A load forecasting and scheduling method adapted to thermal user behavior

Abstract

The present invention discloses a load forecasting and scheduling method adapted to the behavior of heat users, relates to the technical field of load forecasting, and solves the technical problem in the prior art that it is difficult to capture all factors affecting the load when using linear methods to deal with complex problems. Specifically, historical load data of a source-side pipeline network is collected, and the behavior patterns of heat users are analyzed; a pipeline network load simulation model is established based on the historical load data and the behavior patterns of heat users; the real-time operation status of the pipeline network is simulated by using digital twin technology, and the behavior data of heat users is updated in real time; the load changes of the pipeline network are predicted in real time according to the simulation results and the real-time updated behavior data of heat users; adaptive regulation and scheduling are performed according to the prediction results to adapt to the real-time and changeable switching needs of heat users; and the regulation and control strategy is optimized by a machine learning algorithm to ensure the optimization of the scheduling plan.

Description

Technical Field

[0001] The present invention relates to the technical field of load forecasting, and specifically to a load forecasting and scheduling method adapted to the behavior of heat users. Background Art

[0002] Currently, load forecasting techniques mainly rely on the following methods:

[0003] Artificial intelligence techniques: In recent years, artificial intelligence techniques have been widely applied in load forecasting, especially in new power systems. These techniques include deep learning, neural networks, machine learning, etc., and are used to process complex and ever-changing load data.

[0004] Traditional forecasting models: Include time series methods, regression analysis methods, etc. These methods still play a role in short-term load forecasting.

[0005] Gas load forecasting techniques: With the development of the natural gas industry, gas load forecasting techniques are also constantly evolving. These techniques are not only related to the investment efficiency and reliability of the pipeline network, but also related to the ability of gas pipeline network planning and optimal operation.

[0006] Some patents of the prior art closest to the above patent technology:

[0007] Intelligent Grid Short-Term Load Forecasting Method (CN114169645A): This technology provides an intelligent grid short-term load forecasting method. By combining data preprocessing technology and load forecasting technology, the LMD algorithm is used to combine reinforcement learning and deep learning to reduce the error of intelligent grid short-term load forecasting data.

[0008] Power Load Forecasting Method Based on Neural Network (CN114444750A): This invention discloses a power load forecasting method based on neural network. Using relevant data affecting power load, a power load forecasting model based on BP neural network is established to improve the efficiency and accuracy of power load forecasting.

[0009] Load Forecasting and Analysis Method for Typical Urban Cable Network Systems: This technology constructs an urban power grid spatial load forecasting platform based on power GIS, proposes an urban power grid spatial load forecasting method and forecasting model, and realizes the optimal output of forecasting load accuracy.

[0010] Regional Distribution Network Short-Term Load Forecasting Method: This invention relates to a regional distribution network short-term load forecasting method based on twin network classification method, grey wolf algorithm and long short-term memory network, which effectively solves the problems of low efficiency, high operation cost and lack of adaptability of existing forecasting models.

[0011] In view of the above technical deficiencies, a solution is now proposed. Summary of the Invention

[0012] The object of the present invention is to solve the above-mentioned problems, and to propose a load prediction and scheduling method adapted to the behavior of heat users, and the specific technical problems to be solved are as follows:

[0013] 1. High data requirements: Strong dependence on historical data, and a large amount of accurate and detailed data is required.

[0014] 2. Simple model: Using linear methods to handle complex problems, it is difficult to capture all factors affecting the load.

[0015] 3. Insufficient accuracy: The fitting degree between the prediction result and the actual load is low, and the error is large.

[0016] 4. Difficulty in adapting to changes: The load of the power system is affected by various factors, such as weather, seasonal changes, etc., and it is difficult for the existing technologies to adapt to the uncertainties of these changes.

[0017] The object of the present invention can be achieved by the following technical solutions:

[0018] A load prediction and scheduling method adapted to the behavior of heat users, comprising the following steps:

[0019] Step 1: Collect historical load data of the source-side pipe network and analyze the behavior patterns of heat users;

[0020] Step 2: Based on the historical load data and the behavior patterns of heat users, establish a pipe network load simulation model;

[0021] Step 3: Use digital twin technology to simulate the real-time operation state of the pipe network and update the behavior data of heat users in real time;

[0022] Step 4: According to the simulation results and the behavior data of heat users updated in real time, conduct real-time prediction of the load change of the pipe network;

[0023] Step 5: According to the prediction results, perform adaptive regulation and scheduling to adapt to the real-time and variable switching requirements of heat users;

[0024] Step 6: Optimize the regulation strategy through machine learning algorithms to ensure the optimization of the scheduling plan.

[0025] As a preferred embodiment of the present invention, the specific steps of Step 1 are as follows:

[0026] Step 11 Data collection: Determine data collection points, such as user access points, key nodes; use sensors and smart meters to collect load data at each collection point; transmit the collected data to the central database for storage and processing;

[0027] Step 12 Data preprocessing: Clean the data, remove outliers and noise; standardize the data to ensure the consistency of different data sources; perform data aggregation, such as summarizing the load data by hour or day.

[0028] Step 13 Analysis of heat user behavior patterns: Use clustering algorithms to classify user behaviors and identify different behavior patterns.

[0029] Clustering algorithm: ; where is the i-th cluster, k is the number of clusters, is the set of points in the j-th cluster, is the center point of

[0030] Apply the association rule learning algorithm to find the correlations between user behaviors; Association rule learning: ; where A and B are item sets, is the frequency of item set A in all transactions, represents the probability that B occurs given that A has occurred;

[0031] Time series analysis: ; where is the observed value at time t, c is the constant term, is the white noise error term, is the autoregressive coefficient, is the moving average coefficient, and p and q are the orders of autoregression and moving average respectively; Use time series analysis methods to analyze the changing trend of user behaviors over time.

[0032] As a preferred embodiment of the present invention, the specific steps of step 2 are as follows:

[0033] Step 21: Adopt the Seasonal Autoregressive Integrated Moving Average Model (SARIMA) to characterize the load characteristics and construct a pipe network load simulation model:

[0034] ; where L is the lag operator, s is the seasonal period, and (P, D, Q) are the orders of seasonal autoregression, differencing, and moving average;

[0035] Complete the construction of the pipe network load simulation model according to the selected mathematical model:

[0036] Step 22: Estimate the parameters of the selected model based on the historical load data and heat user behavior patterns;

[0037] Use the least squares method to fit the model parameters;

[0038] Validate and adjust the model to ensure that its prediction performance meets the requirements of practical applications;

[0039] Step 23: The goal of parameter estimation is to find a set of parameters ( , , , ) such that the model best fits the historical load data; this can be achieved by minimizing the sum of the squares of the error terms ;

[0040] Least squares fitting: The objective function of the least squares method can be expressed as: ;

[0041] Model validation and adjustment: Model validation usually involves calculating the differences between the predicted values and the actual observed values, such as the mean squared error (MSE) or the root mean squared error (RMSE): ;

[0042] where T is the number of test data points, is the load value predicted by the model; by comparing the MSE or RMSE of different parameter sets, the best model parameters can be selected and used to predict future loads, and the model can be further adjusted and optimized according to the requirements of practical applications.

[0043] As a preferred embodiment of the present invention, the application of the digital twin technology in step 3 further includes:

[0044] Step 31: Build a digital twin platform;

[0045] Step 32: Create a virtual copy of the pipe network on the digital twin platform;

[0046] Step 33: Input the real-time load data into the virtual copy;

[0047] Step 34: Simulate the operating state of the pipe network through the virtual copy.

[0048] As a preferred embodiment of the present invention, the real-time prediction of the pipe network load change in step 4 further includes:

[0049] Step 41: Analyze the data provided by the digital twin platform;

[0050] Step 42: Use machine learning algorithms to predict future loads;

[0051] Step 43: Evaluate the accuracy of the prediction results.

[0052] As a preferred embodiment of the present invention, it is as follows:

[0053] Collect real-time data: Collect real-time load data from sensors and monitoring systems in the pipe network; simultaneously collect the behavioral data of heat users, such as usage frequency and duration;

[0054] Data integration: Integrate the real-time load data with the behavioral data of heat users; use data preprocessing techniques to ensure data quality, such as removing noise and filling missing values;

[0055] Update model input: Input the integrated real-time data into the established pipe network load simulation model; update the model parameters to reflect the latest user behavior and load conditions;

[0056] Load prediction: Use the simulation model to predict the pipe network load for a future period of time; apply time series analysis, machine learning or other prediction techniques to generate prediction results;

[0057] Result analysis: Analyze the prediction results to identify possible load peaks or troughs; adjust the pipe network operation strategy according to the prediction results;

[0058] As a preferred embodiment of the present invention, the implementation of the adaptive regulation and scheduling in step 5 further includes:

[0059] The implementation of the adaptive regulation and scheduling further includes:

[0060] Step 511: According to the prediction results, formulate a scheduling plan;

[0061] Step 512: Implement the scheduling plan and adjust the pipe network operation parameters;

[0062] Step 513: Monitor the scheduling effect and make adjustments according to the actual situation;

[0063] Among them, the formulation of the scheduling plan further includes:

[0064] Step 521: Determine heat users with high priority;

[0065] Step 522: Allocate necessary resources to the heat users with high priority;

[0066] Step 523: Adjust the resources for non-priority users;

[0067] The step of monitoring the scheduling effect further includes:

[0068] Step 531: Set monitoring indicators;

[0069] Step 532: Collect real-time pipe network operation data;

[0070] Step 533: Compare the prediction results with the actual operation data to evaluate the scheduling effect.

[0071] As a preferred embodiment of the present invention, a feedback control mechanism can be further added in step three during the implementation of the adaptive regulation and scheduling:

[0072] Performance evaluation: is the predicted load at time t, is the actual load, ;

[0073] Parameter adjustment: Parameter adjustment can be achieved using the gradient descent method or other optimization algorithms to minimize the prediction error: ; where, represents the model parameters, is the learning rate, is the gradient of MSE with respect to the parameter ; Through this feedback control mechanism, the prediction model self-corrects to adapt to the changes in the behavior of heat users and the fluctuations in the actual load situation, thereby improving the accuracy of prediction and the efficiency of pipe network operation.

[0074] As a preferred embodiment of the present invention, the steps of optimizing the regulation strategy by the machine learning algorithm in step 6 are further included:

[0075] Step 61: Collect data on the results of regulation execution;

[0076] Step 62: Analyze the deviation between the results of regulation execution and the prediction results;

[0077] Step 63: Based on the results of deviation analysis, adjust the parameters of the machine learning algorithm;

[0078] Step 64: Retrain the prediction model to reduce the error of future predictions.

[0079] Compared with the prior art, the beneficial effects of the present invention are:

[0080] 1. In the present invention, the role of the heat user behavior pattern in the pipe network load simulation model is crucial. Specifically, the analysis results of the heat user behavior pattern can provide the following functions: Enhance prediction accuracy: By analyzing the behavior patterns of heat users, the simulation model can more accurately predict the load demand within a specific time period, especially during peak hours. Provide dynamic adaptability: The analysis of heat user behavior patterns enables the simulation model to dynamically adapt to changes in user behavior, thereby adjusting predictions in a real-time environment. Optimize resource allocation: The model can make advance resource allocation and scheduling plans based on the predicted load changes of heat user behavior patterns to meet upcoming demands. Improve risk management: By predicting the load fluctuations that heat users may cause, the simulation model helps the pipe network operators identify potential risks and take preventive measures. Generally speaking, the heat user behavior pattern provides a mechanism for the simulation model to understand and predict how user behavior affects the pipe network load, thus making the pipe network operation more efficient and reliable.

[0081] 2. In the present invention, user behavior adaptability: Considering the differences in user behavior can more accurately predict the load demand; Dynamic adjustment ability: Can dynamically adjust the prediction model according to real-time data to improve the accuracy of prediction. Economic operation: While meeting user needs, achieve the economic operation of the heating system. Optimize the scheduling strategy: By optimizing the scheduling model, improve the peak shaving and valley filling effect of the distribution network, which is beneficial to the economic and safe operation of the system. Improve accuracy: By adapting to user behavior, improve the accuracy of load prediction. Enhance responsiveness: Optimize the scheduling strategy to enhance the responsiveness to changes in the grid load. Economic benefits: Through more accurate prediction and scheduling, reduce the operation cost and improve the economic benefits. System stability: Reduce prediction errors and improve the stability and reliability of the power system BRIEF DESCRIPTION OF THE DRAWINGS

[0082] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0083] Figure 1 is the method flow chart of the present invention;

[0084] Figure 2 is the principle flow chart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0085] In order to enable the personnel in the technical field to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0086] As used herein, reference to "embodiments" means that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0087] Embodiment 1

[0088] Please refer to Figure 1 As shown, a load prediction and scheduling method adapted to thermal user behavior includes the following steps:

[0089] Step 1: Collect historical load data of the source-side pipe network and analyze the thermal user behavior patterns;

[0090] Step 2: Based on the historical load data and thermal user behavior patterns, establish a pipe network load simulation model;

[0091] Step 3: Use digital twin technology to simulate the real-time operation status of the pipe network and update the thermal user behavior data in real time;

[0092] Step 4: According to the simulation results and the real-time updated thermal user behavior data, perform real-time prediction on the change of the pipe network load;

[0093] Step 5: According to the prediction results, perform adaptive regulation and scheduling to adapt to the real-time and variable switching requirements of thermal users;

[0094] Step 6: Optimize the regulation strategy through machine learning algorithms to ensure the optimization of the scheduling plan;

[0095] Analyzing the thermal user behavior patterns in Step 1 generally involves the following specific steps:

[0096] Data collection: First, collect the usage data of thermal users in different time periods, including information such as user activity frequency, duration, and load change.

[0097] Behavior recognition: Through data mining techniques, identify the behavior patterns of thermal users, such as high-frequency activities or load peaks in specific time periods.

[0098] Pattern classification: Classify the identified behavior patterns to determine which are regular patterns and which are abnormal patterns.

[0099] Association analysis: Conduct association analysis to discover the relationships between different behavior patterns, such as whether certain patterns will occur after specific events.

[0100] Prediction model construction: Using statistical and machine learning algorithms, a prediction model is constructed based on historical behavior data to predict the future behavior trends of hot users.

[0101] Model verification: Test the accuracy of the prediction model through actual data and adjust the model parameters as needed;

[0102] Please refer to Figure 2 As shown, in step 1, collect the historical load data of the source-side pipe network and analyze the behavior patterns of hot users; the specific steps are as follows:

[0103] Step 11 Data collection: Determine the data collection points, such as user access points, key nodes, etc.; use devices such as sensors and smart meters to collect load data at each collection point; transmit the collected data to the central database for storage and processing;

[0104] Step 12 Data preprocessing: Clean the data, remove outliers and noise; standardize the data to ensure the consistency of different data sources; perform data aggregation, such as summarizing load data by hour or day;

[0105] Step 13 Analysis of hot user behavior patterns: Use clustering algorithms to classify user behaviors and identify different behavior patterns;

[0106] Clustering algorithms, such as K-means: ; where, is the i-th cluster, k is the number of clusters, is the set of points in the j-th cluster, is the center point of;

[0107] Apply association rule learning algorithms to find the correlations between user behaviors;

[0108] Association rule learning, such as Apriori algorithm: ; where, A and B are item sets, is the frequency of item set A appearing in all transactions, represents the probability of B occurring given that A has occurred;

[0109] Time series analysis, such as ARIMA model: ; where, is the observation value at time t, c is the constant term, is the white noise error term, is the autoregressive coefficient, is the moving average coefficient, p and q are the orders of autoregression and moving average respectively; use time series analysis methods to analyze the changing trends of user behaviors over time;

[0110] In step 2, based on the historical load data and the thermal user behavior patterns, a pipe network load simulation model is established; the specific steps are as follows:

[0111] Step 21: Use the Seasonal AutoRegressive Integrated Moving Average model (SARIMA) to characterize the load characteristics and construct a pipe network load simulation model:

[0112] ; where L is the lag operator, s is the seasonal period, and (P, D, Q) are the orders of seasonal autoregression, differencing, and moving average.

[0113] According to the selected mathematical model, complete the construction of the pipe network load simulation model:

[0114] Step 22: Estimate the parameters of the selected model based on the historical load data and the thermal user behavior patterns;

[0115] Use the least squares method to fit the model parameters;

[0116] Verify and adjust the model to ensure that its prediction performance meets the actual application requirements.

[0117] The goal of step 23: parameter estimation is to find a set of parameters ( , , , ) such that the model best fits the historical load data; this can be achieved by minimizing the sum of the squares of the error terms .

[0118] Least squares fitting: The objective function of the least squares method can be expressed as: ;

[0119] Model verification and adjustment: Model verification usually involves calculating the difference between the predicted values and the actual observed values, such as the Mean Squared Error (MSE) or Root Mean Squared Error (RMSE): ;

[0120] where T is the number of test data points, is the load value predicted by the model.

[0121] By comparing the MSE or RMSE of different parameter sets, the best model parameters can be selected. Then, these parameters can be used to predict future loads, and the model can be further adjusted and optimized according to the actual application requirements;

[0122] The application of the digital twin technology in step 3 further includes:

[0123] Step 31: Construct a digital twin platform;

[0124] Step 32: Create a virtual copy of the pipe network on the digital twin platform;

[0125] Step 33: Input the real-time load data into the virtual copy;

[0126] Step 34: Simulate the operating status of the pipe network through the virtual copy;

[0127] The real-time prediction of the pipe network load change described in Step 4 further includes:

[0128] Step 41: Analyze the data provided by the digital twin platform;

[0129] Step 42: Use machine learning algorithms to predict the future load;

[0130] Step 43: Evaluate the accuracy of the prediction results.

[0131] Specifically as follows:

[0132] Collect real-time data (continuing from the data collection in the previous text): Collect real-time load data from the sensors and monitoring systems of the pipe network. At the same time, collect the behavior data of heat users, such as usage frequency, duration, etc.

[0133] Data integration: Integrate the real-time load data with the behavior data of heat users. Use data preprocessing techniques to ensure data quality, such as removing noise, filling in missing values, etc.

[0134] Model input update: Input the integrated real-time data into the established pipe network load simulation model; update the model parameters to reflect the latest user behavior and load conditions.

[0135] Load prediction: Use the simulation model to predict the pipe network load for a future period of time. Apply time series analysis, machine learning, or other prediction techniques to generate prediction results.

[0136] Result analysis: Analyze the prediction results to identify possible load peaks or troughs. Adjust the pipe network operation strategy according to the prediction results, such as adjusting pressure, flow rate, etc.

[0137] The implementation of the adaptive regulation and scheduling described in Step 5 further includes:

[0138] The implementation of the adaptive regulation and scheduling further includes:

[0139] Step 511: Develop a scheduling plan based on the prediction results;

[0140] Step 512: Implement the scheduling plan and adjust the pipe network operation parameters;

[0141] Step 513: Monitor the scheduling effect and make adjustments according to the actual situation.

[0142] Among them, the formulation of the scheduling plan further includes:

[0143] Step 521: Determine the hot users with high priority;

[0144] Step 522: Allocate necessary resources to the hot users with high priority;

[0145] Step 523: Adjust the resources of non-priority users.

[0146] The steps for monitoring the scheduling effect further include:

[0147] Step 531: Set monitoring indicators;

[0148] Step 532: Collect the operation data of the pipe network in real time;

[0149] Step 533: Compare the prediction results with the actual operation data to evaluate the scheduling effect.

[0150] In step three of the implementation process of the adaptive regulation and scheduling, a feedback control mechanism can also be added:

[0151] Performance evaluation: is the predicted load at time t, is the actual load, ;

[0152] Parameter adjustment: Parameter adjustment can be achieved using the gradient descent method or other optimization algorithms to minimize the prediction error: ;

[0153] Among them, represents the model parameters, is the learning rate, is the gradient of MSE with respect to the parameter .

[0154] Through this feedback control mechanism, the prediction model can self-correct, adapt to the changes in the behavior of hot users and the fluctuations in the actual load situation, thereby improving the accuracy of prediction and the efficiency of the pipe network operation;

[0155] The steps of optimizing the regulation strategy by the machine learning algorithm in step 6 further include:

[0156] Step 61: Collect the data of the regulation execution results;

[0157] Step 62: Analyze the deviation between the regulation execution results and the prediction results;

[0158] Step 63: Based on the deviation analysis results, adjust the parameters of the machine learning algorithm;

[0159] Step 64: Retrain the prediction model to reduce the error of future predictions;

[0160] Example 2

[0161] Based on the previous embodiment, a simulation of the actual scenario is carried out as follows:

[0162] Suppose a city gas company hopes to optimize the operation of its pipeline network and improve its adaptability to the changes in the behavior of heat users and the accuracy of load forecasting.

[0163] Step 1: Data collection and analysis

[0164] Install intelligent sensors at key nodes of the urban gas pipeline network to collect the usage data of heat users, including usage time, frequency, and load.

[0165] Transmit the collected data to the central processing system and perform preprocessing, including data cleaning, standardization, and aggregation.

[0166] Step 2: Analysis of user behavior patterns

[0167] Apply clustering algorithms to classify user behavior and identify regular and abnormal usage patterns.

[0168] Use association rule learning algorithms to analyze the relationships between different user behavior patterns.

[0169] Adopt time series analysis methods to predict the trends and periodic changes of user behavior.

[0170] Step 3: Construction of load simulation model

[0171] Based on historical load data and user behavior patterns, select a suitable mathematical model, such as the SARIMA model, to characterize the load characteristics.

[0172] Use historical data to estimate the model parameters and optimize the model through cross-validation.

[0173] Step 4: Application of digital twin technology

[0174] Construct a digital twin platform and create a virtual copy of the pipeline network on the platform.

[0175] Input the real-time load data into the virtual copy to simulate the operating state of the pipeline network.

[0176] Step 5: Load forecasting and scheduling

[0177] Utilize the constructed simulation model and combine the data provided by the digital twin platform to conduct load forecasting.

[0178] Automatically adjust the operation parameters of the pipe network, such as pressure and flow rate, according to the prediction results to meet the needs of heat users.

[0179] Step 6: Optimization and feedback

[0180] Continuously optimize the control strategy through machine learning algorithms, such as reinforcement learning.

[0181] Set monitoring indicators, collect operation data in real time, evaluate the scheduling effect, and adjust the prediction model according to the feedback.

[0182] Result: By implementing the above methods, the gas company can achieve a rapid response to the behavior of heat users, improve the accuracy of load prediction, optimize resource allocation, reduce operating costs, and improve user satisfaction.

[0183] The above formulas are all obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value. The coefficients in the formula are set by those skilled in the art according to the actual situation.

[0184] When the present invention is in use, historical load data of the source-side pipe network is collected, and the behavior patterns of heat users are analyzed; based on the historical load data and the behavior patterns of heat users, a pipe network load simulation model is established; digital twin technology is used to simulate the real-time operation state of the pipe network, and the behavior data of heat users is updated in real time; according to the simulation results and the behavior data of heat users updated in real time, real-time prediction of the change of the pipe network load is carried out; according to the prediction results, adaptive control scheduling is carried out to adapt to the real-time and variable switching needs of heat users; the control strategy is optimized through machine learning algorithms to ensure the optimization of the scheduling plan.

[0185] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the present invention to only the specific embodiments. Obviously, many modifications and changes can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principle and practical application of the present invention, so that those skilled in the art in the technical field can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A load forecasting and scheduling method adapted to the behavior of heat users, characterized in that: The following steps are involved: Step 1: Collect historical load data of the source-side pipe network and analyze the behavior patterns of heat users; the specific steps of step 1 are as follows: Step 11: Data collection: determine data collection points, such as user access points and key nodes; use sensors and smart meters to collect load data at each collection point; transmit the collected data to the central database for storage and processing; Step 12: Data preprocessing: clean the data and remove outliers and noise; Standardize data to ensure consistency across different data sources; Perform data aggregation, such as summarizing load data by hour or day; Step 13: Hot user behavior pattern analysis: Use clustering algorithms to classify user behaviors and identify different behavior patterns; Clustering Algorithms: ;in, is the i-th cluster, k is the number of clusters, is the set of points in the jth cluster, yes The center point of Apply association rule learning algorithms to find the correlation between user behaviors; Association rule learning: ; where A and B are item sets, is the frequency of item set A appearing in all transactions, It represents the probability of B happening when A happens; Time Series Analysis: ;in, is the observed value at time t, c is a constant term, is the white noise error term, is the autoregressive coefficient, is the moving average coefficient, p and q are the orders of autoregression and moving average respectively; use time series analysis method to analyze the changing trend of user behavior over time; Step 2: Based on the historical load data and the behavior pattern of heat users, a pipe network load simulation model is established; the specific steps of step 2 are as follows: Step 21: Use the seasonal autoregressive integrated moving average model to characterize the load characteristics and build a pipe network load simulation model: ; Where L is the lag operator, s is the seasonal period, and (P, D, Q) are the orders of seasonal autoregression, difference, and moving average; According to the selected mathematical model, the construction of the pipeline network load simulation model is completed: Step 22: estimating parameters of the selected model based on the historical load data and the thermal user behavior pattern; The least squares method was used to fit the model parameters; Verify and adjust the model to ensure that its prediction performance meets the actual application requirements; Step 23: The goal of parameter estimation is to find a set of parameters ( , , , ), so that the model best fits the historical load data; this can be achieved by minimizing the error term This is achieved by the sum of the squares of Least squares fitting: The objective function of the least squares method can be expressed as: ; Model validation and tuning: Model validation usually involves calculating the difference between the predicted values ​​and the actual observed values, such as the mean squared error or root mean squared error: ; Where T is the number of test data points, is the load value predicted by the model; by comparing the MSE or RMSE of different parameter sets, the best model parameters can be selected and used to predict future loads, and the model can be further adjusted and optimized according to actual application requirements; Step 3: Use digital twin technology to simulate the real-time operation status of the pipeline network and update the heat user behavior data in real time; Step 4: Based on the simulation results and real-time updated heat user behavior data, real-time prediction of network load changes is performed; Step 5: Based on the prediction results, adaptive control and scheduling are performed to adapt to the real-time and changing switching needs of hot users; Step 6: Optimize the control strategy through machine learning algorithms to ensure the optimization of the scheduling plan.

2. A load forecasting and scheduling method adapted to thermal user behavior according to claim 1, characterized in that: The application of digital twin technology in step 3 further includes: Step 31: Build a digital twin platform; Step 32: Create a virtual copy of the pipe network on the digital twin platform; Step 33: Input the real-time load data into the virtual copy; Step 34: Simulate the operation status of the pipeline network through the virtual copy.

3. A load forecasting and scheduling method adapted to thermal user behavior according to claim 1, characterized in that: The real-time prediction of the network load change in step 4 further includes: Step 41: Analyze the data provided by the digital twin platform; Step 42: Use machine learning algorithms to predict future loads; Step 43: Evaluate the accuracy of the prediction results.

4. A load forecasting and scheduling method adapted to thermal user behavior according to claim 3, characterized in that: The details are as follows: Collect real-time data: collect real-time load data from sensors and monitoring systems in the pipe network; also collect behavioral data of heat users, such as frequency and duration of use; Data integration: Integrate real-time load data with heat user behavior data; Use data preprocessing techniques to ensure data quality, such as removing noise and filling missing values; Model input update: input the integrated real-time data into the established pipe network load simulation model; update the model parameters to reflect the latest user behavior and load conditions; Load forecasting: Use simulation models to predict the network load over a period of time in the future; apply time series analysis, machine learning or other forecasting techniques to generate forecast results; Result analysis: Analyze the forecast results and identify possible load peaks or troughs; adjust the pipeline network operation strategy based on the forecast results.

5. A load forecasting and scheduling method adapted to thermal user behavior according to claim 1, characterized in that: The implementation of the adaptive control scheduling in step 5 further includes: The implementation of the adaptive control scheduling further includes: Step 511: Formulate a scheduling plan based on the prediction results; Step 512: Implement the dispatching plan and adjust the pipe network operation parameters; Step 513: Monitor the scheduling effect and make adjustments based on the actual situation; The formulation of the scheduling plan further includes: Step 521: Determine a high-priority hot user; Step 522: Allocate necessary resources to the high-priority hot users; Step 523: Adjust resources for non-priority users; The step of monitoring the scheduling effect further includes: Step 531: Setting monitoring indicators; Step 532: Collecting pipe network operation data in real time; Step 533: Compare the prediction results with the actual operation data to evaluate the scheduling effect.

6. A load forecasting and scheduling method adapted to thermal user behavior according to claim 5, characterized in that: In the implementation process of the adaptive control scheduling, a feedback control mechanism can also be added in step 3: Performance evaluation: is the forecast load at time t, is the actual load, ; Parameter Tuning: Parameter tuning can be done using gradient descent or other optimization algorithms to minimize the prediction error: ;in, represents the model parameters, is the learning rate, is the MSE with respect to the parameter Through this feedback control mechanism, the prediction model self-corrects and adapts to changes in heat user behavior and fluctuations in actual load conditions, thereby improving the accuracy of the prediction and the efficiency of the network operation.

7. A load forecasting and scheduling method adapted to thermal user behavior according to claim 1, characterized in that: Step 6 The step of optimizing the control strategy with the machine learning algorithm further includes: Step 61: Collect control execution result data; Step 62: Analyze the deviation between the control execution result and the prediction result; Step 63: Adjust the machine learning algorithm parameters based on the deviation analysis results; Step 64: Retrain the prediction model to reduce the error of future predictions.

Images