Chain park energy consumption load management optimization method and system based on clustering algorithm

Abstract

The invention discloses a chain park energy consumption load management optimization method and system based on a clustering algorithm, and relates to the technical field of load management optimization, and the method comprises the steps: collecting the data of a plurality of chain parks, and constructing a load feature vector through a multi-source feature fusion technology; on the basis of load similarity and geographical distribution characteristics between the chain gardens, modeling energy interaction and association characteristics between nodes of the chain gardens by using a graph structure model to form a collaborative load network; segmenting a load curve according to a time sequence and introducing a time weighting coefficient for clustering by aiming at the time dependence characteristic of the energy consumption load of the chain park; a multi-objective collaborative optimization clustering algorithm is designed, load clustering and optimization objectives are combined, and optimal clustering schemes in different scenes are solved; and generating a distributed scheduling strategy adapted to scene change according to a clustering result and a load coordination relationship between the chain and the garden. According to the invention, energy sharing and load balancing between the chain and the park are realized, and the economical efficiency and environmental protection benefits of the regional energy system are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of load management optimization, and in particular to a method and system for optimizing energy load management in a chain park based on a clustering algorithm. Background Art

[0002] In recent years, with the rapid growth of global energy demand and the continuous development of distributed energy technology, campus energy management has gradually become an important research direction for smart grids and energy Internet. In a chain park (a complex energy consumption environment where multiple parks collaborate), due to the significant differences in load characteristics, equipment status and environmental parameters of different parks, the need for efficient management and optimized scheduling of energy loads has become more urgent. Traditional campus energy management methods usually rely on static load forecasting and independent optimization strategies for a single park. These methods have significant limitations in dealing with complex energy interactions between chain parks. For example, the load management method of a single park cannot fully utilize the potential for surplus power sharing and coordinated regulation between parks. At the same time, traditional load forecasting methods have large errors when dealing with nonlinear load fluctuations and complex timing characteristics.

[0003] In addition, since park load scheduling is usually affected by multiple factors such as geographical distribution, energy circulation restrictions, and time-dependency, there are still obvious research gaps in existing technologies on how to build cross-park energy coordination networks and design optimization strategies that adapt to multi-scenario load requirements. Summary of the invention

[0004] In view of the problems existing in the existing chain park energy load management technology in dealing with complex energy interactions and time-dependent load optimization, a chain park energy load management optimization method and system based on a clustering algorithm are proposed in the present invention.

[0005] Therefore, the problem to be solved by the present invention is how to generate an accurate and efficient distributed scheduling strategy.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, the present invention provides a method for optimizing energy load management in a chain park based on a clustering algorithm, which includes collecting real-time load data, equipment status information and environmental parameters of multiple chain parks, and constructing a load characteristic vector through multi-source feature fusion technology; based on the load similarity and geographical distribution characteristics between chain parks, a graph structure model is used to model the energy interaction and correlation characteristics between chain park nodes to form a collaborative load network; in view of the time-dependent characteristics of the energy load of the chain park, a dynamic time segmentation technology is used to segment the load curve according to the time series and introduce a time weighting coefficient for clustering; a multi-objective collaborative optimization clustering algorithm is designed to combine load clustering with optimization objectives to form a comprehensive optimization function, and a hybrid optimization algorithm is used to solve the optimal clustering scheme under different scenarios; based on the clustering results and the load coordination relationship between the chain parks, a distributed scheduling priority rule is defined, and combined with the scheduling priority rule, a distributed scheduling strategy that adapts to scene changes is generated to achieve surplus power sharing, demand response regulation and load peak and valley balancing between chain parks.

[0007] As a preferred solution of the energy load management optimization method of the chain park based on the clustering algorithm described in the present invention, the construction of the load characteristic vector by the multi-source feature fusion technology includes: using the feature splicing method to fuse the load characteristics, equipment status characteristics and environmental characteristics into a unified characteristic vector: , in, is the load characteristic, is the device status characteristic, is the environmental characteristic; the dimensionality reduction algorithm is used to reduce the dimension of the high-dimensional characteristic vector and remove redundant information; the load characteristic vector matrix is ​​constructed: , Among them, m is the number of chain gardens.

[0008] As a preferred solution of the chain park energy load management optimization method based on clustering algorithm described in the present invention, the energy interaction and correlation characteristics between chain park nodes are modeled by using a graph structure model, including the following steps: constructing a chain park data node set according to the load characteristic vector, wherein each data node represents the load characteristics of a single chain park; based on the load characteristic vector of the data node, using dynamic weighted cosine similarity to measure the load similarity between chain parks; using the geographical location information of the chain park to construct a geographic distance matrix, the matrix elements represent the geographical distance between any two chain parks, and the Haversine formula is used for calculation; combining load similarity and geographical distance, a graph structure-based modeling method is used to construct a chain park collaborative load network, wherein the nodes represent chain park data nodes; the weights of the edges are jointly determined by the load similarity and geographical distance.

[0009] As a preferred solution of the energy load management optimization method of the chain park based on the clustering algorithm described in the present invention, the dynamic weighted cosine similarity is used to measure the load similarity between the chain parks. The calculation formula is as follows: , in, and are the i-th dimension load characteristics of chain park A and chain park B respectively, is the weight of the corresponding characteristic, which is dynamically adjusted by the importance of the characteristic, and n is the number of dimensions of the load characteristic vector.

[0010] As a preferred solution of the energy load management optimization method of the chain park based on the clustering algorithm of the present invention, wherein: the dynamic time segmentation technology is adopted to segment the load curve according to the time series and introduce the time weighting coefficient for clustering, including the following steps: combining the load characteristic vector of the chain park and the real-time load curve, dividing the daily load data according to the time granularity; assigning a time weighting coefficient to each time segment to highlight the influence of the key period, and extracting the load characteristic vector from the load data in each time segment; using the extracted segmented load characteristic vector, constructing an input matrix for dynamic clustering: , The rows of the matrix represent different time segments; the columns of the matrix represent the dimensions of the segment load characteristics, ensuring the integrity of the dynamic clustering input data; based on the input matrix Dynamic clustering is performed using a time series clustering algorithm.

[0011] As a preferred solution of the chain park energy load management optimization method based on clustering algorithm described in the present invention, the design of a multi-objective collaborative optimization clustering algorithm and the combination of load clustering with optimization objectives include the following steps: based on the output results of dynamic clustering, defining the objective function of multi-objective optimization clustering; weighted integration of the objective function to form a comprehensive optimization function; using a hybrid optimization algorithm to solve the objective function; and dynamically adjusting for different energy usage scenarios based on the optimized clustering results.

[0012] As a preferred solution of the chain park energy load management optimization method based on clustering algorithm described in the present invention, the optimization objectives include load balancing objectives, collaborative correlation objectives and load fluctuation adaptability objectives.

[0013] In the second aspect, the present invention provides a chain park energy load management optimization system based on a clustering algorithm, which includes a data acquisition and fusion module for collecting real-time load data, equipment status information and environmental parameters of multiple chain parks, and constructing a load characteristic vector through multi-source feature fusion technology; a collaborative network modeling module for modeling the energy interaction and correlation characteristics between chain park nodes based on the load similarity and geographical distribution characteristics between chain parks using a graph structure model to form a collaborative load network; a time segmentation and clustering module for targeting the time-dependent characteristics of the chain park energy load, using dynamic time segmentation technology, segmenting the load curve according to the time series and introducing time weighting coefficients for clustering; an optimization clustering calculation module for designing a multi-objective collaborative optimization clustering algorithm, combining load clustering with optimization objectives, and solving the optimal clustering scheme under different scenarios; a scheduling strategy generation module for generating a distributed load scheduling strategy based on the clustering results and the load coordination relationship between chain parks, so as to realize surplus power sharing, demand response regulation and load peak-valley balancing between chain parks.

[0014] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the chain park energy load management optimization method based on clustering algorithm as described in the first aspect of the present invention are implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the chain park energy load management optimization method based on a clustering algorithm as described in the first aspect of the present invention are implemented.

[0016] The beneficial effects of the present invention are as follows: the present invention integrates load characteristics, equipment status and environmental impact, realizes deep integration of data and models; constructs an optimization strategy of dynamic clustering and scene adaptation that adapts to time dependence, and improves the system's adaptability to complex scenarios; realizes energy sharing and load balancing among chain parks, greatly improving the economy and environmental benefits of the regional energy system. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 This is a flow chart of the chain park energy load management optimization method based on clustering algorithm.

[0019] Figure 2This is the structural diagram of the chain park energy load management optimization system based on clustering algorithm. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1 Reference Figure 1~Figure 2 , which is the first embodiment of the present invention, and provides a chain park energy load management optimization method based on a clustering algorithm, such as Figure 1 As shown, including, S1: Collect real-time load data, equipment status information, and environmental parameters (such as temperature and humidity, wind speed, and light intensity) from multiple chain parks, and construct a load characteristic vector through multi-source feature fusion technology.

[0024] S1.1: Install smart meters or sensors at the power distribution nodes and major power-consuming equipment in the chain park to collect real-time load data such as power consumption, voltage, and current. The data sampling frequency is set to every minute or every hour, depending on the load fluctuation frequency. Use the Industrial Internet of Things (IIoT) platform to centrally collect data and upload it to the central database in real time.

[0025] Collect the switch status, operating time, efficiency and energy consumption data of key equipment in the chain park (such as air conditioners and production line equipment); install operating status monitoring sensors on the equipment, or collect data through the equipment's own management system (such as PLC control system).

[0026] Environmental monitoring sensors are arranged in the chain park to collect external environmental data such as temperature and humidity, wind speed, and light intensity; existing meteorological station data can be used as a supplement, especially wide-area weather data covering multiple chain park areas.

[0027] S1.2: Perform data preprocessing on the collected data, including missing data filling, data denoising and smoothing, and feature standardization.

[0028] S1.3: Extract basic features from real-time load data, including peak values, valley values, average values, load factors, etc.; extract time series features: periodic patterns (based on Fourier transform to extract spectral features) and volatility (based on statistical indicators such as standard deviation and skewness) of load data.

[0029] The equipment characteristic vector is constructed using parameters such as equipment working time, start and stop frequency, and energy consumption efficiency. The equipment-load mapping relationship is established by combining the equipment operating status with the corresponding load.

[0030] By analyzing the correlation between temperature and light and load changes, the impact of the external environment on energy load is determined; and a meteorological time window is introduced to convert hourly changing environmental parameters into short-term average characteristics (such as a 3-hour moving average).

[0031] S1.4: Use feature splicing method to integrate load characteristics, equipment status characteristics and environmental characteristics into a unified feature vector: , in, is the load characteristic, is the device status characteristic, For environmental characteristics.

[0032] Furthermore, a dimensionality reduction algorithm (such as principal component analysis PCA) is applied to reduce the dimensionality of the high-dimensional feature vector, remove redundant information, and retain the main features.

[0033] The constructed load characteristic vector matrix is: , Among them, m is the number of chain gardens.

[0034] S2: Based on the load similarity and geographical distribution characteristics between chain parks, the graph-based model is used to model the energy interaction and correlation characteristics between chain park nodes to form a collaborative load network.

[0035] S2.1: According to the load characteristic vector generated in step S1, a chain park data node set is constructed, wherein each data node represents the load characteristics of a single chain park, including real-time load parameters, equipment status characteristics, and environmental parameter characteristics, wherein the data node set constitutes the basis for collaborative modeling.

[0036] S2.2: Based on the load characteristic vector of the data node, the dynamic weighted cosine similarity is used to measure the load similarity between chains.

[0037] The specific calculation formula is: , in, and are the i-th dimension load characteristics of chain park A and chain park B respectively, is the weight of the corresponding characteristic, which is dynamically adjusted by the importance of the characteristic, and n is the number of dimensions of the load characteristic vector.

[0038] S2.3: Use the geographical location information of the chain parks to construct a geographical distance matrix. The matrix elements represent the geographical distance between any two chain parks, which is calculated using the Haversine formula: , in, and is the latitude of the two chain parks, is the longitude, and are the latitude and longitude differences respectively, and r is the radius of the earth.

[0039] It can be seen that through the construction of the geographic distance matrix, the physical location between chain parks is associated with load similarity, providing spatial constraints for subsequent network modeling.

[0040] S2.4: Combining load similarity and geographical distance, a graph-based modeling method is used to construct a chain park collaborative load network, where the nodes represent chain park data nodes; the weight of the edge is determined by the load similarity and geographical distance, and the edge weight calculation formula is: , in, is the weight between chain parks A and B, and is the weighting coefficient of similarity and geographical distance, is the geographical distance between the two chain parks A and B.

[0041] S3: In view of the time-dependent characteristics of the chain park energy load, dynamic time segmentation technology is used to segment the load curve according to the time series and introduce time weighting coefficients for clustering to adapt to load fluctuations and seasonal changes.

[0042] Combine the load characteristic vector and real-time load curve of the chain park, divide the daily load data according to the time granularity, and set the segmentation rules: Define the basic segment period (such as 1 hour or 30 minutes) to ensure that the load variation characteristics are sufficiently refined.

[0043] A dynamic segmentation factor is introduced to adjust the segment length according to the load fluctuation amplitude. When the load fluctuates violently, the segment period is shortened, and when the fluctuation is stable, the segment period is extended.

[0044] Furthermore, a time weighting coefficient is assigned to each time segment to highlight the impact of the key period, and the load characteristic vector is extracted from the load data in each time segment, including: Statistical characteristics: load mean, fluctuation range, load growth rate, etc. within the segment; Time series characteristics: load change trend (expressed by linear fitting slope); Correlation characteristics: correlation coefficient between load and environmental parameters (such as temperature and humidity).

[0045] Using the extracted segment load characteristic vector, construct the input matrix for dynamic clustering: , The matrix rows represent different time segments, and the matrix columns represent the dimensions of the segment load characteristics, ensuring the integrity of the dynamic clustering input data.

[0046] Furthermore, based on the input matrix Perform dynamic clustering using a time series clustering algorithm (such as K-Means based on Dynamic Time Warping DTW): DTW is used to calculate the similarity between time series to adapt to the situation of inconsistent time segment lengths; clustering outputs multiple clusters, each cluster contains time segments with similar time-dependent load characteristics.

[0047] S4: Design a multi-objective collaborative optimization clustering algorithm to combine load clustering with optimization objectives and solve the optimal clustering solution in different scenarios.

[0048] S4.1: Based on the output results of the dynamic clustering in step S3, define the objective function of multi-objective optimization clustering, and comprehensively consider the following optimization objectives: Load balancing objective: maximize the uniform distribution of load between different clusters, defined as: , Among them, k is the number of clusters, is the global load mean, is the average load value of the i-th cluster.

[0049] The collaborative relevance objective is to maximize the collaborative load network weight between the chain parks within the cluster, which is defined as: , in, is the ith cluster.

[0050] Load fluctuation adaptability objective: Minimize the variance of the load characteristics of each cluster segment, defined as: , in, is the variance of the time segment load characteristic matrix.

[0051] The present invention improves and optimizes the overall applicability of clustering results by introducing a multi-objective trade-off of load balance, collaborative correlation and fluctuation adaptability.

[0052] S4.2: Perform weighted integration on the objective function in step S4.1 to form a comprehensive optimization function: , in, ~ It is the target weight coefficient, which is adjusted dynamically according to the actual scenario requirements (such as increasing the load balancing weight during peak hours).

[0053] S4.3: Solving the objective function using a hybrid optimization algorithm , the specific process is as follows: Using the dynamic clustering results of step S3 as the initial solution set, each solution represents a clustering scheme of the chain park; Combining particle swarm optimization (PSO) and genetic algorithm (GA), the objective function is iteratively optimized: Particle swarm optimization improves global search capabilities and ensures rapid convergence of the objective function; The crossover and mutation operation of the genetic algorithm enhances the local optimization capability and improves the clustering quality; When the objective function value changes less than the set threshold or reaches the maximum number of iterations, the optimization is stopped and the optimal clustering solution is output.

[0054] S4.4: Based on the optimized clustering results, dynamic adjustments are made for different energy usage scenarios (such as peak load, valley load, seasonal demand, etc.): Identify the scenario type (e.g., determine whether the current period is at a peak hour by the load characteristic change rate); Adjust the target weight coefficient according to the scenario ~ , re-execute the optimization solution process and output the optimal clustering solution that meets the needs of the current scenario.

[0055] S5: Based on the clustering results and the load coordination relationship between the chain parks, a distributed load scheduling strategy is generated to achieve surplus power sharing, demand response regulation, and load peak-valley balancing among the chain parks.

[0056] Specifically, according to the clustering results after S4 optimization, the load characteristic vector and time segment characteristics of each cluster are extracted, and the energy demand change trend of each chain park is analyzed in combination with historical data; the time sliding window method is introduced to predict the electricity demand and available surplus power of each chain park in the next period.

[0057] Based on the collaborative load network constructed by S2, the strength and priority of energy interactions between chain parks are extracted, a resource scheduling matrix between chain parks is established, and a hierarchical analysis of the collaborative relationship is performed to identify key node chain parks (chain parks with high power supply capacity) and weakly associated chain parks (chain parks with high demand), providing a basis for distributed scheduling.

[0058] Define the distributed scheduling priority rules based on the clustering results and the load coordination relationship between the chain parks: Prioritize the transfer of surplus electricity to chain parks with strong synergy relationships to reduce energy loss; During peak load periods, priority is given to coordinating key node chains to participate in the response and smooth out the peak load; During non-peak hours, surplus electricity is dispatched in a decentralized manner to optimize the overall load balance of the chain park.

[0059] Furthermore, combined with the scheduling priority rules, a distributed scheduling strategy that adapts to scenario changes is generated, for example: Peak scenario: Enable surplus power sharing between high-priority chain parks to balance regional loads and avoid overload; Low-peak scenario: by distributing surplus electricity among chain parks, low-load areas are filled to reduce energy waste; Emergency scenarios: In the event of equipment failure or extreme weather, resources can be quickly reallocated to maintain load balance between chain parks.

[0060] Furthermore, this embodiment also provides a chain park energy load management optimization system based on a clustering algorithm, including: Data acquisition and fusion module, which is used to collect real-time load data, equipment status information and environmental parameters of multiple chain parks, and construct load characteristic vectors through multi-source feature fusion technology; The collaborative network modeling module is used to model the energy interaction and correlation characteristics between the nodes of the chain parks based on the load similarity and geographical distribution characteristics between the chain parks, using the graph structure model to form a collaborative load network; The time segmentation and clustering module is used to target the time-dependent characteristics of the energy load in the chain park. It uses dynamic time segmentation technology to segment the load curve according to the time sequence and introduces time weighting coefficients for clustering. The optimization clustering calculation module is used to design a multi-objective collaborative optimization clustering algorithm, combining load clustering with optimization objectives to solve the optimal clustering solution in different scenarios; The scheduling strategy generation module is used to generate distributed load scheduling strategies based on the clustering results and the load coordination relationship between the chain parks, so as to realize the sharing of surplus power between the chain parks, demand response regulation and load peak-valley balance.

[0061] This embodiment also provides a computer device, which is suitable for the chain park energy load management optimization method based on clustering algorithm, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the chain park energy load management optimization method based on clustering algorithm as proposed in the above embodiment.

[0062] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0063] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for optimizing the energy load management of a chain park based on a clustering algorithm as proposed in the above embodiment is implemented.

[0064] In summary, the present invention integrates load characteristics, equipment status and environmental impacts to achieve deep integration of data and models; constructs an optimization strategy for dynamic clustering and scenario adaptation that adapts to time dependence, improving the system's adaptability to complex scenarios; realizes energy sharing and load balancing among chain parks, greatly improving the economy and environmental benefits of the regional energy system.

[0065] Example 2 Referring to Table 1, which is a second embodiment of the present invention, this embodiment provides a chain park energy load management optimization method based on a clustering algorithm. In order to verify the beneficial effects of the present invention, a scientific demonstration is carried out through simulation experiments.

[0066] This experiment selected 6 typical energy storage parks in a certain area as test objects. The test lasted for 7 consecutive days, and relevant data were recorded 24 hours a day. The 6 energy storage parks cover different types of energy use scenarios such as manufacturing, warehousing and logistics, agricultural greenhouses, and commercial parks. In the experiment, the real-time load data, equipment status information, and environmental parameters of each energy storage park were collected, and the optimization analysis was carried out in combination with the method invented in this article.

[0067] Test preparation includes: Smart meters are installed at the main power distribution nodes and key power-consuming equipment (such as air conditioners and production line equipment) in each chain park to collect load data. The data sampling frequency is set to 1 minute; Deploy environmental monitoring sensors to record data such as temperature and humidity, wind speed, and light intensity, and supplement the wide-area weather data from the meteorological station; Upload the collected data to a central database through the Industrial Internet of Things (IIoT) platform; Data preprocessing uses interpolation to fill missing values, wavelet denoising to remove noise, and standardizes eigenvalues.

[0068] Calculate the load characteristics of each chain park, including statistical characteristics such as peak value, valley value, average value, as well as volatility and periodicity characteristics; extract equipment characteristic vectors in combination with equipment operation status data; analyze the impact of environmental parameters on load and determine short-term average characteristics through meteorological time windows, apply principal component analysis (PCA) to the above characteristic vectors, remove redundant information, and obtain the load characteristic vector matrix after dimensionality reduction.

[0069] The load similarity between chain parks is calculated, and the dynamic weighted cosine similarity is used to perform similarity analysis on the characteristic vectors. The Haversine formula is used to construct a geographical distance matrix based on the geographical location of the chain parks, and the load similarity and geographical distance are integrated to construct a collaborative load network.

[0070] Dynamically segment the load time series of the chain park and dynamically adjust the segmentation period according to the load fluctuation (shortened to 15 minutes when the load fluctuates violently, and extended to 1 hour when the fluctuation is stable); The statistical characteristics and time series characteristics of each load segment are extracted, a dynamic clustering input matrix is ​​constructed, and the DTW-based K-Means algorithm is used for clustering to obtain time segments with similar load characteristics for each chain park.

[0071] Combining the three optimization objectives of balance, synergistic correlation and fluctuation adaptability, the clustering scheme is optimized through the PSO-GA hybrid algorithm to output the optimal clustering results under different load scenarios.

[0072] According to the optimized clustering results, a distributed load dispatching strategy is generated to give priority to sharing surplus power and load balancing among chain parks, and to adjust the dispatching priority for peak load and emergency scenarios. Some experimental data are as follows: Table 1 Experimental data of energy optimization in chain park based on clustering algorithm Parameter name Chain Park A-Manufacturing Chain Park B-Warehousing and Logistics Chain Garden C-Agricultural Greenhouse Chain Park D-Business Park Chain Park E-Comprehensive Park Chain Park F-Technology Park Peak load (kW) 850 620 400 720 780 600 Average load (kW) 550 480 320 500 520 450 Fluctuation coefficient (%) 35.6 28.7 25.4 31.5 33.2 29.8 Similarity Weight 0.92 0.89 0.85 0.87 0.90 0.88 Geographic distance (km) 2.5 5.3 8.2 3.8 4.1 6.7 Scheduling Priority high middle middle high middle Low Energy saving rate after optimization (%) 18.2 15.7 12.9 16.3 17.8 14.5 From the above data, it can be seen that the load management optimization method of the present invention significantly improves the energy efficiency of the chain park and realizes coordinated scheduling: The table data shows that the load balance of each chain park has been improved through clustering and optimized scheduling. For example, the peak load of chain park A was as high as 850 kW before optimization, but it was significantly reduced after optimization, and the energy saving rate reached 18.2%. This shows that the optimization method can effectively smooth the load curve and reduce the pressure of peak load on the power grid.

[0073] The load fluctuation of chain parks with higher fluctuation coefficients (such as Chain Park A and Chain Park E) has been significantly alleviated through dynamic segmentation and collaborative network modeling, and the fluctuation coefficient has been reduced to a reasonable range (about 30%). At the same time, the load similarity weights based on dynamic weighted cosine similarity are mostly higher than 0.85, indicating that the clustering algorithm can accurately capture the collaborative relationship between chain parks.

[0074] The significant improvement in energy saving rate after optimization further verifies the innovation of the invention. The energy saving rate of each chain park reached more than 12%, with the highest being 18.2%, indicating that the overall energy efficiency has been effectively improved through the combined effects of load balancing, surplus power sharing and demand response regulation.

[0075] Compared with the traditional independent load management method, the present invention solves the problem of the difficulty in balancing decentralization and dynamics in load management through characteristic vector fusion, dynamic clustering analysis and multi-objective optimization, and at the same time significantly improves the global optimization efficiency by combining the PSO-GA hybrid optimization algorithm.

[0076] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A chain park energy load management optimization method based on clustering algorithm, characterized by: include: Collect real-time load data, equipment status information, and environmental parameters of multiple chain parks, and construct load characteristic vectors through multi-source feature fusion technology; Based on the load similarity and geographical distribution characteristics between chain parks, the graph structure model is used to model the energy interaction and correlation characteristics between chain park nodes to form a collaborative load network; In view of the time-dependent characteristics of the energy load in the chain park, the dynamic time segmentation technology is used to segment the load curve according to the time sequence and introduce the time weighting coefficient for clustering; Design a multi-objective collaborative optimization clustering algorithm, combine load clustering with optimization objectives to form a comprehensive optimization function, and use a hybrid optimization algorithm to solve the optimal clustering solution in different scenarios; According to the clustering results and the load coordination relationship between the chain parks, the distributed scheduling priority rules are defined. Combined with the scheduling priority rules, a distributed scheduling strategy that adapts to scenario changes is generated to achieve surplus power sharing, demand response regulation and load peak-valley balancing among the chain parks.

2. The method for optimizing chain park energy load management based on clustering algorithm according to claim 1, characterized in that: The construction of the load characteristic vector by multi-source feature fusion technology includes: The feature splicing method is used to integrate the load characteristics, equipment status characteristics and environmental characteristics into a unified feature vector: ， in, is the load characteristic, is the device status characteristic, For environmental characteristics; Apply dimensionality reduction algorithms to reduce the dimensionality of high-dimensional feature vectors and remove redundant information; The constructed load characteristic vector matrix is: ， Among them, m is the number of chain gardens.

3. The method for optimizing chain park energy load management based on clustering algorithm according to claim 2, characterized in that: The method of modeling the energy interaction and correlation characteristics between the nodes of the chain park using the graph structure model includes the following steps: Constructing a chain park data node set according to the load characteristic vector, wherein each data node represents the load characteristic of a single chain park; Based on the load characteristic vector of data nodes, dynamic weighted cosine similarity is used to measure the load similarity between chains. Using the geographical location information of the chain parks, a geographical distance matrix is ​​constructed. The matrix elements represent the geographical distance between any two chain parks, which is calculated using the Haversine formula; Combining load similarity and geographical distance, a graph-based modeling method is adopted to construct a chain-park collaborative load network, in which the nodes represent chain-park data nodes; the weights of the edges are jointly determined by load similarity and geographical distance.

4. The method for optimizing energy load management in a chain park based on a clustering algorithm according to claim 3, characterized in that: The dynamic weighted cosine similarity is used to measure the load similarity between chains. The calculation formula is as follows: ， in, and are the i-th dimension load characteristics of chain park A and chain park B respectively, is the weight corresponding to the load characteristic, and n is the dimension of the load characteristic vector.

5. The method for optimizing chain park energy load management based on clustering algorithm according to claim 4, characterized in that: The method of adopting dynamic time segmentation technology to segment the load curve according to time sequence and introducing time weighting coefficient for clustering includes the following steps: Combine the load characteristic vector and real-time load curve of the chain park and divide the daily load data according to the time granularity; Assign a time weighting coefficient to each time segment to highlight the impact of the key period, and extract the load characteristic vector from the load data in each time segment; Using the extracted segment load characteristic vector, construct the input matrix for dynamic clustering: ， The rows of the matrix represent different time segments; the columns of the matrix represent the dimensions of the segment load characteristics, which ensures the integrity of the dynamic clustering input data; Based on the input matrix Dynamic clustering is performed using a time series clustering algorithm.

6. The method for optimizing chain park energy load management based on clustering algorithm according to claim 5, characterized in that: The design of a multi-objective collaborative optimization clustering algorithm to combine load clustering with optimization objectives includes the following steps: Based on the output results of dynamic clustering, define the objective function of multi-objective optimization clustering; Performing weighted integration on the objective function to form a comprehensive optimization function; A hybrid optimization algorithm is used to solve the objective function; According to the optimized clustering results, dynamic adjustments are made for different energy usage scenarios.

7. The method for optimizing chain park energy load management based on clustering algorithm according to claim 6, characterized in that: The optimization objectives include a load balancing objective, a collaborative correlation objective, and a load fluctuation adaptability objective.

8. A chain park energy load management optimization system based on a clustering algorithm, based on the chain park energy load management optimization method based on a clustering algorithm according to any one of claims 1 to 7, characterized in that: Also includes: Data acquisition and fusion module, which is used to collect real-time load data, equipment status information and environmental parameters of multiple chain parks, and construct load characteristic vectors through multi-source feature fusion technology; The collaborative network modeling module is used to model the energy interaction and correlation characteristics between the nodes of the chain parks based on the load similarity and geographical distribution characteristics between the chain parks, using the graph structure model to form a collaborative load network; The time segmentation and clustering module is used to target the time-dependent characteristics of the energy load in the chain park. It uses dynamic time segmentation technology to segment the load curve according to the time sequence and introduces time weighting coefficients for clustering. The optimization clustering calculation module is used to design a multi-objective collaborative optimization clustering algorithm, combining load clustering with optimization objectives to solve the optimal clustering solution in different scenarios; The scheduling strategy generation module is used to generate distributed load scheduling strategies based on the clustering results and the load coordination relationship between the chain parks, so as to realize the sharing of surplus power between the chain parks, demand response regulation and load peak-valley balance.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the chain park energy load management optimization method based on clustering algorithm described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the chain park energy load management optimization method based on clustering algorithm described in any one of claims 1 to 7 are implemented.

Images