Rule engine driven power distribution network planning problem library construction method

Abstract

The invention relates to the technical field of power grid planning, in particular to a rule engine driven power distribution network planning problem library construction method. The method comprises the following steps: acquiring environment information data of the power distribution network; performing data preprocessing on the power distribution network environment information data to generate standard power distribution network environment information data; performing substation site selection on the power distribution network environment information data to obtain power distribution network substation site selection data; carrying out transformer substation capacity distribution on the power distribution network transformer substation site selection data to generate transformer substation capacity distribution data; performing transformer substation layout according to the transformer substation capacity distribution data and the power distribution network transformer substation site selection data so as to generate transformer substation layout data; and carrying out power transmission line path selection on the standard power distribution network environment information data based on the substation layout data to generate power transmission line route data. Through systematic data integration, flexible rule extraction, dynamic decision monitoring and knowledge management, the accuracy and adaptability of power distribution network planning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid planning, and in particular to a method for constructing a distribution network planning problem library driven by a rule engine. Background Art

[0002] With the growth of electricity demand and the widespread use of renewable energy, traditional planning methods have gradually exposed problems such as insufficient flexibility and poor adaptability. Planning methods based on optimization algorithms began to gain popularity in the 1980s, focusing on solving network topology and load forecasting problems. However, they were slow to respond to the complex and ever-changing real-world conditions. In the 21st century, the rapid development of information technology has injected new vitality into distribution network planning. Big data analysis and machine learning technologies have been gradually applied to load forecasting and fault diagnosis, greatly improving the accuracy and efficiency of planning. At the same time, the rise of rule-based engine technology has provided a flexible solution for decision support systems. Rule-based engines can dynamically generate decision rules based on expert experience and existing data, enhancing the intelligence of the planning process. However, existing technologies lack flexible rule generation mechanisms for complex distribution network layouts. Furthermore, the extraction and application of rules are often static and unable to respond to dynamic changes in real time. This results in low adaptability and accuracy in distribution network planning. Summary of the Invention

[0003] Based on this, it is necessary to provide a rule engine driven distribution network planning problem library construction method to solve at least one of the above technical problems.

[0004] To achieve the above objectives, a method for constructing a distribution network planning problem database driven by a rule engine is provided, the method comprising the following steps:

[0005] Step S1: acquiring distribution network environmental information data; performing data preprocessing on the distribution network environmental information data to generate standard distribution network environmental information data; performing substation site selection on the distribution network environmental information data to obtain distribution network substation site selection data; performing substation capacity allocation on the distribution network substation site selection data to generate substation capacity allocation data; performing substation layout based on the substation capacity allocation data and the distribution network substation site selection data to generate substation layout data;

[0006] Step S2: performing transmission line path selection on the standard distribution network environment information data based on the substation layout data to generate transmission line route data; performing distribution network topology construction constraints on the standard distribution network environment information data using the transmission line route data and the substation layout data to generate distribution network geographic planning constraint data; performing first planning rule extraction on the distribution network geographic planning constraint data to obtain first distribution network planning rule data;

[0007] Step S3: Acquire regional electricity consumption data; perform electricity consumption trend analysis on the regional electricity consumption data to generate regional electricity consumption trend data; perform load growth forecast on the regional electricity consumption data based on the regional electricity consumption trend data to generate regional electricity load growth forecast data; impose distribution network load demand constraints on the regional electricity consumption data based on the regional electricity load growth forecast data to generate distribution network operation planning constraint data; perform second planning rule extraction on the distribution network operation planning constraint data to obtain distribution network planning second rule data;

[0008] Step S4: performing rule mapping on the first distribution network planning rule data and the second distribution network planning rule data to generate a distribution network planning logic rule base; generating a distributed rule calculation graph for the distribution network planning logic rule base to obtain a distributed logic rule calculation graph; expressing the distribution network planning logic rule base in a problem matrix based on the distributed logic rule calculation graph to generate a multi-dimensional planning problem matrix;

[0009] Step S5: construct a multidimensional planning matrix for the distribution network geographical planning constraint data and the distribution network operation planning constraint data through a multidimensional planning problem matrix to generate a multidimensional planning matrix; integrate the multidimensional planning matrix with a rule engine to generate a rule-driven model; perform real-time planning decision monitoring on the rule-driven model to generate real-time planning decision monitoring data; perform dynamic planning problem storage on the real-time planning decision monitoring data to generate a distribution network planning problem library.

[0010] This invention ensures data consistency and accuracy by preprocessing distribution network environmental information data, providing a reliable foundation for subsequent analysis. Scientifically selecting substation sites and optimizing capacity allocation improves power resource utilization, reduces construction and operating costs, and ensures power supply reliability. Transmission line routing enables adaptive planning to the environment, reduces obstacles and conflicts during construction, and improves transmission efficiency. The generated geographic planning constraint data provides clear guidance for distribution network design and implementation, promoting transparency and operability in the planning process. Regional electricity consumption trend analysis and load growth forecasting can promptly reflect changes in electricity demand, help optimize distribution network design and operation, and enhance power supply reliability. The logical rule base generated through rule mapping facilitates systematic management of distribution network planning and promotes intelligent and automated decision-making. The generation of distributed rule computation graphs enables efficient and flexible large-scale data processing, improving decision-making response speed. The establishment of a multidimensional planning problem matrix provides a comprehensive perspective for complex decision-making, enabling better response to the interactions of multiple factors. The integration of a rule engine combined with real-time decision monitoring ensures real-time feedback and adjustments during the planning process, improving the accuracy and timeliness of decisions. The storage of dynamic programming problems not only provides historical references for subsequent decision-making but also provides data support for continuous optimization and learning, promoting iterative improvements in the planning process. The integrated planning system can quickly respond to changing environments and demands, improving the adaptability and resilience of the distribution network. Therefore, the present invention improves the accuracy and adaptability of distribution network planning through systematic data integration, flexible rule extraction, dynamic decision monitoring, and knowledge management.

[0011] Preferably, step S1 includes the following steps:

[0012] Step S11: Acquire distribution network environment information data;

[0013] Step S12: performing data preprocessing on the distribution network environment information data to generate standard distribution network environment information data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization;

[0014] Step S13: performing substation site selection on the distribution network environment information data to obtain distribution network substation site selection data; performing center position load analysis on the distribution network substation site selection data to generate substation center position load data;

[0015] Step S14: Allocate substation capacity to the distribution network substation site selection data using the substation center position load data to generate substation capacity allocation data; and perform substation layout based on the substation capacity allocation data and the distribution network substation site selection data to generate substation layout data.

[0016] This invention improves the processing efficiency and accuracy of distribution network environmental information data through data preprocessing techniques, such as data cleaning and missing value filling, ensuring data quality and laying the foundation for subsequent analysis. By employing advanced site selection algorithms combined with load analysis, intelligent substation site selection is achieved, improving the scientific and rational nature of site selection and ensuring the timeliness and stability of power supply. Through in-depth analysis of the load at the substation center, a dynamic load forecasting model is developed that can effectively predict load changes and enhance the resilience of the distribution system. A capacity allocation algorithm is utilized to rationally allocate substation capacity based on load demand, ensuring optimal resource utilization and avoiding capacity waste and system overload. By optimizing substation layout and developing a decision support system based on data analysis, the management efficiency of the distribution network and the scientific nature of decision-making are improved. An integrated information management platform is constructed to support comprehensive management of distribution network environmental information, substation site selection, and layout, improving the collaborative efficiency of the system. By analyzing environmental information and load data, a dynamically adaptable distribution network design solution is developed that can respond to changes in the external environment in real time and enhance system resilience.

[0017] Preferably, step S2 includes the following steps:

[0018] Step S21: performing geographic elevation conversion on the standard distribution network environmental information data based on the substation layout data to generate geographic elevation conversion data; performing environmental terrain difference analysis on the geographic elevation conversion data to generate distribution network environmental terrain difference data;

[0019] Step S22: performing terrain analysis on the geographic elevation conversion data according to the distribution network environment terrain difference data to generate distribution network environment terrain data;

[0020] Step S23: Using the distribution network environment terrain data to select the transmission line path for the substation layout data, and generating transmission line route data; using the transmission line route data and substation layout data to constrain the standard distribution network environment information data for distribution network topology construction, and generating distribution network geographical planning constraint data;

[0021] Step S24: extracting the first planning rule from the distribution network geographical planning constraint data to obtain the distribution network planning first rule data.

[0022] By converting standard distribution network environmental information data into geographic elevation, the present invention ensures that the distribution network design closely matches the actual terrain, providing accurate foundational data for subsequent analysis. The generated distribution network environmental terrain difference data effectively identifies the impact of terrain variations on transmission line layout, thereby accounting for terrain complexity during the design phase and improving the scientific nature of planning. Through in-depth analysis of environmental terrain data, the impact of terrain characteristics on power facility layout is understood, ensuring that transmission line designs can adapt to complex terrain conditions and reducing engineering risks. Transmission line routing based on environmental terrain data effectively avoids unfavorable terrain, reduces line construction and maintenance costs, and improves transmission efficiency. By combining transmission line route data with substation layout data, the resulting distribution network geographic planning constraint data provides a systematic basis for structured management of the distribution network and enhances the stability of the power network. The extraction of first planning rule data simplifies the complexity of distribution network planning, improves planning efficiency through a rule-based approach, reduces the possibility of manual intervention, and ensures planning consistency and accuracy. Based on a comprehensive analysis of environmental terrain and terrain difference, a power planning scheme is developed that flexibly adapts to diverse terrain conditions, enhancing the adaptability and stability of the distribution network in complex terrain conditions. By integrating geographic elevation, terrain difference and terrain analysis data, the overall efficiency of distribution network information management is improved, providing comprehensive data support for subsequent decision-making.

[0023] Preferably, step S23 includes the following steps:

[0024] Step S231: extracting main terrain features from the distribution network environment terrain data to obtain main terrain feature data of the distribution network environment, wherein the main terrain feature extraction includes slope extraction, river extraction, and building-dense area extraction;

[0025] Step S232: Using the distribution network environment terrain data to perform shortest transmission line path planning on the substation layout data, generating shortest path planning data; using the distribution network environment main terrain feature data to perform detour area obstacle avoidance on the shortest path planning data, generating an initial transmission line plan;

[0026] Step S233: performing a complexity evaluation on the initial transmission line solution to generate initial transmission line complexity data; performing an optimal transmission line path selection on the initial transmission line solution based on the initial transmission line complexity data to generate transmission line route data;

[0027] Step S234: Perform multi-dimensional distribution network topology decision using transmission line route data and substation layout data to generate distribution network topology decision data; perform distribution network topology construction constraints on standard distribution network environmental information data based on the distribution network topology decision data to generate distribution network geographical planning constraint data.

[0028] By utilizing terrain data to plan the shortest transmission line path, this invention can effectively reduce line length, lower construction costs, improve transmission efficiency, and ensure reliable power transmission. The initial transmission line plan effectively avoids terrain obstacles during detours, ensuring the feasibility and safety of the line, thereby reducing difficulties in later construction. Complexity assessment of the initial transmission line plan ensures that the complexity of line construction and maintenance is taken into account during path selection, improving the scientific nature of the design. Optimal path selection based on the initial transmission line complexity data helps reduce the difficulty and frequency of line maintenance and enhance long-term economic benefits. The decision data generated by multi-dimensional distribution network topology decisions enhances the structural rationality of the distribution network and ensures the stability and security of power supply. The combination of distribution network topology decision data with geographic planning constraints provides comprehensive constraints for distribution network design, thereby improving design feasibility and efficiency. By integrating environmental terrain characteristics, transmission line planning, and topology decisions, a comprehensive information management system is formed, providing data support for subsequent monitoring and optimization. Based on a comprehensive environmental analysis, the distribution network design can flexibly adapt to different terrain and environmental changes, improving the adaptability of the overall system.

[0029] Preferably, step S234 includes the following steps:

[0030] Step S2341: performing load center distance distribution analysis on the transmission line route data and the substation layout data to generate load center distance distribution data; calculating power supply coverage rate on the transmission line route data and the substation layout data using the load center distance distribution data to generate power supply coverage rate data; performing radial topology decision making based on the power supply coverage rate data and the load center distance distribution data to generate radial topology decision data;

[0031] Step S2342: Performing a line-break recovery capability analysis on the transmission line route data to generate transmission line recovery capability data; performing a power supply reliability calculation on the substation layout data based on the transmission line recovery capability data to obtain power supply reliability data; performing a ring network topology decision based on the transmission line recovery capability data and the power supply reliability data to generate ring network topology decision data;

[0032] Step S2343: Calculating the number of redundant paths in the load center based on the transmission line route data and the substation layout data to obtain redundant path quantity data; performing complexity analysis on the redundant path quantity data to generate redundant path complexity data; and making a grid topology decision based on the redundant path quantity data and the redundant path complexity data to generate grid topology decision data.

[0033] Step S2344: Integrate the radial topology decision data, the ring network topology decision data and the grid topology decision data to generate distribution network topology decision data; perform distribution network topology construction constraints on the standard distribution network environmental information data based on the distribution network topology decision data to generate distribution network geographical planning constraint data.

[0034] The present invention provides an in-depth understanding of power demand and power supply capacity by analyzing the load center distance distribution of transmission line route data and substation layout data, helping to optimize the power supply layout. Power supply coverage is calculated based on the load center distance distribution data, ensuring that each area has access to sufficient power supply, thereby improving the service capacity of the power supply system. By analyzing the power supply coverage and load center distance distribution data, radial topology decisions are made, forming an efficient power supply network layout, reducing power supply line redundancy, and lowering costs. Line break recovery capability analysis is performed on the transmission line route to ensure that the system can quickly restore power supply in the event of a fault, thereby improving the reliability and risk resistance of the power grid. Calculating power supply reliability based on transmission line recovery capability data helps identify potential power supply risk points, provides data basis for subsequent improvements, and enhances the security of power supply. Ring network topology decisions are made based on transmission line recovery capability and power supply reliability data, improving the flexibility and stability of the power grid and enabling overall power supply to be maintained in the event of local faults. Calculating the number of redundant paths to the load center ensures that the distribution system has multiple power supply paths, thereby enhancing the reliability and flexibility of the power supply. Complexity analysis of redundant paths helps optimize network structure design, reduce unnecessary complexity, and improve system management convenience. Using redundant path data and complexity data to make grid topology decisions creates a more uniform and stable power supply network, improving the security and efficiency of the overall power grid.

[0035] Preferably, step S3 includes the following steps:

[0036] Step S31: Acquire regional electricity consumption data;

[0037] Step S32: performing a time series analysis on the regional electricity consumption data to generate regional electricity consumption time series data; performing curve conversion on the regional electricity consumption time series data to generate a regional electricity consumption time series curve; performing a power consumption trend analysis on the regional electricity consumption time series curve data to generate regional electricity consumption trend data;

[0038] Step S33: Dividing the regional electricity consumption data into electricity consumption patterns based on the regional electricity consumption trend data to generate regional daytime electricity consumption patterns and regional nighttime electricity consumption patterns; performing load growth prediction on the regional electricity consumption data based on the regional daytime electricity consumption patterns and regional nighttime electricity consumption patterns to generate regional electricity load growth prediction data;

[0039] Step S34: Based on the regional electricity load growth forecast data, the regional electricity consumption data is constrained by the distribution network load demand to generate distribution network operation planning constraint data; the distribution network operation planning constraint data is subjected to second planning rule extraction to obtain distribution network planning second rule data.

[0040] By acquiring regional electricity consumption data, the present invention forms a detailed electricity usage baseline, providing essential data support for subsequent analysis. Time-series analysis of regional electricity consumption data can clearly reveal dynamic changes in electricity consumption, generating regional electricity consumption time-series data that provides fundamental information for electricity demand forecasting and management. Electricity consumption trend analysis generates regional electricity consumption trend data, which can identify changes in electricity consumption patterns and provide a scientific basis for power grid scheduling and planning. Classifying electricity consumption patterns based on electricity consumption trend data helps understand regional daytime and nighttime electricity consumption differences, enabling more refined strategy formulation for power supply and demand management. By analyzing regional daytime and nighttime electricity consumption patterns to predict load growth, the generated regional electricity load growth forecast data can provide a reference for power system expansion and adjustment, improving power supply reliability. Based on the electricity load growth forecast data, distribution network load demand constraints are applied to regional electricity consumption data to ensure that power grid planning can meet future electricity demand and avoid power shortages or surpluses. By extracting second planning rules from distribution network operation planning constraint data, the resulting distribution network planning second rule data enhances the scientific and rationality of power grid planning and supports decision-making. The resulting operational planning constraint data provides an effective reference for the operational management of the distribution network and improves the flexibility and efficiency of power dispatching.

[0041] Preferably, dividing the regional electricity consumption data into electricity consumption patterns according to the regional electricity consumption trend data includes:

[0042] Perform time series segmentation on regional electricity consumption trend data to generate daytime electricity consumption data and nighttime electricity consumption data; perform cluster analysis on daytime electricity consumption data and nighttime electricity consumption data to generate time period electricity consumption difference data; classify regional electricity consumption trend data based on time period electricity consumption difference data to generate preliminary electricity consumption trend classification data;

[0043] The daytime electricity consumption data is used to analyze the preliminary electricity consumption trend classification data for daytime electricity consumption peak and valley data, generating daytime electricity consumption peak data and daytime electricity consumption valley data; the daytime electricity consumption curvature is calculated for the daytime electricity consumption peak data and daytime electricity consumption valley data to obtain the regional daytime electricity consumption pattern;

[0044] The nighttime electricity consumption data is used to analyze the preliminary electricity consumption trend classification data, and the nighttime electricity consumption peak and valley data are generated. The nighttime electricity consumption curvature is calculated for the nighttime electricity consumption peak and valley data to obtain the regional nighttime electricity consumption pattern.

[0045] By segmenting regional electricity consumption trend data into time series, the present invention can clearly delineate daytime and nighttime electricity consumption periods, providing a structured data foundation for subsequent analysis. Time-period electricity consumption difference data generated through cluster analysis can reveal the characteristics and differences of electricity consumption in different time periods, providing a basis for load forecasting and power scheduling. The generation of preliminary electricity consumption trend classification data further refines the electricity consumption trend classification, improving the accuracy and reliability of the classification. By generating daytime and nighttime peak and valley data, it is possible to effectively identify peak and valley periods of electricity consumption, helping power companies to conduct more accurate load forecasting and scheduling. The calculation of daytime and nighttime electricity consumption curvature allows the extraction of regional daytime and nighttime electricity consumption patterns, providing an important reference for power system operation and management. Clarifying daytime and nighttime electricity consumption patterns helps power companies rationally allocate power resources in different time periods, optimize power supply, and improve power utilization efficiency. By identifying peak and valley data, the power system can respond promptly during peak demand periods, ensuring power supply reliability and reducing the risk of power shortages. Analyzing electricity usage patterns supports the implementation of demand-side management, encouraging users to consume electricity during off-peak hours and reducing the overall burden on the power system. The generated daytime and nighttime electricity usage patterns provide reliable data for power dispatch, ensuring a stable power supply under varying demand conditions. Understanding peak and off-peak electricity usage patterns helps plan the integration of renewable energy and improve its utilization.

[0046] Preferably, step S4 includes the following steps:

[0047] Step S41: performing semantic analysis on the first rule data and the second rule data of the distribution network planning to generate constraint semantic analysis data;

[0048] Step S42: performing rule mapping on the constraint semantic parsing data to generate a distribution network planning logic rule base;

[0049] Step S43: generating a distributed rule calculation graph for the distribution network planning logic rule base to obtain a distributed logic rule calculation graph;

[0050] Step S44: Based on the distributed logic rule calculation graph, the distribution network planning logic rule base is expressed in a matrix form to generate a multi-dimensional planning problem matrix.

[0051] By performing semantic parsing on the first and second rule data for distribution network planning, the present invention can extract key constraints, improve data comprehensibility, and provide a clear basis for subsequent decision-making. The distribution network planning logic rule base generated through rule mapping centrally manages planning rules, helps ensure the consistency and integrity of the rules, and facilitates subsequent rule maintenance and updates. The generation of a distributed logic rule calculation graph enables parallel processing of complex rule calculations, improving computational efficiency and shortening planning time, which is particularly evident in large-scale distribution network planning. Matrixing the distribution network planning logic rules to generate a multidimensional planning problem matrix makes the problem structure clearer, facilitates quantitative analysis and optimization, and improves the accuracy of decision-making. The multidimensional planning problem matrix provides structured data support for complex decisions, enabling planners to better conduct scenario analysis and compare options, thereby enhancing the scientific nature of decision-making. The standardized and matrixed expression of the rule base provides a foundation for subsequent automated algorithms and models, facilitating the implementation of automated distribution network planning and optimization. The combination of the establishment of a logic rule base and a distributed computing architecture enhances the system's flexibility and adaptability to different planning requirements and environmental changes. Distributed logical rule computation graphs can be visualized, helping planners more intuitively understand and analyze the relationships between rules and improving communication efficiency. Combined with advanced computing technologies, intelligent decision support based on multidimensional problem matrices can be implemented, enhancing the intelligence of distribution network planning. By combining the advantages of constraint semantic parsing and multidimensional planning problem matrices, this approach helps achieve systematic optimization of the distribution network and improve power supply reliability and efficiency.

[0052] Preferably, step S43 includes the following steps:

[0053] Step S431: performing structured data format conversion on the distribution network planning logic rule base to generate logic rule format conversion data; constructing a relationship dependency matrix on the logic rule format conversion data to obtain a relationship dependency matrix; performing parallel execution path analysis on the logic rule format conversion data using the relationship dependency matrix to generate a parallel execution path list;

[0054] Step S432: constructing a rule calculation graph using the relationship dependency matrix as edges and the logical rule format conversion data as nodes to generate a preliminary rule calculation graph;

[0055] Step S433: Evaluate the node computing requirements of the preliminary rule computing graph using the parallel execution path list to generate node computing requirement data; use the node computing requirement data to perform node load balancing adjustment on the preliminary rule computing graph to generate an optimized distributed computing graph;

[0056] Step S434: Perform distributed computing environment configuration on the optimized distributed computing graph to generate computing environment configuration data; perform execution monitoring on the optimized distributed computing graph according to the computing environment configuration data to generate a distributed logic rule computing graph.

[0057] This invention unifies logical rules through structured data format conversion, improving data processability and consistency and facilitating subsequent operations. Constructing a dependency matrix helps reveal the interrelationships between rules, facilitates deeper logical analysis, and optimizes the decision-making process. Generating a parallel execution path list enables efficient task allocation during the computation process, significantly improving processing speed and adapting to the real-time demands of complex distribution networks. Constructing a preliminary rule computation graph provides a visualization tool for understanding the relationships between rules and the computational process, enhancing communication and collaboration efficiency. The use of node computation demand data allows for the rational distribution of node loads, optimizes resource utilization, reduces computational bottlenecks, and improves overall system performance. Generating a distributed computing environment configuration enables the computation graph to flexibly adapt to different computing environments, improving system scalability and flexibility. Monitoring the execution process ensures real-time and accuracy of computations, enabling timely identification and resolution of potential issues and enhancing system reliability. The optimized distributed computation graph enables more intelligent computational strategies, supports complex decision-making processes, and promotes the implementation of smart distribution networks. The combined use of parallel computing and a distributed environment significantly improves the system's ability to process complex logical rules and meet higher data processing requirements. By integrating multiple computing elements, the optimized distributed logic rule computing graph forms a collaborative working platform, enhancing the system integration capability of distribution network planning.

[0058] Preferably, step S5 includes the following steps:

[0059] Step S51: Identify key decision factors for the distribution network geographic planning constraint data and the distribution network operation planning constraint data to generate key decision factor data; establish a decision dimension framework based on the key decision factor data to generate decision dimension framework data; fill the decision dimension framework data with data using a multidimensional planning problem matrix to generate a multidimensional planning matrix;

[0060] Step S52: Using smart contract technology to integrate the multi-dimensional planning matrix into a rule engine to generate a rule-driven model; performing real-time planning decision monitoring on the rule-driven model to generate real-time planning decision monitoring data;

[0061] Step S53: Dynamically record the real-time planning decision monitoring data to generate dynamic planning problem record data; upload the dynamic planning problem record data to the cloud platform for data storage, thereby generating a distribution network planning problem library.

[0062] The present invention helps to clarify the core elements of decision-making and improve the pertinence and effectiveness of decision-making by analyzing geographic planning constraints and operational planning constraint data. Establishing a decision-making dimension framework provides a systematic perspective, helps to comprehensively evaluate the impact of various decision-making factors, and promotes scientific decision-making. The multidimensional planning matrix formed by data filling makes the decision-making process more intuitive and helps to better understand the relationship and mutual influence between various factors. Using smart contract technology to integrate the planning matrix into the rule engine improves the degree of automation of decision-making, reduces the risk of human intervention, and improves decision-making efficiency. Real-time planning decision monitoring of the rule-driven model ensures the transparency and real-time nature of the planning process, enabling rapid response to changes and adjustment of strategies. Dynamic problem recording of real-time monitoring data helps to capture problems that arise in the planning process and provide a basis for subsequent analysis and optimization. Uploading dynamic planning problem record data to the cloud platform not only ensures the secure storage of data, but also facilitates subsequent data analysis and sharing, promoting the optimal use of resources. By generating a distribution network planning problem library, experience and lessons are accumulated to provide data support for future decision-making.

[0063] The beneficial effects of the present invention are that by acquiring and pre-processing distribution network environmental information data, the accuracy and consistency of the data are ensured; the substation site selection and capacity allocation optimize resource allocation, improve the rationality of the overall planning, and the generated layout data lays the foundation for subsequent planning. The transmission line path selection is carried out based on the substation layout, which optimizes the topological structure of the distribution network and ensures the efficiency and reliability of the transmission line. At the same time, the extracted planning rules provide a basis for subsequent decision-making. By performing trend analysis and load growth forecasting on regional electricity consumption data, the changes in electricity demand can be accurately grasped. The generated load demand constraints provide practical basic data for planning, which improves the foresight and practicality of planning. The generation of rule mapping and distributed rule calculation graphs makes the planning logic clearer, promotes the efficient integration and application of planning rules, and the generated multi-dimensional problem matrix provides a framework for the systematic solution of complex planning problems. Through the construction of the multi-dimensional planning matrix and the integration of the rule engine, a dynamically responsive rule-driven model is formed, which makes real-time monitoring and adjustment possible, thereby ensuring the flexibility and adaptability of the planning. The planning problem library finally generated is convenient for future knowledge management and reuse. Therefore, the present invention improves the accuracy and adaptability of distribution network planning through systematic data integration, flexible rule extraction, dynamic decision monitoring and knowledge management. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 A flowchart of the steps of a rule engine driven distribution network planning problem library construction method;

[0065] Figure 2 for Figure 1 Detailed implementation steps of step S2 in FIG.

[0066] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0067] Figure 4 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0068] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0069] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. It is obvious that the embodiments described are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0071] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0072] To achieve this, please refer to Figures 1 to 4 A method for constructing a distribution network planning problem database driven by a rule engine, the method comprising the following steps:

[0073] Step S1: acquiring distribution network environmental information data; performing data preprocessing on the distribution network environmental information data to generate standard distribution network environmental information data; performing substation site selection on the distribution network environmental information data to obtain distribution network substation site selection data; performing substation capacity allocation on the distribution network substation site selection data to generate substation capacity allocation data; performing substation layout based on the substation capacity allocation data and the distribution network substation site selection data to generate substation layout data;

[0074] Step S2: performing transmission line path selection on the standard distribution network environment information data based on the substation layout data to generate transmission line route data; performing distribution network topology construction constraints on the standard distribution network environment information data using the transmission line route data and the substation layout data to generate distribution network geographic planning constraint data; performing first planning rule extraction on the distribution network geographic planning constraint data to obtain first distribution network planning rule data;

[0075] Step S3: Acquire regional electricity consumption data; perform electricity consumption trend analysis on the regional electricity consumption data to generate regional electricity consumption trend data; perform load growth forecast on the regional electricity consumption data based on the regional electricity consumption trend data to generate regional electricity load growth forecast data; impose distribution network load demand constraints on the regional electricity consumption data based on the regional electricity load growth forecast data to generate distribution network operation planning constraint data; perform second planning rule extraction on the distribution network operation planning constraint data to obtain distribution network planning second rule data;

[0076] Step S4: performing rule mapping on the first distribution network planning rule data and the second distribution network planning rule data to generate a distribution network planning logic rule base; generating a distributed rule calculation graph for the distribution network planning logic rule base to obtain a distributed logic rule calculation graph; expressing the distribution network planning logic rule base in a problem matrix based on the distributed logic rule calculation graph to generate a multi-dimensional planning problem matrix;

[0077] Step S5: construct a multidimensional planning matrix for the distribution network geographical planning constraint data and the distribution network operation planning constraint data through a multidimensional planning problem matrix to generate a multidimensional planning matrix; integrate the multidimensional planning matrix with a rule engine to generate a rule-driven model; perform real-time planning decision monitoring on the rule-driven model to generate real-time planning decision monitoring data; perform dynamic planning problem storage on the real-time planning decision monitoring data to generate a distribution network planning problem library.

[0078] This invention ensures data consistency and accuracy by preprocessing distribution network environmental information data, providing a reliable foundation for subsequent analysis. Scientifically selecting substation sites and optimizing capacity allocation improves power resource utilization, reduces construction and operating costs, and ensures power supply reliability. Transmission line routing enables adaptive planning to the environment, reduces obstacles and conflicts during construction, and improves transmission efficiency. The generated geographic planning constraint data provides clear guidance for distribution network design and implementation, promoting transparency and operability in the planning process. Regional electricity consumption trend analysis and load growth forecasting can promptly reflect changes in electricity demand, help optimize distribution network design and operation, and enhance power supply reliability. The logical rule base generated through rule mapping facilitates systematic management of distribution network planning and promotes intelligent and automated decision-making. The generation of distributed rule computation graphs enables efficient and flexible large-scale data processing, improving decision-making response speed. The establishment of a multidimensional planning problem matrix provides a comprehensive perspective for complex decision-making, enabling better response to the interactions of multiple factors. The integration of a rule engine combined with real-time decision monitoring ensures real-time feedback and adjustments during the planning process, improving the accuracy and timeliness of decisions. The storage of dynamic programming problems not only provides historical references for subsequent decision-making but also provides data support for continuous optimization and learning, promoting iterative improvements in the planning process. The integrated planning system can quickly respond to changing environments and demands, improving the adaptability and resilience of the distribution network. Therefore, the present invention improves the accuracy and adaptability of distribution network planning through systematic data integration, flexible rule extraction, dynamic decision monitoring, and knowledge management.

[0079] In the embodiment of the present invention, reference Figure 1 The above is a flowchart of the steps of a rule engine-driven distribution network planning question library construction method of the present invention. In this example, the rule engine-driven distribution network planning question library construction method includes the following steps:

[0080] Step S1: acquiring distribution network environmental information data; performing data preprocessing on the distribution network environmental information data to generate standard distribution network environmental information data; performing substation site selection on the distribution network environmental information data to obtain distribution network substation site selection data; performing substation capacity allocation on the distribution network substation site selection data to generate substation capacity allocation data; performing substation layout based on the substation capacity allocation data and the distribution network substation site selection data to generate substation layout data;

[0081] In an embodiment of the present invention, environmental information data related to the distribution network, including topography, population density, load demand, and existing grid structure, is collected. This data can be obtained using GIS (Geographic Information System) technology, satellite remote sensing data, and local government statistical data. The acquired environmental information data is cleaned to address missing values, outliers, and noise. Data standardization methods (such as Z-score standardization) are used to convert the data into standard distribution network environmental information data for subsequent analysis. Based on this standard distribution network environmental information data, a site selection model (such as the nearest neighbor algorithm or genetic algorithm) is applied to select substation sites, taking into account factors such as load demand, distance, and cost, to obtain distribution network substation site selection data. Based on the site selection results and load demand, a load forecasting model (such as time series analysis or machine learning model) is used to allocate substation capacity, generating substation capacity allocation data to ensure that the capacity of each substation can meet the projected load. The substation site selection and capacity allocation data are used to design the substation layout. Layout optimization algorithms (such as simulated annealing and linear programming) are applied to ensure the efficiency and operability of the layout, ultimately generating the substation layout data.

[0082] Step S2: performing transmission line path selection on the standard distribution network environment information data based on the substation layout data to generate transmission line route data; performing distribution network topology construction constraints on the standard distribution network environment information data using the transmission line route data and the substation layout data to generate distribution network geographic planning constraint data; performing first planning rule extraction on the distribution network geographic planning constraint data to obtain first distribution network planning rule data;

[0083] In an embodiment of the present invention, a transmission line path is selected from the standard distribution network environmental information data using a shortest path algorithm (such as the Dijkstra algorithm) based on the substation layout data. Factors including terrain characteristics, environmental impact, existing infrastructure, and cost are considered to generate transmission line route data. The transmission line route data and substation layout data are used to impose topological constraints on the standard distribution network environmental information data. A topological model is established to ensure that the connection between the transmission line and the substation meets geographical and technical requirements, and distribution network geographical planning constraint data is generated. The distribution network geographical planning constraint data is analyzed to identify key planning rules. Rule mining technology (such as decision tree or association rule learning) is used to extract the first rule data for distribution network planning to ensure that the rules can guide subsequent planning and design.

[0084] Step S3: Acquire regional electricity consumption data; perform electricity consumption trend analysis on the regional electricity consumption data to generate regional electricity consumption trend data; perform load growth forecast on the regional electricity consumption data based on the regional electricity consumption trend data to generate regional electricity load growth forecast data; impose distribution network load demand constraints on the regional electricity consumption data based on the regional electricity load growth forecast data to generate distribution network operation planning constraint data; perform second planning rule extraction on the distribution network operation planning constraint data to obtain distribution network planning second rule data;

[0085] In this embodiment of the present invention, electricity consumption data from relevant regions is collected from sources such as power companies, smart meter data, and historical electricity consumption records. The data is ensured to cover different time periods (e.g., daily, monthly, and annual) for comprehensive analysis. The collected electricity consumption data is analyzed, and time series analysis methods (e.g., moving average and exponential smoothing) are applied to identify electricity consumption trends, generating regional electricity consumption trend data. The analysis results are visualized to identify peak and trough periods and determine electricity consumption patterns. Based on the regional electricity consumption trend data, a forecasting model (e.g., linear regression, ARIMA model, or machine learning algorithm) is used to predict future load growth, generating regional electricity load growth forecast data containing projected electricity consumption for different time periods. Using the regional electricity load growth forecast data, load demand constraints are applied to the regional electricity consumption data to generate distribution network operation planning constraint data, ensuring that the distribution network design can meet future load demand while accounting for seasonal and cyclical fluctuations. The distribution network operation planning constraint data is analyzed to extract key secondary planning rules. Rule mining techniques (e.g., association rule learning and decision trees) are used to identify important planning constraints and rules, generating secondary distribution network planning rule data.

[0086] Step S4: performing rule mapping on the first distribution network planning rule data and the second distribution network planning rule data to generate a distribution network planning logic rule base; generating a distributed rule calculation graph for the distribution network planning logic rule base to obtain a distributed logic rule calculation graph; expressing the distribution network planning logic rule base in a problem matrix based on the distributed logic rule calculation graph to generate a multi-dimensional planning problem matrix;

[0087] In an embodiment of the present invention, by comparing and integrating the first rule data and the second rule data of the distribution network planning, similarities and differences are identified. Based on these analysis results, a distribution network planning logic rule base is constructed, and all rules are systematically stored to ensure that they are searchable and scalable. Using graph theory methods (such as directed graphs), each rule in the distribution network planning logic rule base is regarded as a node, and edges are constructed based on the relationship between the rules. A distributed computing framework (such as Apache Spark or Hadoop) is applied to generate a distributed logic rule calculation graph to optimize computing performance and parallel processing capabilities. Based on the distributed logic rule calculation graph, the distribution network planning logic rule base is expressed in a problem matrix. The rules are associated with the corresponding problem variables to generate a multi-dimensional planning problem matrix to ensure that it can clearly show how each rule affects the specific problems in the planning process.

[0088] Step S5: construct a multidimensional planning matrix for the distribution network geographical planning constraint data and the distribution network operation planning constraint data through a multidimensional planning problem matrix to generate a multidimensional planning matrix; integrate the multidimensional planning matrix with a rule engine to generate a rule-driven model; perform real-time planning decision monitoring on the rule-driven model to generate real-time planning decision monitoring data; perform dynamic planning problem storage on the real-time planning decision monitoring data to generate a distribution network planning problem library.

[0089] In an embodiment of the present invention, a multidimensional planning matrix is ​​constructed by using a multidimensional planning problem matrix in combination with the distribution network geographical planning constraint data and the distribution network operation planning constraint data. The position of each dimension (such as geographical location, load demand, cost, etc.) in the matrix is ​​determined, and relevant data is filled in to fully reflect all aspects of distribution network planning. The multidimensional planning matrix is ​​combined with a rule engine to design a rule-driven model. Business rules and decision logic are embedded into the model through coding to ensure that the system can automatically generate decisions based on the input data. A real-time monitoring system is deployed to dynamically monitor the rule-driven model, track data changes and execution results during the decision-making process, generate real-time planning decision monitoring data, provide feedback for subsequent optimization, and ensure the flexibility and effectiveness of the decision-making process. The real-time planning decision monitoring data is analyzed, and the dynamic planning problems that arise are recorded to ensure the integrity and traceability of the information. The dynamic planning problems are stored in the distribution network planning problem library to form a knowledge base that can be used for subsequent analysis and decision support.

[0090] Preferably, step S1 includes the following steps:

[0091] Step S11: Acquire distribution network environment information data;

[0092] Step S12: performing data preprocessing on the distribution network environment information data to generate standard distribution network environment information data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization;

[0093] Step S13: performing substation site selection on the distribution network environment information data to obtain distribution network substation site selection data; performing center position load analysis on the distribution network substation site selection data to generate substation center position load data;

[0094] Step S14: Allocate substation capacity to the distribution network substation site selection data using the substation center position load data to generate substation capacity allocation data; and perform substation layout based on the substation capacity allocation data and the distribution network substation site selection data to generate substation layout data.

[0095] In an embodiment of the present invention, environmental information data related to the distribution network is collected, including geographic information, load data, meteorological data, and data on existing distribution facilities. Data sources may include sensor data, historical operating data, drone aerial photography, satellite imagery, etc. Noise data, outliers, and duplicate data are removed to ensure data accuracy. Appropriate methods (such as mean filling and interpolation) are used to fill missing values ​​in the data to ensure data integrity. Different features are standardized so that each feature is in the same dimension, facilitating subsequent analysis and modeling. A site selection model is constructed, considering factors such as load demand, geographic location, environmental impact, and cost. Optimization algorithms (such as genetic algorithms and particle swarm optimization) are used to optimize the location of substations and obtain distribution network substation site selection data. Load analysis is performed on the selected substation locations, and the load at the substation center location is calculated to generate substation center location load data. Based on the load demand and site selection results, a substation capacity allocation model is established to rationally allocate the capacity of each substation and generate substation capacity allocation data. Combining substation capacity allocation data and substation site selection data, design the substation layout plan to ensure the rationality and feasibility of the layout, and finally generate the substation layout data.

[0096] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0097] Step S21: performing geographic elevation conversion on the standard distribution network environmental information data based on the substation layout data to generate geographic elevation conversion data; performing environmental terrain difference analysis on the geographic elevation conversion data to generate distribution network environmental terrain difference data;

[0098] Step S22: performing terrain analysis on the geographic elevation conversion data according to the distribution network environment terrain difference data to generate distribution network environment terrain data;

[0099] Step S23: Using the distribution network environment terrain data to select the transmission line path for the substation layout data, and generating transmission line route data; using the transmission line route data and substation layout data to constrain the standard distribution network environment information data for distribution network topology construction, and generating distribution network geographical planning constraint data;

[0100] Step S24: extracting the first planning rule from the distribution network geographical planning constraint data to obtain the distribution network planning first rule data.

[0101] In an embodiment of the present invention, the layout data of the substation (such as location coordinates) and the elevation data of the target area (using a digital elevation model DEM) are obtained. GIS software (such as ArcGIS or QGIS) is used to match the coordinates of the distribution network environment information data, and output geographic elevation conversion data to ensure that all locations have corresponding elevation information. Terrain analysis tools are used to calculate the elevation difference between different locations, extract the elevation difference information of each area, and output distribution network environmental terrain difference data, including specific elevation difference values ​​and their corresponding coordinate information. Based on the environmental terrain difference data, analysis tools such as slope and aspect are used to extract terrain features and generate distribution network environmental terrain data, including information such as slope maps and terrain classifications (such as mountains and plains). The shortest path algorithm (such as Dijkstra) is used, combined with the distribution network environmental terrain data, to evaluate the feasibility and cost of different lines, output transmission line route data, mark the optimal path and take into account terrain obstacles. The transmission line route is combined with the substation layout data, and topological constraint rules are applied to ensure that the line layout is reasonable. The distribution network geographical planning constraint data is output, including information on topological structure requirements and terrain restrictions. Extract the first-stage planning rules from the distribution network geographical planning constraint data, define constraints such as minimum distance and environmental impact, and output the first-stage distribution network planning rule data to provide a basis for detailed design.

[0102] Preferably, step S23 includes the following steps:

[0103] Step S231: extracting main terrain features from the distribution network environment terrain data to obtain main terrain feature data of the distribution network environment, wherein the main terrain feature extraction includes slope extraction, river extraction, and building-dense area extraction;

[0104] Step S232: Using the distribution network environment terrain data to perform shortest transmission line path planning on the substation layout data, generating shortest path planning data; using the distribution network environment main terrain feature data to perform detour area obstacle avoidance on the shortest path planning data, generating an initial transmission line plan;

[0105] Step S233: performing a complexity evaluation on the initial transmission line solution to generate initial transmission line complexity data; performing an optimal transmission line path selection on the initial transmission line solution based on the initial transmission line complexity data to generate transmission line route data;

[0106] Step S234: Perform multi-dimensional distribution network topology decision using transmission line route data and substation layout data to generate distribution network topology decision data; perform distribution network topology construction constraints on standard distribution network environmental information data based on the distribution network topology decision data to generate distribution network geographical planning constraint data.

[0107] In this embodiment of the present invention, terrain analysis tools are used to calculate the slope value of each area and generate a slope data map. Slope extraction considers multiple angles to identify steep areas and gentle slopes. A water system analysis tool is used to extract river and related water body information from the environmental terrain data, generating a river distribution map that indicates the direction and width of major rivers. Land use data is used to analyze the distribution network environment for built-up areas, outputting data on built-up areas and indicating potential construction restriction areas. Combined with this data, data on the main terrain characteristics of the distribution network environment is generated, including information on slope, river, and building distribution. Based on this distribution network environment terrain data, a shortest path algorithm (such as Dijkstra) is used to analyze substation layout data and generate shortest path planning data. Topographic features (such as slope and river) are considered to optimize route selection. Based on this data, obstacles such as built-up areas and rivers are identified and avoided, generating an initial transmission line plan to ensure the feasibility and safety of the line. A complexity analysis is performed on the initial transmission line plan, taking into account path length, intersections, and potential construction difficulty. Initial transmission line complexity data is output and provided as evaluation metrics. Based on initial transmission line complexity data, optimization selection is performed, using algorithms (such as genetic algorithms or simulated annealing) to evaluate different options and generate final transmission line routing data, ensuring a balance between economy and efficiency. Combining transmission line routing data with substation layout data, topology optimization algorithms (such as graph theory) are used to make multi-dimensional decisions and generate distribution network topology decision data, ensuring efficient and reliable network connectivity. Based on this distribution network topology decision data, structural constraint analysis is performed on standard distribution network environmental information data, and the resulting distribution network geographic planning constraint data is output to ensure that the design meets topographic and environmental requirements.

[0108] Preferably, step S234 includes the following steps:

[0109] Step S2341: performing load center distance distribution analysis on the transmission line route data and the substation layout data to generate load center distance distribution data; calculating power supply coverage rate on the transmission line route data and the substation layout data using the load center distance distribution data to generate power supply coverage rate data; performing radial topology decision making based on the power supply coverage rate data and the load center distance distribution data to generate radial topology decision data;

[0110] Step S2342: Performing a line-break recovery capability analysis on the transmission line route data to generate transmission line recovery capability data; performing a power supply reliability calculation on the substation layout data based on the transmission line recovery capability data to obtain power supply reliability data; performing a ring network topology decision based on the transmission line recovery capability data and the power supply reliability data to generate ring network topology decision data;

[0111] Step S2343: Calculating the number of redundant paths in the load center based on the transmission line route data and the substation layout data to obtain redundant path quantity data; performing complexity analysis on the redundant path quantity data to generate redundant path complexity data; and making a grid topology decision based on the redundant path quantity data and the redundant path complexity data to generate grid topology decision data.

[0112] Step S2344: Integrate the radial topology decision data, the ring network topology decision data and the grid topology decision data to generate distribution network topology decision data; perform distribution network topology construction constraints on the standard distribution network environmental information data based on the distribution network topology decision data to generate distribution network geographical planning constraint data.

[0113] In this embodiment of the present invention, a geographic information system (GIS) is used to identify and analyze load centers using transmission line route data and substation layout data. Load center distance distribution data is generated, showing the distance distribution of each load center to the substation and lines. Based on the load center distance distribution data, the power supply coverage rate of each substation is calculated, and its power supply capacity to surrounding load centers is evaluated. Power supply coverage data, including coverage percentage and service range, is output. Power supply coverage data and load center distance distribution data are used to make design decisions for a radial topology, generating radial topology decision data to ensure that the power supply network radiates from the substation. Transmission line route data is used to evaluate the ability to recover from line outages, taking into account factors such as line redundancy design and response time. Transmission line recovery capacity data is generated to assess the recovery capacity of each line under fault conditions. Based on the transmission line recovery capacity data, the power supply reliability of the substation is analyzed, the power supply stability under different fault conditions is calculated, and power supply reliability data, including reliability indicators such as mean time to repair (MTTR) and mean time between failures (MTBF), is output. Based on transmission line resilience and power supply reliability data, design decisions for a ring network topology are made to ensure power supply flexibility and reliability. Ring network topology decision data is generated, forming a ring power supply network with redundant power supply paths. Transmission line route data and substation layout data are analyzed to calculate the number of redundant power supply paths for each load center. Redundant path quantity data is output and available alternative paths are identified. Based on the redundant path quantity data, the complexity between paths, including intersections and the length of alternative paths, is analyzed to generate redundant path complexity data and assess the complexity level of network redundancy. Based on the redundant path quantity and complexity data, design decisions for a mesh network topology are made to ensure distribution network flexibility and reliability. Mesh network topology decision data is generated to form a mesh structure with multiple power supply paths. Decision data for radial, ring, and mesh topologies are comprehensively analyzed to identify the optimal topology combination. The final distribution network topology decision data is generated, combining the advantages of each decision type to ensure design rationality and reliability. Based on the distribution network topology decision data, a structural constraint analysis is performed on the standard distribution network environmental information data to ensure that the network design meets the actual environment and operation requirements, and the distribution network geographical planning constraint data is output to provide guidance for subsequent implementation.

[0114] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes:

[0115] Step S31: Acquire regional electricity consumption data;

[0116] Step S32: performing a time series analysis on the regional electricity consumption data to generate regional electricity consumption time series data; performing curve conversion on the regional electricity consumption time series data to generate a regional electricity consumption time series curve; performing a power consumption trend analysis on the regional electricity consumption time series curve data to generate regional electricity consumption trend data;

[0117] Step S33: Dividing the regional electricity consumption data into electricity consumption patterns based on the regional electricity consumption trend data to generate regional daytime electricity consumption patterns and regional nighttime electricity consumption patterns; performing load growth prediction on the regional electricity consumption data based on the regional daytime electricity consumption patterns and regional nighttime electricity consumption patterns to generate regional electricity load growth prediction data;

[0118] Step S34: Based on the regional electricity load growth forecast data, the regional electricity consumption data is constrained by the distribution network load demand to generate distribution network operation planning constraint data; the distribution network operation planning constraint data is subjected to second planning rule extraction to obtain distribution network planning second rule data.

[0119] In embodiments of the present invention, smart meters, regional energy management systems, and other devices are used to acquire regional electricity consumption data, including information such as electricity consumption, time periods, and user categories. Data accuracy and completeness are ensured by considering variations in electricity consumption within different time periods (e.g., hourly, daily, and monthly). Time series analysis is performed on the acquired regional electricity consumption data to identify temporal characteristics of electricity consumption, such as peak and off-peak periods. Regional electricity consumption time series data is generated to reflect the time-varying characteristics of electricity consumption. The regional electricity consumption time series data is converted into curve data, and interpolation or smoothing methods (e.g., spline interpolation) are used to generate a regional electricity consumption time series curve. This curve is used to more intuitively display electricity consumption variations. Trend analysis is performed on the regional electricity consumption time series curve data to identify long-term variation patterns (e.g., seasonal and annual trends). Regional electricity consumption trend data is generated to provide quantitative indicators of electricity consumption growth or decline. Based on the regional electricity consumption trend data, the electricity consumption data is divided into daytime and nighttime patterns. The data is divided based on peak and off-peak periods to generate regional daytime and nighttime patterns, respectively reflecting the electricity consumption characteristics of different time periods. Based on regional daytime and nighttime electricity consumption patterns, time series forecasting models (such as ARIMA and LSTM) are used to predict load growth in regional electricity consumption data. This generates regional load growth forecast data, providing an estimate of future electricity demand. Based on the regional load growth forecast data, constraint analysis is performed on the regional electricity consumption data to identify distribution network load demands. Distribution network operation planning constraint data is generated to ensure that the plan meets the projected load demands. Second-stage planning rules, including load management, dispatch strategies, and other operating procedures, are extracted from the distribution network operation planning constraint data. The second-stage distribution network planning rule data is then output to provide guidance for subsequent distribution network management and optimization.

[0120] Preferably, dividing the regional electricity consumption data into electricity consumption patterns according to the regional electricity consumption trend data includes:

[0121] Perform time series segmentation on regional electricity consumption trend data to generate daytime electricity consumption data and nighttime electricity consumption data; perform cluster analysis on daytime electricity consumption data and nighttime electricity consumption data to generate time period electricity consumption difference data; classify regional electricity consumption trend data based on time period electricity consumption difference data to generate preliminary electricity consumption trend classification data;

[0122] The daytime electricity consumption data is used to analyze the preliminary electricity consumption trend classification data for daytime electricity consumption peak and valley data, generating daytime electricity consumption peak data and daytime electricity consumption valley data; the daytime electricity consumption curvature is calculated for the daytime electricity consumption peak data and daytime electricity consumption valley data to obtain the regional daytime electricity consumption pattern;

[0123] The nighttime electricity consumption data is used to analyze the preliminary electricity consumption trend classification data, and the nighttime electricity consumption peak and valley data are generated. The nighttime electricity consumption curvature is calculated for the nighttime electricity consumption peak and valley data to obtain the regional nighttime electricity consumption pattern.

[0124] In this embodiment of the present invention, regional electricity consumption trend data is used to perform time series segmentation on electricity consumption, dividing the data into daytime and nighttime periods. The daytime period is generally defined as 6:00 AM to 10:00 PM, and the nighttime period is 10:00 PM to 6:00 AM. Daytime and nighttime electricity consumption data are generated to ensure data integrity. Cluster analysis is performed on the daytime and nighttime electricity consumption data, using algorithms (such as K-means or DBSCAN) to identify differences in electricity usage patterns. This generates period-specific electricity consumption difference data, which displays significant characteristics of electricity usage behavior within different time periods. Based on the period-specific electricity consumption difference data, regional electricity consumption trends are analyzed and classified to generate preliminary electricity consumption trend classification data. This data may include classification labels such as "peak," "stable," and "valley." The preliminary electricity consumption trend classification data is analyzed using the daytime electricity consumption data to extract peak and vale characteristics of daytime electricity consumption. Peak and vale data for daytime electricity consumption are generated, clarifying the specific time points and power consumption of peak and vale periods. Curvature calculations are performed on daytime peak and valley data, and the degree of change in the electricity consumption curve is evaluated using a curvature formula to generate a regional daytime electricity consumption pattern, reflecting the changing trends and characteristics of daytime electricity consumption. Preliminary electricity consumption trend classification data is analyzed using nighttime electricity consumption data, and peak and valley characteristics of nighttime electricity consumption are extracted to generate nighttime peak and valley data, clarifying the specific time points and power consumption of peaks and valleys. Curvature calculations are performed on nighttime peak and valley data, using a similar calculation method as for daytime data, to generate a regional nighttime electricity consumption pattern, reflecting the changing trends and characteristics of nighttime electricity consumption.

[0125] As an example of the present invention, refer to Figure 4 As shown, in this example, step S4 includes:

[0126] Step S41: performing semantic analysis on the first rule data and the second rule data of the distribution network planning to generate constraint semantic analysis data;

[0127] Step S42: performing rule mapping on the constraint semantic parsing data to generate a distribution network planning logic rule base;

[0128] Step S43: generating a distributed rule calculation graph for the distribution network planning logic rule base to obtain a distributed logic rule calculation graph;

[0129] Step S44: Based on the distributed logic rule calculation graph, the distribution network planning logic rule base is expressed in a matrix form to generate a multi-dimensional planning problem matrix.

[0130] In an embodiment of the present invention, by performing semantic analysis on the first rule data and the second rule data of the distribution network planning, key constraints and logical relationships are extracted, and constraint semantic parsing data is generated, which contains clear constraint descriptions and logical relationships for subsequent processing. The constraint semantic parsing data is mapped to a unified rule framework to ensure the compatibility and operability between different rules, and a distribution network planning logic rule base is generated, which contains standardized logic rules to support the decision-making process of distribution network planning. The distribution network planning logic rule base is used to construct a distributed rule calculation graph to display the relationship and calculation path between each rule. It is ensured that the structure of the graph can support parallel computing, improve the efficiency of rule application, output a distributed logic rule calculation graph, and clearly depict the calculation process. Based on the distributed logic rule calculation graph, the problems in the distribution network planning logic rule base are expressed in a matrix form to generate a multi-dimensional planning problem matrix, covering variables and constraints in multiple dimensions, which is convenient for subsequent analysis and optimization.

[0131] Preferably, step S43 includes the following steps:

[0132] Step S431: performing structured data format conversion on the distribution network planning logic rule base to generate logic rule format conversion data; constructing a relationship dependency matrix on the logic rule format conversion data to obtain a relationship dependency matrix; performing parallel execution path analysis on the logic rule format conversion data using the relationship dependency matrix to generate a parallel execution path list;

[0133] Step S432: constructing a rule calculation graph using the relationship dependency matrix as edges and the logical rule format conversion data as nodes to generate a preliminary rule calculation graph;

[0134] Step S433: Evaluate the node computing requirements of the preliminary rule computing graph using the parallel execution path list to generate node computing requirement data; use the node computing requirement data to perform node load balancing adjustment on the preliminary rule computing graph to generate an optimized distributed computing graph;

[0135] Step S434: Perform distributed computing environment configuration on the optimized distributed computing graph to generate computing environment configuration data; perform execution monitoring on the optimized distributed computing graph according to the computing environment configuration data to generate a distributed logic rule computing graph.

[0136] In an embodiment of the present invention, raw data from a distribution network planning logic rule library is collected. Data parsing tools (such as the Pandas library in Python) are used to convert the raw data into a structured format (such as CSV, JSON, etc.) to generate logic rule format conversion data. Relationships between logic rules (such as causal relationships, priorities, etc.) are determined. A graph theory algorithm is used to construct a dependency matrix, representing the dependencies between rules in matrix form. Based on the dependency matrix, identification is performed, and parallel execution paths are analyzed to generate a list of parallel execution paths, identifying which rules can be executed simultaneously to improve computational efficiency. The dependency matrix is ​​considered as the edges of a graph, and the logic rule format conversion data as nodes. A preliminary rule computation graph is generated using a graph theory algorithm (such as the Dijkstra or Kruskal algorithm). Ensure that the connections between nodes and edges in the graph conform to the relationships between the logic rules. Using the parallel execution path list, the computational requirements of each node are evaluated, taking into account factors such as execution time and resource consumption. Node computation requirement data is generated, forming a dictionary or table containing the requirements of each node. Based on the node computation requirement data, nodes with uneven loads are identified. Use load balancing algorithms (such as Round Robin and Least Connections) to adjust the preliminary rule computation graph to distribute the load and improve overall efficiency, generating an optimized distributed computation graph. Based on the optimized distributed computation graph, determine the required computing resources (such as CPU, memory, storage, etc.). Use automation tools (such as Kubernetes or Docker) to configure the distributed computing environment to ensure high availability and elasticity of resources. Use monitoring tools (such as Prometheus and Grafana) to monitor the computing environment and track resource usage and computing efficiency during execution. Adjust the execution strategy based on the computing environment configuration data to ensure efficient execution of the distributed logic rule computation graph.

[0137] Preferably, step S5 includes the following steps:

[0138] Step S51: Identify key decision factors for the distribution network geographic planning constraint data and the distribution network operation planning constraint data to generate key decision factor data; establish a decision dimension framework based on the key decision factor data to generate decision dimension framework data; fill the decision dimension framework data with data using a multidimensional planning problem matrix to generate a multidimensional planning matrix;

[0139] Step S52: Using smart contract technology to integrate the multi-dimensional planning matrix into a rule engine to generate a rule-driven model;

[0140] Conduct real-time planning and decision-making monitoring on the rule-driven model to generate real-time planning and decision-making monitoring data;

[0141] Step S53: Dynamically record the real-time planning decision monitoring data to generate dynamic planning problem record data; upload the dynamic planning problem record data to the cloud platform for data storage, thereby generating a distribution network planning problem library.

[0142] In an embodiment of the present invention, distribution network geographic planning constraint data and distribution network operational planning constraint data are collected. Data analysis tools (such as data mining or machine learning algorithms) are used to identify key decision factors and generate key decision factor data. Feature selection methods (such as decision trees or random forests) can be used to determine the key factors influencing decision making. Based on the key decision factor data, a decision dimension framework is designed, including different decision dimensions (such as cost, efficiency, reliability, etc.). Decision dimension framework data is generated to form a structured document or database record. A multidimensional planning problem matrix is ​​constructed. In combination with the decision dimension framework, specific data for each dimension is filled into the matrix. Statistical analysis methods (such as regression analysis) are used to verify the data to ensure the accuracy and completeness of the multidimensional planning matrix. Utilizing smart contract technology, a rule-driven model is designed, and the decision rules in the multidimensional planning matrix are encoded into smart contracts. This ensures that the rule engine can call on the matrix data in real time to make decisions and generate dynamic responses. A monitoring system is deployed to track parameter changes and execution results during the decision-making process in real time, generate real-time planning decision monitoring data, provide feedback and optimization suggestions, and ensure an efficient and flexible decision-making process. Analyze real-time planning decision monitoring data, record any issues and challenges, and generate dynamic planning problem logs. Use log management tools (such as the ELK Stack) to log data to ensure information integrity and traceability. Upload dynamic planning problem logs to the cloud platform and protect them using secure data transmission protocols (such as HTTPS). Establish a distribution network planning problem database on the cloud platform to facilitate subsequent data analysis and decision support.

[0143] The beneficial effects of the present invention are that by acquiring and pre-processing distribution network environmental information data, the accuracy and consistency of the data are ensured; the substation site selection and capacity allocation optimize resource allocation, improve the rationality of the overall planning, and the generated layout data lays the foundation for subsequent planning. The transmission line path selection is carried out based on the substation layout, which optimizes the topological structure of the distribution network and ensures the efficiency and reliability of the transmission line. At the same time, the extracted planning rules provide a basis for subsequent decision-making. By performing trend analysis and load growth forecasting on regional electricity consumption data, the changes in electricity demand can be accurately grasped. The generated load demand constraints provide practical basic data for planning, which improves the foresight and practicality of planning. The generation of rule mapping and distributed rule calculation graphs makes the planning logic clearer, promotes the efficient integration and application of planning rules, and the generated multi-dimensional problem matrix provides a framework for the systematic solution of complex planning problems. Through the construction of the multi-dimensional planning matrix and the integration of the rule engine, a dynamically responsive rule-driven model is formed, which makes real-time monitoring and adjustment possible, thereby ensuring the flexibility and adaptability of the planning. The planning problem library finally generated is convenient for future knowledge management and reuse. Therefore, the present invention improves the accuracy and adaptability of distribution network planning through systematic data integration, flexible rule extraction, dynamic decision monitoring and knowledge management.

[0144] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0145] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for constructing a distribution network planning problem library driven by a rule engine, characterized in that: The following steps are involved: Step S1: Acquire distribution network environment information data; perform data preprocessing on the distribution network environment information data to generate standard distribution network environment information data; Performing substation site selection on the distribution network environment information data to obtain distribution network substation site selection data; performing substation capacity allocation on the distribution network substation site selection data to generate substation capacity allocation data; performing substation layout according to the substation capacity allocation data and the distribution network substation site selection data to generate substation layout data; Step S2: Based on the substation layout data, the standard distribution network environment information data is subjected to transmission line path selection to generate transmission line route data; the standard distribution network environment information data is subjected to distribution network topology construction constraints through the transmission line route data and the substation layout data to generate distribution network geographic planning constraint data; the first planning rule is extracted from the distribution network geographic planning constraint data to obtain the first rule data for distribution network planning; Step S3: Obtaining regional electricity consumption data; Conduct electricity consumption trend analysis on regional electricity consumption data to generate regional electricity consumption trend data; Carry out load growth forecast on regional electricity consumption data according to regional electricity consumption trend data to generate regional electricity load growth forecast data; Based on the regional electricity load growth forecast data, the regional electricity consumption data is constrained by the distribution network load demand, and the distribution network operation planning constraint data is generated; Extracting the second planning rule from the distribution network operation planning constraint data to obtain the distribution network planning second rule data; Step S4: performing rule mapping on the first rule data of distribution network planning and the second rule data of distribution network planning, thereby generating a distribution network planning logic rule base; Generate a distributed rule calculation graph for the distribution network planning logic rule base to obtain a distributed logic rule calculation graph; express the distribution network planning logic rule base in a matrix based on the distributed logic rule calculation graph to generate a multi-dimensional planning problem matrix; Step S5: constructing a multidimensional planning matrix for the distribution network geographical planning constraint data and the distribution network operation planning constraint data through a multidimensional planning problem matrix to generate a multidimensional planning matrix; Integrate the rule engine into the multi-dimensional planning matrix to generate a rule-driven model; Conduct real-time planning decision monitoring on the rule-driven model and generate real-time planning decision monitoring data; The real-time planning decision monitoring data is dynamically stored to generate a distribution network planning problem library.

2. The method for constructing a distribution network planning problem library driven by a rule engine according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire distribution network environment information data; Step S12: performing data preprocessing on the distribution network environment information data to generate standard distribution network environment information data, wherein the data preprocessing includes data cleaning, data missing value filling and data standardization; Step S13: performing substation site selection on the distribution network environment information data to obtain distribution network substation site selection data; performing central position load analysis on the distribution network substation site selection data to generate substation central position load data; Step S14: Allocate substation capacity to distribution network substation site selection data through substation center position load data to generate substation capacity allocation data; perform substation layout according to substation capacity allocation data and distribution network substation site selection data to generate substation layout data.

3. The method for constructing a distribution network planning problem library driven by a rule engine according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing geographic elevation conversion on the standard distribution network environment information data based on the substation layout data to generate geographic elevation conversion data; performing environmental terrain difference analysis on the geographic elevation conversion data to generate distribution network environmental terrain difference data; Step S22: performing terrain analysis on the geographic elevation conversion data according to the distribution network environment terrain difference data to generate distribution network environment terrain data; Step S23: using the distribution network environment terrain data to select the transmission line path for the substation layout data, and generating the transmission line route data; using the transmission line route data and the substation layout data to constrain the standard distribution network environment information data for distribution network topology construction, and generating the distribution network geographical planning constraint data; Step S24: extracting the first planning rule from the distribution network geographical planning constraint data to obtain the distribution network planning first rule data.

4. The method for constructing a distribution network planning problem library driven by a rule engine according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: extracting main terrain features from the distribution network environment terrain data to obtain main terrain feature data of the distribution network environment, wherein the main terrain feature extraction includes slope extraction, river extraction and building-dense area extraction; Step S232: using the distribution network environment terrain data to perform shortest path planning for the substation layout data, and generating shortest path planning data; performing detour area obstacle avoidance on the shortest path planning data through the distribution network environment main terrain feature data, and generating an initial transmission line plan; Step S233: performing complexity evaluation on the initial transmission line scheme to generate initial transmission line complexity data; performing optimal transmission line path selection on the initial transmission line scheme based on the initial transmission line complexity data to generate transmission line route data; Step S234: Perform multi-dimensional distribution network topology decision through transmission line route data and substation layout data to generate distribution network topology decision data; perform distribution network topology construction constraints on standard distribution network environmental information data based on the distribution network topology decision data to generate distribution network geographical planning constraint data.

5. The method for constructing a distribution network planning problem library driven by a rule engine according to claim 4, characterized in that: Step S234 includes the following steps: Step S2341: performing load center distance distribution analysis on the transmission line route data and the substation layout data to generate load center distance distribution data; performing power supply coverage calculation on the transmission line route data and the substation layout data through the load center distance distribution data to generate power supply coverage data; performing radial topology structure decision based on the power supply coverage data and the load center distance distribution data to generate radial topology structure decision data; Step S2342: Perform line break recovery capability analysis on the transmission line route data to generate transmission line recovery capability data; perform power supply reliability calculation on the substation layout data based on the transmission line recovery capability data to obtain power supply reliability data; perform ring network topology structure decision based on the transmission line recovery capability data and the power supply reliability data to generate ring network topology structure decision data; Step S2343: Calculate the number of redundant paths of the load center based on the transmission line route data and the substation layout data to obtain redundant path number data; perform complexity analysis on the redundant path number data to generate redundant path complexity data; perform grid topology structure decision based on the redundant path number data and the redundant path complexity data to generate grid topology structure decision data; Step S2344: Integrate the radial topology decision data, the ring network topology decision data and the grid topology decision data to generate distribution network topology decision data; perform distribution network topology construction constraints on the standard distribution network environmental information data based on the distribution network topology decision data to generate distribution network geographical planning constraint data.

6. The method for constructing a distribution network planning problem library driven by a rule engine according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Acquire regional electricity consumption data; Step S32: performing a power consumption time series analysis on the regional power consumption data to generate regional power consumption time series data; performing a curve conversion on the regional power consumption time series data to generate a regional power consumption time series curve; performing a power consumption trend analysis on the regional power consumption time series curve data to generate regional power consumption trend data; Step S33: dividing the regional electricity consumption data into electricity consumption patterns according to the regional electricity consumption trend data, generating regional daytime electricity consumption patterns and regional nighttime electricity consumption patterns; performing load growth forecasting on the regional electricity consumption data through the regional daytime electricity consumption patterns and regional nighttime electricity consumption patterns, generating regional electricity load growth forecasting data; Step S34: Based on the regional electricity load growth forecast data, the regional electricity consumption data is constrained by the distribution network load demand to generate distribution network operation planning constraint data; the second planning rule is extracted from the distribution network operation planning constraint data to obtain the distribution network planning second rule data.

7. The method for constructing a distribution network planning problem library driven by a rule engine according to claim 6, characterized in that: The electricity consumption patterns of regional electricity consumption data are divided according to regional electricity consumption trend data, including: Perform time series segmentation on regional electricity consumption trend data to generate daytime electricity consumption data and nighttime electricity consumption data; perform cluster analysis on daytime electricity consumption data and nighttime electricity consumption data to generate time period electricity consumption difference data; classify regional electricity consumption trend data according to time period electricity consumption difference data to generate preliminary electricity consumption trend classification data; The daytime electricity consumption data is used to classify the preliminary electricity consumption trend data into daytime electricity consumption peak and valley data, generating daytime electricity consumption peak data and daytime electricity consumption valley data; the daytime electricity consumption curvature is calculated for the daytime electricity consumption peak data and daytime electricity consumption valley data to obtain the regional daytime electricity consumption pattern; The night-time electricity consumption data is used to classify the preliminary electricity consumption trend data into night-time electricity peak and valley data to generate night-time electricity consumption peak data and night-time electricity consumption valley data; the night-time electricity consumption curvature is calculated for the night-time electricity consumption peak data and night-time electricity consumption valley data to obtain the regional night-time electricity consumption pattern.

8. The method for constructing a distribution network planning problem library driven by a rule engine according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: semantically parse the first rule data and the second rule data of the distribution network planning to generate constraint semantic parsing data; Step S42: performing rule mapping on the constraint semantic parsing data, thereby generating a distribution network planning logic rule base; Step S43: generating a distributed rule calculation graph for the distribution network planning logic rule base to obtain a distributed logic rule calculation graph; Step S44: Based on the distributed logic rule calculation graph, the distribution network planning logic rule base is expressed in a matrix form to generate a multi-dimensional planning problem matrix.

9. The method for constructing a distribution network planning problem library driven by a rule engine according to claim 8, characterized in that: Step S43 includes the following steps: Step S431: converting the structured data format of the distribution network planning logic rule base to generate logic rule format conversion data; constructing a relationship dependency matrix for the logic rule format conversion data to obtain a relationship dependency matrix; performing identification parallel execution path analysis on the logic rule format conversion data through the relationship dependency matrix to generate a parallel execution path list; Step S432: construct a rule calculation graph by using the relationship dependency matrix as an edge and the logical rule format conversion data as a node to generate a preliminary rule calculation graph; Step S433: evaluating the node computing requirements of the preliminary rule computing graph through the parallel execution path list to generate node computing requirement data; using the node computing requirement data to perform node load balancing adjustment on the preliminary rule computing graph to generate an optimized distributed computing graph; Step S434: Perform distributed computing environment configuration on the optimized distributed computing graph to generate computing environment configuration data; perform execution monitoring on the optimized distributed computing graph according to the computing environment configuration data to generate a distributed logic rule computing graph.

10. The method for constructing a distribution network planning problem library driven by a rule engine according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: Identify key decision factors for the distribution network geographic planning constraint data and the distribution network operation planning constraint data to generate key decision factor data; establish a decision dimension framework through the key decision factor data to generate decision dimension framework data; fill the decision dimension framework data with data through a multidimensional planning problem matrix to generate a multidimensional planning matrix; Step S52: Using smart contract technology to integrate the multi-dimensional planning matrix into a rule engine to generate a rule-driven model; Conduct real-time planning decision monitoring on the rule-driven model and generate real-time planning decision monitoring data; Step S53: dynamically record the real-time planning decision monitoring data to generate dynamic planning problem record data; The dynamic planning problem record data is uploaded to the cloud platform for data storage, thereby generating a distribution network planning problem library.

Images