A method for predicting the cost of distribution network projects based on big data

Abstract

The present invention discloses a method for predicting the construction cost of a distribution network project based on big data, which relates to the technical field of electric power engineering, and comprises the following steps: obtaining historical power supply and demand data of a distribution room, and obtaining historical power impact data; constructing a power impact model based on a machine learning algorithm according to the historical power impact data and the power supply and demand data; obtaining distribution network project document data to be predicted, and obtaining optimal cable data based on the power impact model; selecting a cable model according to the optimal cable data to predict the cost required for the distribution room cable; the present application solves the problem that the prediction results are not objective and accurate enough, lack scientificity and systematicity, and have a weak ability to adjust the model when facing changing project requirements or market conditions by establishing a power impact model.

Description

Technical Field

[0001] The present invention relates to the field of electric power engineering technology, and more specifically, to a method for predicting the cost of a distribution network project based on big data. Background Art

[0002] With the acceleration of urbanization and the widespread use of renewable energy, the construction and transformation of distribution networks, as a key component of the power system, are facing growing demand. Accurate project cost forecasting is of great significance to the rational allocation of resources, effective budget control and smooth implementation of projects, and the rapid development of big data technology has provided new opportunities for project cost forecasting. By collecting, storing and analyzing massive amounts of data, potential patterns and trends can be discovered, thereby improving the accuracy and reliability of forecasts. With the continuous advancement of data technology, future project cost forecasting will be more scientific and accurate, providing strong support for the construction and management of distribution networks.

[0003] The above disclosed technical solutions have at least the following technical problems:

[0004] Traditional engineering cost forecasting methods mainly rely on empirical methods and historical data comparison, which can lead to different problems. For example, data from different departments and systems cannot be effectively integrated, resulting in information asymmetry; empirical methods rely too much on the subjective experience of engineers, resulting in the forecast results being not objective and accurate, lacking scientificity and systematicity; and the ability to adjust the model is weak when facing changing project requirements or market conditions. 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 distribution network project cost prediction method based on big data, by acquiring the distribution network project document data to be predicted, and obtaining the optimal cable data based on the power impact model; selecting the cable model according to the optimal cable data, and obtaining the required cable length and the selling price of the selected cable model, and obtaining the cost of the cable in the distribution network project according to the selling price of the cable and the required cable length, so as to solve the problems that data from different departments and systems cannot be effectively integrated, resulting in information asymmetry; the prediction results are not objective and accurate, lack scientificity and systematicity; and the ability to adjust the model is weak when facing changing project requirements or market conditions.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method for predicting the cost of a distribution network project based on big data includes: obtaining historical power supply and demand data of distribution rooms, and obtaining historical power impact data; constructing a power impact model based on a machine learning algorithm according to the historical power impact data and the power supply and demand data; obtaining document data of a distribution network project to be predicted, and obtaining optimal cable data based on the power impact model; selecting a cable model according to the optimal cable data, and obtaining the required cable length and the selling price of the selected cable model, and obtaining the cost required for the cable in the distribution network project according to the selling price of the cable and the required cable length.

[0008] In a preferred embodiment, the historical power impact data obtained includes cable heat dissipation correction factor, power loss, grid load and voltage drop.

[0009] In a preferred embodiment, the specific steps for obtaining the cable heat dissipation correction coefficient are as follows: obtain the ambient temperature of the cable and the resistance at the ambient temperature; obtain the actual maximum temperature of the cable during use and the resistance at the maximum temperature; calculate based on a preset temperature coefficient formula according to the ambient temperature of the cable and the resistance at the ambient temperature, as well as the actual maximum temperature of the cable during use and the resistance at the maximum temperature, to obtain the temperature coefficient of the cable; calculate based on a preset cable heat dissipation correction coefficient formula according to the ambient temperature of the cable, the actual maximum temperature of the cable during use and the temperature coefficient of the cable, to obtain the cable heat dissipation correction coefficient.

[0010] In a preferred embodiment, the specific steps for obtaining the power loss are as follows: obtain the cross-sectional area of ​​the cable to be tested and the length of the cable to be tested; measure the resistance of the cable section by an ohmmeter, and calculate the resistivity of the cable based on the resistivity formula according to the cross-sectional area of ​​the cable, the length of the cable and the resistance of the cable; obtain the rated current of the cable to be tested by a cable current carrying capacity measurement method; and obtain the power loss of the cable based on a preset power loss formula according to the obtained cross-sectional area of ​​the cable, the length of the cable, the resistivity of the cable and the rated current of the cable.

[0011] In a preferred embodiment, the specific steps for obtaining the grid load of the cable are as follows: obtain the rated voltage of the cable to be tested by a withstand voltage test method; obtain the rated current of the cable to be tested by a cable current carrying capacity measurement method; use a phase measuring instrument to measure the phase difference of the cable under rated voltage and rated current; and obtain the grid load by calculating based on a preset grid load formula according to the rated voltage of the cable, the rated current of the cable and the phase difference of the cable.

[0012] In a preferred embodiment, the specific steps for obtaining the voltage drop are as follows: obtain a section of the cable to be tested, and obtain the resistance temperature coefficient of the cable to be tested through a resistance temperature coefficient measurement experiment; obtain the resistance of the cable to be tested at a standard temperature and the resistance in a stable state with power on through an ohmmeter, and record the cable temperature when these two resistances are measured to obtain the temperature difference; calculate the resistance change caused by temperature change based on the resistance of the cable at the standard temperature, the resistance temperature coefficient and the cable temperature difference based on a preset resistance change formula; obtain the additional resistance of the cable through an additional resistance test, and obtain the length and rated current of the cable to be tested; calculate the voltage drop of the cable to be tested based on the preset voltage drop calculation formula according to the length of the cable, the rated current of the cable, the resistance change caused by temperature change, the resistance at standard temperature and the additional resistance of the cable.

[0013] In a preferred embodiment, the construction of the power impact model based on the machine learning algorithm according to the historical power impact data and the power supply and demand data is specifically: the power impact model is constructed based on the machine learning algorithm according to the cable heat dissipation correction coefficient, power loss, power supply and demand data, grid load and voltage drop.

[0014] In a preferred embodiment, the method of obtaining the distribution network engineering document data to be predicted and obtaining the optimal cable data based on the power impact model is specifically as follows: obtaining the distribution network engineering document data to be predicted including the power supply and demand data of the distribution room, the rated current of the cable, the resistance of the cable and the power line; and obtaining the power impact coefficient based on the power impact model through the distribution network engineering document data.

[0015] Technical effects and advantages of a distribution network engineering cost prediction method based on big data in the present invention:

[0016] 1. The present invention obtains historical power supply and demand data and power impact data, and uses machine learning algorithms to build a power impact model to achieve accurate prediction of the distribution network project cost, thereby reducing the errors caused by traditional methods.

[0017] 2. The present invention provides a more comprehensive analysis perspective through cable heat dissipation correction coefficient, power loss, power supply and demand data, grid load and voltage drop, and enhances the scientificity and reliability of the prediction. And through the calculation and selection of the best cable data, it helps decision makers make better choices in material selection and capital allocation, reducing unnecessary costs.

[0018] 3. The present invention effectively avoids economic losses caused by budget shortfalls or overspending through accurate cost forecasting, thereby improving the overall economic benefits of the project. At the same time, it adopts automated data acquisition and model building methods, reduces manual intervention and tedious steps in traditional methods, and improves work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic diagram of the structure of a distribution network engineering cost prediction method based on big data in the present invention. DETAILED DESCRIPTION

[0020] 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.

[0021] Embodiment 1, Figure 1 The present invention provides a method for predicting the cost of a distribution network project based on big data, comprising the following steps:

[0022] S1, obtain the historical power supply and demand data of the distribution room, and obtain the historical power impact data.

[0023] In this embodiment, the acquisition of historical power supply and demand data of the power distribution room and the acquisition of historical power impact data are specifically as follows:

[0024] Cable heat dissipation correction factor, also known as heat dissipation correction factor, is an important parameter used in cable design and cable current carrying capacity calculation. It is mainly used to consider the change of cable heat dissipation capacity under actual operating conditions, so that the cable can work within a safe temperature range, thereby ensuring that the cable can carry the load without overloading.

[0025] The specific steps for obtaining the cable heat dissipation correction coefficient are as follows:

[0026] Get the ambient temperature and resistance of the cable at ambient temperature;

[0027] Obtain the actual maximum temperature of the cable during use and its resistance at the maximum temperature;

[0028] The temperature coefficient of the cable is obtained by calculating based on the preset temperature coefficient formula according to the ambient temperature of the cable and the resistance at the ambient temperature, as well as the actual maximum temperature of the cable during use and the resistance at the maximum temperature;

[0029] The cable heat dissipation correction factor is obtained by calculating based on the preset cable heat dissipation correction factor formula according to the ambient temperature of the cable, the actual maximum temperature of the cable during use and the temperature coefficient of the cable.

[0030] The specific calculation formula of the cable heat dissipation correction coefficient is as follows:

[0031]

[0032] The specific calculation formula of the temperature coefficient is as follows:

[0033]

[0034] Where K is the cable heat dissipation correction factor, α is the temperature coefficient, T is the actual maximum cable temperature, T0 is the ambient temperature, R T is the resistance in ohms at temperature T, R S is the resistance at reference temperature T0.

[0035] It should be noted that by reasonably applying the cable heat dissipation correction factor, it can be ensured that the cable will not cause safety risks such as aging, damage or fire of the insulation material due to overheating during operation, thereby reducing the cost of cable maintenance in the later stage and improving the safety and reliability of power equipment. At the same time, the heat dissipation performance of the cable is affected by environmental factors. The heat dissipation correction factor will be adjusted according to specific environmental changes such as temperature and humidity, making the design more flexible and adaptable to different application scenarios.

[0036] Power loss refers to the energy that cannot be effectively utilized due to conductor resistance, equipment loss and other factors during the transmission and conversion of power.

[0037] The specific steps for obtaining the power loss are as follows:

[0038] Obtain the cross-sectional area and length of the cable to be tested;

[0039] The resistance of the cable is measured by an ohmmeter, and the resistivity of the cable is calculated based on the resistivity formula according to the cross-sectional area of ​​the cable, the length of the cable and the resistance of the cable;

[0040] The rated current of the cable to be tested is obtained by the cable current carrying capacity measurement method;

[0041] The power loss of the cable is calculated based on the obtained cross-sectional area of ​​the cable, the length of the cable, the resistivity of the cable and the rated current of the cable based on a preset power loss formula to obtain the power loss of the cable.

[0042] The specific calculation formula of the power loss is as follows:

[0043] P loss =J 2 *ρ*L*A

[0044] The specific calculation formula of the resistivity is as follows:

[0045]

[0046] The specific calculation formula of the rated current density of the cable is as follows:

[0047]

[0048] Where P loss is the power loss, J is the rated current density of the cable, A is the cross-sectional area of ​​the cable, ρ is the resistivity of the cable, L is the length of the cable, and I is the rated current of the cable.

[0049] It should be noted that the rated current density of the cable refers to the maximum current that the cable can carry per unit cross-sectional area under specific conditions. It is used in cable design and selection and is an important indicator for evaluating the current carrying capacity of the cable. By controlling the rated current density of the cable, it can be ensured that the cable will not overheat during operation and damage to the cable insulation material can be avoided. A reasonable current density can reduce the loss of electric energy during transmission, improve the working efficiency of the cable system, and reduce operating costs. The increase in ambient temperature will increase the heat load of the cable and reduce the rated current density.

[0050] Furthermore, power loss is directly related to the overall efficiency of the power system. High loss means that the actual power delivered to the load will be reduced under the same power generation, thereby reducing the system's working efficiency. At the same time, large power loss will affect the stability of the power grid, causing the corresponding generator set to increase the load to compensate for the loss, thereby causing power grid frequency fluctuations and potential power supply instability. Reasonable control of power loss will effectively reduce the cost of subsequent operations.

[0051] Grid load, grid load refers to the total demand for electric energy by all power users in the power system within a specific period of time.

[0052] The specific steps for obtaining the power grid load of the cable are as follows:

[0053] The rated voltage of the cable to be tested is obtained through the withstand voltage test method;

[0054] The rated current of the cable to be tested is obtained by the cable current carrying capacity measurement method;

[0055] Use a phase measuring instrument to measure the phase difference of the cable at rated voltage and rated current;

[0056] The grid load is calculated based on the preset grid load formula according to the rated voltage of the cable, the rated current of the cable and the phase difference of the cable.

[0057] The specific calculation formula of the power grid load is as follows:

[0058]

[0059] Where P is the grid load, U is the rated voltage of the cable, I is the rated current of the cable, cosΦ is the power factor, and Φ is the phase difference between current and voltage.

[0060] It should be noted that changes in grid load directly affect decisions on power production and dispatching, and the operation of generator sets needs to be adjusted according to real-time load changes to ensure the reliability and stability of power supply. Reasonable planning and management of grid load will encourage users to use energy more efficiently during low-load periods, thereby reducing overall losses in the power system.

[0061] Voltage drop refers to the voltage drop caused by the presence of resistance or impedance when current passes through a conductor, load or other electrical components. Specifically, when current flows through a resistor or inductor component, the difference between the input voltage and the output voltage caused by these components' resistance to current is called voltage drop.

[0062] The specific steps for obtaining the voltage drop are as follows:

[0063] Obtain a section of the cable to be tested, and obtain the resistance temperature coefficient of the cable to be tested through a resistance temperature coefficient measurement experiment;

[0064] The resistance of the cable to be tested at standard temperature and the resistance in a stable state of power supply are obtained by using an ohmmeter, and the cable temperature when the two resistances are measured is recorded to obtain the temperature difference;

[0065] The resistance change caused by temperature change is calculated based on the resistance of the cable at standard temperature, the resistance temperature coefficient and the cable temperature difference based on the preset resistance change formula;

[0066] The additional resistance test is used to obtain the additional resistance of the cable, and the length and rated current of the cable to be tested;

[0067] The voltage drop of the cable to be tested is calculated based on a preset voltage drop calculation formula according to the length of the cable, the rated current of the cable, the resistance change caused by temperature change, the resistance at standard temperature and the additional resistance of the cable.

[0068] The specific calculation formula of the voltage drop is as follows:

[0069]

[0070] The specific calculation formula for the resistance change caused by temperature change is as follows:

[0071] ΔR T =R0*β*(T-T0)

[0072] Where ΔV is the voltage drop, I is the rated current of the cable, L is the cable length, R0 is the resistance of the cable at standard temperature (ohms / km), and ΔR T is the resistance change caused by temperature change, β is the resistance temperature coefficient, T is the actual maximum cable temperature, T0 is the ambient temperature, ΔR type is the additional resistance caused by the cable type and insulation material.

[0073] It should be noted that voltage drop helps to evaluate and adjust the load, ensure that each part of the circuit can work effectively, avoid potential risks caused by voltage imbalance, and effectively reduce voltage drop by reasonably designing the circuit and optimizing the wiring, thereby improving the efficiency of the entire power system or circuit and reducing energy loss.

[0074] S2, builds a power impact model based on the machine learning algorithm according to the historical power impact data and power supply and demand data.

[0075] In this embodiment, the power impact model is constructed based on the machine learning algorithm according to the cable heat dissipation correction coefficient, power loss, power supply and demand data, grid load and voltage drop as follows:

[0076] The specific calculation formula of the power impact model is as follows:

[0077]

[0078] Where λ is the power influence coefficient, K is the cable heat dissipation correction coefficient, and P loss is the power loss, P sy is the power supply and demand data of the distribution room, P is the grid load, ΔV is the voltage drop, I max is the maximum current that the cable can carry.

[0079] It should be noted that the power impact model reflects the performance and efficiency of the cable under specific conditions, and its size has an important impact on the use of the cable and the overall stability of the power system. The power impact coefficient is proportional to the cable heat dissipation correction coefficient. If the heat dissipation correction coefficient is high, it means that the cable has a good heat dissipation capacity under specific conditions and can effectively dissipate heat, thereby reducing the risk of overheating and increasing safety and service life; conversely, a low heat dissipation correction coefficient will cause the cable to overheat and increase the probability of failure.

[0080] Furthermore, a lower power impact coefficient means that cable thermal management and energy loss problems will lead to overheating and equipment failure, thus affecting the safety of the system. By increasing the power impact coefficient, higher system efficiency and safety can be achieved.

[0081] S3, obtaining the distribution network engineering document data to be predicted, and obtaining the optimal cable data based on the power impact model.

[0082] In this embodiment, the method of obtaining the distribution network engineering document data to be predicted and obtaining the optimal cable data based on the power impact model is as follows:

[0083] Obtain the distribution network engineering document data to be predicted, including the power supply and demand data of the distribution room, the rated current of the cable, the resistance of the cable and the power line;

[0084] The power impact coefficient is obtained based on the power impact model through the distribution network engineering document data.

[0085] S4, select the cable model based on the best cable data to predict the cost of the distribution room cable.

[0086] In this embodiment, the optimal data of the cable is the cable coefficient obtained by removing the non-cable parameters in the power impact model, and the cable coefficient is obtained by obtaining the parameters of multiple types of cables and substituting them into the calculation. The model of the cable is obtained according to the cable parameters that achieve the optimal data of the cable, and then the selling price of the cable is obtained according to the model of the cable, and the required length of the cable is obtained according to the power line in the distribution network engineering document data. The length of the cable is multiplied by the selling price of the cable to predict the cost of the distribution room on the cable.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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 predicting the construction cost of a distribution network project based on big data, characterized in that: include Obtain historical power supply and demand data of power distribution rooms, and obtain historical power impact data; Build a power impact model based on historical power impact data and power supply and demand data using machine learning algorithms; Obtain the engineering document data of the distribution network to be predicted and obtain the optimal cable data based on the power impact model; Select the cable model based on the best cable data and predict the cost of the distribution room cable.

2. According to a method for predicting the cost of distribution network engineering based on big data according to claim 1, it is characterized in that: The acquired historical power impact data includes cable heat dissipation correction factor, power loss, grid load and voltage drop.

3. According to a method for predicting the cost of distribution network engineering based on big data according to claim 2, it is characterized in that: The specific steps for obtaining the cable heat dissipation correction coefficient are as follows: Get the ambient temperature and resistance of the cable at ambient temperature; Obtain the actual maximum temperature of the cable during use and its resistance at the maximum temperature; The temperature coefficient of the cable is obtained by calculating based on the preset temperature coefficient formula according to the ambient temperature of the cable and the resistance at the ambient temperature, as well as the actual maximum temperature of the cable during use and the resistance at the maximum temperature; The cable heat dissipation correction factor is obtained by calculating based on the preset cable heat dissipation correction factor formula according to the ambient temperature of the cable, the actual maximum temperature of the cable during use and the temperature coefficient of the cable.

4. According to a method for predicting the cost of distribution network engineering based on big data according to claim 3, it is characterized in that: The specific steps for obtaining the power loss are as follows: Obtain the cross-sectional area and length of the cable to be tested; The resistance of the cable is measured by an ohmmeter, and the resistivity of the cable is calculated based on the resistivity formula according to the cross-sectional area of ​​the cable, the length of the cable and the resistance of the cable; The rated current of the cable to be tested is obtained by the cable current carrying capacity measurement method; The power loss of the cable is calculated based on the obtained cross-sectional area of ​​the cable, the length of the cable, the resistivity of the cable and the rated current of the cable based on a preset power loss formula to obtain the power loss of the cable.

5. A method for predicting the cost of a distribution network project based on big data according to claim 4, characterized in that: The specific steps for obtaining the power grid load of the cable are as follows: The rated voltage of the cable to be tested is obtained through the withstand voltage test method; The rated current of the cable to be tested is obtained by the cable current carrying capacity measurement method; Use a phase measuring instrument to measure the phase difference of the cable at rated voltage and rated current; The grid load is calculated based on the preset grid load formula according to the rated voltage of the cable, the rated current of the cable and the phase difference of the cable.

6. A method for predicting the cost of a distribution network project based on big data according to claim 5, characterized in that: The specific steps for obtaining the voltage drop are as follows: Obtain a section of the cable to be tested, and obtain the resistance temperature coefficient of the cable to be tested through a resistance temperature coefficient measurement experiment; The resistance of the cable to be tested at the standard temperature and the resistance in the stable state of power supply are obtained by using an ohmmeter, and the cable temperature when the two resistances are measured is recorded to obtain the temperature difference; The resistance change caused by temperature change is calculated based on the resistance of the cable at standard temperature, the resistance temperature coefficient and the cable temperature difference based on the preset resistance change formula; The additional resistance test is used to obtain the additional resistance of the cable, and the length and rated current of the cable to be tested; The voltage drop of the cable to be tested is calculated based on a preset voltage drop calculation formula according to the length of the cable, the rated current of the cable, the resistance change caused by temperature change, the resistance at standard temperature and the additional resistance of the cable.

7. A method for predicting the cost of a distribution network project based on big data according to claim 6, characterized in that: The method of constructing a power impact model based on a machine learning algorithm according to historical power impact data and power supply and demand data is specifically: constructing a power impact model based on a machine learning algorithm according to cable heat dissipation correction coefficient, power loss, power supply and demand data, grid load and voltage drop.

8. The method for predicting the cost of a distribution network project based on big data according to claim 7 is characterized in that: The method of obtaining the distribution network engineering document data to be predicted and obtaining the optimal cable data based on the power impact model is as follows: Obtain the distribution network engineering document data to be predicted, including the power supply and demand data of the distribution room, the rated current of the cable, the resistance of the cable and the power line; Obtain the power impact coefficient level of the desired functional effect based on the power impact model through the distribution network engineering document data; The optimal data for the cable is obtained based on the level of power influence coefficient for the functional effect you want to achieve.

9. The method for predicting the construction cost of a distribution network project based on big data according to claim 8, characterized in that: The specific calculation formula of the cable heat dissipation correction coefficient is as follows: The specific calculation formula of the temperature coefficient is as follows: The specific calculation formula of the power loss is as follows: P loss =J 2 *p*L*A The specific calculation formula of the resistivity is as follows: The specific calculation formula of the rated current density of the cable is as follows: The specific calculation formula of the power grid load is as follows: The specific calculation formula of the voltage drop is as follows: The specific calculation formula for the resistance change caused by temperature change is as follows: ΔR T =R0*β*(T-T0) Where K is the cable heat dissipation correction factor, α is the temperature coefficient, T is the actual maximum cable temperature, T0 is the ambient temperature, R T is the resistance in ohms at temperature T, R S is the resistance at reference temperature T0, P loss is the power loss, J is the rated current density of the cable, A is the cross-sectional area of ​​the cable, ρ is the resistivity of the cable, L is the length of the cable, I is the rated current of the cable, P is the grid load, U is the rated voltage of the cable, cosΦ is the power factor, Φ is the phase difference between current and voltage, ΔV is the voltage drop,, R0 is the resistance of the cable at standard temperature (ohm / km), ΔR T is the resistance change due to temperature change, β is the temperature coefficient of resistance, ΔR type is the additional resistance caused by the cable type and insulation material.

10. A method for predicting the cost of distribution network engineering based on big data according to claim 9, characterized in that: The specific calculation formula of the power impact model is as follows: Where λ is the power influence coefficient, K is the cable heat dissipation correction coefficient, and P loss is the power loss, P sy is the power supply and demand data of the distribution room, P is the grid load, ΔV is the voltage drop, I max is the maximum current that the cable can carry.

Images