Multi-terminal interconnected flexible microgrid performance evaluation method, system and medium

Abstract

The present invention provides a multi-terminal interconnected flexible microgrid performance evaluation method, system, and medium, belonging to the field of microgrid technology. The method comprises: constructing a training set based on the original parameters of the flexible microgrid and the evaluation results of the multi-terminal interconnected flexible microgrid performance; constructing an LSTM model, determining the number of hidden layer nodes k, the learning rate #imgabs0#, and the dropout rate #imgabs1# of the LSTM model as parameters to be optimized, using the evaluation accuracy of the LSTM model of the 5-fold cross-validation of the training set as the objective function, optimizing the parameters to be optimized using an improved snake optimization algorithm to obtain the optimal LSTM model parameters; and constructing an LSTM model based on the optimal LSTM model parameters for evaluating the performance of the multi-terminal interconnected flexible microgrid. This method can effectively improve the accuracy of the multi-terminal interconnected flexible microgrid performance evaluation and achieve ideal evaluation results.

Description

Technical Field

[0001] The present invention relates to the field of microgrid technology, and in particular to a multi-terminal interconnected flexible microgrid performance evaluation method, system and medium. Background Art

[0002] Multi-terminal interconnected flexible microgrids are one of the key technologies for future land warfare platforms. In-depth research on the technical characteristics and performance evaluation of multi-terminal interconnected flexible microgrids is fundamental to further developing their design and optimization. LSTM (Long Short-Term Memory) is a special type of recurrent neural network (RNN), a neural network model in the field of deep learning. It has been applied in performance evaluation in the power sector and other fields.

[0003] During LSTM training, the number of hidden layer nodes of LSTM k , learning rate , Dropout rate The quality of selection directly affects the accuracy of the final unmanned cluster performance evaluation results. Intelligent optimization algorithms are an effective method for optimizing LSTM model parameters. The Snake Optimization Algorithm (SOA) is a new metaheuristic algorithm that mimics the unique mating behavior of snakes and can also be applied to the performance evaluation of multi-terminal interconnected flexible microgrids. However, the SOA still has some flaws, making it prone to local optimality and low convergence accuracy. This often fails to achieve ideal performance evaluation results for multi-terminal interconnected flexible microgrids. Summary of the Invention

[0004] The present invention provides a multi-terminal interconnected flexible microgrid performance evaluation method, which can effectively improve the accuracy of multi-terminal interconnected flexible microgrid performance evaluation and achieve ideal evaluation results. The method specifically includes the following steps:

[0005] Based on the original parameters of the flexible microgrid and the evaluation results of the multi-terminal interconnected flexible microgrid performance, a training set is constructed;

[0006] Build an LSTM model and determine the number of hidden layer nodes k and learning rate of the LSTM model , Dropout rate The evaluation accuracy of the 5-fold cross-validation LSTM model of the training set is used as the objective function. The parameters to be optimized are optimized using an improved snake optimization algorithm to obtain the optimal LSTM model parameters. The improved snake optimization algorithm introduces the position update mechanism of the crayfish optimization algorithm and the gradient optimization algorithm into the mating mode of the exploration and development stages of the original snake optimization algorithm. Different position update modes, the current optimal position of the snake individual, the optimal position of the previous generation of the snake individual, the snake individual's burrow, the snake individual's decline curve, and the adaptive parameters of the snake individual's gradient are selected according to the switching probability to update the position of the next generation.

[0007] An LSTM model is constructed based on the optimal LSTM model parameters to evaluate the performance of multi-terminal interconnected flexible microgrids.

[0008] Preferably, the position update formula in the exploration phase of the improved snake optimization algorithm is:

[0009] ;

[0010] ;

[0011] Where, For the t +1 iteration of male position; The randomly selected t The position of the male in the iteration; rand is a random number in the range [0,1]; the ability to find food for males; For the t +1 iteration of female position; The randomly selected t The position of the female in the iteration; the ability to find food for the females; For the t The position of the individual snake at the iteration; 、 is a random number in the range [0,1];

[0012] ;

[0013] ;

[0014] ;

[0015] ;

[0016] Where, Indicates the t The optimal position of the individual snake in the iteration; Indicates thet -1 iteration of the best position of the individual snake; Indicates the t The burrow of the snake individual of the iteration; is a decreasing curve; 、 is the adaptive parameter of the gradient of the individual snake, 、 1.2 and 0.2 respectively.

[0017] Preferably, the position update formula in the mating mode of the development stage of the improved snake optimization algorithm is:

[0018] ;

[0019] ;

[0020] Where: For the t +1 iteration i The position of the male; For the t The first iteration i The position of the male; For the t +1 iteration i The position of the female; For the t The first iteration i The position of the female; rand is a random number in the range [0,1]; and Separate mating abilities of males and females; 、 is a random number in the range [0,1].

[0021] Preferably, the evaluation indicators of the multi-terminal interconnected flexible microgrid performance include reliability, coordination, safety, efficiency, quality and scalability;

[0022] The flexible microgrid original parameters include power supply output power, output voltage, frequency, load power, system normal operation time, total operation time, current total power of the microgrid and maximum power of the microgrid.

[0023] Preferably, the reliability evaluation value is the ratio of the system normal operation time to the total operation time;

[0024] The evaluation value of the coordination is power matching; the power matching is the matching degree between the power supply output power and the load power;

[0025] The safety assessment value is the ratio of the current power output power to the maximum power of the microgrid;

[0026] The evaluation value of the efficiency is the ratio of the current load power to the total power of the microgrid;

[0027] The evaluation values ​​of the quality are voltage and frequency fluctuation rate;

[0028] The evaluation value of the scalability is the ratio of the current load power to the maximum power of the microgrid.

[0029] Preferably, the formula for the evaluation result of the multi-terminal interconnected flexible microgrid performance is:

[0030] ;

[0031] Where, is the weight of each evaluation indicator, is the evaluation value of each evaluation indicator after normalization.

[0032] The present invention also proposes a multi-terminal interconnected flexible microgrid performance evaluation system, the system comprising:

[0033] processor;

[0034] a memory having stored thereon a computer program executable on the processor;

[0035] Among them, when the computer program is executed by the processor, the steps of the multi-terminal interconnected flexible microgrid performance evaluation method are implemented.

[0036] The present invention also proposes a computer-readable storage medium, on which a data processing program is stored. When the data processing program is executed by a processor, the steps of the multi-terminal interconnected flexible microgrid performance evaluation method are implemented.

[0037] Beneficial effects of the present invention:

[0038] The present invention proposes a performance evaluation method for a multi-terminal interconnected flexible microgrid. The method adopts an optimized snake optimization algorithm to optimize the parameters of an LSTM model, and constructs an evaluation model for the performance of a multi-terminal interconnected flexible microgrid based on the LSTM model after parameter optimization. The evaluation model for the performance of a multi-terminal interconnected flexible microgrid can obtain more accurate and objective evaluation results. Among them, the present invention introduces a position update mechanism of a crayfish optimization algorithm and a gradient optimization algorithm into the exploration stage and mating mode of the snake optimization algorithm, and comprehensively considers factors such as selecting different position update modes according to the switching probability, the current optimal position of the snake individual, the optimal position of the previous generation of the snake individual, the snake individual's cave, the snake individual's decreasing curve, and the adaptive parameters of the snake individual's gradient to update the snake individual position, thereby improving the diversity of the algorithm's search direction and avoiding the occurrence of local optimality in each iteration. The optimal model parameters obtained by the algorithm further effectively improve the performance of the LSTM model, thereby improving the performance evaluation effect of the multi-terminal interconnected flexible microgrid. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flow chart of a multi-terminal interconnected flexible microgrid performance evaluation method according to an embodiment of the present invention;

[0040] Figure 2 4 is an execution flow chart of the improved snake optimization algorithm according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0042] Example 1

[0043] Snake optimization algorithm (SOA) is a new meta-heuristic algorithm proposed in 2022. This algorithm is a new intelligent optimization algorithm that imitates the special mating behavior of snakes. It can also be applied to the performance evaluation problem of multi-terminal interconnected flexible microgrids. However, the existing snake optimization algorithm still has some defects: (1) The position update method of male (female) snake individuals in the exploration stage of the snake optimization algorithm only relies on the position of randomly selected males (males and females) to update. The search direction lacks diversity and cannot effectively cover the entire problem search space, which may cause the algorithm to fall into local optimality. (2) In the mating mode of the snake optimization algorithm development stage, parents are selected only based on fitness values, ignoring the diversity distribution of the population, which may cause high-quality individuals to be too concentrated, reduce the global search potential, and easily fall into local optimality. The above two key deficiencies result in the inability to achieve the best design effect when using the snake optimization algorithm for multi-terminal interconnected flexible microgrid performance evaluation. To this end, the present invention proposes a multi-terminal interconnected flexible microgrid performance evaluation method, and its flow chart is as follows. Figure 1 The specific steps are as follows:

[0044] S1: Construct a training set based on the original parameters of the flexible microgrid and the evaluation results of the multi-terminal interconnected flexible microgrid performance.

[0045] S2: Build an LSTM model and determine the number of hidden layer nodes k and learning rate of the LSTM model , Dropout rate The evaluation accuracy of the LSTM model on the 5-fold cross-validation of the training set was used as the objective function. The optimized parameters were then optimized using an improved snake optimization algorithm to obtain the optimal LSTM model parameters. The improved snake optimization algorithm incorporated the position update mechanisms of the crayfish optimization algorithm and the gradient optimization algorithm into the mating patterns of the original snake optimization algorithm during the exploration and development phases. The algorithm then selected different position update modes based on the switching probability, the current optimal position of the individual snake, the optimal position of the previous generation of the individual snake, the individual snake's burrow, the individual snake's decline curve, and the adaptive parameters of the individual snake's gradient for the next generation of position updates.

[0046] S3: Build an LSTM model based on the optimal LSTM model parameters to evaluate the performance of multi-terminal interconnected flexible microgrids.

[0047] The construction of the evaluation model includes:

[0048] The evaluation indicators for determining the performance of multi-terminal interconnected flexible microgrids include reliability, coordination, safety, efficiency, quality and scalability; the original parameters of the flexible microgrid include power supply output power, output voltage, frequency, load power, system normal operation time, total operation time, current total power of the microgrid and maximum power of the microgrid.

[0049] Calculate the evaluation value of each evaluation indicator: the evaluation value of reliability is the proportion of system normal operation time in the total operation time; the evaluation value of coordination is power matching; power matching is the matching degree between power supply output power and load power; the evaluation value of safety is the ratio of current power supply output power to the maximum power of microgrid; the evaluation value of efficiency is the ratio of current load power to the total power of microgrid; the evaluation value of quality is voltage and frequency fluctuation rate; the evaluation value of scalability is the ratio of current load power to the maximum power of microgrid.

[0050] Further: The evaluation formula of the multi-terminal interconnected flexible microgrid performance is:

[0051] ;

[0052] Where, is the weight of each evaluation indicator, is the evaluation value of each evaluation indicator after normalization.

[0053] Specifically, such as Figure 2 As shown in the figure, the improved snake optimization algorithm for optimizing the optimization parameters includes the following steps:

[0054] S2.1: Determine the number of hidden layer nodes in the LSTM model k , learning rate , Dropout rate As the parameter to be optimized, the evaluation accuracy of the LSTM model of the 5-fold cross-validation of the training set is used as the objective function, that is, the fitness function; at the same time, the corresponding constraints are set: the number of hidden layer nodes k of LSTM, the learning rate , Dropout rate upper and lower limits.

[0055] S2.2: Set parameters, including: population size (i.e., number of snakes) N; maximum number of iterations (i.e., conditions for stopping iterations) T ; Problem optimization lower bound ; Problem optimization upper bound .

[0056] S2.3: Initialize the snake population position:

[0057] (1);

[0058] Where: is the position of the i-th snake; r is a random number in the range [0,1]; and are the upper and lower bounds of the problem to be solved.

[0059] S2.4: Divide the population into two groups: females and males

[0060] Assume that the number of males is 50% and the number of females is 50%. The population is divided into two groups: males and females. The following two formulas are used to divide the population:

[0061] (2);

[0062] (3);

[0063] Where: N The size of the snake population; is the number of males; The number of females.

[0064] S2.5: Evaluate each group and define the temperature and amount of food

[0065] According to the objective function, find the best individual in each group and get the best male and the best females and food location .

[0066] Temperature can be defined by the following formula:

[0067] (4);

[0068] Where: t is the current iteration number; T is the maximum number of iterations.

[0069] Food quantity It can be defined by the following formula:

[0070] (5);

[0071] Where: is a constant, take 0.5.

[0072] S2.6: If (Threshold ), enter the exploration phase and calculate the positions of male and female individuals respectively, otherwise go to S2.7.

[0073] S2.7: If Temp>0.6, enter the exploration phase and calculate the position of individual snakes, otherwise enter S2.8.

[0074] S2.8: If rand >0.6, enter the combat mode of the development stage and calculate the positions of male and female individuals respectively; otherwise, enter S2.9.

[0075] S2.9: Enter the mating mode of the development stage, calculate the positions of males and females respectively, and replace the positions of the worst males and the worst females.

[0076] Specifically, the exploration and development phases include the following steps:

[0077] Exploration phase (no food)

[0078] if (Threshold ), the snakes search for food by choosing any random location and update their position.

[0079] During the SOA exploration phase, the snake optimization algorithm's position update method for male (female) snakes relies solely on the positions of randomly selected males (males and females). This lacks diversity in search directions, fails to effectively cover the entire problem search space, and can cause the algorithm to become stuck in a local optimum. To more effectively improve the algorithm's performance, this algorithm introduces a position update mechanism based on the crayfish optimization algorithm and the gradient-based optimizer (GBO). This refines the snake position update method, comprehensively considering factors such as the selection of different position update modes based on switching probability, the current optimal position of the snake, the optimal position of the previous generation, the snake's burrow, the snake's decline curve, and the adaptive parameters of the snake's gradient. This improves the diversity of the algorithm's search directions, avoids local optima in each iteration, and thus improves the algorithm's performance.

[0080] In the exploration phase of SOA, the crayfish optimization algorithm and gradient optimization algorithm are introduced. After improvement, the position update formula of male and female snake individuals is:

[0081] (6);

[0082] (7);

[0083] Where, For the t +1 iteration of male position; The randomly selected t The position of the male in the iteration; rand is a random number in the range [0,1]; The ability to find food for males, , Position of randomly selected males The fitness value of For male position The fitness value of is a constant, take 0.05; For the t +1 iteration of female position; The randomly selected t The position of the female in the iteration; The ability to find food for females, , Position of randomly selected males The fitness value of For male position The fitness value of For the t The position of the individual snake at the iteration; 、 is a random number in the range [0,1];

[0084] (8);

[0085] (9);

[0086] (10);

[0087] (11);

[0088] Where, Indicates the t The optimal position of the individual snake in the iteration; Indicates the t -1 iteration of the best position of the individual snake; Indicates the t The burrow of the snake individual of the iteration; is a decreasing curve; 、 is the adaptive parameter of the gradient of the individual snake, 、 1.2 and 0.2 respectively.

[0089] Development stage (with food)

[0090] exist Under the conditions, if the temperature , then the temperature is hot. The snake will only look for food, and the position update formula is as follows:

[0091] (12);

[0092] Where: is the position of the individual snake (male or female) at the t+1th iteration; is the optimal position of the snake individual at the tth iteration, that is, the food position; rand is a random number in the range of [0,1]; is a constant, take 2.

[0093] exist Under the conditions, if the temperature , then the temperature is cold. The snake will be in fighting mode or mating mode.

[0094] (a) Combat Mode

[0095] (13);

[0096] Where: is the position of the i-th male at the t+1-th iteration; is the position of the i-th male at the t-th iteration; is the best position in the female snake group; rand is a random number in the range of [0,1]; For male fighting ability.

[0097] (14);

[0098] Where: is the position of the i-th female at the t+1-th iteration; is the position of the i-th female at the t-th iteration; is the best position in the male snake group; rand is a random number in the range of [0,1]; For female fighting ability.

[0099] and It can be calculated by the following formula:

[0100] (15);

[0101] (16);

[0102] Where: The best position for female snakes The fitness value of The best position for male snakes The fitness value of is the fitness value of the individual snake.

[0103] (b) Mating pattern

[0104] During the SOA development phase, the snake optimization algorithm's mating model selected parents solely based on fitness, ignoring the diversity of the population. This could lead to an over-concentration of high-quality individuals, reducing global search potential and making them prone to local optima. To more effectively improve the algorithm's performance, the position update mechanism of the crayfish optimization algorithm and the gradient-based optimizer (GBO) was introduced to improve the snake's position update method. This method updates the snake's position by comprehensively considering factors such as the selection of different position update modes based on switching probability, the snake's current optimal position, the optimal position of the previous generation, the snake's burrow, the snake's decline curve, and the adaptive parameters of the snake's gradient. This prevents the potential rapid loss of population diversity, which could lead to premature convergence to a local optimum, thereby improving the algorithm's performance.

[0105] In the mating mode of the development phase of SOA, the crayfish optimization algorithm and the gradient optimization algorithm are introduced. After improvement, the position update formula of male and female snake individuals is:

[0106] (17);

[0107] (18);

[0108] Where: is the position of the i-th male at the t+1-th iteration; is the position of the i-th male at the t-th iteration; is the position of the i-th female at the t+1-th iteration; is the position of the i-th female in the t-th iteration; rand is a random number in the range [0,1]; 、 is a random number in the range [0,1]; and The mating capacity of males and females can be calculated by the following formula:

[0109] (19);

[0110] (20);

[0111] Where: is the fitness value of the ith male position; is the fitness value of the ith female position.

[0112] If the eggs hatch, select the worst male and female and replace them.

[0113] (twenty one);

[0114] (twenty two);

[0115] Where: It is the worst position in the male snake group; This is the worst position among the female snakes.

[0116] S2.10: Determine whether the stopping condition is met. If not, repeat S2.5-S2.10. Otherwise, output the optimal snake individual, that is, the number of hidden layer nodes with the optimal parameters of LSTM. , learning rate , Dropout rate .

[0117] S2.11: A multi-terminal interconnected flexible microgrid performance evaluation model is established using the output optimal parameters as LSTM parameters, and the test data set is input into the model to obtain the evaluation results and evaluation accuracy of the multi-terminal interconnected flexible microgrid performance.

[0118] In this embodiment:

[0119] 1000 samples of multi-terminal interconnected flexible microgrids were selected, and 800 of them were randomly selected as training samples, and the remaining 200 were used as test samples. SOA-LSTM and ISOA-LSTM were used to evaluate the performance of multi-terminal interconnected flexible microgrids. MATLAB was used as the simulation platform, and the parameters of the SOA algorithm were: N=50, Maxiter=200, number of hidden layer nodes k, learning rate , Dropout rate The search range is between 0 and 100. The parameters in the ISOA algorithm are: N=50, Maxiter=200, the number of hidden layer nodes k, and the learning rate , Dropout rate The search range is between 0-100.

[0120] Evaluation metrics for the SOA-LSTM and ISOA-LSTM models include mean absolute error (MAE), mean relative error (MRE), and root mean square error (RMSE). As shown in Table 1, ISOA-LSTM achieves higher accuracy in performance evaluation of multi-terminal interconnected flexible microgrids compared to SOA-LSTM. This means that the LSTM parameters obtained by searching with ISOA are superior to those obtained with SOA. Simulation results demonstrate that the ISOA algorithm has stronger search capabilities than the SOA algorithm, and that ISOA-LSTM achieves higher evaluation accuracy than SOA-LSTM, validating the effectiveness of this approach.

[0121] Table 1 Comparison of evaluation methods

[0122]

[0123] The above is a multi-terminal interconnected flexible microgrid performance evaluation method provided by one embodiment of this embodiment. Based on the same idea, this embodiment also provides a corresponding multi-terminal interconnected flexible microgrid performance evaluation system. For the specific definition of the multi-terminal interconnected flexible microgrid performance evaluation system, please refer to the definition of the multi-terminal interconnected flexible microgrid performance evaluation method above, which will not be repeated here. Each module in the above-mentioned multi-terminal interconnected flexible microgrid performance evaluation system can be fully or partially implemented through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0124] This embodiment also provides a computer-readable storage medium, which stores a computer program that can be used to execute the above Figure 1 A performance evaluation method for multi-terminal interconnected flexible microgrid is provided.

[0125] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0126] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A multi-terminal interconnected flexible microgrid performance evaluation method, characterized in that: The following steps are involved: A training set is constructed based on the original parameters of the flexible microgrid and the evaluation results of the performance of the multi-terminal interconnected flexible microgrid; the original parameters of the flexible microgrid include power supply output power, output voltage, frequency, load power, system normal operation time, total operation time, current total power of the microgrid, and maximum power of the microgrid; Build an LSTM model and determine the number of hidden layer nodes k and learning rate of the LSTM model , Dropout rate The evaluation accuracy of the 5-fold cross-validation LSTM model of the training set is used as the objective function. The parameters to be optimized are optimized using an improved snake optimization algorithm to obtain the optimal LSTM model parameters. The improved snake optimization algorithm introduces the position update mechanism of the crayfish optimization algorithm and the gradient optimization algorithm into the mating mode of the exploration and development stages of the original snake optimization algorithm. Different position update modes, the current optimal position of the snake individual, the optimal position of the previous generation of the snake individual, the snake individual's burrow, the snake individual's decline curve, and the adaptive parameters of the snake individual's gradient are selected according to the switching probability to update the position of the next generation. An LSTM model is constructed based on the optimal LSTM model parameters to evaluate the performance of multi-terminal interconnected flexible microgrids. The position update formula of the exploration phase of the improved snake optimization algorithm is: ； ； Where, For the t +1 iteration of male position; The randomly selected t The position of the male in the iteration; rand is a random number in the range [0,1]; the ability to find food for males; For the t +1 iteration of female position; The randomly selected t The position of the female in the iteration; the ability to find food for the females; For the t The position of the individual snake at the iteration; 、 is a random number in the range [0,1]; X min Find the lower bound for the problem; X max Find the upper bound of the problem; c 2 is a constant; T is the maximum number of iterations; ； ； ； ； Where, Indicates the t The optimal position of the individual snake in the iteration; Indicates the t -1 iteration of the best position of the individual snake; Indicates the t The burrow of the snake individual of the iteration; is a decreasing curve; 、 is the adaptive parameter of the gradient of the individual snake, 、 1.2 and 0.2 respectively.

2. The multi-terminal interconnected flexible microgrid performance evaluation method according to claim 1 is characterized in that: The position update formula in the mating mode of the development stage of the improved snake optimization algorithm is: ； ； Where: For the t +1 iteration i The position of the male; For the t The first iteration i The position of the male; For the t +1 iteration i The position of the female; For the t The first iteration i The position of the female; and the mating capacity of males and females, respectively; 、 is a random number in the range [0,1]; Q For the amount of food; c 3 is a constant.

3. The multi-terminal interconnected flexible microgrid performance evaluation method according to claim 1 is characterized in that: The evaluation indicators of the performance of the multi-terminal interconnected flexible microgrid include reliability, coordination, safety, efficiency, quality and scalability.

4. The multi-terminal interconnected flexible microgrid performance evaluation method according to claim 3 is characterized in that: The reliability evaluation value is the ratio of the system's normal operation time to the total operation time; The evaluation value of the coordination is power matching; the power matching is the matching degree between the power supply output power and the load power; The safety assessment value is the ratio of the current power output power to the maximum power of the microgrid; The evaluation value of the efficiency is the ratio of the current load power to the total power of the microgrid; The evaluation values ​​of the quality are voltage and frequency fluctuation rate; The evaluation value of the scalability is the ratio of the current load power to the maximum power of the microgrid.

5. The multi-terminal interconnected flexible microgrid performance evaluation method according to claim 3 is characterized in that: The formula for evaluating the performance of the multi-terminal interconnected flexible microgrid is: ； Where, is the weight of each evaluation indicator, is the evaluation value of each evaluation indicator after normalization.

6. A multi-terminal interconnected flexible microgrid performance evaluation system, characterized in that: The system comprises: processor; a memory having stored thereon a computer program executable on the processor; Wherein, when the computer program is executed by the processor, the steps of the multi-terminal interconnected flexible microgrid performance evaluation method as described in any one of claims 1 to 5 are implemented.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a data processing program, which, when executed by a processor, implements the steps of the multi-terminal interconnected flexible microgrid performance evaluation method according to any one of claims 1 to 5.

Images