Flexible interconnection equipment resource optimization method, system, equipment and medium

Abstract

The invention discloses a flexible interconnection equipment resource optimization method, system, device and medium, and the method comprises the steps: obtaining the power change data of each access energy source, predicting the access power of each energy source through the power change data, obtaining the predicted access power of each energy source, and obtaining the predicted access power of each energy source; calculating a predicted weight vector according to the predicted access power; obtaining historical power data, calculating a reduction index according to the historical power data, and adjusting the prediction weight vector by using the reduction index to obtain a reduction weight; calculating a prediction reference degree according to the similarity between the predicted access power and the historical power data, and obtaining an actual weight of each access energy based on the historical weight and the reduction weight; based on the actual weight, the input proportion of each energy source is obtained, resource optimization of the flexible interconnection equipment is realized, and the effect of stable operation of a power supply system is effectively ensured.

Description

Technical Field

[0001] This invention relates to the field of power system resource optimization technology, and in particular to a method, system, equipment and medium for optimizing resources of flexible interconnection equipment. Background Technology

[0002] Currently, the penetration rate of new energy sources such as wind power and photovoltaics in new power systems has exceeded 50%, and the distribution network is transforming from a unidirectional radial structure to a flexible AC / DC interconnection model with multiple sources and mutual support. However, the high proportion of distributed energy access brings challenges such as increased power volatility and spatiotemporal imbalance between source and load. Traditional static allocation modes based on fixed weights are difficult to meet the needs of multi-energy coordination. In existing technologies, the dynamic weight allocation of multiple energy sources faces problems such as the inability to meet the power changes of various energy sources, making it impossible for the power supply quality and efficiency to meet the requirements of actual production. Therefore, a flexible interconnection equipment resource optimization method is urgently needed.

[0003] In conventional flexible interconnection equipment, the dynamic power allocation weighting process for multiple energy sources relies solely on historical data, failing to consider the evolving power data of various energy sources. While conventional particle swarm optimization algorithms allocate weights based on historical data, the power of these energy sources fluctuates unpredictably. Dynamic weighting based on historical data struggles to adapt to subsequent energy changes, resulting in unsuitable dynamic weights that fail to meet the resource requirements of the flexible interconnection equipment and leading to instability in the power supply system. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention provides a method, system, device and medium for optimizing resources of flexible interconnected equipment.

[0005] This invention provides a flexible interconnection equipment resource optimization method, system, device, and medium to solve the problems of power fluctuation and source-load imbalance caused by high proportion of new energy access, which cannot meet the multi-energy coordination requirements and the unstable operation of the power supply system due to the inability of traditional static allocation mode and existing dynamic weight allocation method to meet the needs of multi-energy coordination.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for optimizing resources in flexible interconnected equipment, comprising: Obtain power change data for each type of access energy source, use the power change data to predict the access power of each type of energy source, obtain the predicted access power of each type of energy source, and calculate the prediction weight vector based on the predicted access power. Historical power data is acquired, a reduction index is calculated based on the historical power data, and the prediction weight vector is adjusted using the reduction index to obtain the reduction weight; Based on the similarity between the predicted access power and the historical power data, a prediction reference degree is calculated, and based on the historical weight and the reduction weight, the actual weight of each access energy is obtained; Based on the actual weights, the input ratio of each energy source is obtained, thereby achieving resource optimization for flexible interconnected equipment.

[0007] As a preferred embodiment of the flexible interconnection equipment resource optimization method described in this invention, the calculation of the prediction weight vector includes: The access power of each energy source is predicted using a time series forecasting algorithm to obtain the predicted access power within a set future time period. The predicted access power is used as input, and the predicted weight vector is obtained by using an optimization algorithm to calculate the weight allocation.

[0008] As a preferred embodiment of the flexible interconnection equipment resource optimization method described in this invention, the calculation of the reduction index includes: Historical power data is used as nearby power data, and the fluctuation weighting of each type of access energy is calculated based on the nearby power data. The fluctuation weighted value is standardized to obtain the fluctuation evaluation value for each type of energy source, and the reduction index is calculated based on the fluctuation evaluation value.

[0009] The beneficial effects of this preferred technical solution are that by calculating the reduction index and dynamically adjusting the weights, the impact of power fluctuations can be effectively reduced, and power supply stability can be improved.

[0010] As a preferred embodiment of the flexible interconnection equipment resource optimization method described in this invention, adjusting the prediction weight vector includes: Based on historical weights, the difference between predicted weights and historical weights is adjusted by combining the reduction index to obtain the reduction weights corresponding to each energy source. When adjusting the predicted weight vector, the larger the reduction exponent, the closer the reduced weights are to the predicted weights; the smaller the reduction exponent, the closer the reduced weights are to the historical weights.

[0011] The beneficial effects of this preferred technical solution are that by dynamically adjusting the weights and taking into account both historical and forecast data, energy allocation is optimized and system stability is improved.

[0012] As a preferred embodiment of the flexible interconnection equipment resource optimization method described in this invention, the calculation of the prediction reference degree includes: Based on the statistical characteristics of the historical power data and the statistical characteristics of the predicted power of each access energy source, the standardized position of each predicted data point in the predicted power is calculated in the historical data distribution and the predicted data distribution, respectively. For each data point, calculate the absolute value of the difference between standardized positions and map it to a single-point similarity evaluation value that characterizes the prediction reliability of the corresponding data point; By comprehensively evaluating the single-point similarity values ​​of all data points in the predicted access power, the overall predictive reference value of the corresponding energy is obtained.

[0013] As a preferred embodiment of the flexible interconnection equipment resource optimization method described in this invention, obtaining the actual weight of each access energy source includes: Using the predictive reference level as a weighting coefficient, the historical weight and the reduction weight are weighted and fused together to obtain the actual weight of each type of energy access.

[0014] As a preferred embodiment of the flexible interconnection equipment resource optimization method described in this invention, obtaining the input ratio of each energy source includes: The actual weight of each access energy source is normalized, and the normalized value is used as the input ratio of the corresponding energy source.

[0015] Secondly, this invention provides a flexible interconnected equipment resource optimization system, comprising: The prediction module is used to acquire power change data for each type of access energy source, predict the access power of each type of energy source using the power change data, obtain the predicted access power of each type of energy source, and calculate the prediction weight vector based on the predicted access power. An adjustment module is used to acquire historical power data, calculate a reduction index based on the historical power data, and adjust the predicted weight vector using the reduction index to obtain the reduction weight; The calculation module is used to calculate the prediction reference degree based on the similarity between the predicted access power and the historical power data, and to obtain the actual weight of each access energy based on the historical weight and the reduction weight. The proportion determination module is used to obtain the input proportion of each energy source based on the actual weight, thereby realizing resource optimization of the flexible interconnection equipment.

[0016] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, characterized in that the processor executes the computer program to implement the steps of the flexible interconnection equipment resource optimization method described above.

[0017] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of the flexible interconnection equipment resource optimization method described above.

[0018] Compared with existing technologies, the beneficial effects of this invention are as follows: The technical solution of this invention effectively solves the problems of power fluctuations and source-load imbalance caused by a high proportion of renewable energy access. The dynamic power weight allocation method of this invention can adjust the weights of each energy source in real time according to the changing trends of renewable energy power, effectively addressing power fluctuations. Compared with existing methods, this invention considers historical data and combines the dynamic characteristics of predicted data, making the weight allocation more adaptable. This invention optimizes the accuracy of weight allocation through fluctuation reduction factors and similarity adjustments, improving the stability and reliability of the power supply system. The calculation process of dynamic power allocation weights in this invention achieves optimized resource allocation, improving the flexibility and power supply quality of renewable energy access. This invention provides an effective solution for the coordinated optimization of multiple energy sources in new power systems. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram of the overall process logic of a flexible interconnected equipment resource optimization method provided in one embodiment of the present invention. Detailed Implementation

[0021] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0022] Example 1, referring to Figure 1 As an embodiment of the present invention, a method for optimizing resources of flexible interconnected equipment is provided, comprising: S100: Obtain power change data for each type of access energy source, use the power change data to predict the access power of each type of energy source, obtain the predicted access power of each type of energy source, and calculate the prediction weight vector based on the predicted access power. In this embodiment of the invention, for flexible interconnected devices, during the dynamic power weight calculation of multiple energy access, it is necessary to collect the access power of various energy sources. This can be achieved by installing an energy meter at the output end of each energy source to collect voltage and current data, and multiplying them as instantaneous power.

[0023] Specifically, electricity meters are installed at the output terminals of each access energy source in the flexible interconnection device to collect current and voltage data. The data collection cycle is one second, and the average current and voltage are collected every second. These averages are then multiplied to obtain the power of each access energy source within one second. The main access energy types designed include: photovoltaic power generation, wind power generation, and energy storage system output. The output power of each of these energy sources is collected separately, and the power of the second energy source is calculated. The first collection The output power of this energy source is denoted as For the current moment, the power weights of various access energy sources at this time are denoted as... .

[0024] S200: Obtain historical power data, calculate the reduction index based on the historical power data, and adjust the prediction weight vector using the reduction index to obtain the reduction weight; S300: Calculate the prediction reference degree based on the similarity between the predicted access power and historical power data, and obtain the actual weight of each access energy based on historical weight and reduction weight; In an optional embodiment, the prediction reference degree can be calculated using a sequence similarity algorithm based on dynamic time warping, aligning the predicted power sequence with the historical power sequence. The distance matrix between the two sequences is calculated, the cumulative distance matrix is ​​initialized, and starting from the bottom right corner of the matrix, the globally optimal path (i.e., the path with the minimum cumulative distance) is backtracked to find the path. The reciprocal of the cumulative distance is used as the similarity metric, and this similarity is used as the prediction reference degree. In another optional embodiment, the prediction reference degree can also be calculated as a similarity measure based on the correlation coefficient. For the predicted power sequence and the historical power sequence, the mean and standard deviation are calculated respectively. The covariance between the predicted sequence and the historical sequence is calculated. The correlation coefficient is calculated using the covariance and standard deviation. The correlation coefficient is then converted into the prediction reference degree. In this embodiment of the invention, calculating the prediction reference degree includes comparing the standardized deviation of the predicted data with the historical data, calculating the similarity of each predicted data point using an exponential function, and taking the average value as the final prediction reference degree. The consistency between the predicted data and the historical data is comprehensively evaluated. The greater the difference between the predicted data and the historical data, the lower the prediction reference degree.

[0025] S400: Based on actual weights, the input ratio of each energy source is obtained, realizing resource optimization of flexible interconnected equipment.

[0026] It should be noted that by collecting power data from various energy sources and predicting future power, combined with historical data to calculate the reduction index and predictive reference level, the weights are dynamically adjusted to optimize the energy input ratio. This effectively addresses power fluctuations from new energy sources, improves power supply stability and efficiency, optimizes flexible interconnection equipment resources, meets the multi-energy synergy needs of new power systems, and facilitates the transformation and upgrading of the power system.

[0027] In this embodiment of the invention, step S100 includes the following sub-steps A1-A2; In A1: The access power of each energy source is predicted using a time series forecasting algorithm to obtain the predicted access power within a set future time period; In A2: the predicted access power is used as input, and the predicted weight vector is obtained by weight allocation calculation using an optimization algorithm.

[0028] In one alternative embodiment, the time series prediction algorithm can be a Long Short-Term Memory (LSTM) network. Historical power data is collected and normalized, scaling the data to the [0,1] interval to construct a time series dataset. The historical data is divided into input sequences and target values. An LSTM network is constructed, typically including an input layer, LSTM layers, fully connected layers, and an output layer. The number of units in the LSTM layers is set, and dropout layers are added to prevent overfitting. The LSTM model is trained using historical power data, selecting mean squared error (MSE) as the loss function, and Adam can be chosen as the optimizer. Multiple rounds of training are performed, and hyperparameters are adjusted based on the validation set. The trained LSTM model is then used to predict the access power for each energy source. In another alternative embodiment, the time series forecasting algorithm can be the Prophet algorithm. Historical power data is collected and converted into the format required by Prophet, including a table containing timestamps and power values. The Prophet model is initialized, and seasonal and trend parameters can be set. Custom seasonal components are added based on the characteristics of the energy power data. The Prophet model is fitted using historical power data; the model automatically identifies and fits the trend and seasonal components in the data. A forecast data frame for future time points is constructed, and the fitted Prophet model is used to predict the access power for each energy source. In this embodiment of the invention, the time series prediction algorithm includes the ARIMA algorithm; Specifically, power is dynamically weighted based on the fluctuation of power data for each type of energy source. Therefore, power data for each type of energy source is predicted, and then the power is dynamically weighted by combining historical data and predicted data.

[0029] Preset prediction window size Technicians can set the prediction window size according to the actual implementation situation. For the power data of each type of access energy source, the ARIMA algorithm is used to predict future power levels. The power data, of which the first The first item in the predicted data The number is denoted as The ARIMA algorithm can directly obtain prediction data based on historical power data.

[0030] It should be noted that by using the ARIMA algorithm to predict future power data and combining it with historical data for dynamic weighting, we can effectively address the fluctuations in new energy power, optimize resource allocation, and improve the stability and operating efficiency of the power supply system.

[0031] In one alternative embodiment, the optimization algorithm can be a genetic algorithm. A random set of initial weight vectors is generated as a population, with each weight vector representing a possible solution. The population size is set according to the problem size. A fitness function is defined, and the fitness value of each weight vector is calculated to evaluate the quality of the weights. Based on the fitness value, the best weight vectors are selected to enter the next generation. Two parent weight vectors are randomly selected, and a crossover operation is performed to generate new offspring weight vectors. The generated offspring weight vectors are then randomly mutated to introduce new genetic mutations. The fitness evaluation, selection, crossover, and mutation operations are repeated until the termination condition is met. The weight vector with the highest fitness is selected from the final population as the optimal solution.

[0032] In another alternative embodiment, the optimization algorithm can also be a differential evolution algorithm. A set of initial weight vectors is randomly generated as the population, with each weight vector representing a possible solution. For each target vector, three different vectors are randomly selected, and their difference vectors are calculated. The difference vector is multiplied by a scaling factor to generate a mutation vector. The mutation vector is crossed with the target vector to generate trial vectors. The crossover operation controls the gene segments of the mutation vector by introducing a crossover probability. The fitness values ​​of the trial vector and the target vector are compared, and the vector with higher fitness is selected to enter the next generation. The mutation, crossover, and selection operations are repeated until the termination condition is met, and the weight vector with the highest fitness is selected from the final population as the optimal solution. In this embodiment of the invention, the optimization algorithm includes the particle swarm optimization algorithm; Specifically, for the predicted data, the conventional dynamic power weights are obtained through iterative search using the particle swarm optimization algorithm. Therefore, this invention performs the same optimization search on the predicted data to obtain its weights. The weights of the predicted data are calculated using the particle swarm optimization algorithm, and the obtained weights are then... The weight of each data item is denoted as .

[0033] Based on historical data, each particle represents a set of power allocation weights. The fitness function is based on comprehensive economic efficiency. The particle position is adjusted according to the individual optimality and the group optimality. The optimal particle position, i.e. the initial weight, is obtained iteratively.

[0034] It should be noted that by using the particle swarm optimization algorithm to optimize the weights of the predicted data, and taking economic efficiency as the fitness function, the weights are dynamically adjusted to achieve optimal resource allocation and improve the stability and economy of the power supply system.

[0035] In this embodiment of the invention, step S200 includes the following sub-steps B1-B2; In B1: Historical power data is used as nearby power data, and the fluctuation weighting of each access energy source is calculated based on the nearby power data. In B2: The fluctuation weighted quantity is standardized to obtain the fluctuation evaluation value for each type of energy source, and the reduction index is calculated based on the fluctuation evaluation value.

[0036] In one optional embodiment, the fluctuation weighting can be calculated using a moving average weighting method. A fixed window size is set, weights are assigned to each data point, the weighted sum of each data point within the window is calculated, and then the result is divided by the sum of the weights to obtain the weighted average. The difference between the current data point and the weighted average is used to measure the fluctuation weighting. In another optional embodiment, the fluctuation weighting can also be calculated using a linear decay weighting method, which sets a fixed window size, assigns a linear decay weight to each data point, performs a weighted summation on each data point within the window, calculates the fluctuation weighting, and normalizes the calculated fluctuation weighting. In this embodiment of the invention, the calculation of the fluctuation weighting includes an exponential decay weighting method; Specifically, the prediction data is obtained using the ARIMA algorithm. While the ARIMA algorithm can effectively describe the trend of data changes, it is less effective at predicting local fluctuations. Furthermore, the fluctuations in the power data of the accessed energy sources also affect the energy weights; the greater the fluctuation, the lower the weight of the accessed energy source. Therefore, the prediction weights are reduced based on the fluctuations of each data point to ensure that the prediction weights account for the impact of fluctuations in each type of accessed energy source.

[0037] Before obtaining historical data collection time The power data of each type of access energy source is recorded as the neighboring power data, and the power data of the first type of access energy source is recorded as the neighboring power data. The first The adjacent power data is denoted as , will the The average of the nearest neighboring data is denoted as According to the nearest energy source for each access point The degree of fluctuation in power data is obtained by reducing the index, which is expressed as follows: in, For the first The reduction index of the data item Indicates the number of neighboring data. Indicates the first The first item in the adjacent data One data point, Indicates the first The average of the nearest neighboring data, This represents the exponential decay coefficient, which is taken as 0.9 in this embodiment of the invention. This represents the index values ​​of nearby data, sorted from furthest to nearest from the current data. Indicates the first The standard deviation of the nearest neighboring data.

[0038] The greater the volatility of historical data, the lower the reliability of the prediction weights obtained from smoothed data is considered, therefore a smaller reduction in the exponent is desired; among them... The partial representation indicates the sampling distance weight. The predicted power data fluctuation is obtained by weighting the sampling distance and then calculating the reduction index.

[0039] It should be noted that by reducing the index through exponential decay weighting calculation, the prediction weights are dynamically adjusted to reduce the impact of historical data fluctuations on the prediction weights, thereby improving the adaptability of weight allocation and the stability of the power supply system.

[0040] In this embodiment of the invention, after completing steps B1-B2, step S200 also includes steps B3-B4. In B3: Based on historical weights, the difference between the predicted weights and historical weights is adjusted by combining the reduction index to obtain the reduction weights corresponding to each energy source; In B4: When adjusting the predicted weight vector, the larger the reduction exponent, the closer the reduced weights are to the predicted weights; the smaller the reduction exponent, the closer the reduced weights are to the historical weights.

[0041] In this embodiment of the invention, the portion of the predicted weight that differs from the historical weight is adjusted according to the reduction index: in, This indicates the adjusted weight reduction. and They represent the first Historical weights and predicted weights of the data items. Indicates the first The reduction index of the data item.

[0042] The reduction index measures the difference between historical and predicted transmission data in terms of the volatility of each energy source. The greater the volatility of the historical data, the greater the difference between it and the ARIMA prediction based on stationary data. Therefore, the prediction weights can be adjusted according to the reduction index, so that the weights of data items with larger reduction indices are closer to the weights of historical data. Thus, the reduction weights for the power data corresponding to all energy sources are obtained.

[0043] It should be noted that this invention adjusts the prediction weights by reducing the index, making the weights closer to historical data fluctuations, optimizing weight allocation, and improving system stability.

[0044] In this embodiment of the invention, step S300 includes the following sub-steps C1-C3; In C1: Based on the statistical characteristics of the historical power data and the statistical characteristics of the predicted power of each access energy source, calculate the standardized position of each predicted data point in the historical data distribution and the predicted data distribution, respectively; In C2: For each data point, calculate the absolute value of the difference between standardized locations and map it to a single-point similarity evaluation value that characterizes the prediction reliability of the corresponding data point; In C3: The overall prediction reference degree of the corresponding energy is obtained by comprehensively predicting the single-point similarity evaluation value of all data points in the access power.

[0045] In this embodiment of the invention, the average value and standard deviation of the historical power data corresponding to each type of access energy are obtained, and are respectively denoted as... and , will the The mean and standard deviation of the predicted data are denoted as . and The predictive reference value for forecasting data obtained from historical data is expressed as: in, Indicates the first The predictive reference value of the data. Indicates the number of predicted data points. Indicates the first The first Forecast data, Indicates the first The average of the predicted data, Indicates the first The standard deviation of the predicted data Indicates the first The average of historical data, Indicates the first The standard deviation of historical data.

[0046] Among them Partially representing the compliance of each predicted data point with historical data, while This indicates the outlier of the predicted data. The greater the difference between the two, the greater the difference in performance between each predicted data point and the historical data. In this case, the predictive reference value of the predicted data is lower. The predictive reference value is obtained by combining all the predicted data.

[0047] It should be noted that by calculating the standardized deviation between the predicted data and historical data, the compliance and outlierness of the predicted data are quantified, weights are dynamically adjusted, resource allocation is optimized, and the adaptability and stability of the system are improved.

[0048] In this embodiment of the invention, after completing steps C1-C3, step S300 further includes step C4; In C4: The predicted reference degree is used as the weighting coefficient, and the historical weight and reduction weight are weighted and fused to obtain the actual weight of each access energy.

[0049] In this embodiment of the invention, the predictive reference degree measures the referenceability of the predictive data by the similarity between the predicted data and the historical data, that is, it reflects the ability of the predicted data to be used to adjust the historical power weights, so the actual weight of each access energy can be obtained accordingly.

[0050] Specifically, the actual weight of each type of access energy power is obtained by combining historical weights and predicted weights based on the prediction reference degree, as expressed as follows: in, Indicates the first The actual weight of the energy power data accessed. and They represent the first Historical weights and predicted weights of the data items. Indicates the first The predictive reference value of the data.

[0051] Therefore, the actual weights of all access energy power data are obtained.

[0052] In this embodiment of the invention, step S400 includes the following sub-step D1; In D1: The actual weight of each access energy source is normalized, and the normalized value is used as the input ratio of the corresponding energy source.

[0053] In this embodiment of the invention, the input ratio of each energy source data is obtained by normalizing according to the power weight of each access energy source; Normalization involves dividing the actual weight by the sum of all access energy power data to obtain the input ratio. Here, normalization ensures that the sum of the weights is one.

[0054] It should be noted that the input ratio determination method of this invention not only determines the weights based on historical data, but also predicts the power data of each access energy source. By comprehensively considering the predicted data, a more accurate input ratio that meets the operational requirements of flexible interconnected devices is obtained. This achieves the beneficial effect of dynamically allocating power weights based on the trend of predicted data to better meet the changing power requirements of various energy sources.

[0055] The above is an illustrative scheme of a flexible interconnected equipment resource optimization method according to this embodiment. It should be noted that the technical solution of this flexible interconnected equipment resource optimization system and the technical solution of the aforementioned flexible interconnected equipment resource optimization method belong to the same concept. Details not described in detail in the technical solution of the flexible interconnected equipment resource optimization system in this embodiment can be found in the description of the technical solution of the aforementioned flexible interconnected equipment resource optimization method.

[0056] The flexible interconnected equipment resource optimization system in this embodiment includes: The prediction module is used to acquire power change data for each type of access energy source, predict the access power of each type of energy source using the power change data, obtain the predicted access power of each type of energy source, and calculate the prediction weight vector based on the predicted access power. An adjustment module is used to acquire historical power data, calculate a reduction index based on the historical power data, and adjust the predicted weight vector using the reduction index to obtain the reduction weight; The calculation module is used to calculate the prediction reference degree based on the similarity between the predicted access power and the historical power data, and to obtain the actual weight of each access energy based on the historical weight and the reduction weight. The proportion determination module is used to obtain the input proportion of each energy source based on the actual weight, thereby realizing resource optimization of the flexible interconnection equipment.

[0057] This embodiment also provides a computer device applicable to resource optimization in flexible interconnected equipment, including: The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement a resource optimization method for flexible interconnected equipment as described in the above embodiments.

[0058] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements a flexible interconnection equipment resource optimization method as proposed in the above embodiments.

[0059] The storage medium proposed in this embodiment and the resource optimization method for flexible interconnected equipment proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0060] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computing device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0061] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for optimizing resources in flexible interconnected equipment, characterized in that, include: Obtain power change data for each type of access energy source, use the power change data to predict the access power of each type of energy source, obtain the predicted access power of each type of energy source, and calculate the prediction weight vector based on the predicted access power. Historical power data is acquired, a reduction index is calculated based on the historical power data, and the prediction weight vector is adjusted using the reduction index to obtain the reduction weight; Based on the similarity between the predicted access power and the historical power data, a prediction reference degree is calculated, and based on the historical weight and the reduction weight, the actual weight of each access energy is obtained; Based on the actual weights, the input ratio of each energy source is obtained, thereby achieving resource optimization for flexible interconnected equipment.

2. The flexible interconnection equipment resource optimization method as described in claim 1, characterized in that, The calculation of the prediction weight vector includes: The predicted access power within a set future time period is obtained by using a time series prediction algorithm. The predicted access power is used as input, and the predicted weight vector is obtained by using an optimization algorithm to calculate the weight allocation.

3. The flexible interconnection equipment resource optimization method as described in claim 2, characterized in that, The calculation of the reduction index includes: Historical power data is used as nearby power data, and the fluctuation weighting of each type of access energy is calculated based on the nearby power data. The fluctuation weighted value is standardized to obtain the fluctuation evaluation value for each type of energy source, and the reduction index is calculated based on the fluctuation evaluation value.

4. The flexible interconnection equipment resource optimization method as described in claim 3, characterized in that, Adjusting the prediction weight vector includes: Based on historical weights, the difference between predicted weights and historical weights is adjusted by combining the reduction index to obtain the reduction weights corresponding to each energy source. When adjusting the predicted weight vector, the larger the reduction exponent, the closer the reduced weights are to the predicted weights; the smaller the reduction exponent, the closer the reduced weights are to the historical weights.

5. The flexible interconnection equipment resource optimization method as described in claim 4, characterized in that, The calculation of predictive reference degree includes: Based on the statistical characteristics of the historical power data and the statistical characteristics of the predicted power of each access energy source, the standardized position of each predicted data point in the predicted power is calculated in the historical data distribution and the predicted data distribution, respectively. For each data point, calculate the absolute value of the difference between standardized positions and map it to a single-point similarity evaluation value that characterizes the prediction reliability of the corresponding data point; By comprehensively evaluating the single-point similarity values ​​of all data points in the predicted access power, the overall predictive reference value of the corresponding energy is obtained.

6. The resource optimization method for flexible interconnected equipment as described in claim 5, characterized in that, The actual weights for each type of access energy source are obtained as follows: Using the predictive reference level as a weighting coefficient, the historical weight and the reduction weight are weighted and fused together to obtain the actual weight of each type of energy access.

7. A resource optimization method for flexible interconnected equipment as described in claim 1 or 6, characterized in that, The input proportions for each energy source are as follows: The actual weight of each access energy source is normalized, and the normalized value is used as the input ratio of the corresponding energy source.

8. A flexible interconnected equipment resource optimization system, employing the flexible interconnected equipment resource optimization method as described in any one of claims 1-7, characterized in that, include: The prediction module is used to acquire power change data for each type of access energy source, predict the access power of each type of energy source using the power change data, obtain the predicted access power of each type of energy source, and calculate the prediction weight vector based on the predicted access power. An adjustment module is used to acquire historical power data, calculate a reduction index based on the historical power data, and adjust the predicted weight vector using the reduction index to obtain the reduction weight; The calculation module is used to calculate the prediction reference degree based on the similarity between the predicted access power and the historical power data, and to obtain the actual weight of each access energy based on the historical weight and the reduction weight. The proportion determination module is used to obtain the input proportion of each energy source based on the actual weight, thereby realizing resource optimization of the flexible interconnection equipment.

9. A computer device, characterized in that, include: A memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the flexible interconnected equipment resource optimization method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by a processor, implements the steps of a flexible interconnected equipment resource optimization method according to any one of claims 1 to 7.

Images