device age Age as follows: Where: Age actual is the actual device age, Age life The preset equipment life.

5. The method for optimizing and dispatching distributed power grid power generation equipment according to claim 1, characterized in that: The step B21 specifically includes: B211. Collect the environmental parameters and output of the target distributed power generation equipment, and evaluate the correlation between the output under different numerical conditions of the same type of environmental parameters based on statistical methods; B212. Based on the historical operation data of the target distributed power generation equipment, determine the output stability index of the target distributed power generation equipment under different environmental parameter conditions; the output stability index includes output fluctuation rate, output standard deviation, and output variation coefficient; B213. Classifying the output stability of the target distributed power generation equipment based on the output stability index to determine the output stability evaluation result of the target distributed power generation equipment; the output stability evaluation result includes any one of the following: The first type, stable: 80% of the output stability indicators are normal; The second type is not very stable: at least one stability indicator is abnormal; The third type: extremely unstable: 80% of the output stability indicators are abnormal.

6. The method for optimizing and dispatching distributed power grid power generation equipment according to claim 5, characterized in that: The step B22 specifically includes: B221. Determine the corresponding weighted parameters based on the output stability evaluation results of the target distributed generation equipment under the current environmental parameters; B222. Based on the weighted parameter and the initial output range of the target distributed power generation equipment, the actual output range of the target distributed power generation equipment is calculated; the expression is as follows: P 实际 =P 初始 ×w; Where: P 实际 is the actual output range, P 初始 is the initial output range, and w is the weighting parameter.

7. The method for optimizing and dispatching distributed power grid power generation equipment according to claim 1, characterized in that: The output optimization scheduling model aims to minimize the total operating cost, and takes supply and demand balance restrictions, equipment capacity restrictions, energy storage system state restrictions, energy storage system state upper and lower limit restrictions, diesel generator start and stop restrictions, and power grid network security restrictions as constraints; The objective function of the optimization scheduling model is as follows: Where: T is the total number of time periods, C pv，t , C WT，t are the electricity generation costs of photovoltaic and wind power, C BESS，t is the charging and discharging cost of the energy storage system, C DG，t is the operating cost of the diesel generator, C grid，t is the grid interaction cost, λ is the environmental cost coefficient, P DG，t is the output power of the diesel generator at time t.

8. The method for optimizing and dispatching distributed power grid power generation equipment according to claim 7, characterized in that: The expression of the supply and demand balance constraint is as follows: Where: P load，t is the load power at time t, P BESS，dit , P BESS_chg，t are the discharging and charging power of the energy storage system, P grid_in，t , P grid_out，t They are the power purchased and sold respectively; The equipment capacity limitations include: the output of photovoltaic and wind power generation is limited by natural conditions; the charging and discharging power and state of the energy storage system are limited by capacity and charging and discharging rate; the output power of the diesel generator is limited by the rated power; The expression of the energy storage system state limitation is as follows: Among them: SOC t is the state of the energy storage system at time t, η chg , η dis are the charging and discharging efficiency of the energy storage system, respectively, and Δt is the time step; The expressions of the upper and lower limits of the energy storage system state are as follows: SOC min ≤SOC t ≤SOC max ; Among them: SOC min , SOC max are the upper and lower limits of the energy storage system state respectively; The diesel generator start and stop restrictions include minimum operating time and minimum shutdown time restrictions; The power grid network security restrictions include restrictions on voltage and frequency within allowable ranges.

9. The method for optimizing and dispatching distributed power grid power generation equipment according to claim 8, characterized in that: The photovoltaic power generation cost C pv，t There is no fuel cost, which is simplified to a fixed value of operation and maintenance cost C pv，t =FixedCoct PV Or the cost is zero C pv，t =0; The wind power generation cost C WT，t There is no fuel cost, which is simplified to a fixed value of operation and maintenance cost C WT，t =FixedCost WT Or the cost is zero C WT，t =0; The charging and discharging costs of the energy storage system include investment cost, operation and maintenance cost, replacement cost, and efficiency loss; the expression is as follows: Where: C inv is the initial investment cost of the energy storage system, L BESS is the service life of the energy storage system, C O&M is the annual operation and maintenance cost of the energy storage system, C rep is the possible replacement cost of the energy storage system during its life cycle, C eff_loss Costs incurred due to efficiency losses during the charging and discharging process of the energy storage system; Where: P BESS_dis，t is the discharge power of the energy storage system, η chg , η dis are the charging and discharging efficiencies of the energy storage system, Costper kWh discharged is the discharge cost per kilowatt-hour, Subsidy per kWh charged is the power generation subsidy per kilowatt-hour; The operating cost of the diesel generator is C DG，t Including fuel costs; its expression is as follows: C DG，t =P DG，t ·Δt·Fuel Price per kWh; Where: P DG，t is the power generated by the diesel generator, and Fuel Price per kWh is the fuel cost per kWh of power generated; The grid interaction cost C grid，t Including electricity purchase, electricity sales and electricity price; its expression is as follows: Where: P grid_in，t ·Δt is the amount of electricity purchased, P grid_out ·Δt is the electricity sales amount, Buyback Price per kWh is the electricity purchase cost per kWh, and Selling Price per kWh is the electricity selling cost per kWh.

10. A distributed power grid power generation equipment optimization dispatching system, characterized by: The system is applied to the method described in any one of claims 1 to 9, and the system comprises: A data acquisition module (1) is used to acquire historical operating status data and real-time operating status data of a distributed power generation network; An actual output range determination module (2) is used to determine an initial output range and an actual output range of a target distributed power generation device based on historical operation status data and real-time operation status data, taking a distributed power generation device in the distributed power generation network as a target distributed power generation device; The method of determining the actual output range of the target distributed power generation equipment includes any one of the first solution and the second solution: The steps of the first scheme are as follows: A21. Determine the first and second evaluation scores of the target distributed generation equipment based on the historical operation data and the current working environment data of the target distributed generation equipment; A22. Obtaining equipment status and maintenance data of the target distributed power generation equipment, and determining a third evaluation score of the target distributed power generation equipment; A23. Assign corresponding weights to the first evaluation score, the second evaluation score, and the third evaluation score, and calculate the total evaluation score; the expression of the total evaluation score is as follows: T=H*w H +E*w E +S*w S ; In H +in E +in S =1; Where: T is the total evaluation score, H is the first evaluation score, w H is the weight corresponding to the first evaluation score, E is the second evaluation score, and w E is the weight corresponding to the second evaluation score, S is the third evaluation score, and w S is the weight corresponding to the third evaluation score; A24. Based on the total evaluation score, the initial output range of the target distributed power generation equipment is adjusted by setting an adjustment coefficient α=T / 100 to obtain the actual output range of the target distributed power generation equipment; The actual output range is as follows: P 实际 =[α×P min ,α×P max ]; Where: α is the mapping function, P min is the minimum value of the initial output range, P max is the maximum value of the initial output range; The steps of the second scheme are as follows: B21. Analyze the output stability evaluation results of the target distributed power generation equipment under different environmental parameter conditions based on the historical operation data of the target distributed power generation equipment, and determine the output stability evaluation results of the target distributed power generation equipment under the current environmental parameters according to the current environmental parameters of the target distributed power generation equipment; B22. Based on the output stability evaluation result of the target distributed power generation equipment under the current environmental parameters, the initial output range of the target distributed power generation equipment is adjusted to determine the actual output range of the target distributed power generation equipment; The scheduling optimization module (3) is used to determine the actual output range of multiple distributed power generation devices in the distributed power generation network, construct an output optimization scheduling model and determine the optimization objective function and constraint conditions; solve the output optimization scheduling model, output the optimal scheduling plan, and adjust the output of the distributed power generation equipment based on the optimal scheduling plan.

Images