Power distribution project cost management and control method, device and equipment

Abstract

The invention discloses a power distribution project cost management and control method, device and equipment, and relates to the technical field of project cost management and control, and the method comprises the following steps: coding a cable, and constructing a cost reference library based on the cable code; based on the cost reference library, carrying out optimization calculation on the cable laying path to obtain the installation cost, and quantifying the uncertainty of future operation loss to obtain the operation loss cost; constructing an optimization target in combination with the installation cost and the operation loss cost, and solving the optimization target to obtain the cable optimal area of each cable section; and correcting the optimal area of the cable based on the construction data. The method is used for solving the problem of poor adaptability caused by incomplete consideration of an existing power distribution project cost management and control model.

Description

Technical Field

[0001] This invention relates to the field of engineering cost control technology, and more specifically, to methods, devices and equipment for controlling the cost of power distribution projects. Background Technology

[0002] As a crucial link connecting users in the power system, the distribution network is characterized by large-scale construction, complex technology, and highly geographically dispersed nature. With the large-scale integration of renewable energy, the widespread adoption of electric vehicle charging infrastructure, and the ever-increasing demands of users for power supply reliability, the planning and construction of modern distribution networks are rapidly developing towards intelligence and flexibility. This trend has introduced significant uncertainties into distribution network engineering in areas such as equipment selection, route planning, and handling distributed power source integration. Traditional cost control methods based on historical data and static quotas struggle to accurately quantify the impact of these dynamic factors on initial investment and long-term operating costs, easily leading to budget deviations and resulting in low investment efficiency or high technical costs.

[0003] Currently, the core challenge facing distribution network project cost management lies in shifting from post-event accounting to pre-event optimization. Project costs not only include initial equipment purchase and installation costs but also need to encompass implicit costs such as operating losses and maintenance expenses throughout the equipment's lifecycle. For example, the selection of cable cross-sections involves a significant trade-off between installation costs and operating loss costs. However, existing methods lack the ability to collaboratively analyze and predict multi-dimensional dynamic factors such as market price fluctuations, load growth trends, and complex construction environments, leading to a disconnect between optimization models and actual project conditions. Therefore, developing an intelligent cost control technology that can integrate multi-source data, dynamically assess costs, and provide optimal technical cost solutions during the design phase has become an urgent need to improve the investment efficiency and operational effectiveness of distribution networks.

[0004] For example, the invention patent announcement CN111079982B discloses a method, system, medium, and electronic device for planning cable paths in a wind farm. The planning method includes the following steps: obtaining the operating parameters of the wind farm; constructing a first function using the total unit cost of cables with different cross-sectional areas, the operating parameters, and a preset maximum number of wind turbines that the cable can carry; calculating the total unit cost corresponding to different cross-sectional areas, and taking the cross-sectional area with the lowest total unit cost as the target cross-sectional area; constructing a second function using the total cable cost of the wind farm, the cable path, the target cross-sectional area, the preset maximum number of wind turbines that the cable can carry, and the operating parameters; calculating the total cable cost corresponding to different cable paths, and determining the cable path with the lowest total cable cost as the target cable path.

[0005] For example, the invention patent announcement CN117913881B, entitled "Economic Optimization Method for AC / DC Cable Transmission Schemes under Multiple Voltage Levels in Deep-Sea Areas," includes the following steps: S1, Listing Variable Ranges: Obtaining the installed capacity S and transmission distance l; S2, Listing Voltage Levels: Listing the voltage levels of AC and DC cables based on existing cable transmission projects; S3, Calculating the Number of Circuits; S4, Calculating the Model; S5, Calculating the Optimal Value; S6, Obtaining the Preferred Scheme.

[0006] The above-disclosed technical solutions have at least the following technical problems: Existing cost control methods for power distribution projects are based on static parameters, lacking response to dynamic factors, and do not involve modeling and quantifying the operational losses and uncertainties throughout the cable's entire life cycle.

[0007] To address the above problems, this invention proposes a solution. Summary of the Invention

[0008] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a method, apparatus, and equipment for controlling the cost of power distribution projects. By integrating dynamic programming and curve fitting, the method quantifies the cable installation cost and operating loss cost, constructs and solves an optimization objective based on the cable installation cost and operating loss cost, and corrects the optimal cable area. This addresses the problem of poor adaptability caused by the incomplete consideration of existing power distribution project cost control models.

[0009] To achieve the above objectives, the present invention provides the following technical solution: The method for controlling the cost of power distribution projects includes the following steps: coding cables and building a cost benchmark library based on the cable codes; optimizing the cable laying path based on the cost benchmark library to obtain the installation cost, and obtaining the operating loss cost by quantifying the uncertainty of future operating losses; constructing an optimization objective by combining the installation cost and the operating loss cost, and solving the optimization objective to obtain the optimal cable area for each cable section; and correcting the optimal cable area based on construction data.

[0010] In a preferred embodiment, the step of encoding the cable and constructing a cost benchmark library based on the cable code includes: uniformly encoding the cable according to a pre-built encoding rule to obtain the cable code; acquiring historical engineering data and market price data, and constructing a cost benchmark library in combination with the cable code; adjusting the benchmark cost of the corresponding cable through Kalman filtering when the fluctuation of the market price data exceeds a preset threshold; and correcting the cost benchmark library according to the acquired construction environment data.

[0011] In a preferred embodiment, the step of optimizing the cable laying path based on the cost benchmark library to obtain the installation cost, and obtaining the operating loss cost by quantifying the uncertainty of future operating losses, includes: calculating the cable installation cost based on the cost benchmark library through dynamic programming; and performing curve fitting on electricity price fluctuations and load changes based on the cost benchmark library to obtain the operating loss cost and the operating cost confidence interval.

[0012] In a preferred embodiment, the step of calculating the cable installation cost based on a cost benchmark library through dynamic programming includes: discretizing the cable installation path into cable segments; constructing an installation cost state transition equation and calculating the cable installation cost based on the cable segments; introducing installation constraints and excluding paths that do not meet the installation constraints, wherein the installation constraints include path length limits, current carrying capacity constraints, and voltage drop constraints.

[0013] In a preferred embodiment, the step of performing curve fitting on electricity price fluctuations and load changes based on a cost benchmark library to obtain operating loss costs and operating cost confidence intervals includes: constructing an electricity price fluctuation model and a load change model, generating a price-load combination scenario through random sampling; calculating simulated operating loss costs based on the price-load combination scenario; and obtaining operating loss costs and operating cost confidence intervals based on the simulated operating loss costs.

[0014] In a preferred embodiment, the step of constructing an optimization objective by combining installation cost and operating loss cost, and solving for the optimization objective to obtain the optimal cable area for each cable segment, includes: constructing a comprehensive cost model based on installation cost and operating loss cost, and taking the minimization of comprehensive cost as the optimization objective; solving for the optimization objective to obtain the optimal cable area; and verifying the calculated optimal cable area under comprehensive constraints, including current carrying capacity constraints, voltage drop constraints, and thermal stability constraints.

[0015] In a preferred embodiment, the step of solving the optimization objective to obtain the optimal cable area includes: randomly generating an initial population and setting initial parameters and an external archive, wherein the external archive is used to store the optimal solution during the iteration process; calculating the installation cost and operating loss cost of each individual in the population, stratifying the population based on non-dominated sorting and the obtained crowding degree, and updating the external archive; selecting a leader individual from the external archive, and updating the positions of non-leader individuals in the population according to the position of the leader individual; iterating until a preset convergence condition is met, and selecting the best compromise solution from the final external archive as the optimal cable area based on satisfaction.

[0016] In a preferred embodiment, the step of correcting the optimal cable area based on construction data includes: selecting the cable type closest to and not less than the optimal cable area from the cable specification library; obtaining a comprehensive anomaly probability based on the construction data using a pre-built random forest-LSTM hybrid architecture; triggering an anomaly warning when the comprehensive anomaly probability exceeds a preset probability threshold, and correcting the optimal cable area.

[0017] The power distribution project cost control device includes: a benchmark library construction module, used to encode cables and build a cost benchmark library based on the cable codes; a cost calculation module, used to optimize the cable laying path to obtain the installation cost based on the cost benchmark library, and obtain the operation loss cost by quantifying the uncertainty of future operation losses; an optimal area calculation module, used to combine the installation cost and operation loss cost to construct an optimization objective, and solve the optimization objective to obtain the optimal cable area for each cable section; and a final correction module, used to correct the optimal cable area based on construction data.

[0018] An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the power distribution project cost control method.

[0019] The technical effects and advantages of the power distribution engineering cost control method, device and equipment of the present invention are as follows: This invention addresses the problem of lagging response to market price fluctuations in traditional static cost benchmark libraries by constructing a dynamic cost benchmark library; it quantifies cable installation and operation loss costs by integrating dynamic programming and curve fitting; it achieves optimal cable area decision based on cable installation and operation loss costs by constructing and solving an optimization problem, thus overcoming the energy waste caused by traditional methods; and it transforms cost control from passive post-event accounting to proactive in-event intervention by using machine learning to provide early warnings of anomalies during construction and timely correcting the optimal cable area, effectively solving the problem of poor adaptability caused by incomplete consideration in existing power distribution engineering cost control models. Attached Figure Description

[0020] Figure 1 This is a schematic diagram of the power distribution engineering cost control method provided in an embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram of the power distribution engineering cost control device provided in an embodiment of the present invention.

[0022] Figure 3This is a schematic diagram of the structure of a power distribution engineering cost control device provided in an embodiment of the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0024] Example 1, Figure 1 The present invention provides a method for controlling the cost of power distribution projects, comprising the following steps: S1, encode the cables and build a cost benchmark library based on the cable codes; S2, based on the cost benchmark library, optimizes the cable laying path to obtain the installation cost, and obtains the operating loss cost by quantifying the uncertainty of future operating losses; S3, combine installation cost and operating loss cost to construct optimization objective, and solve the optimization objective to obtain the optimal cable area for each cable section; S4, based on construction data, corrects the optimal cable area.

[0025] This embodiment addresses the problem of lagging response to market price fluctuations in traditional static quota libraries by constructing a dynamic cost benchmark library. It quantifies cable installation and operation loss costs by integrating dynamic programming and curve fitting. By constructing and solving an optimization problem based on these costs, it achieves the optimal cable area decision for overall cost, overcoming the energy waste caused by traditional methods. Furthermore, it uses machine learning to provide early warnings of construction anomalies and promptly correct the optimal cable area, transforming cost control from passive post-construction accounting to proactive in-process intervention. This effectively solves the problem of poor adaptability caused by incomplete consideration in existing power distribution engineering cost control models.

[0026] S1, encode the cable and build a cost benchmark library based on the cable code.

[0027] In this embodiment, the process of encoding the cable and constructing a cost benchmark library based on the cable encoding includes: Cable codes are obtained by uniformly encoding cables based on pre-built encoding rules; Acquire historical engineering data and market price data, and combine them with cable coding to build a cost benchmark database; When market price data fluctuations exceed a preset threshold, the base cost of the corresponding cable is adjusted using Kalman filtering. The cost benchmark database was revised based on the acquired construction environment data.

[0028] In this embodiment, the process of uniformly encoding the cable based on pre-built encoding rules to obtain the cable code specifically involves: The coding rules include type coding segment, voltage level coding segment, conductor material coding segment, and nominal cross-sectional area coding segment; The cable is coded according to the parameters of the target cable.

[0029] In this embodiment, the cost benchmark database specifically includes cable codes, material data, real-time material prices, and construction environment-related data.

[0030] In this embodiment, when the fluctuation of market price data exceeds a preset threshold, the benchmark cost of the corresponding cable is adjusted by Kalman filtering, specifically as follows: In each update cycle, based on the state estimate of the previous moment, the benchmark cost prior estimate and error covariance of the current moment are predicted by using a preset state transition matrix; Real-time monitoring of market price data; calculation of the estimated difference between the observed market price and the prior estimate of the current benchmark cost; when the estimated difference exceeds a preset difference threshold, updating is performed using Kalman filtering.

[0031] In this embodiment, the update via Kalman filtering specifically refers to: Calculate the Kalman gain, fuse the prior estimate of the benchmark cost with the observed market price, obtain the posterior estimate of the benchmark cost at the current time, and update the error covariance; Update the posterior estimate of the current benchmark cost to the dynamic cost benchmark library.

[0032] In this embodiment, the step of correcting the cost benchmark database based on the acquired construction environment data specifically involves: The acquired construction environment data is quantified into corresponding environmental impact values, including geological conditions, topographic slope, and spatial data. Based on the environmental impact value, the comprehensive cost adjustment coefficient is calculated using a pre-constructed environmental-cost impact model; Based on the comprehensive cost adjustment coefficient, the benchmark cost of the corresponding cable code in the cost benchmark database is multiplied and corrected.

[0033] In this embodiment, the environment-cost impact model specifically employs a multilayer perceptron, trained based on historical engineering data, to characterize the mapping relationship between construction environment data and benchmark cost.

[0034] It should be noted that this embodiment uses a unified coding rule to uniquely identify the core parameters of the cable, introduces a Kalman filter algorithm to dynamically update the cost benchmark library, and corrects the benchmark cost according to the construction environment, which significantly improves the anti-interference ability and timeliness of the benchmark cost, and enhances the adaptability of cost data under different geographical, climatic and construction conditions.

[0035] S2, based on the cost benchmark library, optimizes the cable laying path to obtain the installation cost, and obtains the operating loss cost by quantifying the uncertainty of future operating losses.

[0036] In this embodiment, the installation cost is obtained by optimizing the cable laying path based on the cost benchmark library, and the operating loss cost is obtained by quantifying the uncertainty of future operating losses, including: Based on the cost benchmark library, the installation cost of cables is calculated through dynamic programming; Based on the cost benchmark library, curve fitting was performed on the electricity price fluctuations and load changes to obtain the operating loss cost and the confidence interval of the operating cost.

[0037] In this embodiment, the calculation of cable installation cost based on a cost benchmark library using dynamic programming includes: Discretize the cable installation path into cable segments; Construct an installation cost state transition equation and calculate the cable installation cost based on cable sections; Introduce path length constraints, current carrying capacity constraints, and voltage drop constraints to exclude paths that do not meet the constraints.

[0038] In this embodiment, the installation cost state transition equation is specifically formulated as follows:

[0039] In the formula, For the calculation to proceed to the th Each section uses specifications The minimum cost, For the calculation to proceed to the th Each section uses specifications The minimum cost, For the first Specifications for each section The basic cost required for the cable, The cost of converting between the two specifications.

[0040] In this embodiment, excluding paths that do not meet the constraints specifically means excluding paths that do not meet any of the constraints.

[0041] In this embodiment, the step of performing curve fitting on electricity price fluctuations and load changes based on the cost benchmark library to obtain operating loss costs and operating cost confidence intervals is specifically as follows: Construct electricity price fluctuation models and load change models, and generate price-load combination scenarios through random sampling; Calculate and simulate operating loss costs based on price-load combination scenarios; The operating loss cost and the confidence interval of the operating cost are obtained based on the simulated operating loss cost.

[0042] In this embodiment, the electricity price fluctuation model is a geometric Brownian motion model, and the load change model is a mean regression model.

[0043] In this embodiment, the calculation of simulated operating loss cost based on the price-load combination scenario is specifically formulated as follows:

[0044] In the formula, For the first The electricity price in this simulation. For the first The load in this simulation For resistance, Indicates the first Year, For the first The simulation run loss cost of this simulation. This represents the number of hours of maximum load loss.

[0045] It should be noted that the maximum load loss hours are the number of hours required to generate the same power loss as the actual changing load, assuming that the cable always operates at maximum load.

[0046] In this embodiment, the specific formula for obtaining the operating loss cost and the operating cost confidence interval based on the simulated operating loss cost is as follows:

[0047] In the formula, To simulate the total number of times, This represents the expected value of operating loss costs.

[0048] In this embodiment, the confidence interval is obtained based on the standard deviation of the simulated operating loss cost.

[0049] It should be noted that this embodiment discretizes the cable installation path and constructs a state transition equation, obtains the installation cost through a dynamic programming algorithm, and obtains the operating loss cost by fitting the electricity price fluctuation and load change curves based on geometric Brownian motion and mean regression. This provides a highly reliable and adaptable data foundation for subsequent decision-making on the optimal cable area, significantly improving the scientific and refined level of cost control in power distribution projects.

[0050] S3, combining installation cost and operating loss cost to construct an optimization objective, and solving the optimization objective to obtain the optimal cable area for each cable section.

[0051] In this embodiment, the step of constructing an optimization objective by combining installation cost and operating loss cost, and solving for the optimization objective to obtain the optimal cable area for each cable section, includes: Based on installation costs and operating losses, a comprehensive cost model is constructed, with the optimization objective being the minimization of comprehensive costs. The optimal cable area is obtained by solving the optimization objective. The calculated optimal cable area is verified by a comprehensive set of constraints, including current carrying capacity constraints, voltage drop constraints, and thermal stability constraints.

[0052] In this embodiment, the comprehensive cost model is specifically as follows:

[0053] In the formula, The present value of total costs For installation costs, This is the preset discount rate.

[0054] In this embodiment, the step of solving for the optimization objective to obtain the optimal cable area includes: An initial population is randomly generated, and initial parameters and an external archive are set. The external archive is used to store the optimal solution during the iteration process. Calculate the installation cost and operating loss cost of each individual in the population, and based on the non-dominated sorting and the crowding of acquisition, stratify the population and update the external archive. Select a leader from the external archive, and update the positions of non-leader individuals in the population based on the leader's position; Iterate until the preset convergence condition is met, and select the best compromise solution from the final external archive as the optimal cable area based on the satisfaction level.

[0055] In this embodiment, the external archive is used to store the optimal solution during the iteration process, specifically as follows: When a new individual is dominated by at least one resident delimiter in a save file, the new individual is not allowed to enter the save file; When a new individual dominates one or more solutions in the archive, the new individual enters the archive and removes the dominated solutions from the archive. When there is no mutual domination relationship between the new individual and the solutions in the archive, add the new individual to the archive; When the archive is full, remove the solution with the highest congestion and insert the new solution into the position with the lowest congestion.

[0056] In this embodiment, the method for selecting the leader is specifically a roulette wheel betting method.

[0057] In this embodiment, selecting the optimal compromise solution as the optimal cable area based on satisfaction specifically means: Based on the final external archive, the installation cost and operating loss cost are mapped to the range of [0,1] through fuzzy computation to obtain the satisfaction of each solution with the optimization objective; The overall satisfaction level is obtained by weighted fusion of the satisfaction levels of each objective, and the solution with the highest overall satisfaction level is selected as the optimal compromise solution.

[0058] It should be noted that in a non-dominated sorting, if one solution dominates another, it means that it is no worse than the latter in all objectives and is better in at least one objective. By sorting, the solutions are divided into different non-dominated levels.

[0059] It should be noted that crowding is used to evaluate the distribution density of solutions in the target space, and prioritizing solutions that are sparser in the surrounding area can maintain the diversity of solutions.

[0060] It should be noted that this embodiment integrates installation costs and operating loss costs through a comprehensive cost model, and takes minimizing this comprehensive cost as the optimization objective. The optimal cable area is obtained by solving the optimization problem, and the calculated optimal cable area is verified by current carrying capacity, voltage drop and thermal stability constraints. Based on the satisfaction level, the best compromise solution is selected from the solution set, so that the decision-making process can flexibly balance the initial investment and long-term operating costs. The output results have both global optimality and engineering practicality, which significantly improves the level of precision in cable cost control.

[0061] S4, based on construction data, corrects the optimal cable area.

[0062] In this embodiment, the step of correcting the optimal cable area based on construction data includes: Based on the optimal cable area, select the cable type from the cable specification library that is closest to and not less than that value; Based on construction data, a comprehensive anomaly probability is obtained through a pre-built random forest-LSTM hybrid architecture; An anomaly warning is triggered when the overall anomaly probability exceeds a preset probability threshold, and the optimal cable area is corrected.

[0063] In this embodiment, the process of obtaining the comprehensive anomaly probability based on construction data using a pre-built random forest-LSTM hybrid architecture specifically involves: Extract static feature vectors and dynamic time series from construction data; The static feature vector includes cable type, laying method and environmental parameters, and the dynamic time series includes current time series data and temperature time series data. The static feature vector is input into a pre-built random forest model to obtain the static anomaly probability; By inputting the dynamic time series data into a pre-built LSTM model, dynamic anomaly probabilities are obtained. The static anomaly probability and the dynamic anomaly probability are weighted and fused to obtain the comprehensive anomaly probability.

[0064] In this embodiment, the correction of the optimal cable area specifically involves: The anomaly type is determined based on the output of the random forest-LSTM hybrid architecture; The anomaly types include load characteristic anomalies, line loss characteristic anomalies, or environmental characteristic anomalies; If the load characteristics are abnormal, update the load parameters in the operating loss cost model with the actual monitored load data, and recalculate and correct the optimal cable area. If the line loss characteristics are abnormal, the cable resistance or environmental parameters are inferred and updated based on real-time data, and the operating loss cost model and the optimal cable area are corrected. If the environmental characteristics are abnormal, the prediction model is retrained based on historical construction data and the new optimal cable area is calculated.

[0065] It should be noted that this embodiment combines static feature vectors with dynamic time series for anomaly detection. When the overall anomaly probability exceeds the limit, the root cause of the anomaly is determined and targeted corrections are made. This transforms the traditional static, experience-driven cost control into a data-driven, self-learning, and dynamically adjustable intelligent system. This effectively avoids engineering rework or long-term low energy efficiency caused by design assumption deviations or environmental changes, and significantly improves the investment efficiency and operational safety of power distribution projects.

[0066] Example 2, Figure 2 The present invention provides a power distribution engineering cost control device, comprising: The benchmark library construction module is used to encode cables and build a cost benchmark library based on the cable codes; The cost calculation module is used to optimize the cable laying path based on the cost benchmark library to obtain the installation cost, and to obtain the operating loss cost by quantifying the uncertainty of future operating losses. The optimal area calculation module is used to construct an optimization objective by combining installation cost and operating loss cost, and solve the optimization objective to obtain the optimal cable area for each cable section; The final correction module is used to correct the optimal cable area based on construction data.

[0067] Example 3: This example provides a computer electronic device, such as... Figure 3 As shown, the electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute the power distribution project cost control method.

[0068] The processor is the control core of the electronic device. It connects various components of the electronic device through various interfaces and lines. It performs various functions of the electronic device and processes data by running or executing programs or modules stored in the memory and calling data stored in the memory.

[0069] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0070] It should be understood that the embodiments described are for illustrative purposes only and are not limited to this structure in the scope of the patent application.

[0071] The computer program stored in the memory of the electronic device is a combination of multiple instructions. When run in the processor, it can implement the steps in the above-mentioned power distribution project cost control method.

[0072] Specifically, the implementation system of the processor for the above instructions can be referred to the description of the relevant steps in the corresponding embodiments of the accompanying drawings, which will not be repeated here.

[0073] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0074] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0075] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0076] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0077] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0078] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A power distribution engineering cost management and control method, characterized in that, The method comprises the following steps: coding the cable and constructing a cost benchmark library based on the cable code; based on the cost benchmark library, performing optimization calculation on the cable laying path to obtain installation cost, and quantifying the uncertainty of future operation loss to obtain operation loss cost; combining the installation cost and the operation loss cost to construct an optimization target, and solving the optimization target to obtain the optimal cable area of each cable section; based on construction data, correcting the optimal cable area.

2. The power distribution engineering cost management method of claim 1, wherein, The cable is coded, and a cost benchmark library is constructed based on the cable code, which comprises: based on the pre-constructed coding rule, the cable is uniformly coded to obtain the cable code; obtain historical engineering data and market price data, and construct a cost benchmark library based on the cable code; when the fluctuation of the market price data exceeds the preset threshold, adjust the benchmark cost of the corresponding cable through Kalman filtering; correct the cost benchmark library according to the obtained construction environment data.

3. The power distribution engineering cost management method of claim 2, wherein, Based on the cost benchmark library, the installation cost of the cable is calculated by dynamic programming, and the operation loss cost and the operation cost confidence interval are obtained by curve fitting of the price fluctuation and the load change. The installation cost of the cable is calculated based on the cost benchmark library, which comprises: discretize the cable installation path into cable sections; 4. The power distribution engineering cost management method according to claim 3, wherein, construct an installation cost state transition equation to calculate the installation cost of the cable based on the cable sections; introduce installation constraint conditions to exclude paths that do not meet the installation constraint conditions, the installation constraint conditions including path length limit constraint, current-carrying capacity constraint and voltage drop constraint. The price fluctuation model and the load change model are constructed, and the price-load combination scenarios are generated by random sampling; based on the price-load combination scenarios, the simulated operation loss cost is calculated; 5. The power distribution engineering cost management method according to claim 4, wherein, according to the simulated operation loss cost, the operation loss cost and the operation cost confidence interval are obtained. The installation cost and the operation loss cost are combined to construct an optimization target, and the optimal cable area of each cable section is obtained by solving the optimization target, which comprises: based on the installation cost and the operation loss cost, a comprehensive cost model is constructed, and the minimization of the comprehensive cost is taken as the optimization target; solving the optimization target to obtain the optimal cable area; 6. The power distribution engineering cost management method according to claim 5, wherein, the calculated optimal cable area is subjected to comprehensive constraint condition verification, and the comprehensive constraint conditions include current-carrying capacity constraint, voltage drop constraint and thermal stability constraint. The optimal cable area is obtained by solving the optimization target, which comprises: randomly generating an initial population and setting initial parameters and external archives, the external archives are used to save the optimal solution in the iteration process; calculate the installation cost and the operation loss cost of each individual in the population, and stratify the population based on the non-dominated sorting and the obtained crowding degree, and update the external archives; 7. The power distribution engineering cost management method of claim 6, wherein, select a leader individual from the external archives, and update the position of non-leader individuals in the population according to the position of the leader individual; ​ ​ ​ Iterate to meet the preset convergence condition, select the best compromise solution as the optimal cable area according to the satisfaction degree from the final external archive.

8. The power distribution engineering cost management method of claim 7, wherein, The optimal cable area is corrected based on the construction data, including: According to the optimal cable area, select the cable type closest to and not less than the value in the cable specification library; Based on the construction data, the comprehensive abnormal probability is obtained through the pre-constructed random forest-LSTM hybrid architecture; When the comprehensive abnormal probability is greater than the preset probability threshold, an abnormal warning is triggered, and the optimal cable area is corrected.

9. An apparatus using the power distribution engineering cost control method according to any one of claims 1-8, comprising: A reference library construction module for encoding the cable and constructing a cost reference library based on the cable encoding; A cost calculation module for calculating the installation cost based on the cost reference library, and obtaining the operation loss cost by quantifying the uncertainty of future operation loss; An optimal area calculation module for constructing an optimization target by combining the installation cost and the operation loss cost, and solving the optimization target to obtain the optimal cable area of each cable section; A final correction module for correcting the optimal cable area based on the construction data.

10. An electronic device, comprising: The electronic device comprises: At least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the power distribution engineering cost control method according to any one of claims 1-8.

Images