Heat supply adjusting method and system for heat power unit

Abstract

The invention provides a heat supply adjusting method and system for a heat power unit, and belongs to the technical field of temperature and humidity control, and the method specifically comprises the steps that on the basis of a deviation weather type, an evaluation analysis result of the heat storage capacity of a heat supply pipe network of the heat power unit under the deviation weather type is obtained, heat storage matching temperature intervals in different deviation weather types are determined based on the evaluation analysis result, deviation weather type data without the heat storage matching temperature intervals are determined, and the heat storage matching temperature intervals of the deviation weather types and the similar situation of the weather types and the weather data of the different deviation weather types are combined; the heat supply adjusting method of the heat power unit under the weather type is determined, and the operation stability and safety of the heat power unit are improved.

Description

Technical Field

[0001] This invention belongs to the field of heating regulation technology, and particularly relates to a heating regulation method and system for thermal power units. Background Technology

[0002] With the increasing heat supply of thermal power units, traditional heating modes are unable to meet the heating needs of heat users. In particular, the heating capacity of thermal power units is insufficient to meet the needs of heat users due to the influence of thermal equipment and power generation in the plant. Therefore, how to improve the heating capacity of thermal power units has become an urgent technical problem to be solved.

[0003] To address the aforementioned technical issues, existing solutions often enhance heating capacity through electrode boilers, thermal storage tanks, and other similar methods. In invention patent application CN202510945827.8, "Multi-Energy Complementary Peak-Shaving Heating Method and Device Based on Chemical Thermal Storage," a chemical thermal storage device is used to dynamically adjust the opening and closing status of various valves and the output of traditional energy power supply units based on fluctuation curves, achieving multi-energy coordinated scheduling. This mechanism can precisely match heating demand with energy supply, significantly improving energy utilization efficiency, maximizing green electricity consumption, and reducing operating costs. However, it suffers from the following drawbacks: Using energy storage devices for heating regulation often requires a large investment of resources. Therefore, it is important to determine the heating regulation scheme based on the deviation of heating capacity under different weather conditions, which can improve the reliability of heating and effectively reduce the instability and safety of heating regulation.

[0004] To address the aforementioned technical problems, this application provides a heating regulation method and system for thermal power units. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted: Specifically, this application provides a heating regulation method for a thermal power unit, which includes: S1 uses the heating data of the heating unit as a basis to determine the matching status of the heating capacity of the heating unit with the demand of heat users under different weather types. Based on the demand matching status, it determines the matching deviation weather types of the heating unit. According to the distribution data of the deviation weather types in the future preset time period, it determines that the preset scheme does not need to be adopted. When the heating network is used for heating regulation, it proceeds to the next step. S2, based on the aforementioned deviated weather type, evaluates and analyzes the heat storage capacity of the heating network of the thermal power unit under the aforementioned deviated weather type. Based on the evaluation and analysis results, it determines the heat storage matching temperature range in different deviated weather types, identifies deviated weather type data where no heat storage matching temperature range exists, and, in conjunction with the heat storage matching temperature range of the deviated weather type and the similarity between the weather type and weather data of different deviated weather types, determines the heating regulation method of the thermal power unit under the weather type.

[0006] The beneficial effects of this invention are as follows: Based on the demand matching situation, the matching deviation weather type of the heating unit is determined. According to the distribution data of the deviation weather type in the future preset time period, it is determined whether a preset plan needs to be adopted to regulate the heating through the heating network, realizing a fundamental shift from "passive response" to "active pre-control", ensuring heating quality: fundamentally reducing the occurrence of room temperature failures caused by insufficient heating capacity on the user side, greatly improving user satisfaction, improving system safety: avoiding the risk of failure of units and equipment due to temporary overload operation or emergency start and stop, extending equipment life, and enhancing operational stability: changing the system operation from a "impact-response" fluctuation mode to a "prediction-smoothing" smooth mode.

[0007] Using data on deviated weather types that lack a heat storage matching temperature range, the heat storage matching temperature range of the deviated weather type, and the similarity between the weather type and weather data of different deviated weather types, the heating regulation method of the thermal power unit under the weather type is determined, thereby expanding the strategy of preventive maintenance: the "treatment-style" in-depth analysis for known high risks (deviated types) is scientifically extended to the "physical examination-style" preventive analysis for potential risks (similar common types), thus moving the safety defense line forward.

[0008] Optimize the allocation of technical resources: Through multi-level rule filtering, ensure that limited analytical computing resources and expert attention are accurately guided to the most needed, most effective, and most valuable weather types (such as "close relatives" of high-risk types, representatives of common type clusters, and types with weak correlation schemes), thus avoiding blind and wasteful analysis work.

[0009] Building a knowledge system for continuous learning: The system forms a closed loop of "deep analysis of a few key types -> extraction of universal knowledge -> guidance for targeted shallow analysis or verification of similar types -> enrichment and revision of the knowledge base." This enables the system to continuously deepen and expand its understanding of the heating network's behavior under different meteorological conditions.

[0010] Furthermore, the weather types are classified based on weather data including temperature, humidity, and wind speed. Specifically, dates with temperature, humidity, and wind speed within the same range are classified into the same weather type.

[0011] Furthermore, the matching between the heating capacity and the heat user's demand is determined based on the deviation between the unit's heating capacity and the heat user's heat demand at different times.

[0012] Furthermore, the method for determining the weather type of the matching deviation of the thermal power unit is as follows: Based on the demand matching situation, determine the deviation between the heating capacity of the heating unit and the heating demand of the heat user in different time periods under the weather type. Based on the aforementioned deviation, the time periods when the unit's heating capacity is less than the heat demand of the heat users are determined and these periods are considered as periods of insufficient capacity. Based on the data of insufficient capacity periods on different dates within the aforementioned weather type, determine whether the weather type is a mismatch weather type.

[0013] Furthermore, the method for determining the heating regulation method of the thermal power unit under the aforementioned weather type is as follows: Deviated weather types that do not have a matching temperature range for heat storage are classified as heat storage deviation weather types. Based on the similarity of weather data between the weather type and the deviated weather type, the average deviation rate under different weather indicators is determined and used as the weather type deviation rate between the weather type and the deviated weather type. Based on the heat storage deviation weather type data, the weather type deviation rate between the weather type and the deviation weather type, and the heat storage matching temperature range in different weather types, the heating regulation method of the thermal power unit under the weather type is determined.

[0014] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described method for regulating the heating supply of a thermal power unit when running the computer program.

[0015] Other features and advantages will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0016] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0018] Figure 1 This is a flowchart of a heating regulation method for a thermal power unit; Figure 2 This is a flowchart illustrating the method for determining the matching deviation of a thermal power unit based on weather type. Figure 3 This is a flowchart that determines that a preset scheme is not required and utilizes the heating network for heating regulation. Detailed Implementation

[0019] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0020] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that other elements / components / etc. may exist in addition to the listed elements / components / etc. Example

[0021] To solve the above problems, according to one aspect of the present invention, such as Figure 1 As shown, a heating regulation method for a thermal power unit is provided, specifically including: S1 uses the heating data of the heating unit as a basis to determine the matching status of the heating capacity of the heating unit with the demand of heat users under different weather types. Based on the demand matching status, it determines the matching deviation weather types of the heating unit. According to the distribution data of the deviation weather types in the future preset time period, it determines that the preset scheme does not need to be adopted. When the heating network is used for heating regulation, it proceeds to the next step. S2, based on the aforementioned deviated weather type, evaluates and analyzes the heat storage capacity of the heating network of the thermal power unit under the aforementioned deviated weather type. Based on the evaluation and analysis results, it determines the heat storage matching temperature range in different deviated weather types. Based on the heat storage matching temperature range and the similarity between the weather type and the weather data of different deviated weather types, it determines the heating regulation method of the thermal power unit under different weather types.

[0022] Furthermore, the weather types are classified based on weather data including temperature, humidity, and wind speed. Specifically, dates with temperature, humidity, and wind speed within the same range are classified into the same weather type.

[0023] Furthermore, the matching between the heating capacity and the heat user's demand is determined based on the deviation between the unit's heating capacity and the heat user's heat demand at different times.

[0024] Specifically, such as Figure 2 As shown, the method for determining the weather type of the matching deviation of the thermal power unit is as follows: This embodiment aims to provide an intelligent analysis method for identifying and defining specific meteorological conditions (i.e., "matching deviation weather types") that lead to "supply-demand mismatch" in heating systems. Its core decision-making logic is to divide historical weather data into "weather types" with similar meteorological characteristics through clustering, and then deeply analyze the spatiotemporal matching relationship between the actual heating capacity of heating units and the dynamic demand of heat users under each weather type. The system pays particular attention to and identifies weather types where heating capacity is systematically and continuously lower than user demand (i.e., "capacity insufficiency"). The goal of identifying these weather types is to provide precise meteorological scenario targets for the refined scheduling of heating systems, unit upgrades, or emergency plan development, thereby achieving a shift from "passively responding to weather changes" to "proactively predicting and managing specific weather risks."

[0025] S11 Based on the demand matching situation, determine the deviation between the heating capacity of the heating unit and the heating demand of the heat user in different time periods under the weather type. S12 determines, based on the aforementioned deviation, the time period in which the unit's heating capacity is less than the heat demand of the heat users, and identifies this as the period of insufficient capacity. S13 determines whether the weather type is a mismatch weather type based on the data of insufficient capacity periods on different dates in the weather type.

[0026] It is understandable that if there are periods of insufficient capacity on different dates within the stated weather type, then the stated weather type is determined to be a mismatch weather type.

[0027] Specifically, it includes the following: Weather type classification and deviation analysis: Keyword Explanation: "Weather Type" is a classification result obtained through cluster analysis of historical meteorological data (mainly including temperature, humidity, and wind speed—three core parameters that significantly affect building heat load and unit efficiency). Dates where the values ​​of temperature, humidity, and wind speed all fall within the same or similar ranges are grouped into the same weather type. For example, "Low Temperature-High Humidity-Strong Wind" type, "Medium Temperature-Low Humidity-Light Wind" type, etc. "Deviation" refers to the difference between "unit heating capacity" (the maximum heat output that the unit can stably deliver under current operating conditions) and "heat user's heat demand" (the heat required to maintain a comfortable indoor temperature) within a specific time period (such as a certain hour of a day).

[0028] Discretizing continuous and variable meteorological parameters into a finite number of "types" is a prerequisite for conducting regularity statistics and pattern recognition. Temperature, humidity, and wind speed were chosen as the criteria for classification because they collectively determine the rate of heat loss in buildings (affecting demand) and the operating efficiency of some units (affecting capacity). Analyzing "deviations" is a quantitative means of directly linking macro-weather conditions with micro-system operating performance.

[0029] Significance: This step establishes a framework linking "weather models" and "system performance." It allows us to answer the question, "Under what typical weather combinations are our heating systems more prone to problems?", rather than looking at a single weather factor or supply and demand situation in isolation.

[0030] Example: The system clusters daily meteorological data from the past three winters into five weather types. For type W2 (characteristics: daily average temperature -5℃ to -8℃, relative humidity 75% to 85%, average wind speed 4 to 6 m / s), the system analyzes the difference between the "total heating capacity of the unit" and the "total regional heat demand" for each hour (00:00-23:00) on all dates under this type, resulting in a set of deviation curves that change over time.

[0031] Step S12: Period of insufficient recognition capability: Explanation of the keyword: "Period of insufficient capacity" refers to the specific time point or continuous period of a day under a particular weather type where the heating capacity of the generating units is significantly less than the heating demand of the users. In other words, it is the period when the deviation value (capacity - demand) is negative.

[0032] Insufficient capacity is the most direct and severe form of supply-demand imbalance, directly leading to substandard room temperatures on the user side and posing a core threat to heating quality. Identifying these periods is the first step in pinpointing the weak points in the system.

[0033] Significance: It transforms the abstract concept of "poor matching" into a concrete "spatiotemporal gap." It accurately identifies the specific time points when the system "malfunctions" under specific weather conditions (such as the evening rush hour), providing a clear target for subsequent targeted analysis.

[0034] Example: On a certain day under weather type W2, the deviation curve shows that the deviation value is negative for 5 consecutive hours from 17:00 in the evening to 22:00 at night. Then, the "inadequate capacity period" under type W2 on this day is marked as [17:00, 22:00].

[0035] Step S13: Determine the weather type of the matching deviation: Logical judgment: For a given weather type, check whether there are "capacity deficit periods" in all (or most) of the historical dates it covers. If at least one capacity deficit period occurs on every day under this weather type, then the weather type is determined to be a "mismatched weather type".

[0036] An occasional capacity shortage might be due to temporary equipment failure or unusually high demand. However, if a particular weather type consistently results in a capacity shortage, this is not a coincidence but rather reveals inherent flaws or bottlenecks in the system's design or scheduling strategies when facing that specific weather combination. This type of weather is a systemic risk source that requires close attention.

[0037] Significance: Identifying underlying patterns from random failures helps distinguish between "occasional problems" and "structural contradictions." For "matching deviation weather types," simply strengthening routine maintenance is insufficient; fundamental improvements may be needed, such as increasing peak-shaving units, optimizing pipeline network configuration, adjusting scheduling algorithms, or strengthening user-side management.

[0038] Example: Weather type W2 contains 15 historical dates. Analysis in step S12 reveals that each of these 15 days experienced a "capacity deficiency period" during the evening to nighttime hours. Therefore, the system classifies weather type W2 (low temperature-high humidity-strong wind) as a "mismatched weather type." This indicates that whenever such meteorological conditions occur, the existing thermal system faces a systemic risk of being unable to meet demand during the evening peak hours.

[0039] The value of the method described in this embodiment lies in its deep integration of heating system operation analysis with meteorological science, enabling data-driven systemic risk diagnosis. Precise risk warning: By identifying "match deviation weather types," weather forecasts are no longer just temperature figures, but are imbued with the connotation of system operational risk levels. When a "match deviation weather type" that has been marked is forecast to occur in the next few days, the dispatch center can activate emergency plans in advance (such as activating backup units in advance, issuing flexible energy use initiatives, etc.), turning a passive approach into a proactive one.

[0040] Scientific investment and renovation: It provides a quantitative basis for decision-making regarding the expansion, renovation, or equipment selection of heating systems. For example, if the analysis finds that the "matching deviation weather type" is mainly due to a surge in demand caused by low temperatures, then the investment focus may be on increasing the basic heat source capacity; if it is mainly due to strong winds causing a sharp increase in heat loss in the pipeline network or a decrease in the efficiency of some units, then the investment focus may be on pipeline insulation or the design of windproof units.

[0041] Dispatch strategy optimization: It reveals the temporal patterns of supply and demand gaps under specific weather conditions (such as always occurring during the evening peak). This can guide more refined dispatch strategies, such as raising the heat storage temperature of the pipeline network in advance before periods of insufficient capacity arrive, or making flexible adjustments to non-critical users to prioritize residential heating.

[0042] Improve operational efficiency and service quality: By identifying and managing high-risk weather in advance, the system can effectively reduce actual complaints about "heating shortages," thereby improving user satisfaction and avoiding high costs and equipment wear and tear caused by emergency repairs and overload operation.

[0043] This method elevates traditional heating operation management from "experience-driven and post-event response" to a new intelligent stage of "data-driven and pre-event control," and is a key technological tool for building resilient, efficient, and low-carbon modern heating systems.

[0044] Specifically, such as Figure 3 As shown, it has been determined that a pre-set solution is not required; instead, heating regulation will be carried out using the heating network, specifically including: This embodiment aims to provide a system and method for intelligently deciding whether to activate a specific preset scheme of "heating network heat storage regulation" during a specific future period. Its core decision-making logic is as follows: based on future weather forecasts, it quantitatively assesses the risk level of "supply-demand mismatch" faced by the heating system, and automatically determines whether it is worthwhile to activate the costly network heat storage regulation strategy, which involves adjusting system operating conditions, based on the level of risk. This method comprehensively considers the frequency of occurrence of risky weather (proportion of deviation dates) and the severity of individual risky weather events (regulation demand factor). Through multi-level threshold judgments, it achieves a progressive decision-making process from "whether intervention is needed" to "whether intervention is economically effective," ensuring that control commands are timely and accurate while avoiding unnecessary system disturbances and increased operating costs.

[0045] S21 uses the distribution data of the deviation weather type in the future preset time period to determine the proportion of the number of days with the deviation weather type, and uses it as the proportion of deviation days; Calculate the percentage of dates with deviations (risk frequency assessment): Keyword Explanation: "Proportion of Deviation Dates" refers to the percentage of days predicted to fall under the "Match Deviation Weather Type" within a pre-defined time period (e.g., the next 7 days, or a heating season month), out of the total number of days in that period. It reflects the frequency of high-risk weather events that the system will face due to inherent supply-demand imbalances in the near future.

[0046] The primary principle of risk management is to focus on the probability of occurrence. If high-risk weather events occur frequently and in concentrated periods in the future, the system will face significant and sustained pressure, making proactive intervention essential. This is the macro-level context for decision-making.

[0047] Significance: This quantifies future risk exposure over time. A high percentage of dates with deviations indicates that the system will remain under constant pressure, providing a primary basis for subsequent decisions on whether to initiate a continuous, preventative adjustment plan.

[0048] Example: The preset period is 7 days. The weather forecast predicts that the weather type for 4 days (D1, D3, D5, D6) belongs to the known "match deviation weather type". Then the deviation date percentage = 4 / 7 ≈ 57.1%.

[0049] S22 will use the deviation weather type within a future preset time period as the matching type, and determine the adjustment demand factor of the matching type based on the proportion of the number of dates of the matching type and the average proportion of the duration of the insufficient capacity period of the matching type on different dates; Calculate the adjustment demand factor (risk intensity assessment): Keyword Explanation: The "Demand Adjustment Factor" is a quantitative indicator that comprehensively assesses the severity of each specific "matching deviation weather type" (matching type) that is expected to occur in the future. It is determined by two core factors: 1) the percentage of days that this type will occur within the forecast period; and 2) the percentage of the average duration of "capacity shortage periods" that this type will experience in its historical records (e.g., number of hours with insufficient capacity per day / 24 hours). Typically, the average or weighted average of these two factors is used. The larger this factor is, the more likely this type of weather is to occur, and the longer and more severe the supply-demand gap it will create once it does.

[0050] Not all "mismatch weather types" are equally harmful. Some may only cause short-term, minor power shortages, while others may lead to prolonged and severe deficits. This step aims to differentiate the "lethality" of different weather risks, providing a basis for precise policy implementation and refining future risks from a severity perspective. It avoids a "one-size-fits-all" approach to all high-risk weather, allowing decision-making to focus more on "high-impact" weather types that are both likely to occur and will lead to prolonged power outages.

[0051] Example: In the next 7 days, the matching type W2 (low temperature-high humidity-strong wind) occurs for 2 days, accounting for 2 / 7 of the dates. Historical data shows that under the W2 type, the "capacity deficiency period" accounts for an average of 30% of the day's duration (approximately 7.2 hours). Therefore, the adjustment demand factor for W2 = (2 / 7 + 30%) / 2 = (0.286 + 0.3) / 2 = 0.293. The factors for other matching types can be calculated similarly.

[0052] Based on the percentage of deviation dates and the adjustment demand factors for different matching types, S23 determines whether a preset scheme needs to be adopted to adjust the heating supply using the heating network.

[0053] It is understandable that if the percentage of the deviation date is greater than the preset date percentage threshold, then it is determined that a preset scheme needs to be adopted to regulate the heating through the heating network. This means that the heating load that the heating unit can provide is transferred to the heating network, and the heating network is used for heat storage to meet the user's heating needs.

[0054] Decisive Decision-Making in the Face of High-Frequency Risks: Logic and Significance: If the percentage of days with deviations exceeds a preset threshold (e.g., 50%), it means that more than half of the future will be characterized by high-risk weather. In this situation, the system faces widespread and continuous pressure. Activating pipeline heat storage, a solution that can smooth out intraday load fluctuations and provide a continuous supplementary heat source, has high overall value. The decision logic is simple and direct: the risk is too high, so the preset solution (pipeline heat storage) must be activated.

[0055] Example: If the percentage of dates with deviation in the next 7 days is 57.1% (>50% threshold), the system immediately decides: network heat storage regulation needs to be activated. When the deviation rate between heating capacity and heating demand is within 5%, and the heating capacity exceeds the heating demand, the excess heat energy, i.e., the heat energy that the unit can provide, is stored as high-temperature hot water in the vast heating network for release during periods of insufficient capacity during the daytime to meet user needs.

[0056] It should be noted that the adjustment demand factor for the matching type is determined based on the average of the proportion of the number of dates for the matching type and the average of the proportion of the duration of the insufficient capacity period for the matching type on different dates.

[0057] Additionally, it should be noted that the specific contents include: S231 If the percentage of the deviation date is not greater than the preset date percentage threshold, obtain the adjustment demand factor of different matching types, determine whether there is a matching type with an adjustment demand factor greater than the preset demand factor threshold. If yes, proceed to the next step. If no, determine that the preset scheme does not need to be adopted, and use the heating network for heating adjustment. Identifying high-demand risk types: Logic and significance: Check for the existence of a single "matching type" where the adjusting demand factor exceeds a preset demand factor threshold (e.g., 0.25). The purpose of this step is to filter out "killer" weather events that, while not occurring frequently overall, are particularly severe when they do occur.

[0058] Example: The deviation date percentage is 30% (<50%). Calculated, the adjustment demand factor for type W3 is 0.31 (>0.25), and it is identified as a "adjustment demand type".

[0059] S232 takes the matching type where the adjustment demand factor is greater than the preset demand factor threshold as the adjustment demand type, and determines whether the number of the adjustment demand types is greater than the preset demand type number threshold. If so, it is determined that a preset scheme needs to be adopted to adjust the heating using the heating network. If not, proceed to the next step. Assess the clustering effect of high-demand types: Count the number of "adjustment demand types". If the number exceeds the preset threshold (e.g., 2 types), it indicates that while high risk will not occur every day, various severe weather conditions will be encountered. Each type of severe weather requires a response. Activating a pipeline heat storage solution that can flexibly handle multiple peak scenarios is more economical and effective than making specific preparations for each type of weather.

[0060] Example: In addition to W3, the regulation demand factor for type W4 is also 0.28. The number of regulation demand types is 2, which is greater than the threshold (assuming the threshold is 1). The system judges that there are multiple serious risks and tends to activate the pipeline heat storage regulation.

[0061] S233 determines the adjustment demand coefficient by taking the number of the adjustment demand types and combining the sum of the adjustment demand factors of different matching types. Based on the adjustment demand coefficient, it is determined whether a preset scheme needs to be adopted to carry out heating adjustment processing using the heating network.

[0062] Comprehensive quantitative decision-making (adjusting demand coefficient): When the number of high-demand types does not exceed a threshold, a final comprehensive quantitative assessment is conducted. A regulating demand coefficient is calculated, which is a function (such as a product or weighted sum) of the number of regulating demand types and the sum of the regulating demand factors for these types. A higher coefficient indicates a larger number of types and a larger sum of factors. This coefficient comprehensively reflects the diversity and cumulative intensity of future risks. Only when this coefficient exceeds a preset demand coefficient threshold is the overall benefit of activating pipeline heat storage regulation considered sufficient to cover its costs and complexity.

[0063] This is the final hurdle in the cost-benefit analysis. Pipeline thermal storage involves changing unit operating points, increasing pump consumption, and managing thermal inertia, all of which incur costs. If the future risk is singular and temporary, it can likely be addressed through other more flexible and cost-effective methods (such as demand-side response or the activation of small peak-shaving boilers). This step ensures that this "heavy weapon" is only used when facing sufficiently complex and severe compound risks. Example: Assume there is only one type of demand regulation, W3 (quantity = 1, not exceeding the threshold), with a demand regulation factor of 0.31. Demand regulation coefficient = quantity * factor sum = 1 * (0.31 + 0.2 + 0.1) = 0.61. If the preset demand coefficient threshold is 2, then 0.61 < 2. Decision: No need to activate network thermal storage regulation. The system may choose to only notify users in advance of off-peak energy consumption or use energy on the day of the W3 weather forecast, and prepare for more flexible solutions such as activating backup gas boilers.

[0064] It is understood that the adjustment demand coefficient is determined based on the number of adjustment demand types and the sum of adjustment demand factors for different matching types. The more adjustment demand types there are and the greater the sum of adjustment demand factors for different matching types, the larger the adjustment demand coefficient will be.

[0065] Specifically, when the adjustment demand coefficient is greater than the preset demand coefficient threshold, it is determined that a preset scheme needs to be adopted to adjust the heating supply using the heating network.

[0066] The value of the method described in this embodiment lies in its ability to translate the macro-level strategy of thermal energy storage regulation into specific, quantifiable, and optimized operating parameters, thereby achieving refined energy-saving control. Improving the economic efficiency of the regulation scheme: By avoiding the high heat loss temperature zone, the operating cost (fuel cost) of the heat storage link is directly reduced, making the entire peak-shaving scheme more economically feasible on the basis of technical feasibility and improving the return on investment.

[0067] Ensuring regulation efficiency: It ensures that every unit of heat used for thermal storage can be stored and transported with high efficiency, reducing unnecessary energy waste and meeting the requirements of green and low-carbon development.

[0068] Enhancing system adaptability: This method recognizes that different weather conditions have different impacts on heat loss. Therefore, it dynamically matches different optimal temperature ranges for different "deviation weather types", which reflects the refined management concept of "one policy for one type" and is more scientific and reasonable than setting a fixed heat storage temperature.

[0069] Reduced operational complexity: It provides operators with clear and explicit temperature control guidelines, reducing the risk of low heat storage efficiency due to insufficient experience or misjudgment, and improving the reliability and standardization of the entire adjustment process.

[0070] This method extends the optimization of heating system operation from the load side to the pipeline transmission side. It is a key technical link in deeply exploring the energy-saving potential of the system and realizing the coordinated optimization of the entire process of "source-network-load", which is of great significance for building an efficient and intelligent modern heating system.

[0071] Specifically, the method for determining the heat storage matching temperature range in the aforementioned deviated weather type is as follows: S31 uses the evaluation and analysis results to determine the heat loss rate of the heating network under different heating temperature sub-ranges in the aforementioned deviated weather type; S32 determines the heating temperature sub-ranges with heat loss rates less than a preset heat loss rate threshold based on the heat loss rate of the heating network under different heating temperature sub-ranges. S33 determines the heat storage matching temperature range in the deviation weather type based on the heating temperature sub-range where the heat loss rate is less than the preset heat loss rate threshold.

[0072] It should be noted that the heat storage matching temperature range is the heating temperature range obtained by merging the heating temperature sub-ranges with heat loss rates less than the preset heat loss rate threshold.

[0073] This embodiment provides an intelligent method for dynamically determining the optimal operating temperature range for different "deviation weather types" in a heating system's peak-shaving and heat storage scenario. Its core decision-making objective is to minimize heat loss during the heat storage process while ensuring sufficient heat storage and peak-shaving capacity in the pipeline network, achieving an optimal balance between peak-shaving efficiency and operational economy. Specifically, for each identified "deviation weather type," the system analyzes the variation pattern of the pipeline network's heat loss rate under different water supply temperatures, automatically selecting "high-efficiency temperature sub-intervals" where the heat loss rate is below the economic threshold, and merging these sub-intervals into a "heat storage matching temperature range" that can directly guide operation. This method ensures that under different meteorological risks, heat storage operations always operate within the temperature zone with the highest thermal efficiency.

[0074] II. Specific steps, principles, and examples: Step S31: Establish the weather-temperature-heat loss rate mapping relationship: Keyword explanation: "Evaluation and analysis results": refers to the analysis conclusions of the heating network operation data under different historical conditions in the early stage, including the physical parameters of the network, the insulation status, and the heat dissipation characteristic model under different environmental conditions.

[0075] “Heating temperature sub-interval”: The possible range of water supply temperature in the pipeline network (e.g., 50℃-120℃) is divided into continuous small segments by a fixed step size (e.g., 5℃). Each sub-interval represents a narrow temperature band (e.g., [70℃, 75℃]).

[0076] "Heat loss rate": Under fixed environmental conditions (temperature, humidity, wind speed, etc.) of a specific "deviation weather type", when the pipeline network operates at the median temperature of a certain "heating temperature sub-range", the percentage of heat lost per unit length or per unit time to the environment, relative to the total heat transported by the pipeline network. It quantifies the energy transport efficiency of that temperature range under those conditions.

[0077] Pipeline heat loss is influenced by both the internal medium temperature and external environmental conditions. Under "abnormal weather conditions" (such as strong winds and low temperatures), external heat dissipation conditions are severe, and the heat loss characteristics differ significantly from normal conditions. Therefore, the impact of temperature must be analyzed in conjunction with specific weather types. Dividing the temperature into sub-intervals is to obtain a discretized and analyzable temperature-heat loss relationship, avoiding the analytical complexity caused by continuous functions.

[0078] This step constructs a core knowledge base for optimizing decision-making. It transforms the abstract empirical understanding that "high temperatures lead to large heat losses" into precise, weather-linked quantitative data tables. This enables the system to accurately predict the heat loss cost at different heat storage temperatures for each specific adverse weather condition, laying a data foundation for finding the optimal solution.

[0079] Specific examples: Taking the abnormal weather type "W2 (low temperature and strong wind)" as an example, the system calls its historical data model and calculates that when the water supply temperature is in the sub-range [60℃, 65℃), the simulated heat loss rate is 1.8% / km. When it is in the sub-range [75℃, 80℃), the heat loss rate is 2.5% / km. When it is in the sub-range [105℃, 110℃), due to the huge temperature difference, the heat loss rate rises sharply to 6.2% / km.

[0080] Step S32: Screening efficient temperature sub-regions: Keyword Explanation: "Preset Heat Loss Rate Threshold": A pre-set upper limit for the heat loss rate based on energy costs, system energy efficiency standards, and project economic analysis. This threshold represents the highest acceptable level of heat loss per unit from an operational economic perspective.

[0081] Thermal storage is intended to regulate peak-valley differences, but it is itself an energy-consuming process. If pursuing high thermal storage density (high-temperature thermal storage) leads to excessive heat loss during transmission, it may be counterproductive and even increase total energy consumption. Setting an economic threshold is to draw a clear boundary between "thermal storage capacity" and "thermal storage cost".

[0082] This step performs the first round of economic screening. Based on clear energy efficiency standards, it automatically eliminates temperature options that, while increasing heat storage capacity, result in excessively high heat loss costs and poor economic efficiency. This ensures that subsequent optimization choices are made within an economically reasonable framework.

[0083] Specific examples (continued from the previous example): Assuming that the "preset heat loss rate threshold" is set to 3.0% / km based on current energy prices and system energy efficiency targets.

[0084] The system performs judgments on all temperature sub-intervals under type W2: [60℃, 65℃): 1.8% < 3.0%, qualified, retained.

[0085] [75℃, 80℃): 2.5% < 3.0%, qualified, retained.

[0086] [105℃, 110℃): 6.2% > 3.0%, unqualified, eliminated.

[0087] Through this step, all sub-regions with heat loss rates below 3.0% / km were initially screened out.

[0088] Step S33: Merge and determine the heat storage matching temperature range: Keyword explanation: "Heat storage matching temperature range": All qualified "heating temperature sub-ranges" that are continuous or adjacent on the temperature coordinate axis selected in step S32 are merged to form one or more continuous, recommended operating water supply temperature ranges.

[0089] This step outputs the final executable optimization instructions. It transforms the data analysis results into a core parameter that frontline dispatchers can directly understand and use—the temperature setpoint range. This range is a concrete manifestation of the Pareto optimal frontier that balances "peak-shaving capacity" and "transmission economy" under this type of weather deviation. Specific example (completing the decision chain): Assuming that for type W2, the qualified sub-intervals are: [55℃, 60℃), [60℃, 65℃), [65℃, 70℃), [70℃, 75℃), [75℃, 80℃). Intervals below 55℃ and above 80℃ are not qualified.

[0090] The system merges these continuous and qualified sub-intervals to obtain the final "heat storage matching temperature range" of [55℃, 80℃].

[0091] Dispatch Instructions: On days forecast as W2 (low temperature and strong wind type), when performing pipeline heat storage operations, the primary side supply water temperature of the heating pipeline should be controlled between 55℃ and 80℃. It is recommended to operate closer to 80℃ when the expected evening peak shortage is large in order to store more heat; and to operate closer to 55℃ when the shortage is small in order to further save energy.

[0092] The method described in this embodiment successfully decouples the complex operation strategy of peak shaving and heat storage in heating systems and transforms it into a data-driven, dynamically optimized temperature range setting problem, demonstrating significant comprehensive value. Achieving refined energy saving: It changes the previous extensive mode of setting a fixed heat storage temperature based on experience (such as setting it to 90℃ in all cases). By dynamically matching the weather type with the efficient temperature range, it can reduce the ineffective heat loss by 5%-20% in each heat storage operation, directly reducing fuel costs.

[0093] Ensuring the economic viability of peak shaving: This ensures that thermal storage, a powerful means of "filling the valley when electricity is low and shaving the peak when heat is high," will not become uneconomical due to low efficiency, thus improving the return on investment and market competitiveness of energy storage peak shaving projects.

[0094] Enhanced system adaptability: The system possesses the intelligence to "act according to the weather," and can automatically match the optimal internal response parameters (temperature range) for different external challenges (various types of abnormal weather), thereby enhancing the resilience and intelligence of the heating system in the face of complex meteorological conditions.

[0095] Standardized operation procedures: Provides dispatchers with clear, authoritative, and quantitatively analyzed temperature control guidelines, reducing operational risks and improving the safety and standardization of the entire heating network operation.

[0096] Specifically, the method for determining the heating regulation method of the thermal power unit under the aforementioned weather type is as follows: This embodiment provides a method for intelligent decision-making regarding whether and how to implement heating regulation (specifically, refined temperature control based on pipeline heat loss analysis) under non-high-risk (non-biased) weather types. Its core decision-making logic is: utilizing the knowledge already obtained from analyzing "biased weather types" (especially their feasible "heat storage matching temperature ranges"), by assessing the similarity in meteorological characteristics between other "ordinary weather types" and these high-risk types, it determines whether similar refined heating regulation needs to be initiated for ordinary weather types as well, thereby achieving intelligent expansion and knowledge transfer of risk prevention strategies. This method aims to construct a hierarchical heating regulation strategy system covering all weather scenarios, ensuring effective responses to high-risk weather while conditionally extending optimized operation experience to a wider range of weather conditions, comprehensively improving system energy efficiency.

[0097] S41 defines the deviated weather type that does not have a heat storage matching temperature range as the heat storage deviated weather type. Identify weather types with heat storage deviations: "Heat Storage Deviation Weather Type": This specifically refers to weather types that have been identified as "deviation weather types" (i.e., those with a risk of insufficient systemic heating capacity), but for which no "heat storage matching temperature range" was found in subsequent analysis. This means that even if one wanted to use pipeline heat storage for regulation in such weather, a high-efficiency temperature operating zone with an acceptable heat loss rate could not be found.

[0098] This is a crucial step in problem identification. It distinguishes between two types of "deviant weather": one with technically and economically feasible heat storage and regulation solutions (with matching ranges), and the other without. The type without feasible solutions presents a more serious challenge, as their existence affects regulation decisions for similar ordinary weather conditions.

[0099] The weakest link in the positioning system. Weather patterns indicating thermal storage deviations reveal potential structural defects in the system under specific meteorological combinations (such as extremely poor pipeline insulation and severely insufficient unit regulation margin), which cannot be resolved through operational optimization alone. These types of weather are "risk sources" that require close attention in subsequent assessments.

[0100] The system has identified three types of abnormal weather: W1, W2, and W3. Analysis of the "heat storage matching temperature range" shows that W1 and W2 found efficient ranges (e.g., [60℃, 85℃]), but W3's heat loss rate exceeds the economic threshold in all temperature sub-ranges, and it has no matching range. Therefore, W3 is labeled as a "heat storage abnormal weather type".

[0101] S42 Based on the similarity of weather data between the weather type and the deviated weather type, determine the average value of the deviation rate under different weather indicators, and use it as the weather type deviation rate between the weather type and the deviated weather type; Calculate the weather type deviation rate: Keyword explanation: "Weather Indicators": These are the core meteorological parameters used to define weather types, such as temperature, humidity, and wind speed. Each indicator has its own numerical range or level.

[0102] "Deviation Rate": For a specific weather indicator (such as daily average temperature), this is calculated as the percentage difference between the center point of the value interval of a "normal weather type T" and the center point of the corresponding value interval of a "deviation weather type D". "Weather Type Deviation Rate" is a comprehensive similarity measure obtained by arithmetically averaging the deviation rates of all weather indicators (such as temperature, humidity, and wind). The smaller this value, the more similar the two weather types are in meteorological characteristics.

[0103] Meteorological similarity is a reasonable basis for knowledge transfer. If two weather types are highly similar in their causes (meteorological parameters), then the pressure patterns they exert on heating systems are likely to be similar. By quantitatively calculating the deviation rate, the degree of similarity can be objectively and automatically determined, avoiding subjective assumptions.

[0104] Establish a bridge connecting different weather types. This provides a quantitative basis for scientifically extrapolating or applying the analytical conclusions and coping experiences from high-risk weather (deviation types) to ordinary weather types that have not yet been analyzed in depth.

[0105] Specific examples: The indicators for ordinary weather type T_A are: temperature [0℃, 5℃], humidity [60%, 70%], and wind speed [1m / s, 3m / s]. The indicators for deviated weather type W2 are: temperature [-5℃, 0℃], humidity [70%, 80%], and wind speed [4m / s, 6m / s]. The deviation rates for each item are calculated (taking the midpoint of the interval): temperature deviation rate = |2.5 - (-2.5)| / |100| * 100% = 5%; humidity deviation rate = |65 - 75| / |100| * 100% ≈ 10%; wind speed deviation rate = |2 - 5| / |100| * 100% = 3%. Therefore, the weather type deviation rate is 6%.

[0106] S43 determines the heating regulation method of the thermal power unit under the weather type based on the heat storage deviation weather type data, the weather type deviation rate between the weather type and the deviation weather type, and the heat storage matching temperature range in different weather types.

[0107] It should be noted that the weather type mentioned refers to weather types other than those with deviations.

[0108] Furthermore, if there is no weather type with heat storage deviation, then there is no need to adjust the heating supply in different weather types. That is, determine the pipe loss situation in different heating temperature ranges, and only need to handle the heating according to user needs and unit adjustment capacity.

[0109] Furthermore, if a weather type with heat storage deviation exists, it includes the following: S431 determines whether the number of the heat storage deviation weather types is greater than the preset deviation weather type number threshold. If so, it is determined that heating adjustment is required in different weather types, and the pipe loss situation in different heating temperature ranges is determined. If not, proceed to the next step. Global strategy based on the number of heat storage deviation types: If the number of "heat storage deviation weather types" is too high (exceeding the preset threshold for the number of deviation weather types, such as accounting for 30% of the total types), it indicates that the system lacks economically feasible heat storage regulation methods under various severe weather combinations. This suggests that the system's basic risk resistance capability is weak. Therefore, as a conservative and enhanced preventive strategy, the system decides to activate heating regulation for all weather types (including ordinary types) (i.e., analyze pipeline losses and attempt to find optimization space) in order to tap the energy efficiency potential under all possible weather conditions and make up for the lack of basic capabilities.

[0110] Example: If 4 out of 10 weather types are marked as heat storage deviation types (40% > threshold 30%), the system determines that all 10 weather types need to be analyzed for heating regulation.

[0111] S432 uses the weather type deviation rate between the weather type and different deviation weather types to determine whether there is a deviation weather type with a weather type deviation rate less than a preset deviation rate threshold. If so, proceed to the next step; otherwise, determine that no heating adjustment is required for the weather type. Screening based on highly similar risk sources: When the number of heat storage deviation types is controllable, the system first checks whether the current ordinary weather type T is highly similar to any of the deviation weather types (i.e., the weather type deviation rate is less than the preset deviation rate threshold, such as 10%). If there are no highly similar risk "relatives", then from the perspective of risk prevention, the possibility of type T being severely impacted is low, and there is no need to initiate additional fine-tuning of heating for the time being. It can operate in the conventional manner (according to user needs and unit capacity).

[0112] Example: For the normal type T_B, calculate its deviation rate from all deviation types, with a minimum value of 20% (>10% threshold). The system determines that T_B does not require special heating regulation.

[0113] S433 identifies weather types with a deviation rate less than a preset deviation rate threshold as similar weather types, determines whether there are heat storage deviation weather types among the similar weather types, and if so, determines that heating adjustment is required in the weather type and determines the pipe loss situation in different heating temperature ranges; otherwise, proceeds to the next step. Deep decision-making based on similarity type properties: S433 (Risk Transmission Check): If a normal type T is highly similar to a certain deviation type D (deviation rate < threshold), and this D happens to be a heat storage deviation weather type (i.e., an unsolvable type), this is a warning signal. This means that T is very similar to a severe type that is "incurable." Therefore, by adjusting the above weather types, the heat storage temperature range within the above weather types can be determined, thereby enabling a reliable response when there is a heat storage temperature adjustment process, i.e., utilizing the heat storage network for heat storage treatment.

[0114] The deviation rate between T_C and deviation type W3 (heat storage deviation type) is 6% (<10%). The system determines that heating regulation analysis needs to be performed in T_C to prevent the possibility of an unsolvable dilemma similar to W3 in the future.

[0115] S434 determines whether the number of similar weather types is greater than the preset threshold for the number of weather types. If so, it determines that heating regulation is required for the weather type, determines the pipe loss situation in different heating temperature ranges, and lays the foundation for further identification and optimization of heat storage matching temperature ranges in similar weather types. Specifically, (cluster effect check): If there are many types highly similar to T (greater than the preset threshold for the number of weather types), it indicates that T is at the center of a "type cluster" with concentrated meteorological features. Even if there are currently no "heat storage deviation types" in this cluster, the existence of so many similar types means that this meteorological model is common. In-depth analysis of the heating regulation of the representative type T can yield optimization results (such as the found optimal temperature range), which can be easily generalized to the entire cluster of similar types, resulting in a high knowledge output leverage ratio, thus making it worthwhile to invest analytical resources in.

[0116] Scenario: The deviation rate of T_D from 5 other weather types is all <10%, forming a similar type group (number 6 > threshold 5). The system determines that heating regulation analysis is needed for T_D, and the conclusions will benefit the entire similar group.

[0117] Based on the heat storage matching temperature range data of the similar weather types, S435 determines the width of the heat storage matching temperature range, and determines whether heating regulation is required for the weather type according to the width of the heat storage matching temperature range for different similar weather types.

[0118] Furthermore, based on the width of the heat storage matching temperature range for different similar weather types, it is determined whether heating regulation is required for the aforementioned weather type, specifically including: Based on the width of the heat storage matching temperature range for different similar weather types, it is determined whether there are similar weather types with a width less than a preset width threshold. If so, it is determined that heating regulation is required for the weather type, and the pipe loss situation in different heating temperature ranges is determined, thus laying the foundation for further identification and optimization of the heat storage matching temperature range in similar weather types. If not, it is determined that heating regulation is required for the weather type, and the pipe loss situation in the heat storage matching temperature range with the largest width in the similar weather types is determined, thus laying the foundation for further identification and optimization of the heat storage matching temperature range in similar weather types.

[0119] Final decision based on the breadth of feasible options: "Width of the thermal storage matching temperature range": refers to the difference between the upper and lower temperature limits of this range (e.g., the width of the range [60℃, 85℃] is 25℃). The larger the width, the wider the range of temperature options available for safe and efficient operation under this weather type, the greater the operational flexibility, and the stronger the robustness of the solution.

[0120] Logic and Significance: This step is the final refinement decision when neither condition S433 nor S434 is satisfied. It focuses on those types of deviations similar to T but not related to heat storage (i.e., those with existing feasible heat storage schemes) and examines the "quality" of those schemes.

[0121] Vulnerability check: If the width of a similar type of heat storage range is very narrow (less than the preset width threshold, such as 15℃), it indicates that the optimized solution found for it has a small operating window and harsh conditions, making the solution itself relatively "vulnerable". This suggests that a similar type T may also have similar sensitive pipe loss characteristics, so it is necessary to analyze T to see if a better or more stable solution can be found.

[0122] Solution Optimization and Reference: If the width of all similar heat storage intervals is sufficiently large, it indicates strong robustness of the existing solution. The system then selects the similar weather type corresponding to the interval with the largest width as the best reference template. When analyzing type T, priority can be given to examining pipe loss within this wide interval, which is more likely to quickly find the efficient interval of type T itself, achieving efficient knowledge transfer.

[0123] Example: T_E is associated with two similar deviation types, S1 and S2. The heat storage range of S1 is 10℃ wide, and that of S2 is 20℃ wide (preset width threshold 15℃).

[0124] Judgment: The existence of S1 (width 10℃ < 15℃) indicates that there is a related vulnerable scheme.

[0125] Decision: A heating regulation analysis needs to be conducted in T_E, focusing on its pipe loss characteristics, in order to obtain a better or more stable solution than S1, while also ensuring the reliability of the heat storage treatment of the heating network in T_E.

[0126] This embodiment constructs a generalized decision-making system for heating regulation strategies that is clearly structured, logically rigorous, and highly forward-looking. Its core value lies in: The strategy for preventative maintenance has been expanded: the "treatment-style" in-depth analysis targeting known high risks (deviation types) has been scientifically extended to the "check-up-style" preventative analysis targeting potential risks (similar common types), thus moving the safety defense line forward.

[0127] Optimize the allocation of technical resources: Through multi-level rule filtering, ensure that limited analytical computing resources and expert attention are accurately guided to the most needed, most effective, and most valuable weather types (such as "close relatives" of high-risk types, representatives of common type clusters, and types with weak correlation schemes), thus avoiding blind and wasteful analysis work.

[0128] Building a knowledge system for continuous learning: The system forms a closed loop of "deep analysis of a few key types -> extraction of universal knowledge -> guidance for targeted shallow analysis or verification of similar types -> enrichment and revision of the knowledge base." This enables the system to continuously deepen and expand its understanding of the heating network's behavior under different meteorological conditions.

[0129] Enhancing overall operational resilience and energy efficiency: The ultimate goal is to establish an optimized knowledge base of operating parameters covering all weather scenarios. This enables the heating system to automatically match near-optimal operating strategies regardless of the weather conditions, thereby significantly improving the system's energy efficiency, resilience, and economic viability in the long term.

[0130] This method embodies the advanced operation and maintenance concept of moving from "isolated event response" to "system mode management," and is one of the core intelligent engines for achieving full-condition, adaptive, and refined operation of smart heating systems. Example

[0131] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described method for regulating the heating supply of a thermal power unit when running the computer program.

[0132] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0133] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0134] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for regulating the heating supply of a thermal power unit, characterized in that, Specifically, it includes: S1 uses the heating data of the heating unit as a basis to determine the matching status of the heating capacity of the heating unit with the demand of heat users under different weather types. Based on the demand matching status, it determines the matching deviation weather types of the heating unit. According to the distribution data of the deviation weather types in the future preset time period, it determines that the preset scheme does not need to be adopted. When the heating network is used for heating regulation, it proceeds to the next step. S2, based on the aforementioned deviated weather type, evaluates and analyzes the heat storage capacity of the heating network of the thermal power unit under the aforementioned deviated weather type. Based on the evaluation and analysis results, it determines the heat storage matching temperature range in different deviated weather types, identifies deviated weather type data where no heat storage matching temperature range exists, and, in conjunction with the heat storage matching temperature range of the deviated weather type and the similarity between the weather type and weather data of different deviated weather types, determines the heating regulation method of the thermal power unit under the weather type.

2. The heating regulation method for a thermal power unit as described in claim 1, characterized in that, The weather types are classified based on weather data including temperature, humidity, and wind speed. Specifically, dates with temperature, humidity, and wind speed within the same range are classified into the same weather type.

3. The heating regulation method for a thermal power unit as described in claim 1, characterized in that, The matching of heating capacity with the needs of heat users is determined based on the deviation between the heating capacity of the heating unit and the heat demand of heat users at different times.

4. The heating regulation method for a thermal power unit as described in claim 1, characterized in that, The method for determining the weather type of the matching deviation of the thermal power unit is as follows: Based on the demand matching situation, determine the deviation between the heating capacity of the heating unit and the heating demand of the heat user in different time periods under the weather type. Based on the aforementioned deviation, the time periods when the unit's heating capacity is less than the heat demand of the heat users are determined and these periods are considered as periods of insufficient capacity. Based on the data of insufficient capacity periods on different dates within the aforementioned weather type, determine whether the weather type is a mismatch weather type.

5. The heating regulation method for a thermal power unit as described in claim 4, characterized in that, If there are periods of insufficient capacity on different dates within the stated weather type, then the stated weather type is determined to be a mismatch weather type.

6. The heating regulation method for a thermal power unit as described in claim 1, characterized in that, It was determined that a pre-set plan was not needed; instead, heating regulation was carried out using the heating network, specifically including: Based on the distribution data of deviated weather types within a future preset time period, determine the percentage of dates with deviated weather types and use it as the percentage of deviated dates; The deviation weather type within a future preset time period will be used as the matching type. Based on the proportion of the number of dates of the matching type and the average proportion of the duration of the capacity shortage period of the matching type on different dates, the adjustment demand factor of the matching type will be determined. Based on the percentage of deviation dates and the adjustment demand factors for different matching types, it is determined whether a preset scheme needs to be adopted to adjust the heating supply using the heating network.

7. The heating regulation method for a thermal power unit as described in claim 6, characterized in that, If the percentage of the deviation date is greater than the preset date percentage threshold, then it is determined that a preset scheme needs to be adopted, which involves using the heating network for heating regulation. This means that the heating load that the heating unit can provide is transferred to the heating network, and the heating network is used for heat storage to meet the user's heating needs.

8. The heating regulation method for a thermal power unit as described in claim 6, characterized in that, The adjustment demand factor for the matching type is determined based on the average of the proportion of the number of dates for the matching type and the average of the proportion of the duration of the insufficient capacity period for the matching type on different dates.

9. The heating regulation method for a thermal power unit as described in claim 1, characterized in that, The method for determining the heating regulation method of the thermal power unit under the aforementioned weather type is as follows: Deviated weather types that do not have a matching temperature range for heat storage are classified as heat storage deviation weather types. Based on the similarity of weather data between the weather type and the deviated weather type, the average deviation rate under different weather indicators is determined and used as the weather type deviation rate between the weather type and the deviated weather type. Based on the heat storage deviation weather type data, the weather type deviation rate between the weather type and the deviation weather type, and the heat storage matching temperature range in different weather types, the heating regulation method of the thermal power unit under the weather type is determined.

10. A computer system, comprising: A memory and processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes a heating regulation method for a thermal power unit as described in any one of claims 1-9.

Images