Ring main unit temperature and humidity prediction method and device and storage medium

Abstract

The invention discloses a ring main unit temperature and humidity prediction method and device and a storage medium. Ring main unit temperature and humidity serve as input feature data, BiLSTM serves as a prediction model, the BiLSTM has higher time sequence modeling capacity, through simultaneous modeling in the forward direction and the backward direction, context information can be more comprehensively understood, the strong fitting capacity for nonlinear data is achieved, and the prediction accuracy of the ring main unit temperature and humidity is improved. The long-term and short-term dependency relationship can be effectively processed, and the prediction precision and robustness are improved. And a Softmax activation function is used to improve the convergence performance of the model. The ring main unit prediction model based on the bidirectional long short-term memory network can realize accurate and efficient ring main unit temperature and humidity prediction. Related personnel utilize the prediction result to realize real-time monitoring of temperature and humidity changes, discover abnormal conditions in time and take corresponding measures. Meanwhile, when an abnormal condition occurs, the system can automatically trigger an early warning mechanism to inform related personnel to deal with the abnormal condition, so that equipment damage or safety problems are avoided.

Description

Technical Field

[0001] This application relates to the field of power operation and maintenance technology, and in particular to a method, equipment and storage medium for predicting the temperature and humidity of a ring main unit. Background Technology

[0002] As the core carrier of the next-generation power system, the smart grid urgently needs to introduce artificial intelligence technology to improve the overall operating efficiency and reliability of power equipment. Ring main units (RMS), as key equipment in urban distribution networks, directly affect the operational reliability of the equipment and the safety and stability of the power grid due to their internal temperature and humidity conditions. Faults are inevitable due to complex factors. RMS are mostly deployed outdoors, facing harsh environments such as high temperatures, humidity, and dust. Traditional sensors are prone to corrosion and failure, and the wiring is complex, resulting in high maintenance costs. During long-term operation, RMS are susceptible to abnormal local temperature rises due to factors such as aging cable joints, increased contact resistance, and changes in equipment load. If temperature and humidity are not controlled in a timely manner, it may lead to equipment failure, decreased insulation performance, or even fires or large-scale power outages. Therefore, real-time monitoring and prediction of RMS temperature and humidity are of great significance for preventing faults, optimizing operation and maintenance strategies, and reducing operational risks.

[0003] Currently, methods for predicting temperature and humidity data mainly include traditional models such as time series models, machine learning models, and neural network models. Traditional methods cannot accurately make complex predictions. While machine learning methods can handle complex nonlinear problems, they face certain difficulties in processing large-scale data. In recent years, deep learning technology, especially recurrent neural networks (RNNs) and their improved structures (such as Long Short-Term Memory networks (LSTM) and gated recurrent units (GRUs), has shown significant advantages in processing time series data with long-term dependencies. LSTM can effectively alleviate the gradient vanishing problem through a "gating mechanism," thereby learning contextual information over long time spans. Bidirectional LSTM (BiLSTM) further introduces information from the reverse time dimension, considering both past and future contexts at each moment (during the training phase), thus capturing the dynamic characteristics of the time series more comprehensively. This structure has achieved good results in meteorological forecasting, power load forecasting, and equipment condition monitoring. However, a scientifically effective method for predicting temperature and humidity in ring main units based on bidirectional LSTM models is still lacking. Summary of the Invention

[0004] This application provides a method, device, and storage medium for predicting the temperature and humidity of a ring main unit, in order to solve the above-mentioned problems.

[0005] On the one hand, this application provides a method for predicting the temperature and humidity of a ring main unit, the method comprising the following steps: Step S1: Collect raw temperature and humidity data of the ring main unit and perform preprocessing; Step S2: Construct a temperature and humidity prediction model based on a bidirectional long short-term memory network, and train the temperature and humidity prediction model using the preprocessed data as input features; Step S3: Optimize the temperature and humidity prediction model using cross-validation. Step S4: Input the temperature and humidity related data of the ring main unit to be predicted into the optimized temperature and humidity prediction model, and output the temperature and humidity prediction results of the ring main unit to be predicted.

[0006] In one implementation of this application, step S1, the preprocessing specifically includes: sequentially performing data supplementation, outlier removal, and normalization on the original temperature and humidity data; the data supplementation uses spline interpolation, the outlier removal uses z-score detection combined with IQR, and the normalization uses min-max normalization; the spline interpolation method is cubic spline interpolation, and the known data points are set as (x0, y0), (x1, y1)...(x... n ,y n The mathematical expression for each interval [xi, xi+1] is:

[0007] Where (ai,bi,ci,di) are the coefficients of the piecewise polynomial, which are solved by the continuity condition and the boundary condition.

[0008] In one implementation of this application, the specific process of outlier removal is as follows: Let h = {h1, h2, ..., h} n Let T be a humidity data sequence, where T = {T1, T2, ..., T}. n Given a temperature data series, calculate the mean and standard deviation of the humidity data h, and the mean and standard deviation of the temperature data T. Calculate the z-scores Zh and ZT for humidity and temperature data respectively. If |Zh|>z comparison value or |ZT|>z comparison value, the corresponding data is determined to be an outlier. Calculate the interquartile range (IQRh) of humidity data and the interquartile range (IQRT) of temperature data, and combine them with the first quartile (Q1) and the third quartile (Q3) to remove outliers using the IQR method.

[0009] In one implementation of this application, the formula for the minimum-maximum normalization method is:

[0010] In the formula, X represents the original data. minLet X be the minimum value of feature X. max The maximum value of feature X is used to map the normalized data to the interval [0, 1].

[0011] In one implementation of this application, the temperature and humidity prediction model employs a two-layer BiLSTM structure, with a fully connected output layer and a Softmax activation function. The specific settings of the two-layer BiLSTM structure are as follows: The first BiLSTM layer contains two parallel LSTM layers, which process the input feature sequences from front to back and from back to front, respectively. The outputs of the two LSTM layers are merged by concatenation or summation to achieve bidirectional time dependency modeling. The second layer of BiLSTM further processes the features output by the first layer, maintaining the same output dimension as the first layer, thus enhancing the expressive power of complex temporal patterns.

[0012] In one implementation of this application, the cross-validation method specifically involves: dividing the training set into multiple subsets, selecting each subset as the validation set in turn, using the remaining subsets as the training subsets, repeatedly training and validating the model, and adjusting the model parameters based on the validation results to improve the model's generalization ability.

[0013] In one implementation of this application, the method further includes: real-time monitoring of temperature and humidity changes in the ring main unit based on the temperature and humidity prediction results; and automatically triggering an early warning mechanism to notify relevant personnel to handle the situation when the prediction results exceed the preset normal range.

[0014] In one implementation of this application, mean square error and coefficient of determination are used as evaluation indicators to determine whether the temperature and humidity prediction model has been trained successfully. The formula for mean square error is:

[0015] The formula for the coefficient of determination is:

[0016] In the formula: n is the total number of samples; This represents the true value of the i-th sample. Let be the predicted value for the i-th sample; For the true value The average value.

[0017] Secondly, this application also provides a ring main unit temperature and humidity prediction device, the device comprising: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which are executed by the at least one processor to enable the at least one processor to complete the aforementioned method for predicting the temperature and humidity of a ring main unit.

[0018] Finally, this application also provides a non-volatile computer storage medium for predicting the temperature and humidity of a ring main unit, which stores computer-executable instructions, which are executed by a processor to implement the aforementioned method for predicting the temperature and humidity of a ring main unit.

[0019] The ring main unit temperature and humidity prediction method, equipment, and storage medium provided in this application have the following beneficial effects: 1. By combining spline interpolation, z-score detection, and IQR method to preprocess the original temperature and humidity data, we achieved efficient handling of missing and outlier values, improved the integrity and quality of the input data, and provided a reliable data foundation for model training.

[0020] 2. By constructing a two-layer BiLSTM network structure and combining forward and backward LSTMs to perform bidirectional modeling of time series data, we have achieved in-depth capture and high-precision prediction of the temperature and humidity variation patterns of ring main units, which significantly improves the model's fitting ability and robustness in complex nonlinear scenarios.

[0021] 3. By introducing cross-validation to optimize model parameters and combining mean square error and coefficient of determination for model evaluation, a systematic tuning and performance verification of the prediction model was achieved, improving the model's generalization ability and providing reliable technical support for early warning and real-time monitoring of abnormal temperature and humidity. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 A flowchart of a method for predicting temperature and humidity in a ring main unit provided in this application embodiment; Figure 2 This is a flowchart of the BiLSTM model in the embodiments of this application; Figure 3 This is a comparison chart of the predicted and measured temperatures of the ring main unit in the embodiments of this application; Figure 4 This is a comparison chart of the predicted and measured humidity values ​​of the ring main unit in the embodiments of this application; Figure 5 This is a schematic diagram of a ring main unit temperature and humidity prediction device provided in an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] This application provides a method, device, and storage medium for predicting the temperature and humidity of a ring main unit. The technical solution proposed in this application will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 This is a flowchart illustrating a method for predicting the temperature and humidity of a ring main unit, as provided in an embodiment of this application. Figure 1 As shown, the method mainly includes the following steps: Step S1: Collect raw temperature and humidity data of the ring main unit and perform preprocessing; Step S2: Construct a temperature and humidity prediction model based on a bidirectional long short-term memory network, and train the temperature and humidity prediction model using the preprocessed data as input features; Step S3: Optimize the temperature and humidity prediction model using cross-validation. Step S4: Input the temperature and humidity related data of the ring main unit to be predicted into the optimized temperature and humidity prediction model, and output the temperature and humidity prediction results of the ring main unit to be predicted.

[0026] Specifically, spline interpolation is used to fill in missing values ​​in the temperature and humidity data. Spline interpolation can better balance the fitting accuracy and smoothness of the data, while effectively avoiding overfitting that may occur in multiple polynomial interpolations. Specifically, given known data points as (x0, y0), (x1, y1)...(xn, yn), the mathematical expression for cubic spline interpolation on each interval [xi, xi+1] is:

[0027] Where (ai,bi,ci,di) are the coefficients of the piecewise polynomial, solved using continuity and boundary conditions. By supplementing the missing portions of the temperature and humidity data of the ring main unit using spline interpolation, the integrity of the data can be restored to the maximum extent, reducing the adverse effects of missing values ​​on subsequent analysis and prediction models, and providing more reliable data support for the intelligent management of the ring main unit environment.

[0028] Furthermore, the standard score z-score is used to remove outliers from the temperature and humidity data. Let h = {h1, h2, ..., hn} be the humidity data sequence, and T = {T1, T2, ..., Tn} be the temperature data sequence. The z-score is used to detect outliers:

[0029] in, and These are the mean and standard deviation of the humidity data h, respectively. and These are the mean and standard deviation of the temperature data T. If |z h |>z 比较值 or | |>z 比较值 Then it is considered that h i or T i Outliers are removed using the IQR method:

[0030] Among them, Z h ZT is the z-score of the humidity value, and IQR is the z-score of the humidity value. h IQR is the interquartile range of humidity data. T Q1 and Q3 represent the interquartile range of the temperature data, respectively, and are the first and third quartiles of the humidity and temperature data.

[0031] Furthermore, data on the external temperature and humidity of the ring main unit, the internal temperature and humidity of the ring main unit, the highest internal temperature, the lowest internal temperature, and the average internal temperature of the ring main unit were collected. After performing data preprocessing such as outlier handling and data supplementation on the raw temperature and humidity data, the preprocessed temperature and humidity data were normalized.

[0032] To improve the efficiency of model training and reduce the impact of differences in feature values ​​on prediction performance, the input data was normalized. Specifically, the Min-Max Normalization method was used to linearly map all feature values ​​to the interval [0, 1], as shown in the following formula:

[0033] In the formula: X represents the original data, X min Let X be the minimum value of feature X. max Let X be the maximum value of feature X. Normalization can effectively reduce the impact of scale differences between features on model convergence and improve the model's prediction accuracy.

[0034] The extracted data on external temperature and humidity of the ring main unit, internal temperature and humidity of the ring main unit, maximum internal temperature of the ring main unit, minimum internal temperature of the ring main unit, and average internal temperature of the ring main unit are preprocessed and normalized, and used as input features for the model.

[0035] The LSTM network prediction model used in this application yields results that more closely approximate the actual temperature and humidity values ​​of the ring main unit, indicating its higher accuracy in fitting nonlinear test data. The temperature and humidity data of the ring main unit exhibits significant temporal continuity and periodicity (e.g., daily and seasonal variations). LSTM models are inherently adept at handling long-term dependencies in time series, while BiLSTM, through simultaneous forward and backward modeling, can more comprehensively understand contextual information. Furthermore, temperature and humidity are influenced by various factors (e.g., air pressure, wind speed, geographical location, solar radiation), exhibiting a high degree of nonlinearity. As a deep neural network, BiLSTM possesses strong fitting capabilities for nonlinear dynamic systems and can automatically learn complex input-output relationships. Actual sensor-collected temperature and humidity data often contains noise or missing values. BiLSTM demonstrates strong noise resistance. Through gating mechanisms (input gate, forget gate, output gate), BiLSTM can effectively filter irrelevant or redundant information, improving robustness. Therefore, this paper employs a bidirectional long short-term memory network as the prediction model.

[0036] This application establishes a bidirectional long short-term memory (BiLSTM) network prediction model based on historical temperature and humidity data of ring main units. The data used includes external temperature and humidity of the ring main unit, internal temperature and humidity, maximum internal temperature, minimum internal temperature, and average internal temperature. This information is crucial for accurately predicting the temperature and humidity of the ring main unit. Traditional ring main unit temperature and humidity prediction models are insufficient in mining the inherent correlations within the data, particularly in effectively capturing the long- and short-term dependencies and interactions between multidimensional features in time-series data. Therefore, this paper proposes a temperature and humidity prediction model based on a bidirectional long short-term memory network (BiLSTM) to perform deep modeling of the fused feature sequence. This model adopts a two-layer structure, processing the time series in parallel through two LSTM branches: the forward LSTM learns the influence of historical temperature and humidity states on the current value from the past to the present, while the backward LSTM looks back from the future to the present, capturing the implicit feedback of potential subsequent changes on the current state. The two work together to comprehensively characterize the bidirectional dependencies in the time dimension, thereby improving prediction accuracy and robustness. The ring main unit prediction model specifically includes the following modules: First-layer BiLSTM: models bidirectional time dependencies; Second-layer BiLSTM: enhances the expressive power of complex temporal patterns, maintaining the same output dimension to achieve feature deepening; Fully connected output layer: maps spatiotemporal features to predicted temperature and humidity values, using the SoftMax activation function.

[0037] The model input data includes parameters such as external temperature and humidity of the ring main unit, internal temperature and humidity of the ring main unit, highest internal temperature, lowest internal temperature of the ring main unit, and average internal temperature of the ring main unit. Historical temperature and humidity data are used to train the model, and methods such as cross-validation are employed to optimize the model, improving its generalization ability and prediction accuracy. The model is built using training set samples, with a learning rate set to 0.01 and 200 training epochs.

[0038] To comprehensively evaluate the predictive performance of the model in this paper, mean squared error (MSE) and coefficient of determination (R²) were selected. 2 These two parameters serve as the primary evaluation metrics. MSE is suitable for continuous variable prediction scenarios, accurately measuring the model's sensitivity to overall error. It can significantly reflect problems when the model has large prediction bias, which is particularly important for scenarios seeking high-precision predictions. R 2 As a measure of global performance, it can clearly indicate the overall fitting effect of the model. It has a clear quantization range (0, 1), which facilitates the comparison of different models.

[0039] The formula for mean squared error (MSE) is as follows:

[0040] R 2 The formula is as follows:

[0041] In the formula: n is the total number of samples; This represents the true value of the i-th sample. Let be the predicted value for the i-th sample; For the true value The average value.

[0042] The prediction model results in this paper are as follows:

[0043] In this application, the overall flowchart of the model is as follows: Figure 2 As shown, the extracted data on external temperature and humidity of the ring main unit, internal temperature and humidity of the ring main unit, maximum internal temperature, minimum internal temperature of the ring main unit, and average internal temperature of the ring main unit undergo data preprocessing such as outlier removal and data supplementation, followed by normalization, and are used as input features for the model. A Bidirectional Long Short-Term Memory (BiLSTM) network is used as the prediction model, with the Softmax function as the activation function, and the final output is the predicted temperature and humidity results.

[0044] In this application, the comparison between the predicted and measured temperatures of the ring main unit is as follows: Figure 3 As shown, the comparison between predicted and measured humidity values ​​is as follows: Figure 4As shown in the figure, it can be seen that the model proposed in this application is very close to the measured value in terms of prediction accuracy.

[0045] The above is a method for predicting the temperature and humidity of a ring main unit provided in the embodiments of this application. Based on the same inventive concept, the embodiments of this application also provide a device for predicting the temperature and humidity of a ring main unit. Figure 5 A schematic diagram of a ring main unit temperature and humidity prediction device provided in an embodiment of this application is shown below. Figure 5 As shown, the device mainly includes: at least one processor 501; and a memory 502 communicatively connected to the at least one processor; wherein the memory 502 stores instructions that can be executed by the at least one processor 501, and the instructions are executed by the at least one processor 501 to enable the at least one processor 501 to complete the aforementioned method for predicting the temperature and humidity of a ring main unit.

[0046] In addition, this application embodiment also provides a non-volatile computer storage medium for predicting the temperature and humidity of a ring main unit, which stores computer-executable instructions, which are executed by a processor to implement the aforementioned method for predicting the temperature and humidity of a ring main unit.

[0047] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0048] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0049] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0050] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0051] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0052] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0053] The above description is merely an embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of this application should be included within the scope of the claims of this application.

Claims

1. A method for predicting temperature and humidity in a ring main unit, characterized in that, The method includes the following steps: Step S1: Collect raw temperature and humidity data of the ring main unit and perform preprocessing; Step S2: Construct a temperature and humidity prediction model based on a bidirectional long short-term memory network, and train the temperature and humidity prediction model using the preprocessed data as input features; Step S3: Optimize the temperature and humidity prediction model using cross-validation. Step S4: Input the temperature and humidity related data of the ring main unit to be predicted into the optimized temperature and humidity prediction model, and output the temperature and humidity prediction results of the ring main unit to be predicted.

2. The method for predicting temperature and humidity in a ring main unit according to claim 1, characterized in that, In step S1, the preprocessing specifically includes: performing data supplementation, outlier removal, and normalization on the original temperature and humidity data sequentially; the data supplementation uses spline interpolation, the outlier removal uses z-score detection combined with IQR, and the normalization uses min-max normalization; the spline interpolation method is cubic spline interpolation, with known data points set as (x0, y0), (x1, y1)...(x...). n ,y n The mathematical expression for each interval [xi, xi+1] is: Where (ai,bi,ci,di) are the coefficients of the piecewise polynomial, which are solved by the continuity condition and the boundary condition.

3. The method for predicting temperature and humidity in a ring main unit according to claim 2, characterized in that, The specific process of outlier removal is as follows: Let h = {h1, h2, ..., h} n Let T be a humidity data sequence, where T = {T1, T2, ..., T}. n Given a temperature data series, calculate the mean and standard deviation of the humidity data h, and the mean and standard deviation of the temperature data T. Calculate the z-scores Zh and ZT for humidity and temperature data respectively. If |Zh|>z comparison value or |ZT|>z comparison value, the corresponding data is determined to be an outlier. Calculate the interquartile range (IQRh) of humidity data and the interquartile range (IQRT) of temperature data, and combine them with the first quartile (Q1) and the third quartile (Q3) to remove outliers using the IQR method.

4. The method for predicting temperature and humidity in a ring main unit according to claim 2, characterized in that, The formula for the minimum-maximum normalization method is: In the formula, X represents the original data. min Let X be the minimum value of feature X. max The maximum value of feature X is used to map the normalized data to the interval [0, 1].

5. The method for predicting temperature and humidity in a ring main unit according to claim 1, characterized in that, The temperature and humidity prediction model employs a two-layer BiLSTM structure, with a fully connected output layer and a Softmax activation function. The specific settings of the two-layer BiLSTM structure are as follows: The first BiLSTM layer contains two parallel LSTM layers, which process the input feature sequences from front to back and from back to front, respectively. The outputs of the two LSTM layers are merged by concatenation or summation to achieve bidirectional time dependency modeling. The second layer of BiLSTM further processes the features output by the first layer, maintaining the same output dimension as the first layer, thus enhancing the expressive power of complex temporal patterns.

6. The method for predicting temperature and humidity in a ring main unit according to claim 1, characterized in that, The cross-validation method involves dividing the training set into multiple subsets, selecting each subset as the validation set, and using the remaining subsets as the training subsets. The model is then repeatedly trained and validated. Based on the validation results, the model parameters are adjusted to improve the model's generalization ability.

7. The method for predicting temperature and humidity in a ring main unit according to claim 1, characterized in that, The method further includes: real-time monitoring of temperature and humidity changes in the ring main unit based on the temperature and humidity prediction results; when the prediction results exceed the preset normal range, an early warning mechanism is automatically triggered to notify relevant personnel for handling.

8. The method for predicting temperature and humidity in a ring main unit according to claim 1, characterized in that, The mean square error and coefficient of determination are used as evaluation indicators to determine whether the temperature and humidity prediction model has been successfully trained. The formula for the mean square error is: The formula for the coefficient of determination is: Where: n is the total number of samples; This represents the true value of the i-th sample. Let be the predicted value for the i-th sample; For the true value The average value.

9. A ring main unit temperature and humidity prediction device, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform a method for predicting the temperature and humidity of a ring main unit as described in any one of claims 1-8.

10. A non-volatile computer storage medium for predicting temperature and humidity in a ring main unit, storing computer-executable instructions, characterized in that, The computer-executable instructions are executed by the processor to implement the method for predicting the temperature and humidity of a ring main unit as described in any one of claims 1-8.

Images