Distribution network frame multi-target planning model system
Through the distribution network grid multi-objective planning model system, Pareto optimization algorithm and decision support tools are adopted, which solves the problem that traditional distribution network planning methods are difficult to consider multiple goals, and achieves more comprehensive planning results and more efficient decision support.
Patent Information
- Application Number
- CN202411600959.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-11
- Publication Date
- 2025-02-25
AI Technical Summary
Traditional distribution network planning methods focus on a single goal, and it is difficult to effectively consider a variety of factors, such as investment costs, operating costs, power supply reliability, etc., and there is a lack of effective decision-making support tools.
It provides a multi-objective planning model system for distribution network network frames, including objective function module, constraint condition module, multi-objective optimization algorithm module, decision support module, data processing and analysis module and user interface module. The Pareto optimization algorithm is used to optimize multiple objective functions to provide decision support and data analysis.
The system can comprehensively consider multiple planning goals, provide more comprehensive planning results, help planners choose the best planning scheme, and improve the efficiency and quality of planning work.
Smart Images
Figure CN119514359A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power system planning, and in particular to a distribution network framework multi-objective planning model system. Background Art
[0002] With the growth of energy demand, the planning and optimization of distribution networks are becoming increasingly important. In traditional distribution network planning, empirical formulas and single-objective planning methods are usually relied on to design the distribution network framework. This method often focuses on a single goal such as reducing investment costs or improving power supply reliability, ignoring the mutual influence and balance between multiple objectives. However, in practical applications, distribution network planning needs to consider multiple factors, such as investment costs, operating costs, power supply reliability, etc. A single planning method is difficult to meet the needs of multiple objectives and cannot effectively guide actual projects. In addition, traditional planning methods lack effective decision support tools when dealing with multi-objective problems. Summary of the invention
[0003] The purpose of the present invention is to provide a distribution network framework multi-objective planning model system to solve the problems raised in the above background technology.
[0004] To achieve the above-mentioned object, the present invention provides the following technical solutions: a distribution network framework multi-objective planning model system, the multi-objective planning model system includes an objective function module, a constraint condition module, a multi-objective optimization algorithm module, a decision support module, a data processing and analysis module, and a user interface module; The objective function module is used to define multiple objective functions in the planning process, including investment cost, operating cost, reliability, environmental friendliness and power supply quality; The constraint condition module is used to set the constraint conditions in the planning process, including power grid security constraints, node voltage constraints and line capacity constraints; The multi-objective optimization algorithm module uses a multi-objective optimization algorithm to optimize the objective function; The decision support module provides decision support based on the results of the multi-objective optimization algorithm to help planners select the optimal planning solution; The data processing and analysis module is used to process and analyze the data generated during the planning process, provide input for the optimization algorithm and generate visual results; The user interface module is used to provide a user interaction interface to facilitate users to input parameters, start the optimization process and view the results.
[0005] Preferably, the investment cost includes the cost of the distribution equipment, installation costs and land use costs, expressed as a function of the facility capital investment and expected depreciation.
[0006] Preferably, the operating costs include maintenance costs and energy loss costs.
[0007] Preferably, the reliability can be measured by annual average power outage time and power outage frequency indicators of the available system, and the objective function of the reliability can be constructed based on historical data and a prediction model.
[0008] Preferably, the environmental friendliness involves emissions, noise levels and an evaluation of ecological impact, and is expressed through the relationship between emission factors and operating parameters.
[0009] Preferably, the power supply quality includes voltage stability, harmonic level and power supply reliability indicators.
[0010] Preferably, the power grid safety constraints include stability constraints and fault current constraints; the node voltage constraints include voltage amplitude constraints and voltage imbalance constraints; and the line capacity constraints include thermal stability limit constraints and line loss constraints.
[0011] Preferably, the multi-objective optimization algorithm module adopts the Pareto optimization algorithm, and the specific method includes the following steps: S1: Generate the initial population, each individual represents a possible solution, sort the population according to Pareto advantage, and select individuals with Pareto advantage to enter the next generation; S2: Generate new offspring by simulating binary crossover and polynomial mutation operations, evaluate the newly generated offspring, compare them with the previous generation, select dominant individuals, and repeat the above process until the stopping condition is met; S3: The termination condition of the algorithm is set to reaching the maximum number of iterations, and the final output is a set of solutions that constitute the Pareto frontier, representing the optimal trade-off between different objectives.
[0012] Preferably, the decision support module includes a sensitivity analysis function, and the specific method of this function includes the following steps: S11: Analyze the influence of each parameter change on the objective function value and determine which parameters have the greatest influence on the result; S12: Observe the trend of objective function changing with parameters, and understand the sensitivity trend of different parameter adjustments to optimization results; S13: Evaluate the robustness of optimization schemes under different parameter settings and identify those that maintain good performance under parameter fluctuations; S14: Based on the results of sensitivity analysis, adjust the planning scheme to reduce reliance on uncertain parameters and improve the reliability of the scheme.
[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a distribution network framework multi-objective planning model system, which can comprehensively consider multiple planning objectives, provide more comprehensive planning results, and adopt a multi-objective optimization algorithm to obtain a set of non-inferior solutions, providing more choices for decision makers, and providing decision support tools to help planners choose the optimal planning solution. Through the data processing and analysis module, the data processing capability of the planning process and the visualization of the results are improved. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 It is a system block diagram of the distribution network multi-objective planning model system of the present invention.
[0015] Figure 2 Flow chart of the multi-objective optimization algorithm module of the present invention.
[0016] Figure 3 The present invention is a flow chart of a distribution network multi-objective planning model system.
[0017] Figure 4 Flow chart of the work of the decision support module of the present invention. DETAILED DESCRIPTION
[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0019] See also Figures 1 to 4 ,The present invention provides a technical solution: a distribution network framework multi-objective planning model system, the multi-objective planning model system includes an objective function module, a constraint condition module, a multi-objective optimization algorithm module, a decision support module, a data processing and analysis module, and a user interface module; The objective function module is used to define multiple objective functions in the planning process, including investment cost, operating cost, reliability, environmental friendliness and power supply quality; The investment cost includes the cost of the distribution equipment, installation costs, and land use costs, expressed as a function of the facility capital investment and expected depreciation.
[0020] Investment cost: = Operating costs include maintenance costs and energy loss costs.
[0021] Running costs: Reliability can be measured by the annual average power outage time and power outage frequency indicators of the available system. The objective function of reliability can be constructed based on historical data and prediction models.
[0022] reliability: Environmental friendliness involves the evaluation of emissions, noise levels and ecological impacts, and is expressed through the relationship between emission factors and operating parameters.
[0023] Environmental friendliness: Power supply quality includes voltage stability, harmonic level and power supply reliability indicators.
[0024] Power supply quality: The constraint condition module is used to set the constraint conditions in the planning process, including power grid security constraints, node voltage constraints and line capacity constraints; Grid security constraints include stability constraints and fault current constraints; ,in is the stability margin under fault scenario s, is the corresponding weight; the stability constraint ensures that the system can maintain dynamic stability under load fluctuations or emergencies.
[0025] The fault current restraint protection device should be able to operate reliably when a fault occurs to avoid equipment damage. ,in is the fault current, It is the maximum current allowed to flow through the device.
[0026] Node voltage constraints include voltage amplitude constraints and voltage unbalance constraints; The voltage amplitude is constrained to be maintained within acceptable levels. , where node The voltage, and are the minimum and maximum permissible voltages, respectively; Voltage unbalance constraint In a three-phase system, the phase-to-phase voltage unbalance is controlled within the specified range. ,in is the voltage unbalance rate of the node, , and are the maximum, minimum and average values of the node phase voltage respectively. is the maximum allowable imbalance rate.
[0027] Line capacity constraints include thermal stability limit constraints and line loss constraints.
[0028] In the thermal stability limit constraint, the line current carrying capacity does not exceed its design value. ,in It flows through the line The absolute value of the current, It is a line The maximum allowable current of the line; the line loss constraint, the power loss of the line is kept at an acceptable level, ,in It is a line The power loss, is the line resistance, is the maximum allowable power loss.
[0029] In the design of the constraint condition module, this system takes into account the constraints of power grid security, node voltage and line capacity to ensure the scientificity and practicality of the planning scheme, strengthen the power grid security constraints, effectively guarantee the dynamic stability of the system under load fluctuations or emergencies, and prevent equipment damage and large-scale power outages.
[0030] The multi-objective optimization algorithm module uses a multi-objective optimization algorithm to optimize the objective function; The multi-objective optimization algorithm module adopts the Pareto optimization algorithm. The specific method includes the following steps: S1: Generate the initial population, each individual represents a possible solution, sort the population according to Pareto advantage, and select individuals with Pareto advantage to enter the next generation; S2: Generate new offspring by simulating binary crossover and polynomial mutation operations, evaluate the newly generated offspring, compare them with the previous generation, select dominant individuals, and repeat the above process until the stopping condition is met; S3: The termination condition of the algorithm is set to reaching the maximum number of iterations, and the final output is a set of solutions that constitute the Pareto frontier, representing the optimal trade-off between different objectives.
[0031] In this way, the distribution network multi-objective planning model system can effectively use the Pareto optimization algorithm to concretize the optimization of the objective function and find the best balance point between multiple objectives.
[0032] The decision support module provides decision support based on the results of the multi-objective optimization algorithm to help planners select the optimal planning solution; The decision support module includes a sensitivity analysis function, the specific method of which includes the following steps: S11: Analyze the influence of each parameter change on the objective function value and determine which parameters have the greatest influence on the result; S12: Observe the trend of objective function changing with parameters, and understand the sensitivity trend of different parameter adjustments to optimization results; S13: Evaluate the robustness of optimization schemes under different parameter settings and identify those that maintain good performance under parameter fluctuations; S14: Based on the results of sensitivity analysis, adjust the planning scheme to reduce reliance on uncertain parameters and improve the reliability of the scheme.
[0033] The decision support module includes a scheme recommendation unit and a sensitivity analysis unit. The scheme recommendation unit generates multiple planning schemes according to the results of the multi-objective planning model, and the sensitivity analysis unit analyzes the sensitivity of different planning schemes to key parameters.
[0034] The introduction of the decision support module provides planners with a powerful decision-making support tool. The realization of the sensitivity analysis function helps planners identify key parameters, improve the robustness of planning schemes, and reduce the impact of uncertainty on planning results.
[0035] The data processing and analysis module is used to process and analyze the data generated during the planning process, provide input for the optimization algorithm and generate visual results; Data preprocessing includes data cleaning, data filtering and data normalization. Data cleaning processes missing values, outliers and duplicate values in the original data. Data filtering filters the data to exclude irrelevant or low-value information by setting thresholds or identifying outliers based on Z-Score methods. Data normalization converts data into a unified dimension and format. Common methods include Min-Max normalization and Z-Score standardization.
[0036] Encode categorical variables into numerical variables, or discretize continuous variables, and convert the data into an appropriate format according to the input requirements of the optimization algorithm; use Scikit-learn's SelectKBest feature selection method to automatically select key features and reduce redundant information.
[0037] Used to collect the original data of the distribution network, including grid structure, equipment parameters, and load characteristics, the data acquisition module obtains data through sensors, monitoring equipment, etc., and is connected to the model system through a data interface.
[0038] The optimization of data processing and analysis modules can effectively improve the quality of data and the efficiency of optimization algorithms through data preprocessing and feature selection, which not only reduces redundant information but also improves the accuracy of decision-making.
[0039] The user interface module is used to provide a user interaction interface to facilitate users to input parameters, start the optimization process and view the results.
[0040] The Pareto frontier obtained from multi-objective optimization is displayed graphically, with each point representing the objective function value of a planning scheme; interactive charts are used to show the performance changes of planning schemes under different parameters, such as using sliders or hovering the mouse to display detailed information.
[0041] Use data acquisition to monitor and collect the operating data of the distribution network in real time, input the collected data into the multi-objective planning model, build the objective function and constraints, introduce the optimization algorithm module, use the Pareto optimization algorithm to solve the multi-objective planning model, input the results of the multi-objective planning model into the user interface module, and display the planning scheme in a graphical way. Planners view and adjust the displayed planning scheme through the interactive operation platform and finally determine the optimal scheme.
[0042] The present invention integrates the objective function module, constraint condition module, multi-objective optimization algorithm module, decision support module, data processing and analysis module, and user interface module. The system can comprehensively consider various factors in distribution network planning and improve the efficiency and quality of planning work. The objective function module clarifies multiple optimization goals such as investment cost, operating cost, reliability, environmental friendliness and power supply quality to ensure the comprehensiveness of planning. The investment cost module comprehensively considers the cost, installation cost and land use cost of distribution equipment to achieve effective control and prediction of investment cost, which helps planners make more economical decisions. The operating cost module optimizes maintenance cost and energy consumption. loss costs, reduce the daily operating costs of the distribution network, and improve operational efficiency; by introducing the reliability module, the system can build a reliability objective function based on historical data and prediction models, effectively improve the system's annual average power outage time and power outage frequency indicators, reduce the power outage time caused by faults, and improve power supply reliability; the environmental friendliness module realizes a quantitative assessment of environmental friendliness by considering emissions, noise levels and ecological impact factors, which helps to achieve green and sustainable distribution network planning; the power supply quality module improves the quality of power supply by optimizing voltage stability, harmonic levels and power supply reliability indicators, and meets users' needs for high-quality power services.
[0043] The constraint condition module ensures the scientificity and practicality of the planning scheme by comprehensively considering the constraints of power grid safety, node voltage and line capacity, and effectively prevents equipment damage and large-scale power outages; the multi-objective optimization algorithm module adopts the Pareto optimization algorithm, which can effectively find the optimal balance point between multiple objectives and improve the quality of the planning scheme; the data processing and analysis module improves the data quality and the efficiency of the optimization algorithm through data preprocessing and feature selection, providing accurate data support for optimization decisions.
[0044] In summary, the present invention can comprehensively consider multiple planning objectives, provide more comprehensive planning results, and adopt a multi-objective optimization algorithm to obtain a set of non-inferior solutions, providing more choices for decision makers and providing decision support tools to help planners choose the optimal planning solution. Through the data processing and analysis module, the data processing capability of the planning process and the visualization of the results are improved.
[0045] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.
Claims
1. A distribution network multi-objective planning model system, characterized by: The multi-objective planning model system includes an objective function module, a constraint condition module, a multi-objective optimization algorithm module, a decision support module, a data processing and analysis module, and a user interface module; The objective function module is used to define multiple objective functions in the planning process, and the multiple objective functions include investment cost, operation cost, reliability, environmental friendliness and power supply quality; The constraint condition module is used to set the constraint conditions in the planning process, and the constraint conditions include power grid security constraints, node voltage constraints and line capacity constraints; The multi-objective optimization algorithm module uses a multi-objective optimization algorithm to optimize the objective function; The decision support module provides decision support based on the results of the multi-objective optimization algorithm to help planners select the optimal planning solution; The data processing and analysis module is used to process and analyze the data generated during the planning process, provide input for the optimization algorithm and generate visual results; The user interface module is used to provide a user interaction interface to facilitate the user to input parameters, start the optimization process and view the results.
2. A distribution network framework multi-objective planning model system according to claim 1, characterized in that: The investment cost includes the cost of distribution equipment, installation costs and land use costs, expressed as a function of facility capital investment and expected depreciation.
3. A distribution network framework multi-objective planning model system according to claim 1, characterized in that: The operating costs include maintenance costs and energy loss costs.
4. A distribution network framework multi-objective planning model system according to claim 1, characterized in that: The reliability can be measured by the annual average power outage time and power outage frequency indicators of the available system, and the objective function of the reliability can be constructed based on historical data and prediction models.
5. A distribution network framework multi-objective planning model system according to claim 1, characterized in that: The environmental friendliness involves the evaluation of emissions, noise levels and ecological impact, and is expressed through the relationship between emission factors and operating parameters.
6. A distribution network framework multi-objective planning model system according to claim 1, characterized in that: The power supply quality includes voltage stability, harmonic level and power supply reliability indicators.
7. A distribution network framework multi-objective planning model system according to claim 1, characterized in that: The power grid safety constraints include stability constraints and fault current constraints; the node voltage constraints include voltage amplitude constraints and voltage imbalance constraints; Line capacity constraints include thermal stability limit constraints and line loss constraints.
8. A distribution network framework multi-objective planning model system according to claim 1, characterized in that: The multi-objective optimization algorithm module adopts the Pareto optimization algorithm, and the specific method includes the following steps: S1: Generate the initial population, each individual represents a possible solution, sort the population according to Pareto advantage, and select individuals with Pareto advantage to enter the next generation; S2: Generate new offspring by simulating binary crossover and polynomial mutation operations, evaluate the newly generated offspring, compare them with the previous generation, select dominant individuals, and repeat the above process until the stopping condition is met; S3: The termination condition of the algorithm is set to reaching the maximum number of iterations, and the final output is a set of solutions that constitute the Pareto frontier, representing the optimal trade-off between different objectives.
9. A distribution network framework multi-objective planning model system according to claim 1, characterized in that: The decision support module includes a sensitivity analysis function, and the specific method of this function includes the following steps: S11: Analyze the influence of each parameter change on the objective function value and determine which parameters have the greatest influence on the result; S12: Observe the trend of objective function changing with parameters, and understand the sensitivity trend of different parameter adjustments to optimization results; S13: Evaluate the robustness of optimization schemes under different parameter settings and identify those that maintain good performance under parameter fluctuations; S14: Based on the results of sensitivity analysis, adjust the planning scheme to reduce reliance on uncertain parameters and improve the reliability of the scheme.