Planning method, device and configuration system of integrated energy system

Abstract

The invention discloses a planning method and device of an integrated energy system and a configuration system. The method comprises the following steps: acquiring to-be-planned system data; in combination with the historical planning scheme library, different similarity indexes are adopted, and the scheme similarity between the to-be-planned discrete data and the historical planning scheme in the historical planning scheme library and the scheme similarity between the to-be-planned continuous data and the historical planning scheme in the historical planning scheme library are analyzed; based on a preset scheme similarity threshold value, judging the scheme similarity to obtain a similar result; and determining a strategy according to a scheme corresponding to the similar result, performing scheme planning in combination with the to-be-planned system data, and giving a target planning scheme. According to the method, the to-be-planned system data is analyzed, the historical planning schemes with relatively high similarity are screened from the historical planning scheme library based on the scheme similarity, and the target planning scheme is determined by adopting different scheme determination strategies according to the screening result, so that the planning efficiency of the integrated energy system is improved while the planning effect of the integrated energy system is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy system planning, and in particular relates to a planning method, device and configuration system for an integrated energy system. Background Art

[0002] An integrated energy system (IES) utilizes advanced physical information technology and innovative management models within a specific region to integrate multiple energy sources, including coal, oil, natural gas, electricity, and thermal energy. This system enables coordinated planning, optimized operation, collaborative management, interactive response, and complementary support among these heterogeneous energy subsystems. IESs are new, integrated energy systems that effectively improve energy efficiency and promote sustainable energy development while meeting diverse energy demands within the system.

[0003] Current integrated energy system planning faces the challenges of multi-faceted data processing, complex scenario optimization, and economic trade-offs. Energy demand in regional energy systems is influenced by construction area, geographic location, natural resources (such as solar, wind, and geothermal energy), and cooling, heating, and electricity loads. Efficient planning and design require comprehensive integration of diverse information.

[0004] However, traditional planning methods generally build models through analysis of historical plans. Using models to replan the current situation consumes a lot of time and increases costs. On the other hand, it is difficult to simultaneously take into account data diversity and the complexity of model optimization during the model construction process, resulting in low efficiency in energy configuration, cost optimization and solution design.

[0005] Patent CN117810989A discloses a method for establishing and solving a data-mechanism hybrid-driven power grid optimization scheduling model, including: 1. Establishing a physical model of an integrated energy system with uncertainty injection; 2. Generating simulation cases based on the physical model of the integrated energy system and generating corresponding solution data as a training set for machine learning; 3. Training the machine learning model for learning and solving; 4. Fusing the physical model of the integrated energy system with the data model to establish a data-mechanism hybrid-driven power grid optimization scheduling model, and proposing a data-mechanism hybrid-driven optimization scheduling method for the power grid system. This method improves the accuracy of deep neural network mapping, and the data-driven approach significantly reduces scheduling solution time; achieves coordinated optimization of the optimal carrying capacity of new energy and the planning and operation of controllable equipment, and improves the utilization rate of new energy.

[0006] How to improve the planning efficiency of the integrated energy system while ensuring its planning effectiveness is a problem that needs to be solved at present. Summary of the Invention

[0007] In response to the defects existing in the above-mentioned prior art, the present invention provides a planning method, device and configuration system for an integrated energy system, the method comprising: obtaining the system data to be planned, wherein the system data to be planned includes discrete data to be planned and continuous data to be planned; combining with the historical planning scheme library, using different similarity indicators, respectively analyzing the scheme similarity between the discrete data to be planned and the continuous data to be planned and the historical planning schemes in the historical planning scheme library; judging the scheme similarity based on a preset scheme similarity threshold, and obtaining similarity results; determining a strategy based on the scheme corresponding to the similarity result, performing scheme planning in combination with the system data to be planned, and providing a target planning scheme. By analyzing the system data to be planned, based on the scheme similarity, historical planning schemes with higher similarity are screened from the historical planning scheme library; according to the screening results, different scheme determination strategies are used to determine the target planning scheme, thereby improving the planning efficiency of the integrated energy system while ensuring the planning effect of the integrated energy system.

[0008] In a first aspect, the present invention provides a method for planning an integrated energy system, comprising the following steps: Acquiring system data to be planned, wherein the system data to be planned includes discrete data to be planned and continuous data to be planned; Combined with the historical planning scheme database, different similarity indicators are used to analyze the similarity between the discrete data to be planned and the continuous data to be planned and the historical planning schemes in the historical planning scheme database; Based on the preset solution similarity threshold, the solution similarity is judged to obtain similarity results; Determine the strategy based on the solutions corresponding to similar results, carry out solution planning in combination with the data of the system to be planned, and give the target planning solution.

[0009] Furthermore, in combination with the historical planning scheme library, different similarity indicators are used to analyze the similarity between the discrete data to be planned and the continuous data to be planned and the historical planning schemes in the historical planning scheme library, including: Using the first similarity index, analyzing the discrete similarity between the discrete data to be planned and the discrete data in the historical planning scheme; Using the second similarity index, analyze the continuous similarity between the continuous data to be planned and the continuous data in the historical planning schemes; The preset discrete similarity weight and the preset continuous similarity weight are combined to fuse the discrete similarity and the continuous similarity to obtain the solution similarity.

[0010] Furthermore, the first similarity index is the Jaccard coefficient, and the second similarity index is the Euclidean distance.

[0011] Furthermore, the discrete similarity and the continuous similarity are combined with the preset discrete similarity weight and the preset continuous similarity weight to obtain the scheme similarity, which specifically includes: Normalize the discrete similarity and continuous similarity respectively to obtain the standard discrete similarity and standard continuous similarity; Combining the discrete similarity weight and the continuous similarity weight, the standard discrete similarity and the standard continuous similarity are weighted and summed to obtain the scheme similarity.

[0012] Furthermore, the similarity of the solutions is specifically expressed as: ; ; in, is the similarity between the system data to be planned i and the historical planning scheme j in the historical planning scheme library, is the discrete data to be planned in the system data i to be planned and discrete data in historical planning scenarios The standard discrete similarity of is the continuous data to be planned in the system data i to be planned and continuous data in historical planning schemes The corresponding standard continuous similarity, is the continuous similarity weight, is the discrete similarity weight.

[0013] Furthermore, the standard continuous similarity is specifically expressed as: ; in, is the continuous data to be planned in the system data i to be planned and continuous data in historical planning schemes The corresponding standard continuous similarity, For all The maximum value in is the continuous data to be planned in the system data i to be planned and continuous data in historical planning schemes Continuous similarity.

[0014] Furthermore, the continuous similarity is specifically expressed as: ; in, is the continuous data to be planned in the system data i to be planned and continuous data in historical planning schemes The continuous similarity of p is the dimension of the continuous data to be planned. Continuous data to be planned The kth element in is the continuous data in the historical planning scheme j The kth element in the system data to be planned, n is the continuous data to be planned in the system data to be planned i The number of groups, m is the number of historical planning schemes in the historical planning scheme.

[0015] Furthermore, the discrete similarity is specifically expressed as: ; in, is the discrete data to be planned in the system data i to be planned and discrete data in historical planning scenarios The discrete similarity of .

[0016] Furthermore, we determine the strategy based on the solutions corresponding to similar results, combine the system data to be planned, and provide the target planning solution, which specifically includes: If the similarity result corresponding to at least one historical planning scheme in the historical planning scheme library is similar, the historical planning schemes in the historical planning scheme library are sorted based on the scheme similarity, and the pending historical scheme is given according to the sorting result; A target planning scheme is obtained by using a pre-acquired target decision tree model and combining it with the system data to be planned, wherein the pre-acquired target decision tree model is obtained by analyzing and correcting the historical schemes to be planned; If the similar results of the historical planning schemes in the historical planning scheme library are all dissimilar, the target planning scheme is given by combining the system data to be planned and the pre-built scheme generation model.

[0017] Furthermore, the pre-acquired target decision tree model is determined specifically through the following steps: Based on the similar results of various historical planning schemes, the historical planning schemes in the historical planning scheme library are screened to obtain the model training data set; Initialize the decision tree model and set the model parameters in the decision tree model; Use the model training data set to train the decision tree model until convergence; Use model evaluation indicators to evaluate the trained decision tree model and obtain the model evaluation results;

[0018] Based on the model evaluation results, the decision tree model is corrected and trained to obtain the target decision tree model.

[0019] Furthermore, the model evaluation indicator is at least one of mean square error, root mean square error, mean absolute error, and R² score.

[0020] Furthermore, the model evaluation indicators are used to evaluate the trained decision tree model to obtain the model evaluation results, which specifically include: Use multiple model evaluation indicators to evaluate the trained decision tree model and obtain multiple evaluation results; Based on the indicator weights corresponding to different model evaluation indicators, multiple evaluation results are integrated to obtain the model comprehensive indicator; Compare the model comprehensive indicators with the preset model training threshold to obtain the model evaluation results.

[0021] Furthermore, the comprehensive index of the model is specifically expressed as: ; in, is the comprehensive index of the model, is the weight of the mean absolute error, is the weight of the mean square error, MAE is the mean absolute error of the decision tree model, and MSE is the mean square error of the decision tree model.

[0022] Furthermore, the model training data set includes demand training data and solution training data; Based on the model evaluation results, the decision tree model is corrected and trained to obtain the target decision tree model, including: If the model evaluation result is qualified, the demand training data and solution training data are integrated to obtain the integrated features; Based on the integrated features, the trained decision tree model is domain adapted to obtain a mapping function that contains the mapping relationship between demand training data and solution training data; Combined with the mapping function, the trained decision tree model is trained to obtain the target decision tree model.

[0023] Furthermore, the decision tree model is an adaptTree model.

[0024] Furthermore, the pre-built solution generation model is specifically determined by the following steps: Construct a two-level programming model and set the upper-level objective function and the lower-level objective function; Determine the iteration threshold and initialize the particle position and velocity; Combining the upper and lower objective functions, the particle swarm algorithm is used to iteratively solve the bi-level programming model. If the number of iterations reaches the iteration threshold, the bi-level programming model is solved and a solution generation model is obtained.

[0025] Furthermore, the upper-level objective function is used to limit the energy loss of each pipeline network in the integrated energy system, and the lower-level objective function is used to limit the total economic cost of the integrated energy system during its life cycle, where the total economic cost includes the installation cost of each equipment and pipeline network in the integrated energy system, the operation and maintenance cost of the integrated energy system, and the new energy subsidy income in the integrated energy system.

[0026] Furthermore, the upper objective function is specifically expressed as: ; The lower layer objective function is specifically expressed as: ; in, is the upper objective function, i is the pipe network number of the integrated energy system, is the resistance loss of pipe network i, is the inductance and capacitance loss of pipe network i, is the fixed loss of pipeline network i, is the variable loss of pipeline network i, is the other losses of pipeline network i, is the lower layer objective function, is the installation cost of the integrated energy system, The operation and maintenance costs of the integrated energy system are New energy subsidy income for integrated energy systems.

[0027] Furthermore, the target decision tree model obtained in advance is combined with the system data to be planned to obtain the target planning scheme, which specifically includes: Based on the mapping function obtained in the target decision tree model, the data of the planning system is mapped to obtain mapping features; The mapped features are input into the decision tree model to obtain the target planning solution.

[0028] In a second aspect, the present invention further provides a planning device for an integrated energy system, which adopts any of the above-mentioned planning methods for an integrated energy system, comprising: A data acquisition module is used to acquire system data to be planned, wherein the system data to be planned includes discrete data to be planned and continuous data to be planned; A similarity analysis module is used to combine the historical planning scheme library and use different similarity indicators to analyze the similarity between the discrete data to be planned and the continuous data to be planned and the historical planning schemes in the historical planning scheme library; A similarity judgment module is used to judge the similarity of the solutions based on a preset solution similarity threshold and obtain similarity results; The solution determination module is used to determine the strategy according to the solution corresponding to the similar results, carry out solution planning in combination with the system data to be planned, and give the target planning solution.

[0029] In a third aspect, the present invention further provides a configuration system for an integrated energy system, comprising a memory, a processor, and a computer program stored in the memory, wherein the computer program executes instructions according to the above method when the processor runs the computer program.

[0030] The present invention provides a planning method, device, and configuration system for an integrated energy system, which have at least the following beneficial effects: (1) Through the analysis of planning system data, based on the similarity of the schemes, historical planning schemes with high similarity are screened from the historical planning scheme library. According to the screening results, different scheme determination strategies are adopted to determine the target planning scheme, thereby improving the planning efficiency of the integrated energy system while ensuring the planning effect of the integrated energy system.

[0031] (2) By dividing the system data to be planned into discrete data to be planned and continuous data to be planned, and using different similarity indicators to analyze the similarity, the accuracy of the similarity between the system data to be planned and the schemes in the historical planning scheme library is improved, providing a data basis for better determining the target planning scheme.

[0032] (3) The TCA technology is used to perform domain adaptation on the decision tree model. The decision tree model is mapped to a new subspace through a mapping function for further training, so that the target decision tree model can more accurately analyze the data of the system to be planned, ensuring the accuracy of the target planning scheme and, to a certain extent, the planning effect of the integrated energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flow chart of a method for planning an integrated energy system according to an embodiment of the present invention; Figure 2 A flowchart for determining solution similarity provided by an embodiment of the present invention; Figure 3 A flowchart of similarity fusion provided by an embodiment of the present invention; Figure 4 A flow chart of a selection scheme determination strategy provided by an embodiment of the present invention; Figure 5 A flowchart of a target decision tree model provided by an embodiment of the present invention; Figure 6 A flowchart of correcting and training a decision tree model provided by an embodiment of the present invention; Figure 7 A flow chart of a model for determining a solution generation method according to an embodiment of the present invention; Figure 8 This is a structural block diagram of a planning device for an integrated energy system provided by an embodiment of the present invention.

[0034] Among them, 201 is a data acquisition module; 202 is a similarity analysis module; 203 is a similarity judgment module; and 204 is a solution determination module. DETAILED DESCRIPTION

[0035] To better understand the above technical solution, the following will be described in detail with reference to the accompanying drawings and specific implementation methods. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," "the," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0037] It should also be noted that the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a product or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such product or device. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the product or device comprising the element.

[0038] The current development of integrated energy systems faces the challenges of diverse demands and multi-objective optimization, requiring customized planning based on regional and energy characteristics. Due to variations in geography, resource distribution, and energy load, traditional single-objective optimization methods are unable to meet practical engineering needs. Therefore, intelligent, multi-objective planning has become a key research direction for integrated energy systems.

[0039] With the development of intelligent technology, improving planning efficiency through multidimensional data analysis, intelligent optimization algorithms and transfer learning has become a research direction for solving complex problems in integrated energy systems.

[0040] The current integrated energy system generally generates a new planning scheme by analyzing historical planning data or using historical planning data for model training. This approach has limited effect on the planning of integrated energy systems and has low planning efficiency.

[0041] In related technologies, a method for establishing and solving a hybrid data-mechanism-driven power grid optimization scheduling model includes: 1. Establishing a physical model of an integrated energy system with uncertainty injection; 2. Generating simulation cases based on the physical model of the integrated energy system and generating corresponding solution data as a training set for machine learning; 3. Training the machine learning model for learning and solving; 4. Fusing the physical model of the integrated energy system with a data model to establish a hybrid data-mechanism-driven power grid optimization scheduling model, and proposing a hybrid data-mechanism-driven optimization scheduling method for power grid systems. This method improves the accuracy of deep neural network mapping, and the data-driven approach significantly reduces scheduling solution time. It also achieves coordinated optimization of the optimal carrying capacity of new energy resources and the planning and operation of controllable equipment, thereby improving the utilization rate of new energy resources. In related technologies, scheduling of integrated energy systems is achieved by fusing physical and data models. By optimizing the carrying capacity and controllable equipment of new energy resources in the integrated energy system, the utilization rate of new energy resources is achieved, thereby improving the utilization rate of the integrated energy system. However, this method does not consider the adjustment of traditional energy resources other than new energy resources in the integrated energy system, which limits the planning of the integrated energy system and the improvement of its utilization rate.

[0042] The present invention provides a planning method, device and configuration system for an integrated energy system. The method includes: obtaining system data to be planned, wherein the system data to be planned includes discrete data to be planned and continuous data to be planned; combining with a historical planning solution library, using different similarity indicators to analyze the scheme similarity between the discrete data to be planned and the continuous data to be planned and the historical planning solutions in the historical planning solution library; judging the scheme similarity based on a preset scheme similarity threshold to obtain similarity results; determining a strategy based on the scheme corresponding to the similarity result, performing scheme planning in combination with the system data to be planned, and providing a target planning solution. By analyzing the system data to be planned, based on the scheme similarity, historical planning solutions with higher similarity are screened from the historical planning solution library; according to the screening results, different scheme determination strategies are used to determine the target planning solution, thereby improving the planning efficiency of the integrated energy system while ensuring the planning effect of the integrated energy system.

[0043] The integrated energy system planning approach integrates multi-type data similarity calculation, a two-level planning model, and transfer learning methods. By combining Euclidean distance and Jaccard similarity to calculate the similarity of continuous and discrete data, respectively, the accuracy of data analysis is improved. Furthermore, a two-level planning model is constructed. The upper level optimizes the layout of energy stations and pipelines to reduce pipeline energy loss, while the lower level focuses on minimizing the system's lifecycle costs. Transfer learning technology is further employed to transfer historical data patterns to new scenarios through feature distribution alignment and machine learning model training, further improving the adaptability and intelligence of the planning scheme.

[0044] like Figure 1 As shown, an embodiment of the present invention provides a planning method for an integrated energy system, and the specific steps are as follows: S101: Acquire system data to be planned.

[0045] Specifically, the system data to be planned refers to data required for integrated energy system planning. Examples include construction area, geographic location, land use planning, photovoltaic resources, wind resources, geothermal resources, current energy supply and consumption data, environmental data (such as sunshine intensity, wind speed, humidity, and temperature), energy market conditions (such as energy prices), and statistics on cooling, heating, and electricity loads. These load statistics can be presented as duration curves for electricity, heating, cooling, and gas loads. Other data may include the infrastructure status of power distribution and gas networks, typical daily load demands in different seasons, and specific parameters for energy storage devices, photovoltaic power plants, and substations. Data is used based on specific priorities. Furthermore, based on the value extraction method of the system data to be planned, all data can be divided into continuous data (i.e., continuous data to be planned) and discrete data (i.e., discrete data to be planned).

[0046] S102: In combination with the historical planning scheme library, different similarity indices are used to analyze the similarities between the discrete data to be planned and the continuous data to be planned and the historical planning schemes in the historical planning scheme library.

[0047] Reference Figure 2 , specifically including: Using the first similarity index, analyzing the discrete similarity between the discrete data to be planned and the discrete data in the historical planning scheme; Using the second similarity index, analyze the continuous similarity between the continuous data to be planned and the continuous data in the historical planning schemes; The preset discrete similarity weight and the preset continuous similarity weight are combined to fuse the discrete similarity and the continuous similarity to obtain the solution similarity.

[0048] It can be understood that the historical planning scheme library includes multiple previous planning schemes for integrated energy systems, namely historical planning schemes. These historical planning schemes include demand data and scheme data. The demand data is the data required to obtain the scheme data, corresponding to the aforementioned system data to be planned. The scheme data is the relevant data for the integrated energy system planning scheme derived from the demand data. Therefore, the discrete data in the historical planning schemes refers to the discrete data in the demand data. Similarly, the continuous data in the historical planning schemes refers to the continuous data in the demand data.

[0049] In the embodiments provided herein, the first similarity indicator is the Jaccard coefficient, and the second similarity indicator is the Euclidean distance. Other similarity indicators may be used in other embodiments, such as the Manhattan distance, Hamming distance, Mahalanobis distance, and Pearson correlation coefficient, without limitation. The Jaccard coefficient measures the ratio of the intersection to the union of two sets. A larger Jaccard similarity coefficient indicates that the two sets are more similar. Euclidean distance is a metric that calculates the straight-line distance between two vectors. A smaller Euclidean distance indicates that the two vectors are more similar. Manhattan distance calculates the sum of the absolute distances between two vectors on each coordinate axis. A smaller Manhattan distance indicates that the two vectors are more similar. Hamming distance measures the number of different characters between two strings of equal length. A smaller Hamming distance indicates that the two strings are more similar. Mahalanobis distance takes into account the covariance matrix of the data and can better reflect the actual distance between data points. The Pearson correlation coefficient measures the linear relationship between two variables, with a value range of [-1, 1], where 1 indicates a perfect positive correlation and -1 indicates a perfect negative correlation.

[0050] In a specific example, for the continuous data to be planned, the Euclidean distance is used to measure the continuous similarity. If the calculated Euclidean distance is smaller, the continuous similarity is higher. Conversely, if the calculated Euclidean distance is larger, the continuous similarity is lower.

[0051] Assume that each set of continuous data is a vector, and the continuous data to be planned in the planned system data i is represented by Indicates that the continuous data in the historical planning scheme j is Indicates that the continuous data to be planned in the planned system data i is calculated and continuous data in historical planning schemes The Euclidean distance is expressed as: ; in, is the continuous data to be planned in the system data i to be planned and continuous data in historical planning schemes The Euclidean distance, p is the dimension of the continuous data to be planned, Continuous data to be planned The kth element in is the continuous data in the historical planning scheme j The kth element in the system data to be planned, n is the continuous data to be planned in the system data to be planned i The number of groups, m is the number of historical planning schemes in the historical planning scheme.

[0052] For discrete data to be planned, the Jaccard coefficient is used to measure discrete similarity. If the calculated Jaccard coefficient is smaller, the discrete similarity is lower. Conversely, if the calculated Jaccard coefficient is larger, the continuous similarity is higher.

[0053] The discrete data to be planned in the planned system data i is used as a set Indicates that the discrete data in the historical planning scheme j is represented by the set Indicates that the discrete data to be planned in the planned system data i is calculated and discrete data in historical planning scenarios The Jaccard coefficient is specifically expressed as: ; in, is the discrete data to be planned in the system data i to be planned and discrete data in historical planning scenarios Jaccard coefficient.

[0054] Further, refer to Figure 3 , combined with the preset discrete similarity weight and the preset continuous similarity weight, the discrete similarity and the continuous similarity are integrated to obtain the scheme similarity, which specifically includes: Normalize the discrete similarity and continuous similarity respectively to obtain the standard discrete similarity and standard continuous similarity; Combining the discrete similarity weight and the continuous similarity weight, the standard discrete similarity and the standard continuous similarity are weighted and summed to obtain the scheme similarity.

[0055] In a specific implementation, the continuous similarity, ie, the Euclidean distance, is normalized to a range of [0, 1].

[0056] ; in, is the continuous data to be planned in the system data i to be planned and continuous data in historical planning schemes The corresponding standard continuous similarity, For all The maximum value in .

[0057] Since the Jaccard coefficient ranges from [0, 1], there is no need to normalize the Jaccard coefficient.

[0058] The similarity of the scheme is specifically expressed as: ; ; in, is the similarity between the system data to be planned i and the historical planning scheme j in the historical planning scheme library, is the continuous similarity weight, is the discrete similarity weight.

[0059] It can be understood that the continuous similarity weight is the impact of continuous data on the similarity of the solutions, and the discrete similarity weight is the impact of discrete data on the similarity of the solutions. The values of the continuous similarity weight and the discrete similarity weight are set according to actual conditions and are not limited thereto.

[0060] S103: Based on a preset solution similarity threshold, the solution similarity is judged to obtain a similarity result.

[0061] Specifically, each historical planning scheme in the historical planning scheme library corresponds to a scheme similarity threshold, and each scheme similarity is compared with the scheme similarity threshold. If the scheme similarity is greater than or equal to the scheme similarity threshold, the similarity result is similar, indicating that the similarity between the system data to be planned and the demand data in the corresponding historical planning scheme is high, and the corresponding historical planning scheme has a certain degree of reusability. The historical planning scheme can be modified to obtain the target planning scheme corresponding to the system data to be planned. If the scheme similarity is less than the scheme similarity threshold, the similarity result is dissimilar, indicating that the similarity between the system data to be planned and the demand data in the corresponding historical planning scheme is low, and the reusability of the corresponding historical planning scheme is poor, and it is necessary to re-plan to obtain the target planning scheme corresponding to the system data to be planned.

[0062] S104: Determine a strategy based on the solutions corresponding to the similar results, perform solution planning in combination with the system data to be planned, and provide a target planning solution.

[0063] Reference Figure 4 , give the target planning scheme, including: If the similarity result corresponding to at least one historical planning scheme in the historical planning scheme library is similar, the historical planning schemes in the historical planning scheme library are sorted based on the scheme similarity, and the pending historical scheme is given according to the sorting result; A target planning scheme is obtained by using a pre-acquired target decision tree model and combining it with the system data to be planned, wherein the pre-acquired target decision tree model is obtained by analyzing and correcting the historical schemes to be planned; If the similar results of the historical planning schemes in the historical planning scheme library are all dissimilar, the target planning scheme is given by combining the system data to be planned and the pre-built scheme generation model.

[0064] In a specific embodiment, when there is one or more historical planning schemes in the historical planning scheme library with similar corresponding results, the historical planning schemes in the historical planning scheme library are sorted based on the scheme similarity, and the schemes with scheme similarity greater than or equal to the scheme similarity threshold are screened out to obtain the pending historical schemes. The target decision tree model is trained based on the pending historical schemes, and the trained target decision tree model is used to correct the pending historical schemes to obtain the target planning scheme. If the similarity results of the historical planning schemes in the historical planning scheme library are all dissimilar, it means that the schemes in the historical planning scheme library have poor reusability, and it is necessary to combine the system data to be planned and the pre-built scheme generation model to give a new target planning scheme.

[0065] Further, refer to Figure 5 , the pre-acquired target decision tree model is determined by the following steps: Based on the similar results of various historical planning schemes, the historical planning schemes in the historical planning scheme library are screened to obtain the model training data set; Initialize the decision tree model and set the model parameters in the decision tree model; Use the model training data set to train the decision tree model until convergence; Use model evaluation indicators to evaluate the trained decision tree model and obtain the model evaluation results; Based on the model evaluation results, the decision tree model is corrected and trained to obtain the target decision tree model.

[0066] In the example provided by the present invention, the decision tree model is an AdaptTree model.

[0067] In a specific embodiment, historical planning schemes whose scheme similarity reaches a scheme similarity threshold are screened and used as a model training dataset. At the beginning of model training, the model parameters of the decision tree model are set to complete the initialization of the decision tree model. The model parameters include the maximum depth and the minimum number of sample splits. These two parameters are used to control the complexity of the decision tree and prevent overfitting. The setting of model parameters is set according to actual needs and is not limited to this.

[0068] The demand data of each historical planning scheme in the model training data set is the demand training data and solution data, i.e. solution training data As the source domain, the system data to be planned As the target domain, it can be understood that the demand data in the source domain and the system data to be planned in the target domain have a high degree of similarity in distribution or feature form. Relatively close distributions can be aligned through certain mappings, and the "demand data → solution data" pattern in the source domain can be transferred to the target domain.

[0069] The decision tree model is trained on the source domain Train until convergence. and program data The mapping relationship cannot be obtained explicitly, so a data-driven learning method is used in the source domain. Considering the compatibility with mixed features (continuous data and discrete data), a decision tree model is used for training.

[0070] Furthermore, the model evaluation indicators are used to evaluate the trained decision tree model to obtain the model evaluation results, which specifically include: Use multiple model evaluation indicators to evaluate the trained decision tree model and obtain multiple evaluation results; Based on the indicator weights corresponding to different model evaluation indicators, multiple evaluation results are integrated to obtain the model comprehensive indicator; Compare the model comprehensive indicators with the preset model training threshold to obtain the model evaluation results.

[0071] In the example provided by the present invention, mean squared error (MSE) and mean absolute error (MAE) are used as model evaluation indicators to evaluate the performance of the model, and a model comprehensive index is constructed. The model comprehensive index can simultaneously focus on the large errors in the model training process and the overall error between the predicted value and the true value.

[0072] In other embodiments, the model evaluation metric may be one or more of mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and R² score (R² score). MSE is the average of the squares of the differences between the predicted and actual values and is sensitive to large errors. RMSE is the square root of the MSE, and its units are consistent with the original data, making it easier to interpret. MAE is the average of the absolute values of the differences between the predicted and actual values and is insensitive to outliers. The R² score measures the proportion of data variance explained by the model; values closer to 1 indicate better model fit.

[0073] In a specific example, the above four model evaluation indicators are integrated to obtain the model comprehensive indicator. For each model evaluation indicator, the corresponding indicator weight is set ,and In different examples, for different model evaluation indicators, normalization processing can be performed to scale different model evaluation indicators to the same scale and reduce the dimensional differences between model evaluation indicators.

[0074] The comprehensive index of the model is specifically expressed as: ; in, is the comprehensive index of the model, is the weight of the mean absolute error, is the weight of the mean square error, MAE is the mean absolute error of the decision tree model, and MSE is the mean square error of the decision tree model.

[0075] above 、 is the indicator weight, the mean square error of the decision tree model and the mean absolute error of the decision tree model are the evaluation results.

[0076] Compare the model's comprehensive index with the preset model training threshold. If the model's comprehensive index is less than the model training threshold, it indicates that the decision tree model's error is small, meaning the model evaluation result is qualified and the decision tree model training has met the standards. You can proceed directly to the next step. If the model's comprehensive index is greater than or equal to the model training threshold, it indicates that the decision tree model's error is large, meaning the model evaluation result is unqualified and the decision tree model training has not met the standards. Further processing is required, and the decision tree model needs to be retrained.

[0077] If the model evaluation result is unqualified, the similarity threshold is adjusted to allow more historical planning solutions in the historical planning solution library to enter the model training dataset and train the decision tree model. This process is repeated until the model evaluation result is qualified.

[0078] In other embodiments, the historical planning schemes screened out whose scheme similarity reaches a scheme similarity threshold are divided into a training set, a validation set, and a test set according to a certain ratio. For example, the training set, validation set, and test set are divided into a ratio of 6:2:2. When the number of screened historical planning schemes is less than the scheme number threshold, the scheme similarity threshold is adjusted to reduce the screening requirements.

[0079] Further, refer to Figure 6 ,The model training data set includes demand training data and solution training data; Based on the model evaluation results, the decision tree model is corrected and trained to obtain the target decision tree model, including: If the model evaluation result is qualified, the demand training data and solution training data are integrated to obtain the integrated features; Based on the integrated features, the trained decision tree model is domain adapted to obtain a mapping function that contains the mapping relationship between demand training data and solution training data; Combined with the mapping function, the trained decision tree model is trained to obtain the target decision tree model.

[0080] In the embodiments provided by the present invention, transfer component analysis (TCA) is used for domain adaptation. Through unsupervised domain adaptation, the target domain and the source domain are closer distributed in the same feature subspace. A tree model is then trained on this subspace to achieve more accurate predictions for the target domain.

[0081] In a specific embodiment, the required training data and solution training data Integrate and obtain integrated features ,in, , , is the number of source domain samples, is the number of samples in the target domain, and d is the feature dimension.

[0082] Find a mapping function ,Will Projection into a new subspace , u is the spatial dimension of the new subspace, and the source domain mapping is obtained ; Target domain mapping: In the new subspace, the maximum mean discrepancy (MMD) is used as the criterion for measuring the minimum distribution difference between the source domain and the target domain, which is specifically expressed as: ; ; in, is a function that uses MMD to measure the distribution difference between the source domain and the target domain. is a mapping function that maps data to the reproducing kernel Hilbert space (RKHS), is the norm in the reproducing kernel Hilbert space.

[0083] judge Is it within the preset standard range? If it is within the preset standard range, the mapping function is obtained. By mapping the function You can input 、 Mapped to a new subspace. On the contrary, if If the value is not within the preset standard range, it needs to be re-learned, that is, the mapping function needs to be re-searched until the mapping function corresponds to fall within the preset standard range.

[0084] After obtaining the mapping function, the decision tree model is trained in the new subspace corresponding to the mapping function. In a specific example, based on the mapping function Get the mapped source domain features: , and in Train the decision tree model and get the target decision tree model In other embodiments, Corresponding validation set, evaluating the target decision tree model performance.

[0085] Furthermore, the target decision tree model obtained in advance is combined with the system data to be planned to obtain the target planning scheme, which specifically includes: Based on the mapping function obtained in the target decision tree model, the data of the planning system is mapped to obtain mapping features; The mapped features are input into the decision tree model to obtain the target planning solution.

[0086] Specifically, the mapped target domain features are obtained based on the mapping function That is, the mapping feature, where Input the mapped target domain features into the target decision tree model to obtain the target planning solution .

[0087] Further, refer to Figure 7 , the pre-built solution generation model is determined by the following steps: Construct a two-level programming model and set the upper-level objective function and the lower-level objective function; Determine the iteration threshold and initialize the particle position and velocity; Combining the upper and lower objective functions, the particle swarm algorithm is used to iteratively solve the bi-level programming model. If the number of iterations reaches the iteration threshold, the bi-level programming model is solved and a solution generation model is obtained.

[0088] The upper-level objective function is used to limit the energy loss of each pipeline network in the integrated energy system, and the lower-level objective function is used to limit the total economic cost of the integrated energy system during its life cycle. The total economic cost includes the installation cost of each equipment and pipeline network in the integrated energy system, the operation and maintenance cost of the integrated energy system, and the new energy subsidy income in the integrated energy system.

[0089] Furthermore, the upper objective function is specifically expressed as: ; The lower layer objective function is specifically expressed as: ; in, is the upper objective function, i is the pipe network number of the integrated energy system, is the resistance loss of pipe network i, is the inductance and capacitance loss of pipe network i, is the fixed loss of pipeline network i, is the variable loss of network i, is the other losses of pipeline network i, is the lower layer objective function, is the installation cost of the integrated energy system, The operation and maintenance costs of the integrated energy system are New energy subsidy income for integrated energy systems.

[0090] In a specific example, a two-level planning model was established based on actual engineering needs. The upper level considers the minimum energy loss of each pipeline network to determine the optimal location of energy stations and pipelines; the lower level aims to minimize the total economic cost within the life cycle of the integrated energy system, involving the initial investment and installation of equipment and pipelines, operation and maintenance costs, and subsidy income from renewable energy power generation, thereby determining the optimal installation capacity of each equipment in the regional energy supply station and obtaining the target planning scheme.

[0091] In this example, a particle swarm algorithm (PSO) is used to construct an evolutionary function based on the fitness values of particles and the population, shifting the optimization range of the upper and lower objective functions toward the global optimum. The evolutionary function is integrated into the inertia weight and learning factor parameters, dynamically adjusting their values during each iteration. The algorithm then determines whether a threshold number of iterations has been reached. If so, the target planning solution is output; otherwise, iteration continues.

[0092] Specifically, the number of particles and the iteration threshold are determined. The number of particles is set based on actual project requirements and is not limited. Each particle's initial value is a randomly generated position and velocity in the search space. The historical optimal position and global optimal position of each particle are recorded. The iteration threshold is set based on actual requirements or experience.

[0093] Set the inertia weight. In the particle swarm algorithm, the inertia weight plays a role in balancing global exploration and local exploitation capabilities. The inertia weight determines the impact of the previous moment's velocity on the next movement. By adjusting the inertia weight, you can control the algorithm's convergence speed and global search capability. A larger inertia weight facilitates global exploration and increases population diversity, while a smaller inertia weight improves the algorithm's local mining capabilities and accelerates convergence.

[0094] Set the learning factor and social learning factor. The learning factor indicates the degree to which a particle moves toward its own historical optimal position, while the social learning factor indicates the degree to which a particle moves toward the global optimal position. The learning factor adjusts the weight of the particle's update rate based on individual experience and determines the particle's focus on the individual optimal solution during the search process. A larger learning factor increases a particle's global search capability but may cause the particle to oscillate within the search space; a smaller learning factor increases a particle's local search capability but may cause it to become trapped in a local optimal solution. The social learning factor adjusts the weight of the particle's update rate based on group experience and determines the particle's focus on the group optimal solution during the search process. A larger social learning factor increases a particle's global search capability, helping it better utilize group information, but may also cause it to oscillate within the search space; a smaller social learning factor increases a particle's local search capability but may cause it to become trapped in a local optimal solution. According to different optimization scenarios, the values of the learning factor and the social learning factor can be manually adjusted at different stages of the particle swarm algorithm to balance the capabilities of global search and local search; the parameters can also be adjusted according to the convergence of the particle swarm algorithm, for example, a larger learning factor and social learning factor can be used in the early stage of the particle swarm algorithm to speed up the global search, and a smaller learning factor and social learning factor can be used in the later stage of the particle swarm algorithm to perform a fine search.

[0095] The present invention provides a planning method for an integrated energy system, which screens historical planning schemes in a historical planning scheme library by fusing two different similarity indices to obtain historical planning schemes with higher similarity, and combines a decision tree model with TCA technology to obtain a target decision tree model. Finally, the mapped features of the mapped target domain are input into the target decision tree model to obtain a target planning scheme. In this way, when encountering historical planning schemes with similar engineering conditions, there is no need to re-plan, and the target planning scheme can be obtained after correction on the corresponding historical planning scheme. If no historical planning schemes with similar engineering conditions are encountered, the scheme generation model obtained by solving the two-layer planning model can be used to solve the target planning scheme. The planning method for an integrated energy system avoids the problem of information loss or reduced accuracy that may be caused by a single processing method, thereby ensuring the comprehensiveness of data processing, enhancing the adaptability of the planning method to actual needs, and can cope with complex integrated energy system design problems and maintain efficient solution performance in different scenarios.

[0096] Reference Figure 8 , an embodiment of the present invention provides a planning device for an integrated energy system, comprising: The data acquisition module 201 is used to acquire the system data to be planned, wherein the system data to be planned includes discrete data to be planned and continuous data to be planned; Similarity analysis module 202 is used to analyze the similarity between the discrete data to be planned and the continuous data to be planned and the historical planning solutions in the historical planning solution library by using different similarity indices; The similarity judgment module 203 is used to judge the similarity of the solutions based on a preset solution similarity threshold and obtain a similarity result; The solution determination module 204 is used to determine a strategy based on the solutions corresponding to the similar results, perform solution planning in combination with the system data to be planned, and provide a target planning solution.

[0097] In addition, the present invention also provides a configuration system for an integrated energy system, comprising a memory, a processor, and a computer program stored in the memory. When the computer program is run by the processor, the instructions according to the above method are executed.

[0098] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0099] In particular, according to the embodiment of the present application, the above reference flow chart Figure 1 The described processes can be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program carried on a machine-readable medium, the computer program containing program code for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via a communication component and / or installed from a removable medium. When the computer program is executed by a central processing unit, the above-described functions defined in the apparatus of the present application are performed.

[0100] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: 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 disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0101] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0102] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may 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 may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0104] The units described in the embodiments of the present disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0105] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic inventive concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the invention. Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the invention. Thus, the present invention is intended to include such changes and modifications as fall within the scope of the claims and their equivalents.

Claims

1. A planning method for an integrated energy system, characterized in that: include: Acquiring system data to be planned, wherein the system data to be planned includes discrete data to be planned and continuous data to be planned; Combined with the historical planning scheme database, different similarity indicators are used to analyze the similarity between the discrete data to be planned and the continuous data to be planned and the historical planning schemes in the historical planning scheme database; Based on the preset solution similarity threshold, the solution similarity is judged to obtain similarity results; Determine the strategy based on the solutions corresponding to similar results, carry out solution planning in combination with the data of the system to be planned, and give the target planning solution.

2. The integrated energy system planning method according to claim 1, characterized in that: Combined with the historical planning scheme database, different similarity indicators are used to analyze the similarity between the discrete data to be planned and the continuous data to be planned and the historical planning schemes in the historical planning scheme database, including: Using the first similarity index, analyzing the discrete similarity between the discrete data to be planned and the discrete data in the historical planning scheme; Using the second similarity index, analyze the continuous similarity between the continuous data to be planned and the continuous data in the historical planning schemes; The preset discrete similarity weight and the preset continuous similarity weight are combined to fuse the discrete similarity and the continuous similarity to obtain the solution similarity.

3. The integrated energy system planning method according to claim 2, characterized in that: The first similarity index is the Jaccard coefficient, and the second similarity index is the Euclidean distance.

4. The integrated energy system planning method according to claim 2, characterized in that: Combining the preset discrete similarity weight and the preset continuous similarity weight, the discrete similarity and the continuous similarity are fused to obtain the scheme similarity, which specifically includes: Normalize the discrete similarity and continuous similarity respectively to obtain the standard discrete similarity and standard continuous similarity; Combining the discrete similarity weight and the continuous similarity weight, the standard discrete similarity and the standard continuous similarity are weighted and summed to obtain the scheme similarity.

5. The integrated energy system planning method according to claim 4, characterized in that: The similarity of the scheme is specifically expressed as: ； ； in, is the similarity between the system data to be planned i and the historical planning scheme j in the historical planning scheme library, is the discrete data to be planned in the system data i to be planned and discrete data in historical planning scenarios The standard discrete similarity of is the continuous data to be planned in the system data i to be planned and continuous data in historical planning schemes The corresponding standard continuous similarity, is the continuous similarity weight, is the discrete similarity weight.

6. The method for planning an integrated energy system according to claim 1, wherein: Determine strategies based on solutions corresponding to similar results, combine the data of the system to be planned to plan the solution, and provide a target planning solution, including: If the similarity result corresponding to at least one historical planning scheme in the historical planning scheme library is similar, the historical planning schemes in the historical planning scheme library are sorted based on the scheme similarity, and the pending historical scheme is given according to the sorting result; A target planning scheme is obtained by using a pre-acquired target decision tree model and combining it with the system data to be planned, wherein the pre-acquired target decision tree model is obtained by analyzing and correcting the historical schemes to be planned; If the similar results of the historical planning schemes in the historical planning scheme library are all dissimilar, the target planning scheme is given by combining the system data to be planned and the pre-built scheme generation model.

7. The integrated energy system planning method according to claim 6, characterized in that: The pre-obtained target decision tree model is determined by the following steps: Based on the similar results of various historical planning schemes, the historical planning schemes in the historical planning scheme library are screened to obtain the model training data set; Initialize the decision tree model and set the model parameters in the decision tree model; Use the model training data set to train the decision tree model until convergence; Use model evaluation indicators to evaluate the trained decision tree model and obtain the model evaluation results; Based on the model evaluation results, the decision tree model is corrected and trained to obtain the target decision tree model.

8. The integrated energy system planning method according to claim 7, characterized in that: The model evaluation metric is at least one of the mean square error, root mean square error, mean absolute error, and R² score.

9. The method for planning an integrated energy system according to claim 7, wherein: The model training data set includes demand training data and solution training data; Based on the model evaluation results, the decision tree model is corrected and trained to obtain the target decision tree model, including: If the model evaluation result is qualified, the demand training data and solution training data are integrated to obtain the integrated features; Based on the integrated features, the trained decision tree model is domain adapted to obtain a mapping function that contains the mapping relationship between demand training data and solution training data; Combined with the mapping function, the trained decision tree model is trained to obtain the target decision tree model.

10. The integrated energy system planning method according to claim 6, characterized in that: The target decision tree model obtained in advance is combined with the system data to be planned to obtain the target planning solution, which specifically includes: Based on the mapping function obtained in the target decision tree model, the data of the planning system is mapped to obtain mapping features; The mapped features are input into the decision tree model to obtain the target planning solution.

11. The method for planning an integrated energy system according to claim 6, wherein: The pre-built solution generation model is determined by the following steps: Construct a two-level programming model and set the upper-level objective function and the lower-level objective function; Determine the iteration threshold and initialize the particle position and velocity; Combining the upper and lower objective functions, the particle swarm algorithm is used to iteratively solve the bi-level programming model. If the number of iterations reaches the iteration threshold, the bi-level programming model is solved and a solution generation model is obtained.

12. The integrated energy system planning method according to claim 11, characterized in that: The upper-level objective function is used to limit the energy loss of each pipeline network in the integrated energy system, and the lower-level objective function is used to limit the total economic cost of the integrated energy system during its life cycle. The total economic cost includes the installation cost of each equipment and pipeline network in the integrated energy system, the operation and maintenance cost of the integrated energy system, and the new energy subsidy income in the integrated energy system.

13. The integrated energy system planning method according to claim 12, wherein: The upper objective function is specifically expressed as: ； The lower layer objective function is specifically expressed as: ； in, is the upper objective function, i is the pipe network number of the integrated energy system, is the resistance loss of pipe network i, is the inductance and capacitance loss of pipe network i, is the fixed loss of pipeline network i, is the variable loss of network i, is the other losses of pipeline network i, is the lower layer objective function, is the installation cost of the integrated energy system, The operation and maintenance costs of the integrated energy system are New energy subsidy income for integrated energy systems.

14. A planning device for an integrated energy system, characterized in that: A method for planning an integrated energy system according to any one of claims 1 to 13, comprising: A data acquisition module is used to acquire system data to be planned, wherein the system data to be planned includes discrete data to be planned and continuous data to be planned; A similarity analysis module is used to combine the historical planning scheme library and use different similarity indicators to analyze the similarity between the discrete data to be planned and the continuous data to be planned and the historical planning schemes in the historical planning scheme library; A similarity judgment module is used to judge the similarity of the solutions based on a preset solution similarity threshold and obtain similarity results; The solution determination module is used to determine the strategy according to the solution corresponding to the similar results, carry out solution planning in combination with the system data to be planned, and give the target planning solution.

15. A configuration system for an integrated energy system, comprising a memory, a processor, and a computer program stored in the memory, characterized in that: When the computer program is executed by a processor, the computer program executes the instructions of the method according to any one of claims 1 to 13.

Images