Dynamic current-carrying capacity prediction method of buried cable and related device

Abstract

The embodiment of the invention discloses a method for predicting the dynamic current-carrying capacity of a buried cable and a related device. The method comprises the following steps: acquiring historical weather data and historical cable load current which are related to the buried cable in a preset region and are in a historical time period; the historical weather data comprises historical surface temperature and historical precipitation; determining soil dynamic characteristic parameters based on the historical surface temperature and the historical precipitation; determining the historical dynamic current-carrying capacity of the buried cable based on the soil dynamic characteristic parameters and the historical cable load current; acquiring future weather data and future cable load current of the preset region in a future time period; determining a target quantile; determining a regression coefficient vector corresponding to the target quantile based on the target quantile, the historical weather data, the soil dynamic characteristic parameters, the historical dynamic current-carrying capacity and the historical cable load current; and based on the future weather data, the future cable load current and the regression coefficient vector, determining the future dynamic current-carrying capacity corresponding to the target quantile of the buried cable in the future time period.

Description

Technical Field

[0001] The present invention relates to the technical field of current carrying capacity prediction, and in particular to a dynamic current carrying capacity prediction method and a related device for a direct buried cable. Background Art

[0002] In the operation of the power system, the current carrying capacity of the direct buried cable is an important parameter for power dispatching and resource optimization. The current carrying capacity refers to the maximum current that the conductor can continuously carry under specified conditions without causing its stable temperature to exceed the specified value. Determining the current carrying capacity of the direct buried cable can prevent overload and equipment damage in power dispatching, and can improve equipment utilization in terms of resource optimization.

[0003] However, the traditional current carrying capacity prediction method has low prediction accuracy under different environmental conditions and different cable loads.

[0004] Therefore, there is an urgent need for a dynamic current-carrying capacity prediction method for direct buried cables to improve the prediction accuracy when predicting the current-carrying capacity of cables. Summary of the invention

[0005] In order to solve the above problems, an embodiment of the present invention provides a method and related device for predicting the dynamic current carrying capacity of a direct buried cable, which can improve the prediction accuracy when predicting the current carrying capacity of the cable.

[0006] In a first aspect, an embodiment of the present invention provides a method for predicting the dynamic current carrying capacity of a direct buried cable, comprising:

[0007] Acquire historical weather data and historical cable load current related to direct buried cables in a preset area in a historical time period; the historical weather data includes historical surface temperature and historical precipitation in the preset area in the historical time period;

[0008] Determining soil dynamic characteristic parameters based on the historical surface temperature and the historical precipitation;

[0009] Determine the historical dynamic current carrying capacity of the direct buried cable based on the soil dynamic characteristic parameter and the historical cable load current;

[0010] Acquire future weather data and future cable load current of the preset area in a future time period;

[0011] determining a target quantile based on the historical weather data, the historical cable load current, the future weather data, and the future cable load current;

[0012] Determine a regression coefficient vector corresponding to the target quantile based on the target quantile, the historical weather data, the soil dynamic characteristic parameter, the historical dynamic current carrying capacity and the historical cable load current;

[0013] Based on the future weather data, the future cable load current and the regression coefficient vector, the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period is determined.

[0014] In a second aspect, an embodiment of the present invention provides a dynamic current carrying capacity prediction device for a direct buried cable, the device comprising an acquisition unit and a processing unit;

[0015] The acquisition unit is used to acquire historical weather data and historical cable load current related to the direct buried cables in a preset area in a historical time period; the historical weather data includes the historical surface temperature and historical precipitation of the preset area in the historical time period;

[0016] The processing unit is used to determine soil dynamic characteristic parameters based on the historical surface temperature and the historical precipitation;

[0017] Determine the historical dynamic current carrying capacity of the direct buried cable based on the soil dynamic characteristic parameter and the historical cable load current;

[0018] Acquire future weather data and future cable load current of the preset area in a future time period;

[0019] determining a target quantile based on the historical weather data, the historical cable load current, the future weather data, and the future cable load current;

[0020] Determine a regression coefficient vector corresponding to the target quantile based on the target quantile, the historical weather data, the soil dynamic characteristic parameter, the historical dynamic current carrying capacity and the historical cable load current;

[0021] Based on the future weather data, the future cable load current and the regression coefficient vector, the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period is determined.

[0022] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the method described in the first aspect.

[0023] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in the first aspect.

[0024] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer is operable to cause the computer to execute the method described in the first aspect.

[0025] Implementing the embodiments of the present application has the following beneficial effects:

[0026] In an implementation manner of the present application, historical weather data and historical cable load current related to direct buried cables in a preset area in a historical time period are first obtained, wherein the historical weather data include historical surface temperature and historical precipitation in the preset area in the historical time period, then, soil dynamic characteristic parameters are determined based on the historical surface temperature and historical precipitation, and the historical dynamic current carrying capacity of the direct buried cable is determined based on the soil dynamic characteristic parameters and the historical cable load current, next, future weather data and future cable load current of the preset area in a future time period are obtained, then, a target quantile is determined based on the historical weather data, the historical cable load current, the future weather data and the future cable load current, a regression coefficient vector corresponding to the target quantile is determined based on the target quantile, the historical weather data, the soil dynamic characteristic parameters, the historical dynamic current carrying capacity and the historical cable load current, and finally, the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period is determined based on the future weather data, the future cable load current and the regression coefficient vector. Therefore, by determining the soil dynamic characteristic parameters, historical dynamic current carrying capacity and target quantile, and determining the regression coefficient vector corresponding to the target quantile, and finally determining the future dynamic current carrying capacity corresponding to the target quantile in the future time period of the direct buried cable based on the regression coefficient vector, the prediction accuracy can be improved when predicting the current carrying capacity of the cable. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 It is a flow chart of a method for predicting dynamic current carrying capacity of a direct buried cable provided in an embodiment of the present application;

[0029] Figure 2 It is a flow chart of a dynamic current carrying capacity prediction model training of a direct buried cable provided in an embodiment of the present application;

[0030] Figure 3 It is a dynamic current carrying capacity prediction flow chart based on a quantitative regression model provided in an embodiment of the present application;

[0031] Figure 4 It is a structural schematic diagram of a dynamic current carrying capacity prediction device for a direct buried cable provided in an embodiment of the present application;

[0032] Figure 5 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally includes steps or modules that are not listed, or optionally includes other steps or modules inherent to these processes, methods, products or devices.

[0035] Reference to "embodiments" herein means that a particular feature, result, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] In a possible embodiment, for real-time current carrying capacity calculation, cable temperature detection can be performed, for example, optical fiber temperature measurement, thermocouples on the cable skin, infrared imaging, etc., to obtain the temperature of the metal sheath or the cable skin, and combined with a thermal circuit model or a finite element model, the loss is obtained by load current calculation, and the cable core temperature is reversely deduced. The cable core temperature is used to determine whether the cable load can be increased or whether the cable load is overloaded, thereby determining the real-time dynamic current carrying capacity of the cable.

[0037] In a possible embodiment, for the prediction of the dynamic current carrying capacity of the cable, data-driven methods such as random forest regression and neural network are applied to the prediction of the dynamic current carrying capacity of the cable. These two methods can effectively process high-dimensional input variables and have certain noise resistance. However, random forest regression is centered on the mean and cannot provide reliable predictions for specific quantiles, such as the typical behavior of the worst-case risk or the median, which will lead to insufficient predictions of extreme environmental conditions. The neural network requires a large amount of historical data for training, and insufficient training sets will lead to reduced prediction accuracy. In addition, the neural network is highly sensitive to errors in the prediction process, and the predicted value will be aggressive, which is not conducive to ensuring the security of transmission.

[0038] The dynamic current carrying capacity prediction method for direct buried cables provided in the embodiment of the present application focuses on the prediction of the target quantile through quantitative regression, which can more robustly reflect the dynamic current carrying capacity under typical operating conditions of the cable and reduce the impact of extreme values ​​on the prediction. Moreover, by adjusting the target quantile, it can be extended to predict the dynamic current carrying capacity under the worst case or other risk conditions, significantly enhancing the adaptability of the prediction. In addition, the computational complexity of quantitative regression is lower than that of neural networks, and it performs more stably and reliably when the data quality is insufficient or the noise is large. The quantitative regression model clearly provides the relationship between the input features and the prediction results, which is convenient for power dispatchers to understand and use, and improves the trust in practical applications. The quantile is used to describe the position of the data in the distribution. For a given probability distribution, the quantile refers to the numerical point that divides the distribution into several parts. The target quantile in the embodiment of the present application is illustrated by taking the median, i.e., the 50% quantile, as an example.

[0039] See also Figure 1 , Figure 1 : is a flow chart of a method for predicting the dynamic current carrying capacity of a direct buried cable provided in an embodiment of the present application. Figure 1 As shown, the dynamic current carrying capacity prediction method of the direct buried cable provided in the embodiment of the present application includes but is not limited to the following steps:

[0040] Step S101: Acquire historical weather data and historical cable load current in a historical time period related to direct buried cables in a preset area;

[0041] Among them, historical weather data includes historical surface temperature and historical precipitation in preset areas during historical time periods;

[0042] Step S102: determining soil dynamic characteristic parameters based on historical surface temperature and historical precipitation;

[0043] Step S103: determining the historical dynamic current carrying capacity of the direct buried cable based on the soil dynamic characteristic parameters and the historical cable load current;

[0044] Step S104: obtaining future weather data and future cable load current of a preset area in a future time period;

[0045] Step S105: determining a target quantile based on historical weather data, historical cable load current, future weather data, and future cable load current;

[0046] Step S106: determining a regression coefficient vector corresponding to the target quantile based on the target quantile, historical weather data, soil dynamic characteristic parameters, historical dynamic current carrying capacity, and historical cable load current;

[0047] Step S107: Determine the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period based on the future weather data, the future cable load current and the regression coefficient vector.

[0048] In a possible embodiment, the dynamic current carrying capacity refers to the current value that the cable can safely carry at different times, which will change with factors such as the working environment of the cable and load changes. There are many ways to lay cables, such as direct burial, overhead, cable trench, etc. Unlike overhead cables, which are mainly affected by factors such as ambient temperature and wind speed to affect heat dissipation and thus affect current carrying capacity, direct buried cables mainly rely on soil for heat dissipation, and the thermal resistance characteristics of the soil will affect the current carrying capacity of the cable. Surface temperature and precipitation mainly participate in the calculation of soil dynamic characteristic parameters by affecting soil moisture content. Precipitation directly changes soil moisture content, while surface temperature indirectly affects soil moisture content by affecting the dynamic balance between evaporation and soil moisture, thereby affecting parameters such as soil thermal diffusivity, thermal resistivity and temperature.

[0049] In a possible embodiment, when determining the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period based on future weather data, future cable load current and regression coefficient vector, the calculation is based on the 50% quantile quantitative regression model. Figure 2 , Figure 2 is a flow chart of a dynamic current carrying capacity prediction model training for a direct buried cable provided in an embodiment of the present application, such as Figure 2 As shown, first input the historical surface temperature and precipitation, and based on this solve the soil thermal diffusivity, soil thermal resistivity and soil temperature, then use the thermal circuit model to calculate the dynamic current carrying capacity to obtain the historical dynamic current carrying capacity, then build a training data set and a validation data set based on the historical dynamic current carrying capacity, historical soil temperature, precipitation and cable load, and input the training data set into the 50% quantile quantitative regression model for model training, and verify the model with the validation data set, and save the model when the model reaches the ideal accuracy. After determining the quantitative regression model, refer to Figure 3 , Figure 3is a dynamic current carrying capacity prediction flow chart based on a quantitative regression model provided in an embodiment of the present application, such as Figure 3 As shown, for the 50% quantile quantitative regression model, the soil temperature, rainfall and cable load current of the prediction period are input to obtain the dynamic current carrying capacity of the cable in the prediction period.

[0050] In a possible embodiment, adjusting the target quantile can predict the dynamic current carrying capacity under the worst case or other risk conditions. When determining the target quantile based on historical weather data, historical cable load current, future weather data and future cable load current, the first weather feature of the historical weather data is determined. The first weather feature is a representative feature extracted from the historical weather data. For historical precipitation, the average value, variance, maximum value, minimum value, seasonal fluctuation characteristics of precipitation, etc. of historical precipitation can be calculated. For historical soil temperature, the average soil temperature, daily variation amplitude of soil temperature, seasonal variation characteristics of soil temperature, etc. can be calculated. Then, the second weather feature of future weather data is determined. For future precipitation, the predicted precipitation trend and probability distribution characteristics of precipitation are analyzed. For future soil temperature, the predicted variation trend of soil temperature, possible extreme temperature conditions, etc. are considered, and the first adjustment amount is determined based on the first weather feature and the second weather feature. The first adjustment amount reflects the influence of historical weather data on the initial quantile. Next, the historical load characteristics and future load characteristics are determined according to the historical cable load current and the future cable load current, and the second adjustment amount is determined based on the historical load characteristics and the future load characteristics. Finally, the target quantile is determined by combining the first adjustment amount, the second adjustment amount and the initial quantile. For example, the target quantile is the sum of the initial quantile, the first adjustment amount and the second adjustment amount. For example, the initial quantile is 50%, the preset weather characteristics are the weather characteristics under extreme weather conditions, and the preset load characteristics are the load characteristics under extreme load conditions. When the first weather characteristics and the second weather characteristics are consistent with the preset weather characteristics, the first adjustment amount can be determined according to the extreme weather level of the first weather characteristics and the second weather characteristics. For example, the first adjustment amount can be determined to be 30%, then the target quantile is 80%, or, when the historical load characteristics and the future load characteristics are consistent with the preset load characteristics, the second adjustment amount can be determined according to the load level of the load in the historical load characteristics and the future load characteristics. For example, the second adjustment amount can be determined to be 20%, then the target quantile is 70%.

[0051] In the embodiments of the present application, in order to address the problem of insufficient ability to predict the dynamic current-carrying capacity of direct-buried cables, prediction is performed by optimizing the 50% quantile, that is, the median, thereby significantly improving the robustness and accuracy of the prediction, especially under changing environmental conditions, thereby improving the utilization efficiency of existing cable resources while ensuring the safe operation of the power system, and achieving a more efficient and robust prediction of the dynamic current-carrying capacity of direct-buried cables, significantly improving the ability to predict the dynamic current-carrying capacity of direct-buried cables, and providing important support for the efficient utilization and safe operation of cable resources.

[0052] Optionally, the soil dynamic characteristic parameters include soil thermal diffusivity, soil thermal resistivity and historical soil temperature; step S102, determining the soil dynamic characteristic parameters based on historical surface temperature and historical precipitation, may include the following steps:

[0053] Step S201: obtaining soil composition, dry soil density and groundwater level reference temperature of a preset area; the soil composition is used to reflect the ratio of sand and clay particles in the preset area;

[0054] Step S202: determining soil moisture content based on historical precipitation and a preset water diffusion equation;

[0055] Step S203: determining soil thermal diffusivity based on soil composition and soil moisture content;

[0056] Step S204: determining soil thermal resistivity based on dry soil density, soil water content, soil thermal diffusivity and soil composition;

[0057] Step S205: determining an initial temperature range based on historical surface temperature and groundwater level reference temperature;

[0058] Step S206: Determine the historical soil temperature based on the soil thermal diffusivity and the initial temperature range.

[0059] In a possible embodiment, the soil thermal diffusivity, soil thermal resistivity and historical soil temperature of the entire historical time period are calculated by using the surface temperature and precipitation of the historical time period. The historical time period may be 1 to 36 hours from the past to the present. The soil thermal diffusivity, soil thermal resistivity and historical soil temperature are respectively calculated by δ T (t,h),ρ T (t,h) and T S (t,h), where t is time and h is the depth from the ground surface. The soil thermal diffusivity δ can be expressed by formula (1): T (t,h) is calculated:

[0060] δ T (t,h)=-14.8+0.209N+4.79θ(t,h)…………(1)

[0061] Where N is the soil composition, θ(t,h) is the soil moisture content, and soil moisture content is the volume ratio of water per unit volume. The dynamic change of soil moisture content θ(t,h) over time can be expressed by formula (2), which is the water diffusion equation:

[0062]

[0063] Where z is the vertical direction related to depth. The partial derivative of z is used to determine the change in the vertical direction. The left side of the equation is the change of soil moisture θ(t,h) with time t. θ (t,h) is the water diffusivity, k θ (t,h) is the water conductivity, and the calculation formulas of the two can be expressed by formula (3) and formula (4) respectively:

[0064]

[0065] Among them, k sat is the saturated conductivity, α and m are the Van Genuchten coefficients, θ sat is the saturated water content, θ res is the residual water content.

[0066] For soil thermal resistivity ρ T (t,h) can be calculated by formula (5):

[0067]

[0068] Among them, σ s is the dry soil density.

[0069] For the historical soil temperature T S (t,h) can be calculated by formula (6):

[0070]

[0071] Where z is the vertical direction related to depth, and the partial derivative of z is used to determine the change in the vertical direction. The left side of the equation is the historical soil temperature T S (t,h) changes with time t.

[0072] In a possible embodiment, in order to solve the above differential equations in numerical simulation, a finite difference method is used for time and space discretization. The time step can be set to the minute level, for example, 5 minutes, the upper boundary of the initial temperature range of the soil temperature is the soil temperature derived using the historical surface temperature, and the lower boundary of the initial temperature range of the soil temperature is the reference temperature of the groundwater level layer. The initial soil temperature is obtained between the upper and lower boundaries by linear interpolation, and the initial soil moisture content is calculated by the historical precipitation and the water diffusion equation.

[0073] Optionally, step S103, determining the historical dynamic current carrying capacity of the direct buried cable based on the soil dynamic characteristic parameters and the historical cable load current, may include the following steps:

[0074] Step S301: determining multiple time steps of a historical time period based on soil dynamic characteristic parameters and historical cable load current;

[0075] Step S302: determining a plurality of initial current carrying capacity reference values ​​corresponding to a plurality of time steps based on the historical cable load current;

[0076] Step S303: determining the conductor temperature of the direct buried cable corresponding to each time step in a plurality of time steps based on a plurality of initial current carrying capacity reference values, and obtaining a plurality of conductor temperatures;

[0077] Step S304: obtaining the target operating temperature of the direct buried cable;

[0078] Step S305: when the difference between the target conductor temperature and the target operating temperature is less than or equal to the preset error value, the target initial current-carrying capacity reference value is increased based on the difference to obtain the target historical current-carrying capacity; the target conductor temperature is any conductor temperature among the multiple conductor temperatures; the target initial current-carrying capacity reference value is the initial current-carrying capacity reference value corresponding to the target conductor temperature among the multiple initial current-carrying capacity reference values;

[0079] Step S306: Integrate multiple target historical current carrying capacities to obtain historical dynamic current carrying capacities.

[0080] In a possible embodiment, the soil dynamic characteristic parameter, namely the soil thermal diffusivity δ T (t,h), soil thermal resistivity ρ T (t,h) and historical soil temperature T S (t,h) Input the International Electrotechnical Commission (IEC) standard thermal circuit model to calculate the current carrying capacity, and the historical dynamic current carrying capacity can be obtained.

[0081] In a possible embodiment, when determining the historical dynamic current carrying capacity, an iterative calculation method is used. In the first step, the conductor temperature T(t) is set as the target operating temperature, and the initial value of the load current I(t) of the direct buried cable is set as the actual load current of the cable history, that is, the historical cable load current is used as the initial current carrying capacity reference value; in the second step, the conductor loss W of the time step t is calculated. c (t), conductor external temperature rise ΔT o (t) and the internal temperature rise of the conductor ΔT i (t); Step 3, based on the conductor loss W in Step 2 c (t), conductor external temperature rise ΔT o (t) and the internal temperature rise of the conductor ΔT i (t) to obtain the conductor temperature T(t) at time step t (1) , the superscript refers to the first iteration value; the fourth step is to determine T(t) (1) -T(t)≤ε, ε is the preset acceptable error value. If the judgment condition is not met, increase the value of I(t), and repeat the first to third steps until the judgment condition is met, and stop the iteration to obtain the historical dynamic current carrying capacity I(t) (n) ; Step 5, t=t+Δt, and judge If the condition is not met, repeat the first step to the fourth step until the condition is met and stop the calculation. Through the above five steps, the historical dynamic current carrying capacity data of the entire historical time period can be solved.

[0082] Optionally, step S303, determining the conductor temperature of the direct buried cable corresponding to each time step in a plurality of time steps based on a plurality of initial current carrying capacity reference values ​​to obtain a plurality of conductor temperatures, may include the following steps:

[0083] Step S401: obtaining the number of conductor cores, insulation coefficient and cable diameter of the direct buried cable; the insulation coefficient is used to reflect the thermal capacity and thermal resistance of the insulation part of the direct buried cable;

[0084] Step S402: determining the conductor loss corresponding to each time step in a plurality of time steps based on the number of conductor cores and a plurality of initial current carrying capacity reference values, and obtaining a plurality of conductor losses;

[0085] Step S403: determining the internal temperature rise of the conductor corresponding to each time step in a plurality of time steps based on a plurality of conductor losses and insulation coefficients, and obtaining a plurality of internal temperature rises of the conductors;

[0086] Step S404: determining the conductor external temperature rise corresponding to each time step in a plurality of time steps based on a plurality of conductor losses, soil thermal resistivities, a plurality of soil thermal diffusivities and cable diameters, and obtaining a plurality of conductor external temperature rises;

[0087] Step S405: determining a plurality of historical soil temperatures corresponding to a plurality of time steps;

[0088] Step S406: determining a conductor temperature corresponding to each time step in a plurality of time steps based on a plurality of historical soil temperatures, a plurality of conductor internal temperature rises, and a plurality of conductor external temperature rises, to obtain a plurality of conductor temperatures.

[0089] In one possible embodiment, the conductor loss W c (t) can be calculated by formula (7):

[0090] W c (t) = n c R c,20 ℃[1+α T (T(t)-20)]I 2 (t)…………(7)

[0091] Among them, n c is the number of conductor cores of direct buried cable, R c,20℃ is the conductor resistance at 20°C, α T is the temperature correction coefficient, T(t) is the conductor temperature, and I(t) is the load current of the direct buried cable. The conductor temperature T(t) can be calculated using formula (8):

[0092] T(t)=T S (t,h)+α(t)ΔT o (t)+ΔT i (t)…………(8)

[0093] Among them, the conductor temperature T(t) is composed of multiple temperatures superimposed, R S (t,h) is the historical soil temperature at depth h, α(t) is the correction factor for thermal interaction between the cable and the outside, ΔT o (t) is the external temperature rise of the conductor, that is, the temperature rise of the outer surface of the direct buried cable, ΔT i (t) is the temperature rise inside the conductor.

[0094] Conductor internal temperature rise ΔT i (t) due to conductor loss W c (t) can be calculated by formula (9):

[0095]

[0096] Where A, B, a and b are coefficients related to the thermal capacity and thermal resistance of the insulation and sheath, that is, the insulation coefficient, ΔW c (t n ) is the loss change of one time step, that is, W c (t n )-Wc (t n-1 ), k F The total number of time steps is k hours and F time steps per hour.

[0097] Conductor external temperature rise ΔT o (t) can be calculated by formula (10):

[0098]

[0099] Among them, Ei(·) is the exponential integral function, D e is the cable diameter.

[0100] Optionally, step S306, integrating multiple target historical current carrying capacities to obtain historical dynamic current carrying capacities, may include the following steps:

[0101] Step S501: determining a load current value corresponding to each time step in a plurality of time steps based on the historical cable load current, and obtaining a plurality of load current values;

[0102] Step S502: determining a time difference of each time step in a plurality of time steps based on adjacent load current values ​​in a plurality of load current values, to obtain a plurality of time differences;

[0103] Step S503: determining a reference dynamic current carrying capacity of each of a plurality of time differences based on a plurality of target historical current carrying capacities, and obtaining a plurality of reference dynamic current carrying capacities;

[0104] Step S504: Based on multiple time steps and multiple time differences, multiple target historical current carrying capacities and multiple reference dynamic current carrying capacities are integrated to obtain a historical dynamic current carrying capacity.

[0105] In a possible embodiment, the load current value corresponding to each time step in multiple time steps is inconsistent, and each load current value corresponds to a target historical current carrying capacity. Since there is a difference between adjacent load current values, there is a time difference when the target historical current carrying capacity corresponds to the load current value. When integrating multiple target historical current carrying capacities, a reference dynamic current carrying capacity for each time difference in multiple time differences is first determined based on the multiple target historical current carrying capacities to obtain multiple reference dynamic current carrying capacities, and then based on multiple time steps and multiple time differences, multiple target historical current carrying capacities and multiple reference dynamic current carrying capacities are integrated to obtain the historical dynamic current carrying capacity, thereby making the integrated historical dynamic current carrying capacity more consistent and practical.

[0106] Optionally, step S106, determining the regression coefficient vector corresponding to the target quantile based on the target quantile, historical weather data, soil dynamic characteristic parameters, historical dynamic current carrying capacity and historical cable load current, may include the following steps:

[0107] Step S601: Based on historical precipitation, historical soil temperature and historical cable load current, multiple feature matrices are constructed according to multiple time steps and preset time windows; each time step corresponds to a feature matrix;

[0108] Step S602: determining the current carrying capacity of the historical dynamic current carrying capacity corresponding to each characteristic matrix in the plurality of characteristic matrices at the target quantile point, and obtaining a plurality of current carrying capacities;

[0109] Step S603: determining multiple reference vectors corresponding to multiple current carrying capacities and multiple characteristic matrices based on a preset equation relationship; the equation relationship is used to reflect the corresponding relationship between multiple current carrying capacities, multiple characteristic matrices and regression coefficient vectors;

[0110] Step S604: constructing a deviation loss function of the target quantile;

[0111] Step S605: Determine a regression coefficient vector from multiple reference vectors based on the deviation loss function.

[0112] In a possible embodiment, a quantitative regression model is trained based on historical dynamic current carrying capacity, historical precipitation in historical weather data, historical soil temperature in soil dynamic characteristic parameters, and historical cable load current, and a regression coefficient vector β of the model can be obtained after training.

[0113] For the quantitative regression model with a target quantile of 50%, it can be expressed by formula (11):

[0114] Q 0.5 (I DLR_t |X t )=X t β…………(11)

[0115] Among them, Q 0.5 (I DLR_t |X t ) is the feature matrix X at time t t Under the condition, the dynamic current carrying capacity I DLR_t The median of the feature matrix X t It includes the time series of historical soil temperature, historical precipitation and historical cable load current, namely T S is the historical soil temperature, r is the historical precipitation, I is the historical cable load current, and w is the time window. The time window is used to determine the time span of the data in the feature matrix. The time window can be adjusted according to the time range of the historical time period.

[0116] In the training phase, the goal is to minimize the deviation loss function of the 50% quantile to optimize the regression coefficient vector β. The corresponding objective function can be expressed by formula (12):

[0117]

[0118] Among them, I DLR_i is the target dynamic current carrying capacity of the i-th time period, X i is the characteristic matrix vector of the i-th time period, ρ 0.5 (u) is the quantile loss function, which can be expressed by formula (13):

[0119]

[0120] Thus, the optimized regression coefficient vector can be obtained.

[0121] Optionally, the future weather data includes future soil temperature and future precipitation in a future time period; step S107, based on the future weather data, the future cable load current and the regression coefficient vector, determining the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period, may include the following steps:

[0122] Step S701: constructing a prediction matrix based on future soil temperature, future precipitation and future cable load current;

[0123] Step S702: Determine the future dynamic current carrying capacity corresponding to the target quantile based on the regression coefficient vector and the prediction matrix.

[0124] In a possible embodiment, the future weather data and the historical weather data are of the same data type. When the historical weather data include historical precipitation and historical soil temperature, the future weather data accordingly include future precipitation and future soil temperature.

[0125] In a possible embodiment, the future weather data can be predicted and determined by a prediction method for future weather data, and the future cable load current can be predicted and determined by a prediction method for future cable load current. A prediction matrix X is constructed based on the future soil temperature and future precipitation of the future weather data and the future cable load current. f , combined with the regression coefficient vector β, we can get the future dynamic current carrying capacity prediction value I when the target quantile is 50% DLR_f , the calculation method can be expressed by formula (14):

[0126] I DLR_f =X f β…………(14)

[0127] Thus, the dynamic current carrying capacity prediction value in the short time range in the future can be calculated, which can provide a basis for real-time cable scheduling. It can also predict the current carrying capacity trend in the long term in the future by adjusting the data in the prediction matrix, which can provide support for scheduling optimization.

[0128] To summarize, in an implementation manner of the present application, historical weather data and historical cable load current related to direct buried cables in a preset area in a historical time period are first obtained, wherein the historical weather data include the historical surface temperature and historical precipitation of the preset area in the historical time period, and then, the soil dynamic characteristic parameters are determined based on the historical surface temperature and historical precipitation, and the historical dynamic current carrying capacity of the direct buried cable is determined based on the soil dynamic characteristic parameters and the historical cable load current, and next, future weather data and future cable load current of the preset area in a future time period are obtained, and then, the target quantile is determined based on the historical weather data, the historical cable load current, the future weather data and the future cable load current, and the regression coefficient vector corresponding to the target quantile is determined based on the target quantile, the historical weather data, the soil dynamic characteristic parameters, the historical dynamic current carrying capacity and the historical cable load current, and finally, the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period is determined based on the future weather data, the future cable load current and the regression coefficient vector. Therefore, by determining the soil dynamic characteristic parameters, historical dynamic current carrying capacity and target quantile, and determining the regression coefficient vector corresponding to the target quantile, and finally determining the future dynamic current carrying capacity corresponding to the target quantile in the future time period of the direct buried cable based on the regression coefficient vector, the prediction accuracy can be improved when predicting the current carrying capacity of the cable.

[0129] The method of the embodiment of the present invention is described in detail above, and the device of the embodiment of the present invention is provided below.

[0130] See also Figure 4 , Figure 4 800 is a schematic diagram of a dynamic current carrying capacity prediction device for a direct buried cable provided in an embodiment of the present application. The dynamic current carrying capacity prediction device 800 for a direct buried cable includes an acquisition unit 801 and a processing unit 802;

[0131] An acquisition unit 801 is used to acquire historical weather data and historical cable load current related to direct buried cables in a preset area in a historical time period; the historical weather data includes historical surface temperature and historical precipitation in a preset area in a historical time period;

[0132] A processing unit 802 is used to determine soil dynamic characteristic parameters based on historical surface temperature and historical precipitation;

[0133] Determine the historical dynamic current carrying capacity of direct buried cables based on soil dynamic characteristic parameters and historical cable load current;

[0134] Obtain future weather data and future cable load current in a preset area in a future time period;

[0135] Determine the target quantile based on historical weather data, historical cable load current, future weather data and future cable load current;

[0136] Determine the regression coefficient vector corresponding to the target quantile based on the target quantile, historical weather data, soil dynamic characteristic parameters, historical dynamic current carrying capacity and historical cable load current;

[0137] Based on future weather data, future cable load current and regression coefficient vector, the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period is determined.

[0138] In some possible embodiments, the soil dynamic characteristic parameters include soil thermal diffusivity, soil thermal resistivity, and historical soil temperature; in determining the soil dynamic characteristic parameters based on historical surface temperature and historical precipitation, the processing unit 802 is specifically configured to:

[0139] Obtain soil composition, dry soil density and groundwater level reference temperature of a preset area; soil composition is used to reflect the proportion of sand and clay particles in the preset area;

[0140] Determine soil moisture content based on historical precipitation and a preset water diffusion equation;

[0141] Determine soil thermal diffusivity based on soil composition and soil moisture content;

[0142] Determine soil thermal resistivity based on dry soil density, soil moisture content, soil thermal diffusivity, and soil composition;

[0143] Determine the initial temperature range based on historical surface temperatures and groundwater level reference temperatures;

[0144] Determine historical soil temperature based on soil thermal diffusivity and initial temperature range.

[0145] In some possible embodiments, in determining the historical dynamic current carrying capacity of the direct buried cable based on the soil dynamic characteristic parameters and the historical cable load current, the processing unit 802 is specifically configured to:

[0146] Determine multiple time steps of the historical time period based on soil dynamic characteristic parameters and historical cable load current;

[0147] Determine multiple initial current carrying capacity reference values ​​corresponding to multiple time steps based on historical cable load current;

[0148] Determine the conductor temperature of the direct buried cable corresponding to each time step in a plurality of time steps based on a plurality of initial current carrying capacity reference values, and obtain a plurality of conductor temperatures;

[0149] Obtain the target operating temperature of the direct buried cable;

[0150] When the difference between the target conductor temperature and the target operating temperature is less than or equal to the preset error value, the target initial current carrying capacity reference value is increased based on the difference to obtain the target historical current carrying capacity; the target conductor temperature is any conductor temperature among multiple conductor temperatures; the target initial current carrying capacity reference value is the initial current carrying capacity reference value corresponding to the target conductor temperature among multiple initial current carrying capacity reference values;

[0151] Integrate multiple target historical current carrying capacities to obtain historical dynamic current carrying capacities.

[0152] In some possible embodiments, in determining the conductor temperature of the direct buried cable corresponding to each time step in a plurality of time steps based on a plurality of initial current carrying capacity reference values ​​to obtain a plurality of conductor temperatures, the processing unit 802 is specifically configured to:

[0153] Obtain the number of conductor cores, insulation coefficient and cable diameter of the direct buried cable; the insulation coefficient is used to reflect the thermal capacity and thermal resistance of the insulation part of the direct buried cable;

[0154] Determine the conductor loss corresponding to each time step in a plurality of time steps based on the number of conductor cores and a plurality of initial current carrying capacity reference values, and obtain a plurality of conductor losses;

[0155] Determine the internal temperature rise of the conductor corresponding to each time step in a plurality of time steps based on a plurality of conductor losses and insulation coefficients, and obtain a plurality of internal temperature rises of the conductors;

[0156] Determine the conductor external temperature rise corresponding to each time step in a plurality of time steps based on a plurality of conductor losses, a plurality of soil thermal resistivities, a plurality of soil thermal diffusivities and a cable diameter, and obtain a plurality of conductor external temperature rises;

[0157] determining a plurality of historical soil temperatures corresponding to a plurality of time steps;

[0158] A conductor temperature corresponding to each time step in a plurality of time steps is determined based on a plurality of historical soil temperatures, a plurality of conductor internal temperature rises, and a plurality of conductor external temperature rises to obtain a plurality of conductor temperatures.

[0159] In some possible embodiments, in terms of integrating multiple target historical current carrying capacities to obtain historical dynamic current carrying capacities, the processing unit 802 is specifically configured to:

[0160] Determine a load current value corresponding to each time step in a plurality of time steps based on the historical cable load current, and obtain a plurality of load current values;

[0161] Determine a time difference of each time step in a plurality of time steps based on adjacent load current values ​​in a plurality of load current values, and obtain a plurality of time differences;

[0162] Determine a reference dynamic current carrying capacity of each of a plurality of time differences based on a plurality of target historical current carrying capacities, and obtain a plurality of reference dynamic current carrying capacities;

[0163] Based on multiple time steps and multiple time differences, multiple target historical current carrying capacities and multiple reference dynamic current carrying capacities are integrated to obtain the historical dynamic current carrying capacity.

[0164] In some possible embodiments, in determining the regression coefficient vector corresponding to the target quantile based on the target quantile, historical weather data, soil dynamic characteristic parameters, historical dynamic current carrying capacity, and historical cable load current, the processing unit 802 is specifically configured to:

[0165] Based on historical precipitation, historical soil temperature and historical cable load current, multiple feature matrices are constructed according to multiple time steps and preset time windows; each time step corresponds to a feature matrix;

[0166] Determine the current carrying capacity of the historical dynamic current carrying capacity corresponding to each characteristic matrix in the multiple characteristic matrices at the target quantile point, and obtain multiple current carrying capacities;

[0167] Determine multiple reference vectors corresponding to multiple current carrying capacity and multiple characteristic matrices based on a preset equation relationship; the equation relationship is used to reflect the corresponding relationship between multiple current carrying capacity, multiple characteristic matrices and regression coefficient vectors;

[0168] Construct the deviation loss function of the target quantile;

[0169] A regression coefficient vector is determined from multiple reference vectors based on a deviation loss function.

[0170] In some possible embodiments, the future weather data includes future soil temperature and future precipitation in a future time period; based on the future weather data, the future cable load current and the regression coefficient vector, in determining the future dynamic current carrying capacity corresponding to the target quantile of the direct buried cable in the future time period, the processing unit 802 is specifically used to:

[0171] Construct a prediction matrix based on future soil temperature, future precipitation, and future cable load current;

[0172] The future dynamic current carrying capacity corresponding to the target quantile is determined based on the regression coefficient vector and the prediction matrix.

[0173] See also Figure 5 , Figure 5 Schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5As shown, the electronic device 900 includes a transceiver 901, a processor 902 and a memory 903, which are connected via a bus 904. The memory 903 is used to store computer programs and data, and can transmit the data stored in the memory 903 to the processor 902. The electronic device can be the above-mentioned dynamic current carrying capacity prediction device for the direct buried cable, and the processor 902 can be the above-mentioned acquisition unit 801 and processing unit 802.

[0174] The processor 902 is used to read the computer program in the memory 903 and perform the following operations:

[0175] Obtain historical weather data and historical cable load current related to direct buried cables in a preset area in a historical time period; the historical weather data includes historical surface temperature and historical precipitation in a preset area in a historical time period;

[0176] Determine soil dynamic property parameters based on historical surface temperature and historical precipitation;

[0177] Determine the historical dynamic current carrying capacity of direct buried cables based on soil dynamic characteristic parameters and historical cable load current;

[0178] Obtain future weather data and future cable load current in a preset area in a future time period;

[0179] Determine the target quantile based on historical weather data, historical cable load current, future weather data and future cable load current;

[0180] Determine the regression coefficient vector corresponding to the target quantile based on the target quantile, historical weather data, soil dynamic characteristic parameters, historical dynamic current carrying capacity and historical cable load current;

[0181] Based on future weather data, future cable load current and regression coefficient vector, the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period is determined.

[0182] In some possible embodiments, the soil dynamic characteristic parameters include soil thermal diffusivity, soil thermal resistivity, and historical soil temperature; in determining the soil dynamic characteristic parameters based on historical surface temperature and historical precipitation, the processor 902 is specifically configured to perform the following operations:

[0183] Obtain soil composition, dry soil density and groundwater level reference temperature of a preset area; soil composition is used to reflect the proportion of sand and clay particles in the preset area;

[0184] Determine soil moisture content based on historical precipitation and a preset water diffusion equation;

[0185] Determine soil thermal diffusivity based on soil composition and soil moisture content;

[0186] Determine soil thermal resistivity based on dry soil density, soil moisture content, soil thermal diffusivity, and soil composition;

[0187] Determine the initial temperature range based on historical surface temperatures and groundwater level reference temperatures;

[0188] Determine historical soil temperature based on soil thermal diffusivity and initial temperature range.

[0189] In some possible embodiments, in determining the historical dynamic current carrying capacity of the direct buried cable based on the soil dynamic characteristic parameters and the historical cable load current, the processor 902 is specifically configured to perform the following operations:

[0190] Determine multiple time steps of the historical time period based on soil dynamic characteristic parameters and historical cable load current;

[0191] Determine multiple initial current carrying capacity reference values ​​corresponding to multiple time steps based on historical cable load current;

[0192] Determine the conductor temperature of the direct buried cable corresponding to each time step in a plurality of time steps based on a plurality of initial current carrying capacity reference values, and obtain a plurality of conductor temperatures;

[0193] Obtain the target operating temperature of the direct buried cable;

[0194] When the difference between the target conductor temperature and the target operating temperature is less than or equal to the preset error value, the target initial current carrying capacity reference value is increased based on the difference to obtain the target historical current carrying capacity; the target conductor temperature is any conductor temperature among multiple conductor temperatures; the target initial current carrying capacity reference value is the initial current carrying capacity reference value corresponding to the target conductor temperature among multiple initial current carrying capacity reference values;

[0195] Integrate multiple target historical current carrying capacities to obtain historical dynamic current carrying capacities.

[0196] In some possible embodiments, in determining the conductor temperature of the direct buried cable corresponding to each time step in a plurality of time steps based on a plurality of initial current carrying capacity reference values ​​to obtain a plurality of conductor temperatures, the processor 902 is specifically configured to perform the following operations:

[0197] Obtain the number of conductor cores, insulation coefficient and cable diameter of the direct buried cable; the insulation coefficient is used to reflect the thermal capacity and thermal resistance of the insulation part of the direct buried cable;

[0198] Determine the conductor loss corresponding to each time step in a plurality of time steps based on the number of conductor cores and a plurality of initial current carrying capacity reference values, and obtain a plurality of conductor losses;

[0199] Determine the internal temperature rise of the conductor corresponding to each time step in a plurality of time steps based on a plurality of conductor losses and insulation coefficients, and obtain a plurality of internal temperature rises of the conductors;

[0200] Determine the conductor external temperature rise corresponding to each time step in a plurality of time steps based on a plurality of conductor losses, a plurality of soil thermal resistivities, a plurality of soil thermal diffusivities and a cable diameter, and obtain a plurality of conductor external temperature rises;

[0201] determining a plurality of historical soil temperatures corresponding to a plurality of time steps;

[0202] A conductor temperature corresponding to each time step in a plurality of time steps is determined based on a plurality of historical soil temperatures, a plurality of conductor internal temperature rises, and a plurality of conductor external temperature rises to obtain a plurality of conductor temperatures.

[0203] In some possible embodiments, in terms of integrating multiple target historical current carrying capacities to obtain historical dynamic current carrying capacities, the processor 902 is specifically configured to perform the following operations:

[0204] Determine a load current value corresponding to each time step in a plurality of time steps based on the historical cable load current, and obtain a plurality of load current values;

[0205] Determine a time difference of each time step in a plurality of time steps based on adjacent load current values ​​in a plurality of load current values, and obtain a plurality of time differences;

[0206] Determine a reference dynamic current carrying capacity of each of a plurality of time differences based on a plurality of target historical current carrying capacities, and obtain a plurality of reference dynamic current carrying capacities;

[0207] Based on multiple time steps and multiple time differences, multiple target historical current carrying capacities and multiple reference dynamic current carrying capacities are integrated to obtain the historical dynamic current carrying capacity.

[0208] In some possible embodiments, in determining the regression coefficient vector corresponding to the target quantile based on the target quantile, historical weather data, soil dynamic characteristic parameters, historical dynamic current carrying capacity, and historical cable load current, the processor 902 is specifically configured to perform the following operations:

[0209] Based on historical precipitation, historical soil temperature and historical cable load current, multiple feature matrices are constructed according to multiple time steps and preset time windows; each time step corresponds to a feature matrix;

[0210] Determine the current carrying capacity of the historical dynamic current carrying capacity corresponding to each characteristic matrix in the multiple characteristic matrices at the target quantile point, and obtain multiple current carrying capacities;

[0211] Determine multiple reference vectors corresponding to multiple current carrying capacity and multiple characteristic matrices based on a preset equation relationship; the equation relationship is used to reflect the corresponding relationship between multiple current carrying capacity, multiple characteristic matrices and regression coefficient vectors;

[0212] Construct the deviation loss function of the target quantile;

[0213] A regression coefficient vector is determined from multiple reference vectors based on a deviation loss function.

[0214] In some possible embodiments, the future weather data includes future soil temperature and future precipitation in a future time period; based on the future weather data, the future cable load current and the regression coefficient vector, in determining the future dynamic current carrying capacity corresponding to the target quantile of the direct buried cable in the future time period, the processor 902 is specifically configured to perform the following operations:

[0215] Construct a prediction matrix based on future soil temperature, future precipitation, and future cable load current;

[0216] The future dynamic current carrying capacity corresponding to the target quantile is determined based on the regression coefficient vector and the prediction matrix.

[0217] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement part or all of the steps of any method for dynamic current carrying capacity prediction of a direct buried cable as recorded in the above method embodiments.

[0218] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any method for dynamic current carrying capacity prediction of a direct buried cable as recorded in the above method embodiments.

[0219] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0220] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0221] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the modules, which is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or module can be electrical or other forms.

[0222] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0223] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or software program modules.

[0224] If the integrated module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0225] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for predicting the dynamic current carrying capacity of a direct buried cable, characterized in that: include: Acquire historical weather data and historical cable load current related to direct buried cables in a preset area in a historical time period; the historical weather data includes historical surface temperature and historical precipitation in the preset area in the historical time period; Determining soil dynamic characteristic parameters based on the historical surface temperature and the historical precipitation; Determine the historical dynamic current carrying capacity of the direct buried cable based on the soil dynamic characteristic parameter and the historical cable load current; Acquire future weather data and future cable load current of the preset area in a future time period; determining a target quantile based on the historical weather data, the historical cable load current, the future weather data, and the future cable load current; Determine a regression coefficient vector corresponding to the target quantile based on the target quantile, the historical weather data, the soil dynamic characteristic parameter, the historical dynamic current carrying capacity and the historical cable load current; Based on the future weather data, the future cable load current and the regression coefficient vector, the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period is determined.

2. The method according to claim 1, characterized in that The soil dynamic characteristic parameters include soil thermal diffusivity, soil thermal resistivity and historical soil temperature; the soil dynamic characteristic parameters are determined based on the historical surface temperature and the historical precipitation, including: Acquire the soil composition, dry soil density and groundwater level reference temperature of the preset area; the soil composition is used to reflect the ratio of sand and clay particles in the preset area; Determining the soil moisture content based on the historical precipitation and a preset water diffusion equation; determining the soil thermal diffusivity based on the soil composition and the soil moisture content; determining the soil thermal resistivity based on the dry soil density, the soil water content, the soil thermal diffusivity, and the soil composition; determining an initial temperature range based on the historical surface temperature and the groundwater level reference temperature; The historical soil temperature is determined based on the soil thermal diffusivity and the initial temperature range.

3. The method according to claim 2, characterized in that The determining of the historical dynamic current carrying capacity of the direct buried cable based on the soil dynamic characteristic parameter and the historical cable load current comprises: Determining a plurality of time steps of the historical time period based on the soil dynamic characteristic parameter and the historical cable load current; Determine a plurality of initial current carrying capacity reference values ​​corresponding to the plurality of time steps based on the historical cable load current; Determine the conductor temperature of the direct buried cable corresponding to each time step in a plurality of time steps based on the plurality of initial current carrying capacity reference values, and obtain a plurality of conductor temperatures; Obtaining a target operating temperature of the direct buried cable; When the difference between the target conductor temperature and the target operating temperature is less than or equal to a preset error value, the target initial current carrying capacity reference value is increased based on the difference to obtain a target historical current carrying capacity; the target conductor temperature is any conductor temperature among the multiple conductor temperatures; the target initial current carrying capacity reference value is an initial current carrying capacity reference value corresponding to the target conductor temperature among the multiple initial current carrying capacity reference values; A plurality of target historical current carrying capacities are integrated to obtain the historical dynamic current carrying capacity.

4. The method according to claim 3, characterized in that The method of determining the conductor temperature of the direct buried cable corresponding to each time step in a plurality of time steps based on the plurality of initial current carrying capacity reference values ​​to obtain a plurality of conductor temperatures includes: Obtaining the number of conductor cores, insulation coefficient and cable diameter of the direct buried cable; the insulation coefficient is used to reflect the thermal capacity and thermal resistance of the insulation part of the direct buried cable; Determine the conductor loss corresponding to each time step in a plurality of time steps based on the number of conductor cores and the plurality of initial current carrying capacity reference values, and obtain a plurality of conductor losses; Determine the internal temperature rise of the conductor corresponding to each time step in the multiple time steps based on the multiple conductor losses and the insulation coefficient, and obtain multiple internal temperature rises of the conductors; Determine the conductor external temperature rise corresponding to each time step in the multiple time steps based on the multiple conductor losses, the soil thermal resistivity, the multiple soil thermal diffusivities and the cable diameter, and obtain multiple conductor external temperature rises; determining a plurality of historical soil temperatures corresponding to the plurality of time steps; The conductor temperature corresponding to each time step in a plurality of time steps is determined based on the plurality of historical soil temperatures, the plurality of internal temperature rises of the conductors, and the plurality of external temperature rises of the conductors to obtain the plurality of conductor temperatures.

5. The method according to claim 3 or 4, characterized in that The integrating multiple target historical current carrying capacities to obtain the historical dynamic current carrying capacity includes: Determine a load current value corresponding to each time step in the multiple time steps based on the historical cable load current to obtain multiple load current values; Determine a time difference of each time step in the multiple time steps based on adjacent load current values ​​in the multiple load current values ​​to obtain multiple time differences; Determine a reference dynamic current carrying capacity of each of the multiple time differences based on the multiple target historical current carrying capacities, and obtain multiple reference dynamic current carrying capacities; Based on the multiple time steps and the multiple time differences, the multiple target historical current carrying capacities and the multiple reference dynamic current carrying capacities are integrated to obtain the historical dynamic current carrying capacities.

6. The method according to claim 2, characterized in that The step of determining the regression coefficient vector corresponding to the target quantile based on the target quantile, the historical weather data, the soil dynamic characteristic parameter, the historical dynamic current carrying capacity and the historical cable load current includes: Based on the historical precipitation, the historical soil temperature and the historical cable load current, construct multiple feature matrices according to the multiple time steps and the preset time windows; each time step corresponds to a feature matrix; Determine the current carrying capacity of the historical dynamic current carrying capacity corresponding to each characteristic matrix in the multiple characteristic matrices at the target quantile point to obtain multiple current carrying capacities; Determine a plurality of reference vectors corresponding to the plurality of current carrying capacities and the plurality of characteristic matrices based on a preset equation relationship; the equation relationship is used to reflect the corresponding relationship between the plurality of current carrying capacities, the plurality of characteristic matrices and the regression coefficient vector; Constructing a deviation loss function of the target quantile; The regression coefficient vector is determined from the plurality of reference vectors based on the deviation loss function.

7. The method according to claim 6, characterized in that The future weather data includes the future soil temperature and future precipitation in the future time period; the determining the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period based on the future weather data, the future cable load current and the regression coefficient vector includes: constructing a prediction matrix based on the future soil temperature, the future precipitation, and the future cable load current; The future dynamic current carrying capacity corresponding to the target quantile is determined based on the regression coefficient vector and the prediction matrix.

8. A dynamic current-carrying capacity prediction device for a direct buried cable, characterized in that: The device comprises an acquisition unit and a processing unit; The acquisition unit is used to acquire historical weather data and historical cable load current related to the direct buried cables in a preset area in a historical time period; the historical weather data includes the historical surface temperature and historical precipitation of the preset area in the historical time period; The processing unit is used to determine soil dynamic characteristic parameters based on the historical surface temperature and the historical precipitation; Determine the historical dynamic current carrying capacity of the direct buried cable based on the soil dynamic characteristic parameter and the historical cable load current; Acquire future weather data and future cable load current of the preset area in a future time period; determining a target quantile based on the historical weather data, the historical cable load current, the future weather data, and the future cable load current; Determine a regression coefficient vector corresponding to the target quantile based on the target quantile, the historical weather data, the soil dynamic characteristic parameter, the historical dynamic current carrying capacity and the historical cable load current; Based on the future weather data, the future cable load current and the regression coefficient vector, the future dynamic current carrying capacity of the direct buried cable corresponding to the target quantile in the future time period is determined.

9. An electronic device, characterized in that: include: A processor and a memory, the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images