A method and system for optimal management of renewable energy resources in a heating zone

Abstract

This application relates to the field of heating resource management technology, specifically disclosing a method and system for optimizing the management of renewable energy resources in heating areas. The method includes the following steps: collecting heating behavior and feedback data from each user within the heating area, including at least the target room temperature set by the user, the user's manual adjustment behavior, and the subjective feedback information submitted by the user; dividing the heating area into multiple sub-areas, and based on the heating behavior and feedback data, identifying common behavioral patterns representing the collective heating willingness of users in each sub-area; quantifying the urgency of heating demand in each sub-area; and formulating and implementing differentiated heating scheduling schemes to prioritize the allocation of heat to sub-areas with high urgency of heating demand. The technical solution of this application achieves the goal of ensuring heating comfort in local areas while avoiding the waste of overall renewable energy resources, improving user satisfaction and the economic efficiency of the heating system operation.

Description

Technical Field

[0001] This application relates to the field of heating resource management technology, and in particular to a method and system for optimizing the management of renewable energy resources in heating areas. Background Technology

[0002] In district heating networks, optimized management systems are typically deployed to efficiently utilize renewable energy sources such as photovoltaics, biomass energy, and ground source heat pumps while ensuring stable heating supply. However, existing management methods face significant challenges when the system experiences a sudden surge in heating demand with marked spatial unevenness after a prolonged period of mild weather followed by a strong cold front. The core limitation lies in the fact that forecasting mechanisms relying on macro-weather forecasts and regional average loads struggle to accurately capture and identify localized "heat demand hotspots" caused by differences in building insulation performance, population density, and microclimate effects, thus failing to provide a basis for refined scheduling.

[0003] At the scheduling and execution level, the system struggles to coordinate the differentiated characteristics of heterogeneous energy sources to cope with such complex scenarios. Biomass cogeneration units, as the primary heat source, have a slow power ramp-up rate, failing to meet the instantaneous peak demand in localized areas. Ground source heat pumps, with their fast response times, are not designed for large-scale, uneven surges in localized demand. Forcibly increasing the load to meet localized peak demand not only reduces energy efficiency but may also damage the long-term stability of their underground heat exchange fields. Furthermore, due to the physical characteristics of the pipeline network, heat cannot be quickly and accurately delivered to the most urgently needed end-point areas.

[0004] A deeper problem lies in the existing system's lack of precise sensing capabilities at the end of the heating network, specifically at the user end. It relies primarily on lagging parameters such as temperature and pressure from the main network, failing to obtain real-time data on actual indoor temperatures and user comfort levels in different sub-areas. This leads to a tendency for the system to adopt a "one-size-fits-all" scheduling strategy. The result is that in areas with surging demand, users are already feeling cold while the system's response is delayed, leading to insufficient heating and complaints; in other areas, it may cause overheating and energy waste. This supply-demand mismatch prevents the system from balancing local heating comfort with overall economic efficiency at critical moments. Summary of the Invention

[0005] This application proposes a method and system for optimizing the management of renewable energy resources in heating areas, aiming to solve the technical problems of insufficient heating caused by the existing district heating system's inability to accurately identify local heat demand "hot spots," slow dispatch response speed, and lack of fine sensing capabilities at the end-user side when dealing with sudden surges in heating demand caused by strong cold air.

[0006] Firstly, this application provides a method for optimizing the management of renewable energy resources in heating areas, used to coordinate the scheduling of heating energy in scenarios where a sudden surge in heating demand due to a strong cold front causes uneven distribution of heating demand. The method includes the following steps: Collect heating behavior and feedback data from each user in the heating area. The heating behavior and feedback data includes at least the target room temperature set by the user, the user's manual adjustment behavior, and the subjective feedback information submitted by the user. The heating area is divided into multiple sub-areas, and based on the heating behavior and feedback data, common behavioral patterns representing users' collective heating intentions in each sub-area are identified. The common behavioral patterns include: behavioral patterns representing collective changes in heating demand in the corresponding sub-area by statistically analyzing the aggregated behavior of users raising the target room temperature and / or the aggregated situation of users submitting feedback on feeling cold in each sub-area. Based on the identified common behavioral patterns, the urgency of heating demand in each sub-region is quantified; Based on the urgency of the heating demand, a differentiated heating scheduling plan is formulated and implemented to prioritize the allocation of heat to sub-areas with high heating urgency.

[0007] As some embodiments of this application, after the step of collecting heating behavior and feedback data from each user within the heating area, the method further includes: Anonymize the heating behavior and feedback data, remove personally identifiable information and perform abnormal data filtering to obtain the processed heating behavior and feedback data; The abnormal data filtering includes: Data points that exceed the preset reasonable temperature range in the reported target room temperature are marked as abnormal and filtered out; Data points that are reported more than the preset normal number of times within the first preset time window by the same smart temperature control terminal, and whose values ​​are exactly the same, are marked as abnormal and filtered out.

[0008] As some embodiments of this application, the step of dividing the heating area into multiple sub-areas and identifying common behavioral patterns representing users' collective willingness to heat within each sub-area based on the heating behavior and feedback data includes: Based on the topology of the heating network in the heating area and / or based on the geographical location and physical attributes of the buildings in the heating area, the heating area is divided into multiple sub-areas. If, within the second preset time window, the proportion of users in a sub-region who raise the target room temperature exceeds the first preset proportion, and the average increase exceeds the preset threshold, and / or the frequency of user manual adjustment behavior exceeds the historical baseline frequency, then the sub-region is identified as having a general behavioral pattern indicating a collective increase in heating demand. And / or, if the proportion of users submitting subjective feedback information representing a feeling of cold in a sub-region exceeds a second preset proportion within a second preset time window, then the sub-region is identified as having a general behavioral pattern indicating a collective increase in heating demand.

[0009] As some embodiments of this application, the urgency of the heating demand is calculated using the following formula: D = W1 × A + W2 × B + W3 × C; Where A is the product of the proportion of users who raise the target room temperature within the sub-region and the average magnitude of the temperature increase by the users; B is the ratio of the manual adjustment frequency within the second preset time window to the historical reference frequency within the sub-region; C is the proportion of users who submit feedback on the feeling of cold within the sub-region; W1, W2, W3 are preset weighting coefficients of A, B, and C, and satisfy W1+W2+W3=1.

[0010] As some embodiments of this application, after the step of quantifying the urgency of heating demand in each sub-region based on the identified common behavioral patterns, the following steps are also included: Based on the heat transfer coefficient of the building's exterior wall, window type and area ratio, air permeability, real-time outdoor temperature and wind speed parameters within the sub-region, calculate the comprehensive heat loss coefficient of the sub-region. Based on the comprehensive heat loss coefficient, the current indoor temperature and the current outdoor temperature within the sub-region, the expected rate of decrease in indoor temperature within the sub-region without additional heating intervention is predicted. The degree of authenticity matching is obtained by comparing the magnitude and frequency of users raising the target room temperature and the proportion of users submitting feedback on feeling cold in the general behavioral pattern with the degree of deviation between these and the intensity of user feedback reasonably expected based on the expected rate of decrease in indoor temperature. The urgency of heating demand is adjusted based on the accuracy of the matching degree to obtain the adjusted urgency of heating demand, which is then used to formulate and implement differentiated heating scheduling plans.

[0011] As some embodiments of this application, the step of obtaining the degree of authenticity matching by comparing the degree and frequency of users raising the target room temperature and the proportion of users submitting feedback on feeling cold in the general behavioral pattern with the degree of deviation between the deviation and the degree of intensity of user feedback reasonably expected based on the expected rate of decrease in indoor temperature, includes: Based on the expected rate of decrease in indoor temperature, reasonable expected values ​​are determined in three dimensions: temperature adjustment range, adjustment frequency, and cold feedback ratio, according to the pre-stored mapping relationship or threshold model. Calculate the normalized deviation between the average increase in temperature by the user, the actual frequency of manual adjustment, and the proportion of actual submissions of feedback on the feeling of cold, and the reasonable expected value of the corresponding dimension. The weighted sum of the normalized deviations of the three dimensions is used to obtain the comprehensive deviation. Subtracting the comprehensive deviation from 1 yields the degree of authenticity matching.

[0012] As some embodiments of this application, the heating behavior and feedback data also include: a perceived cooling acceleration signal automatically generated and reported by the user-side intelligent temperature control terminal when it detects in real time that the rate of indoor temperature drop exceeds a preset comfort threshold; After determining the degree of authenticity matching by comparing the magnitude and frequency of users raising the target room temperature and the proportion of users submitting feedback on feeling cold in the general behavioral pattern with the degree of deviation between these deviations and the intensity of user feedback reasonably expected based on the expected rate of decrease in indoor temperature, the following steps are also included: Within the third preset time window, the number of terminals that trigger the body-feeling cooling acceleration signal in the sub-region is counted, and the proportion of acceleration signals in the sub-region is calculated by combining the total number of active terminals in the sub-region. Based on the proportion of the acceleration signal, the accuracy of the matching degree of the sub-regions with the perceived cooling acceleration signal is improved, and the corrected accuracy of the matching degree is obtained, which is used to correct the urgency of the heating demand.

[0013] As some embodiments of this application, the authenticity matching degree is corrected based on the following formula: m = M + (1-M) × K × I; Where m is the corrected accuracy, M is the original accuracy, K is the preset amplification factor, and I is the proportion of the acceleration signal.

[0014] As some embodiments of this application, the step of formulating and implementing a differentiated heating scheduling plan based on the urgency of the heating demand, so as to prioritize the allocation of heat to sub-areas with high urgency of heating demand, includes: Prioritize scheduling heating energy with a response speed greater than or equal to a preset speed threshold, and increase heat output to sub-areas with high heating demand. Simultaneously, heating energy with a response speed less than the preset speed threshold is dispatched to maintain the basic heat supply to the heating area. The scheduling methods for heating energy include: adjusting the speed of circulating pumps flowing to different sub-regions in the heating network, and / or adjusting the valve opening on the corresponding branches to change the flow rate of the heat medium to each sub-region.

[0015] Secondly, this application also provides a heating area renewable energy resource optimization management system for coordinating the scheduling of heating energy in scenarios where a sudden surge in heating demand due to a strong cold front causes uneven distribution of heating demand. The system includes: The data acquisition module is used to collect heating behavior and feedback data from each user in the heating area. The heating behavior and feedback data includes at least the target room temperature set by the user, the user's manual adjustment behavior, and the subjective feedback information submitted by the user. The behavior recognition module is used to divide the heating area into multiple sub-areas and, based on the heating behavior and feedback data, identify common behavior patterns in each sub-area that represent the collective heating intention of users; wherein, the common behavior patterns include: by statistically analyzing the aggregated behavior of users raising the target room temperature in each sub-area and / or the aggregated situation of users submitting feedback on feeling cold, the behavior patterns in the corresponding sub-area that represent a collective change in heating demand are identified. The demand quantification module is used to quantify the urgency of heating demand in each sub-region based on identified common behavioral patterns. The scheduling and execution module is used to formulate and execute differentiated heating scheduling plans based on the urgency of the heating demand, so as to prioritize the allocation of heat to sub-areas with high heating demand.

[0016] The technical solution according to the embodiments of this application has at least the following beneficial effects: This application achieves precise perception of end-point heating comfort by converting user behavior and feedback into quantifiable signals, overcoming the perception blind spots caused by relying on macroscopic and lagging physical parameters. By identifying "common behavioral patterns" and calculating urgency scores, it can quickly and automatically locate and quantify local demand "hotspots," solving the problem that traditional forecasting methods cannot capture non-uniform demand. Based on the differentiated collaborative scheduling strategy of urgency scores, it can instruct rapid energy response to accurately meet instantaneous peak demand while respecting the ramp-up characteristics of slow energy sources, thereby improving the overall response speed and accuracy to surges in non-uniform demand. Ultimately, this ensures heating comfort in local areas while avoiding the waste of overall renewable energy resources, improving user satisfaction and the economic efficiency of heating system operation.

[0017] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0018] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0019] Figure 1 This is a flowchart illustrating a method for optimizing the management of renewable energy resources in a heating area, as provided in an embodiment of this application.

[0020] Figure 2 This is a schematic diagram of the architecture of a heating area renewable energy resource optimization management system provided in an embodiment of this application. Detailed Implementation

[0021] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. The components of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] In district heating networks, optimized management systems are typically deployed to coordinate the use of renewable energy sources such as photovoltaics, biomass energy, and ground source heat pumps while ensuring economical and stable operation. However, existing management methods face severe challenges when the system experiences a sudden surge in heating demand due to mild weather followed by a strong cold front, resulting in a rapid and highly uneven spatial distribution. Differences in building type, insulation performance, and microclimate lead to significant "hotspot" distributions in demand growth across different sub-regions, forming a complex "heat demand topography." Faced with such rapid and uneven demand surges, existing systems reveal their core limitations: their reliance on macro-weather forecasts and regional average demand prediction mechanisms makes it difficult to accurately perceive and locate drastic changes in localized demand. While the system can detect the upward trend in overall demand, it cannot precisely identify which specific sub-regions have the most urgent demand and its duration. Therefore, during scheduling, the system still tends to make average adjustments based on overall demand, lacking the ability to accurately identify and quickly respond to localized heat demand "hotspots."

[0024] In this regard, such as Figure 1 As shown, this application discloses a method for optimizing the management of renewable energy resources in heating areas, used for the coordinated scheduling of heating energy in scenarios where a sudden surge in heating demand due to a strong cold front causes uneven distribution of heating demand. The method includes the following steps: S110, collect heating behavior and feedback data from each user in the heating area. The heating behavior and feedback data includes at least the target room temperature set by the user, the user's manual adjustment behavior, and the subjective feedback information submitted by the user. S120, the heating area is divided into multiple sub-areas, and based on the heating behavior and feedback data, the common behavioral patterns representing the collective heating intentions of users in each sub-area are identified; wherein, the common behavioral patterns include: the behavioral patterns representing the collective change in heating demand in the corresponding sub-area are identified by statistically analyzing the aggregated behavior of users raising the target room temperature in each sub-area and / or the aggregated situation of users submitting feedback on feeling cold. S130 quantifies the urgency of heating demand in each sub-region based on identified common behavioral patterns; S140, based on the urgency of the heating demand, formulate and implement a differentiated heating scheduling plan to prioritize the allocation of heat to sub-areas with high urgency of heating demand.

[0025] In this context, a "heating area" refers to a geographically contiguous region or an area connected by a heating network, containing multiple user sides who obtain heat through the heating system. "User side" refers to end users within the heating area, such as residential buildings and commercial buildings, whose heating behaviors and feedback directly reflect actual heating needs. "Heating behavior and feedback data" encompasses various information generated by users during the heating process, including user-set target room temperatures, manual adjustments made by users through temperature control devices (such as raising or lowering the temperature, turning the heater on or off), and subjective feedback submitted by users through various channels (such as apps, customer service hotlines, etc.) (such as "feeling cold," "not enough temperature," etc.). This data forms the basis for understanding users' true heating intentions and needs. A "sub-region" is a smaller management unit within the entire heating area, divided according to specific criteria (such as geographical location, building type, heating network topology), to facilitate more refined demand analysis and scheduling. "General behavior pattern" refers to the consistent heating behavior or feedback trend exhibited by most users in a specific sub-area. It can characterize changes in the collective heating willingness of users in that sub-area, such as collectively raising the target room temperature or collectively submitting feedback on the feeling of cold.

[0026] There are several ways to collect heating behavior and feedback data from each user in the heating area. For example, a smart temperature control terminal can be installed at each user's location. This terminal can monitor and record the user's target room temperature and manual adjustments made to the terminal (such as raising or lowering the set temperature, turning the terminal on or off), and upload this data to the central management platform via wireless networks (such as Wi-Fi, LoRa, NB-IoT, etc.). In addition, users can actively submit their subjective feedback on indoor temperature through mobile applications or WeChat mini-programs, such as selecting preset options like "feels cold," "temperature is suitable," or "feels hot," or entering custom text descriptions. This subjective feedback information is also collected and transmitted to the management platform. Another approach is to deploy a smart home gateway with data acquisition capabilities at the user's location. This gateway can integrate various sensors (such as temperature sensors and humidity sensors) and communication modules, not only collecting the user's target room temperature and manual adjustments, but also extracting implicit heating feedback information from user interactions with smart home devices through voice recognition or text analysis technology.

[0027] Heating zones can be divided based on Geographic Information System (GIS) data, dividing the entire heating area according to administrative divisions, building clusters, or physical zones of the heating network. For example, a large urban heating area can be divided into several street or community-level sub-zones. When identifying common behavioral patterns, the management platform continuously monitors aggregated behavior of users raising their target room temperature within each sub-zone. Specifically, the system counts how many users in the sub-zone raised their target room temperature within a certain time window, and the average increase by these users. Simultaneously, the system also counts aggregated user feedback on perceived coldness, such as how many users submitted feedback stating "feeling cold" within the same time window. Based on these aggregated behaviors or feedback, behavioral patterns indicating collective changes in heating demand within the sub-zone can be identified.

[0028] To quantify the urgency of heating demand in each sub-region, a quantitative model can be used for calculation. For example, an initial heating demand urgency value can be set for each sub-region. When a common behavioral pattern is identified in a sub-region, such as users collectively raising their target room temperature or submitting feedback on how cold they feel, the system will dynamically adjust the heating demand urgency value for that sub-region based on the intensity and scope of these behaviors. The higher the proportion of users raising their target room temperature, the greater the increase, or the higher the proportion of users submitting feedback on how cold they feel, the higher the heating demand urgency value for that sub-region will be. For example, a scoring mechanism can be set up, assigning different weights to the proportion of users raising their target room temperature, the average increase, and the proportion of users submitting feedback on how cold they feel, and then performing a weighted sum to obtain a comprehensive heating demand urgency index.

[0029] Developing and implementing differentiated heating dispatching plans can be done as follows: The management platform will coordinate the dispatching of heating energy based on the quantified urgency of heating demand in each sub-region. For sub-regions with high urgency of heating demand, the system will prioritize increasing their heat allocation. For sub-regions with lower urgency of heating demand, the system will maintain or appropriately adjust their heat allocation to ensure the stable operation of the overall heating system and the rational use of energy.

[0030] This application utilizes smart terminals deployed on the user side to collect and process information in real time, including user-set target room temperature, manual adjustment behavior, and subjective feedback, forming a fine-grained end-point sensing network. The heating area is divided into multiple sub-regions, and by statistically analyzing the aggregated characteristics of user temperature-adjusting behavior and cold feedback within each sub-region, common behavioral patterns representing collective changes in heating demand are identified. Based on this pattern, the system quantitatively calculates the real-time demand urgency score for each sub-region and uses this as the core decision-making basis. This drives the heating management system to prioritize the dispatch of energy sources with fast response times (such as ground source heat pumps) to meet the instantaneous peak demand of high-urgency sub-regions, while simultaneously instructing energy sources with slower response times (such as biomass units) to provide a stable base load. Furthermore, differentiated and precise heat distribution is achieved by adjusting pipeline valves and pump speeds.

[0031] This application achieves precise perception of end-point heating comfort by converting user behavior and feedback into quantifiable signals, overcoming the perception blind spots caused by relying on macroscopic and lagging physical parameters. By identifying "common behavioral patterns" and calculating urgency scores, it can quickly and automatically locate and quantify local demand "hotspots," solving the problem that traditional forecasting methods cannot capture non-uniform demand. Based on the differentiated collaborative scheduling strategy of urgency scores, it can instruct rapid energy response to accurately meet instantaneous peak demand while respecting the ramp-up characteristics of slow energy sources, thereby improving the overall response speed and accuracy to surges in non-uniform demand. Ultimately, this ensures heating comfort in local areas while avoiding the waste of overall renewable energy resources, improving user satisfaction and the economic efficiency of heating system operation.

[0032] In a further embodiment of this application, after the step of collecting heating behavior and feedback data from each user within the heating area, it is preferable to further include: Anonymize the heating behavior and feedback data, remove personally identifiable information and perform abnormal data filtering to obtain the processed heating behavior and feedback data; The abnormal data filtering includes: Data points that exceed the preset reasonable temperature range in the reported target room temperature are marked as abnormal and filtered out; Data points that are reported more than the preset normal number of times within the first preset time window by the same smart temperature control terminal, and whose values ​​are exactly the same, are marked as abnormal and filtered out.

[0033] Anonymization refers to the desensitization of raw heating behavior and feedback data. For example, it may involve replacing a user's unique identifier with an irreversible anonymous ID, or obfuscating the user's geographic location information. The aim is to protect user privacy and prevent the leakage of personally identifiable information. Removing personally identifiable information ensures that any data that could directly or indirectly point to a specific user is removed or transformed.

[0034] Anomaly filtering aims to identify and remove illogical or obviously erroneous data points from a dataset, thereby improving data purity and reliability. For example, if the preset reasonable temperature range is 16°C to 28°C, any reported target room temperature data below 16°C or above 28°C will be considered anomaly data and automatically filtered out by the system. For instance, if a smart temperature control terminal reports the same target room temperature data 10 times consecutively within a first preset time window of one minute, while the preset normal number of reports is five, the data exceeding the threshold will be considered anomaly and filtered out. This helps to eliminate duplicate and invalid data caused by equipment malfunction or data transmission errors.

[0035] This application's solution effectively protects user privacy through anonymization, enhancing users' willingness to participate in data sharing and thus enabling the acquisition of more comprehensive and authentic heating behavior and feedback data. The abnormal data filtering mechanism ensures the quality of input data, avoiding analytical biases caused by erroneous or redundant data, and making the identification of common behavioral patterns and the quantification of the urgency of heating needs more accurate. Therefore, this application, based on high-quality data, can more accurately reflect users' true heating needs, thereby developing more reasonable and efficient heating scheduling schemes, improving the overall operational efficiency of the heating system and user satisfaction.

[0036] In some embodiments of this application, the step of dividing the heating area into multiple sub-areas and identifying common behavioral patterns representing users' collective willingness to heat within each sub-area based on heating behavior and feedback data preferably includes: Based on the topology of the heating network in the heating area and / or based on the geographical location and physical attributes of the buildings in the heating area, the heating area is divided into multiple sub-areas. If, within the second preset time window, the proportion of users in a sub-region who raise the target room temperature exceeds the first preset proportion, and the average increase exceeds the preset threshold, and / or the frequency of user manual adjustment behavior exceeds the historical baseline frequency, then the sub-region is identified as having a general behavioral pattern indicating a collective increase in heating demand. And / or, if the proportion of users submitting subjective feedback information representing a feeling of cold in a sub-region exceeds a second preset proportion within a second preset time window, then the sub-region is identified as having a general behavioral pattern indicating a collective increase in heating demand.

[0037] Heating zones can be divided based on multiple dimensions. For example, users within the same heating branch or the service area of ​​the same heating station can be grouped into a sub-zone based on the topology of the heating network to ensure the physical feasibility of heating scheduling. Alternatively, building groups with similar heat load characteristics or geographical proximity can be grouped into a sub-zone based on their geographical location (e.g., adjacent building clusters) and physical attributes (e.g., building age, insulation performance, window type) to more accurately assess their overall heating demand. The second preset time window refers to the period used to observe and statistically analyze user behavior; its length can be set according to actual conditions, such as several hours or a day, to capture short-term, concentrated changes in heating demand. The first and second preset ratios are used to define the size of the user group that raises the target room temperature and the size of the user group that submits feedback on perceived coldness, respectively. When these ratios are reached or exceeded, it indicates a collective change in demand within a certain range. The preset magnitude threshold is used to measure whether the average magnitude by which users raise their target room temperature is sufficient to indicate an increase in collective demand. Historical baseline frequency refers to the average frequency of manual adjustment behavior by users under normal heating conditions. When the actual adjustment frequency is significantly higher than this baseline, it indicates that users are dissatisfied with the current heating situation and are trying to improve their comfort through frequent adjustments.

[0038] Through the aforementioned technical solution, this application enables refined division of heating areas, making the heating demand characteristics of each sub-area clearer. More importantly, by introducing multi-dimensional and quantitative identification standards, the accuracy and sensitivity of the system in identifying users' collective heating needs can be significantly improved. This allows the system to capture the actual changes in heating demand in different sub-areas more promptly and accurately in scenarios where sudden strong cold air causes uneven surges in heating demand. This provides a solid data foundation and decision-making basis for subsequently developing differentiated heating scheduling plans, thereby improving the response efficiency and user satisfaction of the entire heating system.

[0039] The following is a specific example to illustrate this.

[0040] Suppose a heating area is divided into multiple sub-areas, where sub-area A contains three adjacent residential buildings, all built at the same time and sharing a single heating branch. During a second preset time window (e.g., a continuous 6 hours) following a strong cold front, the system detects that in sub-area A, more than a first preset percentage (e.g., 30%) of users raise their target room temperature, with the average increase exceeding a preset threshold (e.g., an average increase of 2°C). Simultaneously, the frequency with which users in this sub-area manually adjust their smart thermostats is significantly higher than historical baseline frequencies. Furthermore, more than a second preset percentage (e.g., 20%) of users submit subjective feedback regarding feeling cold via smart thermostats or mobile applications. Based on this comprehensive data, the system can accurately identify a common behavioral pattern in sub-area A indicating a collective increase in heating demand, thus providing a basis for prioritizing heat allocation to this sub-area.

[0041] In the above embodiments, the urgency of the heating demand is preferably calculated using the following formula: D = W1 × A + W2 × B + W3 × C; Where A is the product of the proportion of users who raise the target room temperature within the sub-region and the average magnitude of the temperature increase by the users; B is the ratio of the manual adjustment frequency within the second preset time window to the historical reference frequency within the sub-region; C is the proportion of users who submit feedback on the feeling of cold within the sub-region; W1, W2, W3 are preset weighting coefficients of A, B, and C, and satisfy W1+W2+W3=1.

[0042] Parameter A reflects the collective willingness and intensity of users to actively raise their target room temperature. A is calculated by multiplying the proportion of users in a sub-region who raised their target room temperature by the average increase in temperature. This provides a more comprehensive measure of user dissatisfaction with the current room temperature and their expectation of higher temperatures. For example, if a high proportion of users in a sub-region raised their target room temperature by a significant average amount, the value of A will increase accordingly, indicating a more urgent heating demand in that sub-region.

[0043] Parameter B focuses on the user's manual adjustment behavior. B is calculated as the ratio of the frequency of manual adjustments within the sub-region, within the second preset time window, to the historical reference frequency. Manual adjustment behaviors, such as frequently turning the heating on and off or adjusting the thermostat, are usually a direct indication of user dissatisfaction with the current heating effect. By comparing it with the historical reference frequency, it can be determined whether the current manual adjustment behavior is abnormally active, thus reflecting the user's immediate heating needs. When the value of B is high, it indicates that the user is actively seeking improvement, and the urgency of the heating demand increases accordingly.

[0044] Parameter C directly quantifies the proportion of users submitting feedback on their perceived coldness. Perceived coldness feedback is a direct expression of users' subjective feelings and can effectively supplement the shortcomings of behavioral data analysis. When the proportion of users submitting feedback on perceived coldness is high in a sub-region, it directly indicates that residents in that area generally feel cold and have a very urgent need for heating.

[0045] Preset weighting coefficients allow the system to assign different levels of importance to different types of user feedback based on actual conditions or experience. For example, in some scenarios, the user's willingness to actively raise the target room temperature may be considered the most important indicator, in which case W1 can be set relatively high; while in other scenarios, the directness of the perceived cold may be more important, and W3 can be increased accordingly. By adjusting these weights, the system can flexibly adapt to different heating strategies and user group characteristics.

[0046] Compared to traditional evaluation methods that rely on only a single or limited indicator, this proposed solution comprehensively considers users' willingness and extent to raise the target room temperature, the activity level of manual adjustment behavior, and the prevalence of subjective feedback. This allows for a more accurate and objective capture of the actual heat demand of each sub-zone within the heating area under the influence of strong cold air. This multi-dimensional, weighted, and integrated quantitative approach enables heating dispatching decisions to be based on more reliable data, effectively avoiding blind or delayed heat allocation and improving the utilization efficiency of heating resources and user satisfaction.

[0047] In a further embodiment of this application, after the step of quantifying the urgency of heating demand in each sub-region based on the identified common behavioral patterns, the following step is preferably also included: Based on the heat transfer coefficient of the building's exterior wall, window type and area ratio, air permeability, real-time outdoor temperature and wind speed parameters within the sub-region, calculate the comprehensive heat loss coefficient of the sub-region. Based on the comprehensive heat loss coefficient, the current indoor temperature and the current outdoor temperature within the sub-region, the expected rate of decrease in indoor temperature within the sub-region without additional heating intervention is predicted. The degree of authenticity matching is obtained by comparing the magnitude and frequency of users raising the target room temperature and the proportion of users submitting feedback on feeling cold in the general behavioral pattern with the degree of deviation between these and the intensity of user feedback reasonably expected based on the expected rate of decrease in indoor temperature. The urgency of heating demand is adjusted based on the accuracy of the matching degree to obtain the adjusted urgency of heating demand, which is then used to formulate and implement differentiated heating scheduling plans.

[0048] The "external wall heat transfer coefficient" refers to the amount of heat transferred per unit area of ​​a building's external wall under a unit temperature difference, reflecting the wall's thermal insulation performance. The "window type and area ratio" refers to the material, structure, and proportion of windows within the sub-region's building exterior area; windows are a significant pathway for heat loss. The "air permeability" refers to the amount of air exchanged through building gaps or window / door leaks, directly affecting indoor heat loss. The "real-time outdoor temperature and wind speed parameters" are external environmental factors influencing heat loss. These parameters are used to calculate the "comprehensive heat loss coefficient" for the sub-region, which objectively characterizes the overall thermal insulation performance and heat loss rate of the building complex within the sub-region.

[0049] The "expected rate of indoor temperature decrease" refers to the predicted rate of indoor temperature decrease over time, based on physical conditions such as the comprehensive heat loss coefficient of the sub-area, the current indoor temperature, and the current outdoor temperature, without additional heating. This rate provides an objective physical benchmark for evaluating the reasonableness of user feedback. During calculation, the system decomposes the building's total heat loss into three main parts and estimates each part individually, based on the principle of heat balance. The first part is the conductive heat loss through the building envelope (walls, windows, roof, etc.), the magnitude of which is determined by the sum of the products of the heat transfer coefficients of each part and their corresponding areas. The second part is the latent and sensible heat loss due to air infiltration (ventilation), the value of which depends on the building volume, air permeability, and the physical properties of the air (density and specific heat capacity). The third part is the convective heat transfer loss enhanced by outdoor wind blowing across the building surface, which is related to wind speed, building exposed area, and an empirical wind speed influence factor. Finally, the three heat loss rates are added together to obtain the "comprehensive heat loss coefficient" for the sub-area under the current building characteristics and environmental conditions. This coefficient represents the total power of heat loss from this sub-region to the environment per unit indoor-outdoor temperature difference. It is worth noting that, because outdoor temperature and wind speed are input in real time, this coefficient is a dynamic value; the system continuously updates its value to reflect instantaneous changes in the external environment, thereby ensuring the accuracy of subsequent thermal inertia predictions.

[0050] Regarding "realism match", if the severity of the user feedback is highly consistent with the physical prediction of the temperature drop rate, the realism match is high, indicating that the user feedback is real and urgent; conversely, if there is a large deviation, the realism match is low, which may mean that there are certain "non-physical" factors in the user feedback, such as oversensitivity or misoperation.

[0051] To correct the urgency of heating demand, for example, when the accuracy of the match is high, the originally calculated urgency of heating demand may be maintained or slightly increased; when the accuracy of the match is low, the originally calculated urgency of heating demand may be appropriately reduced. Thus, a corrected urgency of heating demand is obtained, which more accurately reflects the actual heating demand of each sub-region, thereby providing a more reliable basis for formulating and implementing differentiated heating scheduling schemes.

[0052] This application, by comprehensively considering the physical characteristics of buildings and external environmental factors, and verifying the authenticity of user feedback, effectively avoids misjudgments of heating demand caused by relying solely on subjective user feedback. This allows for more accurate identification of sub-areas that truly require priority heating, preventing overheating of areas with low actual heat demand and reducing energy waste. Simultaneously, for areas where actual heat dissipation is rapid but user feedback is not significant, this solution can also identify potential heating needs through physical models, ensuring the fairness and timeliness of heat allocation. This revised assessment of heating demand urgency makes the heating scheduling scheme more realistic, optimizing the allocation efficiency of heating resources and improving the overall operational efficiency of the heating system and user satisfaction.

[0053] The following is a specific example to illustrate this.

[0054] Suppose that during a sudden cold snap, a heating area is divided into sub-area A and sub-area B.

[0055] Users in sub-region A generally raised their target room temperature significantly and submitted numerous feedback reports on perceived coldness, indicating a high degree of urgency in their initial heating needs. However, the proposed solution first calculates the overall heat loss coefficient for sub-region A. Assuming that the building's exterior wall heat transfer coefficient is low, the windows are double-glazed with a moderate area, and the air permeability is also low, indicating good insulation performance, and considering real-time outdoor temperature and wind speed, the predicted rate of temperature decrease in sub-region A without additional heating intervention is relatively slow. At this point, comparing the actual increase in target room temperature and frequency, along with the proportion of submitted feedback reports on perceived coldness, with the expected intensity of user feedback based on the slow expected rate of temperature decrease reveals a significant deviation from expectations. Therefore, the calculated accuracy is low. Based on this low accuracy, the initial quantified urgency of heating needs in sub-region A is revised to appropriately reduce its urgency, thus avoiding overheating.

[0056] Conversely, assuming that users in sub-region B do not significantly raise their target room temperature and submit relatively few feedbacks regarding perceived coldness, the initial quantification of heating demand urgency is moderate. However, by calculating the overall heat loss coefficient of sub-region B, it is found that its building exterior wall heat transfer coefficient is high, the windows are single-pane glass with a large area ratio, and the air permeability is high, indicating poor insulation performance. Combining real-time outdoor temperature and wind speed, the predicted rate of indoor temperature decrease in sub-region B without additional heating intervention is relatively fast. At this point, comparing the actual magnitude and frequency of users raising their target room temperature, as well as the proportion of submitted feedbacks regarding perceived coldness, with the reasonably expected severity of user feedback based on the rapid expected rate of indoor temperature decrease, reveals that the severity of user feedback is basically consistent with the expectation, i.e., the deviation is small. Therefore, the calculated accuracy is high. Based on this high accuracy, the initial quantification of heating demand urgency in sub-region B can be revised, possibly maintaining or slightly increasing its urgency to ensure timely fulfillment of its actual heating needs.

[0057] As can be seen from the above examples, the solution proposed in this application can objectively verify and correct user feedback based on the actual physical conditions of each sub-region, thereby obtaining a more realistic and accurate understanding of the urgency of heating demand and guiding the heating system to make more reasonable resource allocation.

[0058] In a specific embodiment of this application, the step of obtaining the degree of authenticity matching by comparing the magnitude and frequency of users raising the target room temperature and the proportion of users submitting feedback on feeling cold in general behavioral patterns with the degree of deviation between these deviations and the degree of intensity of user feedback reasonably expected based on the expected rate of decrease in indoor temperature. Based on the expected rate of decrease in indoor temperature, reasonable expected values ​​are determined in three dimensions: temperature adjustment range, adjustment frequency, and cold feedback ratio, according to the pre-stored mapping relationship or threshold model. Calculate the normalized deviation between the average increase in temperature by the user, the actual frequency of manual adjustment, and the proportion of actual submissions of feedback on the feeling of cold, and the reasonable expected value of the corresponding dimension. The weighted sum of the normalized deviations of the three dimensions is used to obtain the comprehensive deviation. Subtracting the comprehensive deviation from 1 yields the degree of authenticity matching.

[0059] The expected rate of decrease in indoor temperature is predicted based on the comprehensive heat loss coefficient of the sub-region, the current indoor temperature, and the current outdoor temperature, reflecting the physical cooling trend of the sub-region without additional heating intervention. The pre-stored mapping relationship or threshold model can be an empirical lookup table, a regression model trained on historical data, or a set of expert rules. Its purpose is to correlate different expected rates of decrease in indoor temperature with the intensity of typical user behaviors across the three dimensions mentioned above. For example, when the expected cooling rate is higher, the reasonable expectation value may increase accordingly, indicating that the user is more likely to significantly increase the target room temperature, frequently adjust manually, or submit cold feedback.

[0060] The average increase in temperature by users, the actual frequency of manual temperature adjustments, and the proportion of users submitting feedback on perceived coldness are all derived from the identification results of common behavioral patterns within the sub-regions. The calculation of normalized deviation aims to eliminate the influence of different data dimensions and ensure comparability of each dimension in subsequent comprehensive calculations. For example, normalization can be achieved by dividing the difference between the actual and expected values ​​by the maximum possible range of that dimension or the expected value itself.

[0061] The normalized deviations from these three dimensions are weighted and summed to obtain a comprehensive deviation. This weighted summation allows for assigning different weight coefficients to the deviations of different dimensions based on actual application scenarios or expert experience. For example, in some cases, the magnitude by which a user raises the target room temperature may be considered more representative of actual heating demand than the frequency of manual adjustments, and therefore can be given a higher weight. Through weighted summation, a single, comprehensive indicator is obtained that fully reflects the overall degree of deviation between actual user feedback and the feedback reasonably expected from the physical cooling trend.

[0062] Finally, subtracting the overall deviation from 1 yields the final accuracy matching score. This calculation method places the accuracy matching score between 0 and 1, where 1 indicates a perfect match between user feedback and physical reality, while 0 indicates a complete mismatch. A high accuracy matching score indicates that the users' collective heating intentions are highly consistent with the actual physical cooling situation, demonstrating a high degree of authenticity and rationality in their needs.

[0063] This application, by introducing multi-dimensional quantitative analysis, effectively avoids misjudgments caused by the randomness or irrational factors of user feedback, significantly improving the accuracy of assessing the authenticity of users' collective heating needs. Therefore, when adjusting the urgency of heating demand, it can more accurately reflect the actual heating needs, avoiding excessive or insufficient heating scheduling, thereby optimizing energy distribution efficiency, improving user satisfaction, and further saving energy.

[0064] The following is a specific example to illustrate this.

[0065] Assuming that within a certain sub-region, based on building physics parameters and real-time meteorological data, the predicted rate of indoor temperature decrease in that sub-region without additional heating intervention is 1.5°C / hour. Based on a pre-stored mapping model, the system determines that under this rate of decrease, the reasonable expected average increase in target room temperature by users is 1.0°C, the manual adjustment frequency is 3 times / hour, and the proportion of users submitting feedback on perceived coldness is 15%.

[0066] However, the actual monitored general behavioral patterns showed that users in this sub-region actually raised the target room temperature by an average of 1.8°C, manually adjusted it 5 times per hour, and 30% of users submitted feedback on the feeling of cold.

[0067] At this point, the system will calculate the normalized deviation for each of the three dimensions. For example, if the normalized deviation for the temperature adjustment amplitude dimension is 0.4, the normalized deviation for the adjustment frequency dimension is 0.3, and the normalized deviation for the cold feedback ratio dimension is 0.5, and the preset weighting coefficients are W1=0.4, W2=0.3, and W3=0.3.

[0068] The overall deviation is calculated as follows: 0.4 × 0.4 + 0.3 × 0.3 + 0.5 × 0.3 = 0.16 + 0.09 + 0.15 = 0.4.

[0069] Therefore, the degree of authenticity matching = 1 - 0.4 = 0.6.

[0070] This 0.6 accuracy matching score will be used to adjust for the urgency of heating demand in this sub-region, ensuring that the authenticity and rationality of user feedback can be more accurately considered when developing differentiated heating scheduling plans.

[0071] In a further embodiment of this application, the heating behavior and feedback data preferably include: a perceived cooling acceleration signal automatically generated and reported by the user-side intelligent temperature control terminal when it detects in real time that the rate of indoor temperature drop exceeds a preset comfort threshold. After determining the degree of authenticity matching by comparing the magnitude and frequency of users raising the target room temperature and the proportion of users submitting feedback on feeling cold in the general behavioral pattern with the degree of deviation between these deviations and the intensity of user feedback reasonably expected based on the expected rate of decrease in indoor temperature, the following steps are also included: Within the third preset time window, the number of terminals that trigger the body-feeling cooling acceleration signal in the sub-region is counted, and the proportion of acceleration signals in the sub-region is calculated by combining the total number of active terminals in the sub-region. Based on the proportion of the acceleration signal, the accuracy of the matching degree of the sub-regions with the perceived cooling acceleration signal is improved, and the corrected accuracy of the matching degree is obtained, which is used to correct the urgency of the heating demand.

[0072] In addition to user-set target room temperature, user manual adjustments, and user-submitted subjective feedback, heating behavior and feedback data are expanded to include a signal indicating accelerated temperature drop, automatically generated and reported by the user-side smart temperature control terminal. This signal is generated automatically when the smart temperature control terminal detects that the rate of indoor temperature decrease exceeds a preset comfort threshold. For example, if the indoor temperature drops by more than 1 degree Celsius within a short period (e.g., 10 minutes), and this rate of decrease is deemed likely to cause user discomfort, this signal will be generated. The purpose is to provide objective, real-time evidence of a decrease in user perceived comfort, compensating for the potential lag or incompleteness of relying solely on user-initiated feedback.

[0073] After obtaining the accuracy of the match, this application introduces the statistics and utilization of the perceived cooling acceleration signal. Specifically, within a third preset time window, the system counts the number of smart temperature control terminals that triggered the perceived cooling acceleration signal in a specific sub-region. Simultaneously, combined with the total number of all active smart temperature control terminals in that sub-region, the acceleration signal percentage for that sub-region is calculated. For example, if there are 100 active terminals in a sub-region, and 20 of them report the perceived cooling acceleration signal within the third preset time window, then the acceleration signal percentage can be calculated as 20 / 100 = 0.2. This acceleration signal percentage directly reflects the proportion of terminals affected by rapid cooling in the sub-region, characterizing the prevalence of the perceived cooling acceleration signal in that sub-region, rather than the severity of the cooling rate of a single terminal. The acceleration signal reflects the degree to which users in the sub-region generally experience discomfort due to the rapid temperature drop. Based on this, the previously obtained accuracy of the match is improved according to the calculated acceleration signal percentage. Specifically, if a sub-region experiences a signal of accelerated perceived cooling, its accuracy will be increased accordingly, resulting in a corrected accuracy. This corrected accuracy will be used to adjust the urgency of heating demand in subsequent adjustments, to more accurately reflect the actual heating needs of that sub-region.

[0074] This application's solution introduces a perceived cooling acceleration signal, allowing the system to move beyond solely relying on subjective or proactive user feedback. Instead, it incorporates objective monitoring data from smart terminals, enabling a more comprehensive and timely capture of users' actual discomfort. This introduction of objective data effectively compensates for the lag, subjectivity, or incompleteness of user feedback in traditional solutions. Especially when users fail to provide timely feedback, the system's automatic monitoring mechanism can still identify potential surges in heating demand. Furthermore, by calculating the proportion of acceleration signals and adjusting the accuracy of the matching, this application can more accurately determine the authenticity and urgency of user feedback. When a large number of perceived cooling acceleration signals are present, even if other user feedback indicators show little deviation, the system can still identify that the sub-area is indeed experiencing discomfort due to rapid cooling, thus improving its accuracy and avoiding underestimation of actual heating demand. This allows the final urgency of heating demand to more accurately reflect the actual situation, guiding the heating dispatching scheme to more precisely prioritize resource allocation to sub-areas that truly need heat, improving the heating system's response efficiency and user satisfaction.

[0075] The following is a specific example to illustrate this.

[0076] Suppose that in a sub-area of ​​a heating zone, a sudden cold front causes a sharp drop in outdoor temperature, leading to a rapid decrease in indoor temperature in buildings within that sub-area. Although some users may not have actively raised their target room temperature or submitted feedback on perceived coldness due to being outside or not paying attention in time, the smart temperature control terminals installed in that sub-area continuously monitor the indoor temperature. When these terminals detect that the rate of temperature drop exceeds a preset comfort threshold (e.g., a drop of more than 1.5 degrees Celsius per hour), they automatically generate and report a perceived cooling acceleration signal. Within a third preset time window (e.g., the past 30 minutes), the system statistically analyzes and finds that 30% of the active smart temperature control terminals in that sub-area have reported a perceived cooling acceleration signal, thus calculating a high acceleration signal percentage. At this point, even if the initial accuracy of the match calculated based on the magnitude and frequency of users raising their target room temperature and the proportion of submitted perceived coldness feedback is only moderate, the presence of a large number of perceived cooling acceleration signals will significantly improve the accuracy of the match for that sub-area based on this acceleration signal percentage. For example, an initial accuracy match of 0.6 might improve to 0.85 after acceleration signal ratio correction. This higher accuracy match will be used to adjust the urgency of heating demand in that sub-area, making it a higher priority. Consequently, the heating dispatch system will allocate more heat to that sub-area, thus responding promptly to users' actual discomfort and avoiding insufficient heating due to delayed user feedback, thereby improving the timeliness of heating services and user comfort.

[0077] It should be noted that the accuracy of the matching is preferably corrected based on the following formula: m = M + (1-M) × K × I; Where m is the corrected accuracy, M is the original accuracy, K is the preset amplification factor, and I is the proportion of the acceleration signal.

[0078] The corrected accuracy matching degree *m* represents the final accuracy matching degree after adjusting for the acceleration signal proportion *I*. It reflects a more accurate assessment of the accuracy of user feedback after considering the user's perceived cooling acceleration signal. The uncorrected accuracy matching degree *M* refers to the accuracy matching degree obtained before considering the perceived cooling acceleration signal. This is achieved by comparing the magnitude and frequency of users raising their target room temperature and the proportion of users submitting perceived cold feedback in common behavioral patterns with the degree of intensity of user feedback reasonably expected based on the expected rate of indoor temperature decrease. The preset amplification factor *K* is a parameter used to adjust the magnitude of the improvement in accuracy matching degree by the acceleration signal proportion *I*. Its value can be set according to the actual application scenario and the system's response sensitivity requirements. The acceleration signal proportion *I* is calculated based on the number of terminals triggering the perceived cooling acceleration signal in the sub-region and the total number of active terminals in the sub-region, used to quantify the degree to which users in that sub-region generally feel an accelerated temperature decrease.

[0079] Through the above technical solution, this application provides a standardized, transparent, and adjustable accuracy matching correction mechanism. This mechanism avoids the uncertainty caused by subjective judgment or empirical adjustments, ensuring the scientific nature and consistency of the correction process. By introducing an amplification factor K, the system can flexibly adjust the influence of the acceleration signal ratio on the accuracy matching degree according to actual needs, thereby improving the response sensitivity to sudden and collective cooling demands while ensuring system stability. Therefore, the corrected urgency of heating demand can more accurately reflect users' true feelings and actual needs, providing a more reliable decision-making basis for subsequent differentiated heating scheduling schemes, and further optimizing the allocation efficiency of heating energy and user satisfaction.

[0080] In some embodiments of this application, the step of formulating and implementing differentiated heating scheduling schemes based on the urgency of heating demand, to prioritize the allocation of heat to sub-areas with high urgency of heating demand, includes: Prioritize scheduling heating energy with a response speed greater than or equal to a preset speed threshold, and increase heat output to sub-areas with high heating demand. Simultaneously, heating energy with a response speed less than the preset speed threshold is dispatched to maintain the basic heat supply to the heating area. The scheduling methods for heating energy include: adjusting the speed of circulating pumps flowing to different sub-regions in the heating network, and / or adjusting the valve opening on the corresponding branches to change the flow rate of the heat medium to each sub-region.

[0081] Prioritizing heating energy sources with a response speed greater than or equal to a preset speed threshold means that when facing sub-areas with high urgency of heating demand, the system will prioritize the activation of heating equipment or energy types that can quickly adjust heat output. For example, some gas boilers, electric heating equipment, or energy storage systems may have fast start-up and adjustment speeds, enabling them to quickly respond to sudden localized heat demands. By increasing the heat output of these fast-response energy sources to specific sub-areas, the system can ensure that the emergency heating needs of that area are met in the shortest possible time. Simultaneously, prioritizing heating energy sources with a response speed less than a preset speed threshold to maintain the base heat supply to the heating area refers to heating energy sources with relatively slower response speeds, such as waste heat from large coal-fired power plants, geothermal energy, or large-scale biomass boilers. Their main role is to provide a stable and continuous base heat supply. These energy sources typically have lower operating costs and higher operational stability, making them suitable as the base load heat source for the entire heating area, ensuring the stable operation of the overall heating system and avoiding excessive costs or system fluctuations due to over-reliance on fast-response energy sources. The specific methods for scheduling heating energy include adjusting the speed of circulating pumps flowing to different sub-regions in the heating network, and / or adjusting the valve openings on corresponding branches to change the flow rate of the heat medium to each sub-region. The speed of the circulating pumps directly affects the velocity and flow rate of the heat medium (such as hot water) in the network; increasing the speed can increase the heat transfer capacity to a specific sub-region. Adjusting the valve openings allows for more precise control of the heat medium flow rate on specific branches, thereby achieving accurate control of heat distribution to different sub-regions. These two methods can be used individually or in combination to achieve flexible and efficient heat scheduling.

[0082] This application's solution, by differentiating and prioritizing fast-response heating energy sources, ensures that heat is delivered to the sub-areas with the most urgent needs in the shortest possible time, effectively alleviating localized heating shortages and significantly improving user comfort. Simultaneously, by combining this with the basic supply of slow-response energy sources, it achieves optimized energy allocation and efficient utilization, reducing overall operating costs and enhancing the stability and reliability of the heating system. This refined scheduling method allows the heating system to adapt more flexibly to dynamically changing heating demands, thus providing high-quality heating services even under extreme weather conditions.

[0083] like Figure 2 As shown, this application also discloses a heating area renewable energy resource optimization management system for the coordinated scheduling of heating energy in scenarios where a sudden surge in heating demand due to a strong cold front causes uneven distribution of heating demand. The system includes: The data acquisition module 210 is used to collect heating behavior and feedback data from each user in the heating area. The heating behavior and feedback data includes at least the target room temperature set by the user, the user's manual adjustment behavior, and the subjective feedback information submitted by the user. The behavior recognition module 220 is used to divide the heating area into multiple sub-areas and, based on the heating behavior and feedback data, identify common behavior patterns in each sub-area that represent the collective heating intention of users; wherein, the common behavior patterns include: behavior patterns that represent a collective change in heating demand in the corresponding sub-area by statistically analyzing the aggregated behavior of users raising the target room temperature in each sub-area and / or the aggregated situation of users submitting feedback on feeling cold. Demand quantification module 230 is used to quantify the urgency of heating demand in each sub-region based on identified common behavioral patterns. The scheduling execution module 240 is used to formulate and execute differentiated heating scheduling schemes based on the urgency of the heating demand, so as to prioritize the allocation of heat to sub-areas with high urgency of heating demand.

[0084] The data acquisition module 210 can be configured to interact with the user-side smart temperature control terminal, smart home gateway, and user feedback platform via various communication interfaces. For example, the behavior recognition module 220 can be a software service deployed in the cloud or on a local server, responsible for receiving user-set target room temperature and manual adjustment behavior data uploaded from the user's smart temperature control terminal via wireless networks such as Wi-Fi, LoRa, or NB-IoT. Simultaneously, the data acquisition module 210 can also obtain user-submitted subjective feedback information, such as perceived coldness, from user-submitted subjective feedback platforms (such as mobile applications, WeChat mini-programs, or customer service systems) via API interfaces or data scraping technology. This data can undergo preliminary format verification and integrity checks before being stored and processed.

[0085] The behavior recognition module 220 can be implemented as a data analysis engine, running on a central management platform or a high-performance computing server. The behavior recognition module 220 receives heating behavior and feedback data provided by the data acquisition module 210, and logically divides the entire heating area into multiple sub-regions using Geographic Information System (GIS) data or preset regional division rules. Subsequently, the behavior recognition module 220 monitors and analyzes the aggregated behavior patterns within each sub-region in real time. The implementation of the behavior recognition module 220 does not rely on complex machine learning models, but rather on preset statistical rules and thresholds for judgment. For example, when the proportion of users raising the target room temperature in a certain sub-region exceeds a preset threshold, it is identified as exhibiting a prevalent behavior pattern.

[0086] The demand quantification module 230 can be implemented as a calculation service. Its function is to quantify the urgency of heating demand in each sub-region based on the common behavioral patterns identified by the behavior recognition module 220. The demand quantification module 230 can use a preset quantification model or scoring mechanism to convert the intensity of collective user behavior (such as the extent to which the target room temperature is increased, the frequency of manual adjustment, and the proportion of perceived coldness) into a numerical urgency index. For example, different weights can be assigned according to the degree of influence of different behavioral patterns on the urgency of heating demand, and then a weighted summation calculation can be performed.

[0087] The scheduling execution module 240 can be implemented as a control command generation and distribution system, which communicates with the physical control equipment of the heating network (such as circulating pumps, electric valves, etc.). The scheduling execution module 240 can be implemented as a real-time control system, communicating with field devices through protocols such as industrial Ethernet or Modbus to ensure the timely and accurate execution of scheduling commands.

[0088] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0089] The preferred embodiments of this application have been described in detail above, but this application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application.

Claims

1. A method for optimizing the management of renewable energy resources in heating areas, characterized in that, This method is used to coordinate the scheduling of heating energy in scenarios where a sudden surge in heating demand due to a strong cold front causes uneven distribution of heating demand. The method includes the following steps: Collect heating behavior and feedback data from each user in the heating area. The heating behavior and feedback data includes at least the target room temperature set by the user, the user's manual adjustment behavior, and the subjective feedback information submitted by the user. The heating area is divided into multiple sub-areas, and based on the heating behavior and feedback data, common behavioral patterns representing users' collective heating intentions in each sub-area are identified. The common behavioral patterns include: behavioral patterns representing collective changes in heating demand in the corresponding sub-area by statistically analyzing the aggregated behavior of users raising the target room temperature and / or the aggregated situation of users submitting feedback on feeling cold in each sub-area. Based on the identified common behavioral patterns, the urgency of heating demand in each sub-region is quantified; Based on the urgency of the heating demand, a differentiated heating scheduling plan is formulated and implemented to prioritize the allocation of heat to sub-areas with high heating urgency.

2. The method for optimizing the management of renewable energy resources in heating areas according to claim 1, characterized in that, Following the step of collecting heating behavior and feedback data from each user within the heating area, the method further includes: Anonymize the heating behavior and feedback data, remove personally identifiable information and perform abnormal data filtering to obtain the processed heating behavior and feedback data; The abnormal data filtering includes: Data points that exceed the preset reasonable temperature range in the reported target room temperature are marked as abnormal and filtered out; Data points that are reported more than the preset normal number of times within the first preset time window by the same smart temperature control terminal, and whose values ​​are exactly the same, are marked as abnormal and filtered out.

3. The method for optimizing the management of renewable energy resources in heating areas according to claim 1, characterized in that, The steps of dividing the heating area into multiple sub-areas and identifying common behavioral patterns representing users' collective willingness to heat within each sub-area based on the heating behavior and feedback data include: Based on the topology of the heating network in the heating area and / or based on the geographical location and physical attributes of the buildings in the heating area, the heating area is divided into multiple sub-areas. If, within the second preset time window, the proportion of users in a sub-region who raise the target room temperature exceeds the first preset proportion, and the average increase exceeds the preset threshold, and / or the frequency of user manual adjustment behavior exceeds the historical baseline frequency, then the sub-region is identified as having a general behavioral pattern indicating a collective increase in heating demand. And / or, if the proportion of users submitting subjective feedback information representing a feeling of cold in a sub-region exceeds a second preset proportion within a second preset time window, then the sub-region is identified as having a general behavioral pattern indicating a collective increase in heating demand.

4. The method for optimizing the management of renewable energy resources in heating areas according to claim 3, characterized in that, The urgency of the heating demand is calculated using the following formula: D = W1 × A + W2 × B + W3 × C; Where A is the product of the proportion of users who raise the target room temperature within the sub-region and the average magnitude of the temperature increase by the users; B is the ratio of the manual adjustment frequency within the second preset time window to the historical reference frequency within the sub-region; C is the proportion of users who submit feedback on the feeling of cold within the sub-region; W1, W2, W3 are preset weighting coefficients of A, B, and C, and satisfy W1+W2+W3=1.

5. The method for optimizing the management of renewable energy resources in a heating area according to claim 4, characterized in that, Following the step of quantifying the urgency of heating demand in each sub-region based on the identified common behavioral patterns, the following steps are also included: Based on the heat transfer coefficient of the building's exterior wall, window type and area ratio, air permeability, real-time outdoor temperature and wind speed parameters within the sub-region, calculate the comprehensive heat loss coefficient of the sub-region. Based on the comprehensive heat loss coefficient, the current indoor temperature and the current outdoor temperature within the sub-region, the expected rate of decrease in indoor temperature within the sub-region without additional heating intervention is predicted. The degree of authenticity matching is obtained by comparing the magnitude and frequency of users raising the target room temperature and the proportion of users submitting feedback on feeling cold in the general behavioral pattern with the degree of deviation between these and the intensity of user feedback reasonably expected based on the expected rate of decrease in indoor temperature. The urgency of heating demand is adjusted based on the accuracy of the matching degree to obtain the adjusted urgency of heating demand, which is then used to formulate and implement differentiated heating scheduling plans.

6. The method for optimizing the management of renewable energy resources in a heating area according to claim 5, characterized in that, The step of obtaining the degree of authenticity matching by comparing the degree and frequency of users raising the target room temperature and the proportion of users submitting feedback on feeling cold in the general behavioral pattern with the degree of deviation between these deviations and the degree of intensity of user feedback reasonably expected based on the expected rate of decrease in indoor temperature, includes: Based on the expected rate of decrease in indoor temperature, reasonable expected values ​​are determined in three dimensions: temperature adjustment range, adjustment frequency, and cold feedback ratio, according to the pre-stored mapping relationship or threshold model. Calculate the normalized deviation between the average increase in temperature by the user, the actual frequency of manual adjustment, and the proportion of actual submissions of feedback on the feeling of cold, and the reasonable expected value of the corresponding dimension. The weighted sum of the normalized deviations of the three dimensions is used to obtain the comprehensive deviation. Subtracting the comprehensive deviation from 1 yields the degree of authenticity matching.

7. The method for optimizing the management of renewable energy resources in a heating area according to claim 5, characterized in that, The heating behavior and feedback data also include: a perceived cooling acceleration signal automatically generated and reported by the user-side intelligent temperature control terminal when it detects in real time that the rate of indoor temperature drop exceeds the preset comfort threshold. After determining the degree of authenticity matching by comparing the magnitude and frequency of users raising the target room temperature and the proportion of users submitting feedback on feeling cold in the general behavioral pattern with the degree of deviation between these deviations and the intensity of user feedback reasonably expected based on the expected rate of decrease in indoor temperature, the following steps are also included: Within the third preset time window, the number of terminals that trigger the body-feeling cooling acceleration signal in the sub-region is counted, and the proportion of acceleration signals in the sub-region is calculated by combining the total number of active terminals in the sub-region. Based on the proportion of the acceleration signal, the accuracy of the matching degree of the sub-regions with the perceived cooling acceleration signal is improved, and the corrected accuracy of the matching degree is obtained, which is used to correct the urgency of the heating demand.

8. The method for optimizing the management of renewable energy resources in a heating area according to claim 7, characterized in that, The accuracy of the match is corrected based on the following formula: m = M + (1-M) × K × I; Where m is the corrected accuracy, M is the original accuracy, K is the preset amplification factor, and I is the proportion of the acceleration signal.

9. The method for optimizing the management of renewable energy resources in a heating area according to claim 1, characterized in that, The step of formulating and implementing a differentiated heating dispatching plan based on the urgency of heating demand, to prioritize the allocation of heat to sub-areas with high urgency of heating demand, includes: Prioritize scheduling heating energy with a response speed greater than or equal to a preset speed threshold, and increase heat output to sub-areas with high heating demand. Simultaneously, heating energy with a response speed less than the preset speed threshold is dispatched to maintain the basic heat supply to the heating area. The scheduling methods for heating energy include: adjusting the speed of circulating pumps flowing to different sub-regions in the heating network, and / or adjusting the valve opening on the corresponding branches to change the flow rate of the heat medium to each sub-region.

10. A renewable energy resource optimization management system for heating areas, characterized in that, The system is used for coordinated scheduling of heating energy in scenarios where a sudden surge in heating demand due to a strong cold front causes uneven distribution of heating demand. The system includes: The data acquisition module is used to collect heating behavior and feedback data from each user in the heating area. The heating behavior and feedback data includes at least the target room temperature set by the user, the user's manual adjustment behavior, and the subjective feedback information submitted by the user. The behavior recognition module is used to divide the heating area into multiple sub-areas and, based on the heating behavior and feedback data, identify common behavior patterns in each sub-area that represent the collective heating intention of users; wherein, the common behavior patterns include: by statistically analyzing the aggregated behavior of users raising the target room temperature in each sub-area and / or the aggregated situation of users submitting feedback on feeling cold, the behavior patterns in the corresponding sub-area that represent a collective change in heating demand are identified. The demand quantification module is used to quantify the urgency of heating demand in each sub-region based on identified common behavioral patterns. The scheduling and execution module is used to formulate and execute differentiated heating scheduling plans based on the urgency of the heating demand, so as to prioritize the allocation of heat to sub-areas with high heating demand.

Images