Dynamic adjustable potential analysis method and system for heating system based on big data processing

Abstract

The invention discloses a heating system dynamic adjustable potential analysis method and system based on big data processing, and particularly relates to the technical field of data management. By collecting multi-source heterogeneous data such as indoor temperature, heat meter data, meteorological information, building structures and user behaviors of users, performing standardized processing and classified summarization, constructing a heat demand prediction model and an adjustable potential evaluation model, realizing accurate evaluation and classification of regional adjustment capability, and based on a classification result, realizing accurate evaluation and classification of regional adjustment capability. According to the method, personalized heat supply regulation suggestions are dynamically generated, heat distribution is optimized, result visual display is achieved through a graphical interface, and the intelligent regulation and control capacity and the energy utilization efficiency of a heating system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the field of data management technology, and in particular to a method and system for analyzing the dynamic adjustable potential of a heating system based on big data processing. Background Art

[0002] With the acceleration of urbanization, heating systems have become an indispensable infrastructure for winter living and production in cold northern regions. Traditional heating systems mostly allocate heat based on static parameters, such as building area, heat load estimates, and outdoor temperature. These systems lack the ability to dynamically perceive and respond to users' actual heating needs, often leading to uneven heat distribution, energy waste, and reduced user comfort. In recent years, the rapid development of big data processing technology has provided new insights for the intelligent upgrade of heating systems. By collecting, cleaning, analyzing, and modeling multi-source heterogeneous data, including historical user heat usage data, meteorological changes, building energy consumption models, and real-time room temperature feedback, it is possible to dynamically assess and adjust the district's heating potential, thereby improving the operational efficiency and intelligence of the heating system.

[0003] The existing technology has the following shortcomings:

[0004] In actual applications, especially during the intelligent transformation of centralized heating systems in older residential communities, data silos may exist, preventing the accurate identification and utilization of inter-regional heating regulation potential. For example, in some older residential renovation projects, although some buildings have been connected to intelligent temperature control terminals and have data upload capabilities, the lack of unified data standards and interface protocols between different equipment manufacturers makes it difficult to aggregate the collected data into the same analysis platform, resulting in multiple independent data silos. In this case, even if the heat demand of a particular building is significantly reduced, it is difficult for the system to accurately perceive and dynamically adjust the heat supply downward, resulting in the coexistence of heat waste and failure of regulation capabilities. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for analyzing the dynamic adjustable potential of a heating system based on big data processing, so as to address the deficiencies in the background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for analyzing the dynamic adjustable potential of a heating system based on big data processing, comprising:

[0007] Collect multi-source heterogeneous data including user indoor temperature, household heat meter data, outdoor weather data, building structure information, and user behavior patterns;

[0008] Standardize the collected data and classify and summarize them according to buildings, regions or heating stations;

[0009] Based on the classified multi-source heterogeneous data, a heat demand forecasting model and an adjustable potential evaluation model are constructed. Based on the adjustable potential evaluation model, the regulation capacity of the heating system is evaluated.

[0010] Based on the evaluation results, different regions are divided into three categories: high-adjustment potential regions, medium-adjustment potential regions, and low-adjustment potential regions;

[0011] Generate heating adjustment suggestions based on the classification results, dynamically optimize heat distribution in each area, and visualize the analysis results through a graphical interface.

[0012] Preferably, the construction of the heat demand prediction model includes: based on historical data of multiple heating seasons, selecting outdoor temperature, humidity, wind speed, historical heat consumption, building structure parameters and user behavior patterns as input features; using multiple regression models for modeling comparison; the model output is the predicted value of the heat load of the unit building or area in the future time period.

[0013] Preferably, the construction of the adjustable potential assessment model includes: converting the regional thermal energy redundancy degree and thermal energy fluctuation response into a comprehensive feature vector, using the comprehensive feature vector as the input of the machine learning model, the machine learning model uses each group of comprehensive feature vectors to predict the adjustment capacity analysis value label of the heating system without affecting the user comfort as the prediction target, and minimizing the sum of the prediction errors of the adjustment capacity analysis value labels of all heating systems without affecting the user comfort as the training target, training the machine learning model until the sum of the prediction errors reaches convergence, stopping the model training, and determining the adjustment capacity analysis value of the heating system without affecting the user comfort based on the model output results, wherein the machine learning model is a polynomial regression model.

[0014] Preferably, the method for obtaining the regional heat energy redundancy degree is:

[0015] Using the heat demand prediction model, the predicted heat demand Qpred of the target area in a certain time period is obtained;

[0016] Obtain the actual heat supply Qactual for the corresponding time period from the heat metering system;

[0017] According to the building thermal inertia and the user's comfortable temperature range, the upper and lower limits of heat regulation are determined, and an adjustable threshold α∈(0,1) is defined;

[0018] Calculate the regional thermal energy redundancy level, the expression is: Where R region is the degree of regional thermal energy redundancy.

[0019] Preferably, the method for obtaining the thermal energy fluctuation response is:

[0020] The heating input Q(t) and indoor temperature response T(t) of the target area over a period of time are collected. The input signal Q(t) and the output signal T(t) are discrete Fourier transformed to obtain the frequency domain representation Q(f) of the heat input signal and the frequency domain representation T(f) of the room temperature response signal. The frequency response function is calculated and defined as: Here, H(f) is a complex number consisting of two components: magnitude and phase. It is used to extract the attenuation of the output response at frequency f, |H(f)|, and to calculate the response lag angle φ(f) at that frequency: The attenuation degree of the output response and the response lag angle at frequency f are normalized and then weighted averaged to obtain the thermal energy fluctuation response.

[0021] Preferably, the obtained adjustment capacity analysis value of the heating system without affecting the user comfort is compared with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the adjustment capacity analysis value is compared with the first standard threshold and the second standard threshold respectively;

[0022] If the adjustment capability analysis value is greater than the second standard threshold, the area is marked as a high adjustment potential area; if the adjustment capability analysis value is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the area is marked as a medium adjustment potential area; if the adjustment capability analysis value is less than the first standard threshold, the area is marked as a low adjustment potential area.

[0023] Preferably, dynamically optimizing heat distribution in each area includes: constructing a heat distribution objective function to minimize the total heat input while satisfying user comfort constraints: where Q i represents the heat supply of the ith region, and N is the total amount of the region;

[0024] Constraint setting: Adjustment must not cause the regional room temperature to fall below the minimum comfort threshold, and the total heat source output capacity must not be less than the maximum capacity of the boiler or heat exchange station;

[0025] Solve the heat distribution and output the optimized heating plan.

[0026] The present invention also provides a dynamic adjustable potential analysis system for a heating system based on big data processing, comprising a data acquisition module, a data processing module, a model evaluation module, a region division module, and a heat distribution optimization module;

[0027] Data acquisition module: collects multi-source heterogeneous data including user indoor temperature, household heat meter data, outdoor meteorological data, building structure information and user behavior patterns;

[0028] Data processing module: standardizes the collected data and classifies and summarizes them according to buildings, regions or heating stations;

[0029] Model evaluation module: Based on the classified multi-source heterogeneous data, it builds a heat demand forecast model and an adjustable potential evaluation model. Based on the adjustable potential evaluation model, it evaluates the regulation capacity of the heating system.

[0030] Regional division module: Based on the evaluation results, different regions are divided into three categories: high-adjustment potential regions, medium-adjustment potential regions, and low-adjustment potential regions;

[0031] Heat distribution optimization module: Generates heat supply adjustment suggestions based on classification results, dynamically optimizes heat distribution in each area, and visualizes the analysis results through a graphical interface.

[0032] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0033] 1. This invention overcomes the regulatory failures inherent in traditional centralized heating systems due to data silos and inconsistent information by incorporating big data processing and machine learning technologies. It integrates heterogeneous data from multiple sources, including user room temperature, heat consumption, meteorological conditions, buildings, and user behavior. By constructing a heat demand forecasting model and an adjustable potential assessment model, it effectively identifies the regulatory capabilities of different regions. Combined with frequency domain response analysis and redundant heat assessment, this model transforms the complex and dynamic heating system into a predictable, optimizable, intelligently controlled object, significantly improving the system's thermal efficiency and response sensitivity.

[0034] 2. The present invention can dynamically generate personalized heating adjustment suggestions based on the adjustment capacity classification results, and realize intelligent distribution of heat to each area with the support of optimization algorithms, so as to meet the goal of minimizing energy consumption under the premise of user comfort. The adjustment results are visualized through a graphical interface, which allows operation and maintenance personnel to intuitively control the system status and adjustment execution. The overall system has high adaptability, good scalability and significant energy-saving effects. It is particularly suitable for the intelligent upgrade and transformation of the central heating system in old residential areas and has broad prospects for promotion and application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0036] Figure 1 Flow chart of the method of the present invention.

[0037] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0038] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0039] Example 1, please refer to Figure 1 As shown, the method for analyzing the dynamic adjustable potential of a heating system based on big data processing described in this embodiment includes:

[0040] Collect multi-source heterogeneous data including user indoor temperature, household heat meter data, outdoor weather data, building structure information, and user behavior patterns;

[0041] Standardize the collected data and classify and summarize them according to buildings, regions or heating stations;

[0042] Based on the classified multi-source heterogeneous data, a heat demand forecasting model and an adjustable potential evaluation model are constructed. Based on the adjustable potential evaluation model, the regulation capacity of the heating system is evaluated.

[0043] Based on the evaluation results, different regions are divided into three categories: high-adjustment potential regions, medium-adjustment potential regions, and low-adjustment potential regions;

[0044] Generate heating adjustment suggestions based on the classification results, dynamically optimize heat distribution in each area, and visualize the analysis results through a graphical interface.

[0045] Methods for collecting multi-source heterogeneous data include:

[0046] User indoor temperature data: Real-time indoor temperature values are collected through temperature sensors installed in the user's room. The sampling period can be set (such as 1 minute or 5 minutes), and multi-point deployment (such as bedroom, living room, etc.) is supported to reflect the temperature distribution. The data is uploaded to the central data platform via wireless transmission modules (such as LoRa, NB-IoT, Wi-Fi).

[0047] Household heat meter data: Collects data from ultrasonic heat meters installed at each household entrance, including instantaneous heat flow, cumulative heat consumption, inlet and outlet water temperatures, flow rate, and other parameters; uploads data in real time or periodically via the M-Bus or RS485 interface, and can be connected to the Building Energy Management System (BEMS).

[0048] Outdoor meteorological data: The integrated meteorological data source includes locally deployed weather stations or access to third-party authoritative meteorological APIs. The data content includes outdoor temperature, relative humidity, wind speed and direction, solar radiation intensity, etc., which is used to assist in determining the heating load change trend and heat loss model.

[0049] Building structure information: Collect and enter the building's structural static parameters, including the number of floors, construction age, wall material, insulation thickness, window material and sealing, orientation, unit distribution, etc., to construct the building thermal performance model; data sources can be real estate archives, BIM models, on-site surveys, etc.

[0050] User behavior pattern: Modeling is based on the user's heating behavior. Data sources include room temperature setting preferences (such as setting the temperature higher than the average), daily heating time distribution (such as setting the temperature lower at night), window opening behavior monitoring (identified by temperature fluctuations or window sensors), frequency of use of energy-saving mode, etc., which can be obtained through smart terminal interaction, historical data mining or indirect reflection by sensors.

[0051] After completing the collection of multi-source heterogeneous data, in order to ensure the accuracy of the subsequent analysis model and the collaborative computing efficiency of the system, the present invention standardizes the original data and classifies and summarizes it by spatial hierarchy. Specifically, the following steps are included:

[0052] Data format standardization: For data from different sources (such as temperature in °C, heat in MJ, wind speed in m / s, etc.), unify data units and decimal precision to ensure that data of each dimension are comparable and fusible under the same dimensional system.

[0053] Time dimension alignment: There are differences in the data refresh frequency of the acquisition devices (such as once a minute for room temperature and once every 15 minutes for heat meters). The present invention uses linear interpolation, sliding average, etc. to time align the data to the set analysis time step (such as 5 minutes or 10 minutes) and construct a unified time series sample.

[0054] Outlier processing: Using methods such as upper and lower threshold judgment, historical mean deviation detection, and data stability judgment, we can identify and eliminate or correct extreme values, missing values, and mutation points to improve data quality and model input stability.

[0055] Spatial dimension classification and labeling:

[0056] Building-level classification: Based on the heating network topology and user geocoding, each user's data is associated with the corresponding building number;

[0057] Regional classification: Aggregate data from multiple buildings into regional data based on block, community or heating zone standards to form a local heating status profile;

[0058] Thermal power station-level classification: Based on the heat source distribution and secondary network coverage, users and buildings within the jurisdiction of each thermal power station are merged to construct a thermal power station-level heat demand characteristic matrix.

[0059] Feature extraction and structured representation: Extract features from the standardized data (such as average temperature, peak heat consumption, heat consumption fluctuation rate, etc.) and input them into the subsequent regulation potential assessment model in a structured form (such as table, tensor or feature vector).

[0060] The construction of heat demand forecasting model includes:

[0061] Based on historical data from multiple heating seasons, outdoor temperature, humidity, wind speed, historical heat consumption, building structural parameters, and user behavior patterns are selected as input features;

[0062] We use a variety of regression models for modeling comparison, such as support vector regression (SVR), random forest regression (RFR), and long short-term memory network (LSTM).

[0063] The model output is the predicted heat load value of a unit building or area in the future time period, supporting minute or hour granularity;

[0064] Cross-validation and sliding window techniques are used for training and testing to improve the model's generalization ability and prediction accuracy.

[0065] The construction of the adjustable potential assessment model includes: building a data prediction model based on the regional thermal energy redundancy index and the thermal energy fluctuation response index to evaluate the system's adjustment ability without affecting user comfort; dividing the area into three categories of "high adjustable potential", "medium" and "low" according to the assessment results to achieve hierarchical management.

[0066] The regional heat redundancy level reflects the degree of redundancy of heat supply relative to user heat demand in a certain area (such as a building, subnet, or heating station area) during actual heating. In other words, the amount of space in the area that can be reduced without affecting user comfort. For example, the present invention uses the following method to obtain the regional heat redundancy level index:

[0067] Using the heat demand prediction model, the predicted heat demand Qpred of the target area in a certain time period is obtained;

[0068] Obtain the actual heat supply Qactual for the corresponding time period from the heat metering system;

[0069] According to the building thermal inertia and the user's comfortable temperature range, the upper and lower limits of heat regulation are determined, and an adjustable threshold α∈(0,1) is defined;

[0070] Calculate the regional thermal energy redundancy level, the expression is: Where R region is the degree of regional thermal energy redundancy.

[0071] By converting the time domain heat input and room temperature response data into the frequency domain, the system's gain (amplification degree) and phase difference (response delay) to different frequency disturbances are analyzed, and then the thermal energy fluctuation response index is calculated.

[0072] For example, the present invention calculates the thermal energy fluctuation response in the following manner:

[0073] Collect the heating input Q(t) and indoor temperature response T(t) in the target area over a period of time. The recommended sampling period is no longer than 10 minutes. Detrend the data (such as deducting the mean or using a window function) to eliminate non-periodic drift.

[0074] Perform discrete Fourier transform on the input signal Q(t) and the output signal T(t) to obtain the frequency domain representation Q(f) of the heat input signal and the frequency domain representation T(f) of the room temperature response signal. Calculate the frequency response function, which is defined as: Here, H(f) is a complex number consisting of two components: magnitude and phase. It is used to extract the attenuation of the output response at frequency f, |H(f)|, and to calculate the response lag angle φ(f) at that frequency: The attenuation degree of the output response and the response lag angle at frequency f are normalized and then weighted averaged to obtain the thermal energy fluctuation response.

[0075] The regional thermal energy redundancy degree and thermal energy fluctuation response are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the adjustment capacity analysis value label of the heating system without affecting the user comfort as the prediction target, and takes minimizing the sum of the prediction errors of the adjustment capacity analysis value labels of all heating systems without affecting the user comfort as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The adjustment capacity analysis value of the heating system without affecting the user comfort is determined based on the model output results. Among them, the machine learning model is a polynomial regression model.

[0076] Comparing the obtained adjustment capacity analysis value of the heating system without affecting user comfort with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the adjustment capacity analysis value with the first standard threshold and the second standard threshold respectively;

[0077] If the adjustment capability analysis value is greater than the second standard threshold, the area is marked as a high adjustment potential area; if the adjustment capability analysis value is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the area is marked as a medium adjustment potential area; if the adjustment capability analysis value is less than the first standard threshold, the area is marked as a low adjustment potential area.

[0078] Based on the regional level, the following recommended templates are set:

[0079] High potential areas: It is recommended to moderately reduce the heating flow rate or water supply temperature (e.g., by 5% to 10%);

[0080] Medium potential area: maintain current heating parameters and observe feedback for fine-tuning;

[0081] Low potential areas: Maintain or even slightly increase heating parameters to avoid a decrease in comfort.

[0082] Each region forms an adjustment suggestion instruction package, including: region code, adjustment type, target adjustment range, execution period, feedback monitoring requirements, etc.

[0083] Construct a heat distribution objective function to minimize the total heat input while satisfying the user comfort constraint: ; where Q i represents the heating amount of the ith area, and N is the total amount of the area.

[0084] Constraint setting: Adjustment must not cause the regional room temperature to fall below the minimum comfort threshold (such as 20°C); the total heat source output capacity must not exceed the maximum capacity of the boiler or heat exchange station; the adjustment range must fluctuate within the recommended range.

[0085] The heat distribution can be solved using linear programming (LP), heuristic search (such as genetic algorithm GA) or gradient-based optimization method to output the optimized heating plan.

[0086] In order to achieve intuitive expression of adjustment suggestions and optimization results, the present invention provides a graphical user interface (GUI), the main functions of which include: regional map distribution diagram, which displays the regional layout with a map or building structure diagram; different colors identify regional adjustment potential (such as red = high, yellow = medium, blue = low); and support for clicking to view specific adjustment suggestions and heat data.

[0087] The heat distribution heat map shows the current and optimized heat distribution. The color of the area block corresponds to the heat level and is refreshed in real time. You can switch to view historical and predicted data trends.

[0088] The adjustment execution status monitoring diagram displays the execution status of the adjustment task and the feedback temperature curve; abnormal situations are highlighted and trigger the early warning mechanism.

[0089] The strategy simulation and adjustment interface allows operation and maintenance personnel to adjust parameters based on the simulation model; estimate the adjustment results in real time and support one-click transmission to the control system.

[0090] Example 2, please refer to Figure 2 As shown, the dynamic adjustable potential analysis system of a heating system based on big data processing described in this embodiment includes a data acquisition module, a data processing module, a model evaluation module, a region division module and a heat distribution optimization module;

[0091] Data acquisition module: collects multi-source heterogeneous data including user indoor temperature, household heat meter data, outdoor meteorological data, building structure information and user behavior patterns;

[0092] Data processing module: standardizes the collected data and classifies and summarizes them according to buildings, regions or heating stations;

[0093] Model evaluation module: Based on the classified multi-source heterogeneous data, it builds a heat demand forecast model and an adjustable potential evaluation model. Based on the adjustable potential evaluation model, it evaluates the regulation capacity of the heating system.

[0094] Regional division module: Based on the evaluation results, different regions are divided into three categories: high-adjustment potential regions, medium-adjustment potential regions, and low-adjustment potential regions;

[0095] Heat distribution optimization module: Generates heat supply adjustment suggestions based on classification results, dynamically optimizes heat distribution in each area, and visualizes the analysis results through a graphical interface.

[0096] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0097] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0098] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0099] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A method for analyzing the dynamic adjustable potential of a heating system based on big data processing, characterized by: include: Collect multi-source heterogeneous data including user indoor temperature, household heat meter data, outdoor weather data, building structure information, and user behavior patterns; Standardize the collected data and classify and summarize them according to buildings, regions or heating stations; Based on the classified multi-source heterogeneous data, a heat demand forecasting model and an adjustable potential evaluation model are constructed. Based on the adjustable potential evaluation model, the regulation capacity of the heating system is evaluated. Based on the evaluation results, different regions are divided into three categories: high-adjustment potential regions, medium-adjustment potential regions, and low-adjustment potential regions; Generate heating adjustment suggestions based on the classification results, dynamically optimize heat distribution in each area, and visualize the analysis results through a graphical interface.

2. The method for analyzing the dynamic adjustable potential of a heating system based on big data processing according to claim 1, characterized in that: The construction of the heat demand prediction model includes: based on historical data from multiple heating seasons, selecting outdoor temperature, humidity, wind speed, historical heat consumption, building structure parameters and user behavior patterns as input features; using multiple regression models for modeling and comparison; the model output is the predicted heat load value of the unit building or area in the future time period.

3. The method for analyzing the dynamic adjustable potential of a heating system based on big data processing according to claim 1, characterized in that: The construction of the adjustable potential assessment model includes: converting the regional thermal energy redundancy degree and thermal energy fluctuation response into a comprehensive feature vector, and using the comprehensive feature vector as the input of the machine learning model. The machine learning model uses each set of comprehensive feature vectors to predict the adjustment capacity analysis value label of the heating system without affecting the user comfort as the prediction target, and takes minimizing the sum of the prediction errors of the adjustment capacity analysis value labels of all heating systems without affecting the user comfort as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence and the model training is stopped. The adjustment capacity analysis value of the heating system without affecting the user comfort is determined based on the model output results, wherein the machine learning model is a polynomial regression model.

4. The method for analyzing the dynamic adjustable potential of a heating system based on big data processing according to claim 3 is characterized by: The method for obtaining the regional heat energy redundancy degree is: Using the heat demand prediction model, the predicted heat demand Qpred of the target area in a certain time period is obtained; Obtain the actual heat supply Qactual for the corresponding time period from the heat metering system; According to the building thermal inertia and the user's comfortable temperature range, the upper and lower limits of heat regulation are determined, and an adjustable threshold α∈(0,1) is defined; Calculate the regional thermal energy redundancy level, the expression is: Where Rregion is the regional thermal energy redundancy.

5. The method for analyzing the dynamic adjustable potential of a heating system based on big data processing according to claim 4 is characterized in that: The method for obtaining the thermal energy fluctuation response is: The heating input Q(t) and indoor temperature response T(t) of the target area over a period of time are collected. The input signal Q(t) and the output signal T(t) are discrete Fourier transformed to obtain the frequency domain representation Q(f) of the heat input signal and the frequency domain representation T(f) of the room temperature response signal. The frequency response function is calculated and defined as: Here, H(f) is a complex number consisting of two components: magnitude and phase. It is used to extract the attenuation of the output response at frequency f, |H(f)|, and to calculate the response lag angle φ(f) at that frequency: The attenuation degree of the output response and the response lag angle at frequency f are normalized and then weighted averaged to obtain the thermal energy fluctuation response.

6. The method for analyzing the dynamic adjustable potential of a heating system based on big data processing according to claim 5, characterized in that: Comparing the obtained adjustment capacity analysis value of the heating system without affecting user comfort with the gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and comparing the adjustment capacity analysis value with the first standard threshold and the second standard threshold respectively; If the adjustment capability analysis value is greater than the second standard threshold, the region is marked as a high adjustment potential region; If the adjustment capability analysis value is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the region is marked as a medium adjustment potential region; If the adjustment capability analysis value is less than the first standard threshold, the region is marked as a low adjustment potential region.

7. The method for analyzing the dynamic adjustable potential of a heating system based on big data processing according to claim 1, characterized in that: Dynamically optimizing heat distribution in each area involves constructing a heat distribution objective function to minimize total heat input while satisfying user comfort constraints: Where Qi represents the heat supply of the i-th region, and N is the total amount of the region; Constraint setting: Adjustment must not cause the regional room temperature to fall below the minimum comfort threshold, and the total heat source output capacity must not be less than the maximum capacity of the boiler or heat exchange station; Solve the heat distribution and output the optimized heating plan.

8. A system for analyzing the dynamic adjustable potential of a heating system based on big data processing, for implementing the method for analyzing the dynamic adjustable potential of a heating system based on big data processing according to any one of claims 1 to 7, characterized in that: It includes data acquisition module, data processing module, model evaluation module, area division module and heat distribution optimization module; Data acquisition module: collects multi-source heterogeneous data including user indoor temperature, household heat meter data, outdoor meteorological data, building structure information and user behavior patterns; Data processing module: standardizes the collected data and classifies and summarizes them according to buildings, regions or heating stations; Model evaluation module: Based on the classified multi-source heterogeneous data, it builds a heat demand forecast model and an adjustable potential evaluation model. Based on the adjustable potential evaluation model, it evaluates the regulation capacity of the heating system. Regional division module: Based on the evaluation results, different regions are divided into three categories: high-adjustment potential regions, medium-adjustment potential regions, and low-adjustment potential regions; Heat distribution optimization module: Generates heat supply adjustment suggestions based on classification results, dynamically optimizes heat distribution in each area, and visualizes the analysis results through a graphical interface.

Images