Power distribution network project cost analysis method

Abstract

The invention discloses a power distribution network project cost analysis method and system, and relates to the technical field of electronic engineering, and the method comprises the following steps: obtaining transformer substation nodes in a power distribution network project, marking each transformer substation node to construct a transformer substation data set, and obtaining data needed by a transformer substation; constructing a distribution substation complexity evaluation model based on a machine learning algorithm according to the substation data to obtain substation complexity; drawing a broken line graph according to the substation cost and the substation complexity; analyzing and processing the broken line graph through a Spearman correlation coefficient to obtain the relation strength between the cost of the transformer substation and the complexity of the transformer substation; according to the method and the device, by obtaining the relation strength between the substation cost and the substation complexity, the problems that the utilization of human resources is extremely insufficient and the errors caused by manual operation are not easy to perceive are solved.

Description

Technical Field

[0001] The present invention relates to the field of electronic engineering technology, and more specifically, to a method for analyzing the cost of a distribution network project. Background Art

[0002] The distribution network project cost analysis collects and analyzes data from completed projects, and conducts a comprehensive assessment based on factors such as engineering technical solutions, equipment selection, line paths, and external construction environment. This analysis not only reflects the cost management situation in the region, but also guides the direction and needs of cost management improvement, and provides decision-making support for the high-quality development of the distribution network.

[0003] Power supply and distribution design has an important impact on project cost. Through the optimization of power supply and distribution system design, a good foundation is provided for project cost, project cost is reduced, and the accuracy and rationality of project cost are improved. Distribution network project cost management and control play a pivotal role in distribution network construction. Through the analysis and control of distribution network project cost, the construction quality of distribution network projects can be ensured, which is directly related to the economic benefits of power companies.

[0004] The above disclosed technical solutions have at least the following technical problems: The traditional cost analysis method of distribution network engineering collects all the data of the project, including design drawings, bill of materials, engineering specifications and construction plans, and uses an automated cost assessment module to apply intelligent algorithms to calculate the preliminary cost of the project, and compares it with historical project data to verify the assessment results, thereby ensuring the accuracy of the project cost. However, the traditional cost analysis method of distribution network engineering requires professional knowledge and skills, which is an extremely inadequate use of human resources. At the same time, due to the increase in the complexity of the distribution network, the overall cost will also change, resulting in the need for manual adjustment of the parameters involved in the analysis process, which greatly reduces work efficiency, and manual operations are prone to data omissions and deviations, which are not easy to detect. In response to the above problems, the present invention proposes a solution. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a method for analyzing the cost of a distribution network project, by obtaining the substation nodes in the distribution network project, marking each substation node to construct a substation data set, and obtaining the data required for the substation; constructing a distribution substation complexity evaluation model based on the substation data based on a machine learning algorithm to obtain the substation complexity; drawing a line graph based on the substation cost and the substation complexity; analyzing and processing the line graph through the Spearman correlation coefficient to obtain the relationship strength between the substation cost and the substation complexity, so as to solve the problems of data omissions and errors caused by insufficient utilization of human resources and manual operations.

[0006] To achieve the above object, the present invention provides the following technical solutions: A method for analyzing the cost of a distribution network project includes: obtaining substation nodes in the distribution network project, marking each substation node to construct a substation data set, and obtaining data required for the substation; constructing a distribution substation complexity evaluation model based on a machine learning algorithm according to the substation data to obtain the substation complexity; drawing a line graph according to the substation cost and the substation complexity; and analyzing and processing the line graph through the Spearman correlation coefficient to obtain the relationship strength between the substation cost and the substation complexity.

[0007] In a preferred embodiment, the data required for the substation are specifically obtained as follows: standard deviation of load, fluctuation rate of load, frequency of load change and amplitude of load change.

[0008] In a preferred embodiment, a specific method for obtaining the standard deviation of the load is as follows: obtain the load data within a single time period, and calculate the average value of the load data based on the load data within the single time period; calculate the deviation of each load data from the average value of the load data based on each load data within the single time period and the average value of the load data; obtain the variance based on the variance formula according to the deviation of each load data from the average value of the load data; and obtain the standard deviation of the load after taking the square root of the variance.

[0009] In a preferred embodiment, the specific method for obtaining the load volatility is as follows: obtain load data within multiple identical time periods and the number of observations in each time period, and calculate the average value of the load data in each time period; calculate the sum of squares of deviations of each load data from the mean based on the average value of the load data in each time period and the load data in each time period based on the deviation formula; calculate the load volatility based on the number of observations in each time period, the average value of the load data in each time period and the load data in each time period based on a preset load volatility.

[0010] In a preferred embodiment, the specific method for obtaining the frequency of load changes is as follows: obtain the load data and time within a preset time period; determine a change threshold based on the load data within the preset time period to determine whether the load change is significant; traverse the load data within the preset time period and record the number of times the load data within the preset time period exceeds the change threshold; obtain the frequency of load changes based on a preset load change frequency formula according to the number of times the load data within the preset time period exceeds the change threshold and the time of the preset time period.

[0011] In a preferred embodiment, the specific method for obtaining the amplitude of the load change is as follows: obtain all load data within a preset time period; compare each data based on all load data within the preset time period to obtain the maximum and minimum values ​​of the load; subtract the minimum value from the maximum value of the load data in the preset time period to obtain the amplitude of the load change.

[0012] In a preferred embodiment, the substation complexity assessment model is constructed based on a machine learning algorithm according to the substation data to obtain the substation complexity, specifically: a substation complexity assessment model is constructed based on a machine learning algorithm according to the standard deviation of the load, the frequency of load changes, the fluctuation rate of the load and the amplitude of load changes to obtain the substation complexity.

[0013] The technical effects and advantages of a distribution network engineering cost analysis method of the present invention are as follows: 1. The present invention clearly shows the relationship between the cost of a substation and its complexity through a line graph, which facilitates a quick understanding of data trends. At the same time, the trend of cost changes with complexity can be more intuitively observed based on the line graph, and key critical points or outliers can be identified.

[0014] 2. The present invention identifies the necessity of adopting new technologies or processes in some cases through the strength of the relationship between the substation cost and the substation complexity, thereby reducing complexity and cost, or adjusts the construction process according to the analysis results, improves construction efficiency, and reduces unnecessary complexity.

[0015] 3. The present invention understands the impact of complexity on cost through the strength of the relationship between substation cost and substation complexity, effectively helps project managers to reasonably allocate resources, ensures that corresponding human, material and financial resources are invested in projects with higher complexity, and sets corresponding budget caps for projects with higher complexity to avoid cost out of control due to insufficient complexity estimation, formulates project budgets more accurately, improves the scientificity and rationality of the budget, provides scientific basis for relevant government departments to formulate reasonable policies, and promotes the standardization and sustainable development of distribution network projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a schematic diagram of the structure of a method for analyzing the cost of a distribution network project. DETAILED DESCRIPTION

[0017] 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.

[0018] Embodiment 1, Figure 1 The invention provides a method for analyzing the cost of a distribution network project.

[0019] S1, obtain the substation nodes in the distribution network project, mark each substation node to build a substation data set, and obtain the data required by the substation.

[0020] In this embodiment, all substation nodes in the distribution network project are obtained, and each substation node is numbered to construct a data set, and the relevant data required by each substation node is obtained at the same time.

[0021] The acquisition of data required for the substation is specifically as follows: The standard deviation of the load is a statistical indicator to measure the degree of load fluctuation and is defined as the average of the square roots of the differences between the load values ​​and their average values.

[0022] The specific method for obtaining the standard deviation of the load is as follows: Obtain the load data within a single time period, and calculate the average value of the load data based on the load data within the single time period; The deviation of each load data from the average value of the load data is calculated according to each load data and the average value of the load data in a single time period; The variance is obtained based on the variance formula according to the deviation of each load data from the average value of the load data; Taking the square root of the variance gives the standard deviation of the loading.

[0023] The specific calculation formula of the standard deviation of the load is as follows:

[0024] The specific calculation formula of the average value of the load is as follows:

[0025] In the formula, is the standard deviation of the load, Represents the total number of data points, that is, the number of collected load data. is the load data value, represents the i-th load data value, is the average value of the load data, It means from i=1 to All The values ​​of are added.

[0026] It should be noted that the standard deviation of the load reflects the degree of dispersion of the load data. The larger the standard deviation, the more severe the load fluctuation, the more difficult the power dispatching, and the increased complexity of management. When power equipment is operated under highly fluctuating load conditions, it will accelerate the wear of the equipment, shorten the service life of the equipment, and increase the subsequent maintenance costs.

[0027] Load volatility, load volatility is a statistical indicator to measure the degree of fluctuation of load data, reflecting the relative amplitude of load changes and used to describe the risk and uncertainty of load.

[0028] The specific method for obtaining the load fluctuation rate is as follows: Obtain load data in multiple identical time periods and the number of observations in each time period, and calculate the average value of load data in each time period; The sum of squares of deviations between each load data and the mean value is calculated based on the average value of the load data in each time period and the load data in each time period based on the deviation formula; The load fluctuation rate is calculated based on the number of observations in each time period, the average value of the load data in each time period, and the load fluctuation rate of the load data in each time period based on a preset load.

[0029] The specific calculation formula of the load fluctuation rate is as follows:

[0030] In the formula, is the load fluctuation rate, represents the volatility of the ith observation period, is the number of observations in each time period, represents the load value of the jth observation point, Indicates the mean of the load values.

[0031] It should be noted that high load fluctuation means an increased demand for backup power and equipment, leading to higher procurement costs. Frequent load fluctuations will lead to additional operating costs, such as frequent starting and stopping of generator sets. Load fluctuations can effectively help assess the financial risks of projects and affect the expected return on investment. According to the fluctuation of load, resources can be reasonably allocated to reduce unnecessary capital occupation and waste. Volatility can be incorporated into the budget model to ensure sufficient liquidity and emergency reserves.

[0032] The frequency of load changes refers to the number of times the load value changes per unit time, usually expressed in Hertz (Hz), which reflects the speed of load fluctuations.

[0033] The specific method for obtaining the frequency of the load change is as follows: Obtain load data and time within a preset time period; Determine a change threshold value based on the load data within a preset time period to determine whether the load change is significant; Traverse the load data within a preset time period and record the number of times the load data within the preset time period exceeds the change threshold; The frequency of load change is obtained based on a preset frequency formula of load change according to the number of times the load data in a preset time period exceeds the change threshold and the time of the preset time period.

[0034] The specific calculation formula for the frequency of load change is as follows:

[0035] In the formula, is the frequency of load changes, is the number of load changes during the observed period, is the observation period (seconds).

[0036] It should be noted that the frequency of load changes can help evaluate the response speed and stability of the power system when the load changes, provide a basis for power dispatch, formulate more effective power generation and load management strategies, assist in identifying the potential risks of high-frequency changes to equipment and networks, and help prevent failures. By understanding the frequency of load changes, the accuracy of the load forecasting model can be improved. High-frequency load changes mean that additional backup equipment is needed, which increases equipment procurement and maintenance costs. At the same time, frequent load changes require more sophisticated dispatch management, which affects operating costs and resource utilization efficiency. Considering the frequency of load changes in the budget can help more accurately predict related expenses, such as power procurement and emergency expenditures.

[0037] The amplitude of load change refers to the maximum change in load value within a certain period of time, expressed as the difference between the highest and lowest values ​​of the load, reflecting the severity of load fluctuations.

[0038] The specific method for obtaining the amplitude of the load change is as follows: Get all load data within a preset time period; Compare each data according to all load data within a preset time period to obtain the maximum and minimum values ​​of the load; The magnitude of load change is obtained by subtracting the minimum value from the maximum value of load data in the preset time period.

[0039] The specific calculation formula of the load change amplitude is as follows:

[0040] In the formula, is the magnitude of the load change, is the maximum value of the load, is the minimum value of the load.

[0041] It should be noted that larger load fluctuations require more backup equipment, which greatly increases the cost of equipment procurement and installation. Frequent large fluctuations will also increase equipment wear and maintenance requirements, thereby increasing long-term operating costs. By identifying scenarios with high-amplitude changes, emergency plans can be developed in advance to reduce risks.

[0042] S2, constructs a distribution substation complexity evaluation model based on the machine learning algorithm according to the substation data to obtain the substation complexity.

[0043] In this embodiment, the substation complexity assessment model is constructed based on the machine learning algorithm according to the standard deviation of the load, the frequency of load changes, the fluctuation rate of the load and the amplitude of the load changes, specifically: The specific calculation formula of the substation complexity evaluation model is as follows:

[0044] In the formula, is the substation complexity, is the observation period, is the magnitude of the load change, represents the maximum value of the load in the i-th observation period, represents the minimum value of the load in the i-th observation period, is the standard deviation of the load, is the load fluctuation rate, represents the volatility of the ith observation period, is the frequency of load changes.

[0045] It should be noted that the substation complexity assessment model helps optimize resource allocation, such as adjusting power generation capacity and energy storage systems, to cope with demand peaks and troughs and reduce overall costs. The substation complexity assessment model more comprehensively reflects the dynamic characteristics of load fluctuations and plays an important role in cost analysis.

[0046] S3, draw a line graph based on the cost of distribution substation and the complexity of substation.

[0047] In this embodiment, the cost of each substation is obtained and the complexity of each substation is obtained according to the substation complexity evaluation model, and a line graph is drawn according to the cost of each substation and the complexity of each substation. The line graph clearly shows the relationship between the cost of the substation and the complexity of the substation, which is convenient for quickly understanding the data trend. At the same time, the trend of the cost changing with the complexity can be more intuitively observed according to the line graph, and the key critical points or abnormal values ​​can be identified.

[0048] S4, the relationship strength between substation cost and substation complexity is obtained by analyzing the line graph through the Spearman correlation coefficient.

[0049] In this embodiment, the line graph is analyzed and processed by the Spearman correlation coefficient to obtain the strength of the relationship between the substation cost and the substation complexity.

[0050] The specific calculation formula for the relationship strength between the substation cost and the substation complexity is as follows:

[0051] The specific calculation formula of the relationship between the substation cost and the substation complexity is as follows:

[0052] In the formula, is the strength of the relationship between substation cost and substation complexity, represents the complexity of the ith substation, represents the average value of complexity, represents the cost of the ith substation, is the average cost of the substation. It's the cost. is the slope, which indicates the change in cost for each unit increase in complexity. is the intercept, which represents the value when the complexity is zero.

[0053] It should be noted that since the strength of the relationship between substation cost and substation complexity is obtained based on the Spearman correlation coefficient, the value range of the relationship strength coefficient between substation cost and substation complexity is [-1, 1]. When r=1, the strength of the relationship between substation cost and substation complexity is positively correlated; when r=-1, the strength of the relationship between substation cost and substation complexity is negatively correlated; when r=0, there is no linear relationship between the strength of the relationship between substation cost and substation complexity.

[0054] It should be noted that the strength of the relationship between the substation cost and the substation complexity can be used to identify the necessity of adopting new technologies or processes in some cases, thereby reducing complexity and cost, or adjusting the construction process based on the analysis results to improve construction efficiency and reduce unnecessary complexity.

[0055] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0056] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0057] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example 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 performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0058] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0059] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0060] Finally: 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 in the protection scope of the present invention.

Claims

1. A method for analyzing the cost of a distribution network project, characterized in that: include: Obtain the substation nodes in the distribution network project, mark each substation node to build a substation data set, and obtain the data required by the substation; According to the substation data, a distribution substation complexity evaluation model is constructed based on the machine learning algorithm to obtain the substation complexity; Draw a line graph based on the substation cost and substation complexity; The strength of the relationship between substation cost and substation complexity is obtained by analyzing the line graph using the Spearman correlation coefficient.

2. A distribution network engineering cost analysis method according to claim 1, characterized in that: The data required for obtaining the substation are specifically: standard deviation of load, fluctuation rate of load, frequency of load change and amplitude of load change.

3. A distribution network engineering cost analysis method according to claim 2, characterized in that: The specific method for obtaining the standard deviation of the load is as follows: Obtain the load data within a single time period, and calculate the average value of the load data based on the load data within the single time period; The deviation of each load data from the average value of the load data is calculated according to each load data and the average value of the load data in a single time period; The variance is obtained based on the variance formula according to the deviation of each load data from the average value of the load data; Taking the square root of the variance gives the standard deviation of the loading.

4. A distribution network engineering cost analysis method according to claim 3, characterized in that: The specific method for obtaining the load fluctuation rate is as follows: Obtain load data in multiple identical time periods and the number of observations in each time period, and calculate the average value of load data in each time period; The sum of squares of deviations between each load data and the mean value is calculated based on the average value of the load data in each time period and the load data in each time period based on the deviation formula; The load fluctuation rate is calculated based on the number of observations in each time period, the average value of the load data in each time period, and the load fluctuation rate of the load data in each time period based on a preset load.

5. A distribution network engineering cost analysis method according to claim 4, characterized in that: The specific method for obtaining the frequency of the load change is as follows: Obtain load data and time within a preset time period; Determine a change threshold value based on the load data within a preset time period to determine whether the load change is significant; Traverse the load data within a preset time period and record the number of times the load data within the preset time period exceeds the change threshold; The frequency of the load change is obtained according to the number of times the load data in the time period exceeds the change threshold and the time of the time period based on a preset frequency formula of the load change.

6. A distribution network engineering cost analysis method according to claim 5, characterized in that: The specific method for obtaining the amplitude of the load change is as follows: Get all load data within a preset time period; Compare each data according to all load data within a preset time period to obtain the maximum and minimum values ​​of the load; The magnitude of load change is obtained by subtracting the minimum value from the maximum value of load data in the preset time period.

7. A distribution network engineering cost analysis method according to claim 6, characterized in that: The complexity evaluation model of distribution substation is constructed based on the machine learning algorithm according to the substation data to obtain the complexity of the substation, which is specifically: According to the standard deviation of load, the frequency of load change, the fluctuation rate of load and the amplitude of load change, a substation complexity evaluation model is constructed based on a machine learning algorithm to obtain the substation complexity; The specific calculation formula of the substation complexity evaluation model is as follows: In the formula, is the substation complexity, is the observation period, is the magnitude of the load change, represents the maximum value of the load in the i-th observation period, represents the minimum value of the load in the i-th observation period, is the standard deviation of the load, is the load fluctuation rate, represents the volatility of the ith observation period, is the frequency of load changes.

8. A distribution network engineering cost analysis method according to claim 7, characterized in that: According to the cost of distribution substation and the complexity of substation, a line graph is drawn, which is as follows: Obtain the cost of each substation and obtain the complexity of each substation based on the substation complexity assessment model; A line graph is drawn based on the cost of each substation and the complexity of each substation.

9. A distribution network engineering cost analysis method according to claim 8, characterized in that: The specific calculation formula of the standard deviation of the load is as follows: The specific calculation formula of the average value of the load is as follows: The specific calculation formula of the load fluctuation rate is as follows: The specific calculation formula for the frequency of load change is as follows: The specific calculation formula for the amplitude of the load change is as follows: In the formula, is the standard deviation of the load, Represents the total number of data points, that is, the number of collected load data. is the load data value, represents the i-th load data value, is the average value of the load data, It means from i=1 to All Add the values ​​of is the load fluctuation rate, represents the volatility of the ith observation period, is the number of observations in each time period, represents the load value of the jth observation point, represents the mean value of the load value, is the frequency of load changes, is the number of load changes during the observed period, is the observation period (seconds), is the magnitude of the load change, is the maximum value of the load, is the minimum value of the load.

10. A distribution network engineering cost analysis method according to claim 9, characterized in that: The specific calculation formula for the relationship strength between the substation cost and the substation complexity is as follows: The specific calculation formula for the relationship between the substation cost and the substation complexity is as follows: In the formula, is the strength of the relationship between substation cost and substation complexity, represents the complexity of the ith substation, represents the average value of complexity, represents the cost of the ith substation, is the average cost of the substation. It's the cost. is the change in cost for each unit increase in complexity, Represents the value when the complexity is zero.

Images