Optimal scheduling method for heating system considering extreme weather

Abstract

The present invention discloses a method for optimizing and scheduling a heating system taking extreme weather into consideration, comprising: utilizing a digital twin model of a heating system to simulate the operating status of the system under various extreme weather conditions, and generating a set of extreme weather operating scenarios for the system; establishing a fault diagnosis model for the heating system, and obtaining fault information; dividing the operating conditions of the heating system; under normal operating conditions, the heating system executes according to the original scheduling plan; under extreme weather warning operating conditions, the operating output of the heating unit is increased to store heat in heat storage devices, heat networks, and buildings in advance; under resistance operating conditions, the heat storage of buildings, heat networks, and heat storage devices is utilized to supplement and maintain the heat load; under system emergency scheduling conditions, network reconstruction and heat load reduction are performed; establishing an optimized scheduling model for the heating system under different operating conditions and a performance evaluation model for the heating system to resist extreme weather and faults, and selecting the optimal scheduling strategy for optimizing and scheduling the heating system.

Description

Technical Field

[0001] The present invention belongs to the technical field of heating system scheduling, and in particular relates to a heating system optimization scheduling method taking extreme weather into consideration. Background Art

[0002] During the entire heating season, the heating system will usually encounter extremely cold weather, blizzards, etc., which cause the outdoor temperature to drop sharply. Sometimes the extreme low temperature weather lasts for a long time. As the temperature drops, the heat source of the heating system, the temperature, flow rate, and pressure of the heating network reach the safety limit, which brings severe challenges to the heating system.

[0003] Currently, heating companies typically initiate emergency response plans to address extreme weather conditions, taking measures to increase the temperature and flow of heating networks and heating stations. They also strengthen network inspections to promptly detect faults caused by extreme weather. However, if the heating supply continues to increase, the various operating equipment will become unstable, leading to faults such as ruptures and leaks in the heating network, or causing heat exchange station equipment to malfunction, resulting in unpredictable safety risks for the entire system. Clearly, in order to address the increased heat load demand and resulting safety risks caused by extreme low temperatures, heating companies need to plan ahead to adjust the operating parameters of the heating system in response to the upcoming extreme weather. This allows the heating system to adopt a scheduling strategy tailored to the system's operating conditions when encountering extreme weather or faults, improving the heating system's ability to withstand extreme weather and faults, and ensuring heating quality and stable system operation. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing technology and provide a method for optimizing the scheduling of the heating system taking extreme weather into consideration, which can realize the optimized scheduling of the heating system under different operating conditions, improve energy utilization efficiency, reduce operating costs, and at the same time enhance the ability of the heating system to resist extreme weather and failures, thereby ensuring the quality of heating and the stable operation of the system.

[0005] In order to solve the above technical problems, the technical solution of the present invention is:

[0006] The present invention provides a method for optimizing the scheduling of a heating system taking into account extreme weather and performance evaluation, comprising:

[0007] S1. Use the pre-built digital twin model of the heating system to simulate the system's operating status under various extreme weather conditions, analyze the impact of extreme weather on the system's operating conditions, and generate a set of extreme weather operation scenarios for the system;

[0008] S2. Establish a heating system fault diagnosis model based on the heating system network operation data to obtain system fault information;

[0009] S3. Based on the system extreme weather operation scenario set and system fault information, the operating conditions of the heating system are divided into normal operating conditions when extreme weather and fault information have not occurred, extreme weather warning operating conditions, resistance operating conditions when extreme weather and / or fault information are being encountered, and emergency dispatch operating conditions;

[0010] S4. Under normal operating conditions, the heating system will be operated according to the original scheduling plan. Under extreme weather warning operating conditions, the operating output of the heating units will be increased to store heat in heat storage devices, heating networks and buildings in advance. Under defensive operating conditions, the heat stored in buildings, heating networks and heat storage devices will be used to supplement and maintain the heat load. Under system emergency scheduling conditions, network reconstruction and heat load reduction will be carried out.

[0011] S5. Establish an optimal scheduling model for the heating system under different operating conditions. After obtaining the scheduling strategy set under each operating condition, establish a performance evaluation model for the heating system to resist extreme weather and failures, evaluate the scheduling strategy set of the heating system, and select the optimal scheduling strategy for optimal scheduling of the heating system.

[0012] Furthermore, the S1 includes:

[0013] Use mechanism modeling and data-driven methods to establish a digital twin model of the heating system;

[0014] Based on rainfall, snowfall, sleet, temperature, and wind speed, various extreme weather types and parameter ranges are defined to generate information on different extreme weather scenarios, which are then input into the heating system digital twin model for simulation.

[0015] Monitor changes in system heat load supply and demand, changes in network-wide operating parameters under different extreme weather scenarios, and analyze the probability of heat network and equipment failures caused by extreme weather. At the same time, combine the historical operating data of the heating system under extreme weather conditions to generate a set of system extreme weather operation scenarios.

[0016] Further, the S2 includes:

[0017] Obtain historical operation data of the entire network when a heating system failure occurs, and obtain simulated operation data when simulating system heating network and equipment failures using the heating system digital twin model;

[0018] Based on the historical operation data and simulated operation data of the entire heating system network, after extracting fault data features and conducting model training and learning, a heating system fault diagnosis model is established to obtain the system fault type and fault location.

[0019] Furthermore, the S3 includes: obtaining the time of occurrence of extreme weather according to the meteorological data forecast information The operation scheduling time of the heating system is divided into the normal operation period , during the warning operation period , resist during operation and during emergency dispatch ;

[0020] Normal operating conditions are defined as During this period, there was no extreme weather or failure information in the heating system;

[0021] The extreme weather warning operating condition is defined as During this period, there was no extreme weather or failure information in the heating system, but a response plan for the initial occurrence of extreme weather needs to be formulated in advance;

[0022] The resistance operating condition is defined as During this period, the heating system begins to encounter extreme weather and / or fault information, and the pre-planned response plan is implemented to resist and initially meet the missing heat;

[0023] The emergency dispatch condition is defined as During this period, the response plan can no longer meet the missing heat, and it is necessary to further formulate an emergency dispatch plan to maintain the normal operation of the system.

[0024] Furthermore, the optimization scheduling model under normal operating conditions aims to minimize the system operating cost under the load demand of each thermal power station, and outputs the operating output strategy of each heating equipment in the system, which is expressed as:

[0025] ;

[0026] is the operating output of the i-th heating equipment at time t under normal operating conditions; is the unit power operating cost of the i-th heating equipment under normal operating conditions; M is the number of heating equipment.

[0027] Furthermore, the establishment of the optimization scheduling model under the extreme weather warning operating conditions includes:

[0028] When extreme weather occurs Based on the heat load demand of each thermal power station, and compared with the normal operating conditions Compare the heat load demands of each heating station at the current moment to obtain the heat load demand increment;

[0029] By increasing the operating output of conventional heating units and electric heating units, heat that matches the increase in heat load demand is produced and stored in heat storage devices, heat networks, and buildings;

[0030] With the goal of minimizing the incremental operating costs of conventional heating units, electric heating units, and heat storage devices, an optimal scheduling model under extreme weather warning operating conditions is established, which can be expressed as:

[0031] ;

[0032] It is the operating output increment of conventional heating units under extreme weather warning operating conditions; The unit power operating cost of conventional heating units under extreme weather warning operating conditions; It is the operating output increment of the electric heating unit under extreme weather warning operating conditions; The unit power operating cost of the electric heating unit under extreme weather warning operating conditions; The heat storage increment under extreme weather warning operation conditions; It is the unit heat storage operating cost under extreme weather warning operating conditions.

[0033] Furthermore, the establishment of the optimal scheduling model under the operating conditions includes:

[0034] Based on the principle of resisting the heat load shortage of each heating station under operating conditions, the heat stored in the heat storage devices, heating network and buildings is released, while the operating output of the conventional heating units is adjusted to meet the heat load shortage to the maximum extent possible;

[0035] With the goal of minimizing the operating output cost of conventional heating units and the heat release cost of heat storage devices, heat networks, and buildings, an optimal scheduling model under operating conditions is established, which can be expressed as:

[0036] ;

[0037] To cope with the increase in operating output of conventional heating units under operating conditions compared to extreme weather warning operating conditions; To withstand the unit power operating cost of conventional heating units under operating conditions; To resist heat release under operating conditions; To protect against the unit heat release operating cost under operating conditions.

[0038] Furthermore, the establishment of the optimization scheduling model under the emergency scheduling condition includes:

[0039] Under the system emergency dispatch condition, the heat load of each heating station is seriously lacking. Through network reconstruction, the heat network is decoupled and the heat network structure is rearranged. By calculating the importance factor of each heat user load under each heating station, the heat user load is divided into important heat load and non-important heat load. The non-important heat load is reduced first, and then the important heat load is reduced.

[0040] With the goal of minimizing the cost of heat network decoupling and heat network structure re-layout and minimizing the heat load reduction, an optimal dispatch model under emergency dispatch conditions is established, which is expressed as:

[0041] ;

[0042] is the decoupling and layout cost of the kth heating network node at time t under emergency dispatch conditions; is the state of the kth heating network node at time t under emergency dispatch conditions; is the cost coefficient for reducing the jth heat load at time t under emergency dispatch conditions; is the jth heat load reduction at time t under emergency dispatch conditions; K is the number of heat network nodes decoupled; N is the amount of heat load reduction.

[0043] Furthermore, the establishment of a performance evaluation model for the heating system to resist extreme weather and failures includes:

[0044] A performance evaluation model is established by setting performance evaluation indicators, wherein the performance evaluation indicators include a heat load maintenance indicator, a resistance index, a responsiveness index, and a recovery index.

[0045] The beneficial effects of the present invention are:

[0046] (1) The present invention simulates the system operating status under extreme weather conditions through the digital twin model of the heating system, which can understand in advance the impact of extreme weather on the operating conditions of the heating system, provide a basis for formulating response strategies, and help improve the adaptability and stability of the heating system to extreme weather conditions;

[0047] (2) By establishing a fault diagnosis model for the heating system, the present invention can timely and accurately obtain fault information of the system when it faces extreme weather, facilitate rapid location of fault information, reduce the impact of faults caused by extreme weather on the heating system, and improve the reliability and maintainability of the system;

[0048] (3) The present invention divides the operating conditions of the heating system into multiple operating conditions based on extreme weather information and whether the extreme weather has caused system failures, so that the system can adjust the system operating parameters according to the actual operating conditions, thereby improving the system's operating efficiency and ability to respond to emergencies;

[0049] (4) The present invention adopts corresponding scheduling measures for different operating conditions. Under normal operating conditions, the original scheduling plan is implemented to ensure that the heating system operates stably and efficiently under normal circumstances and maintain normal heating. Under extreme weather warning operating conditions, the output of the heating unit is increased in advance and heat is stored, so that when extreme weather arrives, there will be sufficient heat reserves, which will enhance the system's resistance and reduce the impact of extreme weather on the heating effect. Under resistance operating conditions, the stored heat is used to supplement the heat load, which can maintain the basic operation of the heating system in the event of extreme weather and / or failures, ensure the heating needs of users, and improve the stability and reliability of the system. Under emergency scheduling conditions, measures such as network reconstruction and heat load reduction are taken to avoid system collapse when the system faces serious problems, maximize the protection of the heating needs of key areas or users, and improve the emergency response capability of the system.

[0050] (5) The present invention establishes an optimization scheduling model for different operating conditions to obtain a scheduling strategy set, and then establishes a performance evaluation model to evaluate the scheduling strategy set and select the optimal strategy, which can achieve optimized scheduling of the heating system under different operating conditions, improve energy utilization efficiency, reduce operating costs, and at the same time enhance the heating system's ability to resist extreme weather and failures, thereby ensuring the quality of heating and the stable operation of the system.

[0051] Other features and advantages will be described in the following description, and in part will become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 This is a flow chart of a method for optimizing the scheduling of a heating system taking extreme weather into consideration according to the present invention;

[0055] Figure 2 Schematic diagram of the optimization scheduling principle of the heating system under different operating conditions of the present invention;

[0056] Figure 3 This is a schematic diagram of the structure of a heating system that takes extreme weather into consideration according to the present invention. DETAILED DESCRIPTION

[0057] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0058] like Figure 1 、 Figure 2 As shown, this embodiment provides a method for optimizing the scheduling of a heating system considering extreme weather conditions, including:

[0059] S1. Use the pre-built digital twin model of the heating system to simulate the system's operating status under various extreme weather conditions, analyze the impact of extreme weather on the system's operating conditions, and generate a set of extreme weather operation scenarios for the system;

[0060] S2. Establish a heating system fault diagnosis model based on the heating system network operation data to obtain system fault information;

[0061] S3. Based on the system extreme weather operation scenario set and system fault information, the operating conditions of the heating system are divided into normal operating conditions when extreme weather and fault information have not occurred, extreme weather warning operating conditions, resistance operating conditions when extreme weather and / or fault information are being encountered, and emergency dispatch operating conditions;

[0062] S4. Under normal operating conditions, the heating system will be operated according to the original scheduling plan. Under extreme weather warning operating conditions, the operating output of the heating units will be increased to store heat in heat storage devices, heating networks and buildings in advance. Under defensive operating conditions, the heat stored in buildings, heating networks and heat storage devices will be used to supplement and maintain the heat load. Under system emergency scheduling conditions, network reconstruction and heat load reduction will be carried out.

[0063] S5. Establish an optimal scheduling model for the heating system under different operating conditions. After obtaining the scheduling strategy set under each operating condition, establish a performance evaluation model for the heating system to resist extreme weather and failures, evaluate the scheduling strategy set of the heating system, and select the optimal scheduling strategy for optimal scheduling of the heating system.

[0064] like Figure 3As shown, extreme weather at least includes heavy rain, sleet, blizzard and other weather; the heating system mainly includes heat source, heat storage device, primary pipeline network, heating station, secondary pipeline network and heat users. Heat sources may include coal-fired boilers, gas boilers, electric heating units (electric boilers, electric heat pumps), etc.; the function of the primary pipeline network is to transport hot water from the heat source and heat storage device to the thermal power stations distributed in various areas; the thermal power station is composed of a heat exchanger, a control valve, a water pump and a heat metering device. The high-temperature primary water supply transfers heat to the low-temperature secondary return water in the thermal power station. The primary return water after heat exchange is returned to the heat source under the action of the circulation pump. At the same time, the heated secondary supply water is transported to the heat users by the secondary pipeline network; the secondary pipeline network is driven by the water pump to transport the secondary supply water after heat exchange in the thermal power station to each heat user, and then transports the low-temperature secondary return water after heating back to the thermal power station for circulating heating; heat users are different buildings with heating needs; at the same time, the heat storage device, the heat network and the heat user buildings can all be used as flexible heat sources to cope with extreme weather, thereby improving the flexibility of the system to cope with extreme weather. The heat source, pipe sections, heating stations, and heat users of the heating system are coupled and related. Especially when facing extreme weather, the operating conditions will change. Therefore, before predicting the arrival of extreme weather, a scheduling plan needs to be formulated in advance so that timely and effective responses can be made when extreme weather actually occurs, avoiding safety risks in the system and ensuring stable and reliable operation of the system.

[0065] In this embodiment, S1 includes:

[0066] Use mechanism modeling and data-driven methods to establish a digital twin model of the heating system;

[0067] Based on rainfall, snowfall, sleet, temperature, and wind speed, various extreme weather types and parameter ranges are defined to generate information on different extreme weather scenarios, which are then input into the heating system digital twin model for simulation.

[0068] Monitor changes in system heat load supply and demand, changes in network-wide operating parameters under different extreme weather scenarios, and analyze the probability of heat network and equipment failures caused by extreme weather. At the same time, combine the historical operating data of the heating system under extreme weather conditions to generate a set of system extreme weather operation scenarios.

[0069] In actual applications, the specific application implementation process of generating the system extreme weather operation scenario set includes:

[0070] 1) Establish a digital twin model of the heating system, including:

[0071] Mechanism modeling: Based on the physical principles of heating systems, such as the thermodynamic laws of heat conduction, convection, and radiation, as well as the principles of fluid mechanics regarding the flow of water or steam in pipes. For example, a heat transfer equation is established based on Fourier's law to describe the transfer of heat between the pipe wall and the surrounding medium, and the Bernoulli equation is used to describe the relationship between pressure, flow rate, and height of the fluid in the pipe network. Using these basic physical laws, a model of the energy and material flow relationship between the heat source (such as a thermal power plant or boiler), the heating network (pipelines, valves, pumping stations, etc.), and the heat users (such as buildings) in the heating system is constructed;

[0072] Data-driven: This approach leverages the extensive historical data generated during heating system operation, such as temperature, pressure, flow rate, and energy consumption. Machine learning algorithms, such as artificial neural networks (ANNs) and support vector machines (SVMs), are employed. For example, ANNs use historical operating data as input to neurons in the input layer. Through weight adjustments and activation function calculations in the hidden layer, the system's inherent operating patterns are learned, enabling the output layer to predict the system's operating status under different operating conditions. Combining mechanism modeling with data-driven approaches ensures the model's physical plausibility while improving its adaptability to complex real-world operating conditions.

[0073] 2) Define extreme weather scenarios and simulate them

[0074] Extreme weather definition: Extreme weather types are defined based on different thresholds for meteorological parameters (rainfall, snowfall, sleet, temperature, and wind speed). For example, extreme cold weather is defined when the temperature remains below -10°C for a certain period of time; blizzard weather is defined when the amount of snowfall exceeds a certain value within a unit of time (e.g., 5 mm or more per hour). After determining the parameter range for each extreme weather type, scenario information containing specific meteorological parameter values ​​is generated.

[0075] Simulation: These extreme weather scenarios are fed into the established digital twin model of the heating system as external input. Based on the input meteorological parameters, the model combines its internally constructed physical relationships and learned operational rules to simulate the heating system's operation under these extreme weather conditions. For example, in extremely cold weather, the model simulates the increased demand for heat from heat users due to the drop in outdoor temperature, as well as the corresponding adjustments made by heat sources and the heating network to meet this demand. Furthermore, in the extreme cold weather simulation, monitoring revealed a 30% increase in heat load demand from heat users compared to normal weather, increased heat losses in the heating network pipelines, and a decrease in pressure in some pipes. Failure probability analysis revealed a 20% increase in the probability of leaks at some older pipe joints due to the low temperatures. In the heavy snow simulation, snow accumulation was found to cover the pipe insulation, compromising its effectiveness and causing a drop in localized temperatures in the heating network. Furthermore, melted snow could potentially enter the electrical control boxes of some equipment, increasing the probability of short circuit failures.

[0076] 3) Generate extreme weather operation scenario set

[0077] Operational parameter monitoring: During the simulation process, real-time monitoring is performed on changes in the system's heat load supply and demand (e.g., heat supply from the heat source, heat demand from heat users), as well as changes in network-wide operating parameters (e.g., temperature, pressure, flow within the pipeline, operating power of the pumping station, etc.). Operating parameters are obtained from the actual heating system through sensor data collection, and in the digital twin model, these are calculated based on the model's output.

[0078] Failure Probability Analysis: Based on historical data and simulation results, combined with fault tree analysis and reliability theory, we analyze the impact of extreme weather on the probability of failure of heating networks and equipment (such as pipe freezing and cracking, valve failures, and pump station motor overloads). For example, historical data shows that when temperatures drop below -15°C for an extended period, the probability of pipeline rupture increases due to stress concentration caused by thermal expansion and contraction.

[0079] Scenario set generation: Combined with the historical operation data of the heating system under extreme weather conditions, the operating parameters and failure probabilities monitored under different extreme weather scenarios are sorted and summarized to generate the system's extreme weather operation scenario set, providing a basis for subsequent system optimization and emergency management.

[0080] In this embodiment, S2 includes:

[0081] Obtain historical operation data of the entire network when a heating system failure occurs, and obtain simulated operation data when simulating system heating network and equipment failures using the heating system digital twin model;

[0082] Based on the historical operation data and simulated operation data of the entire heating system network, after extracting fault data features and conducting model training and learning, a heating system fault diagnosis model is established to obtain the system fault type and fault location.

[0083] In actual applications, fault simulation settings: Various heat network and equipment failure scenarios are artificially set in the digital twin model, such as pipe rupture, valve failure, pump station shutdown, heat exchanger blockage, etc. By changing the parameters or states of the corresponding components in the model, the operational changes of the system when the fault occurs are simulated. For example, when simulating a pipe rupture, the flow at the rupture point is set to increase abnormally and the pressure is set to decrease abnormally;

[0084] Simulation data acquisition: During the simulated fault operation process, various operating parameter data output by the model are recorded in real time, including temperature, pressure, flow, power, etc., similar to the actual system operation data collection. These simulation operation data are stored in the database for subsequent analysis.

[0085] Establish a heating system fault diagnosis model, including:

[0086] 1) Data preprocessing: Preprocess the acquired network-wide historical and simulated operation data, including data cleaning (removing noise and outliers), data standardization (converting data of different dimensions to a unified dimension), and data normalization, to improve data quality and prepare for subsequent feature extraction and model training.

[0087] 2) Fault Data Feature Extraction: Signal processing techniques (such as Fourier transform and wavelet transform) and machine learning feature engineering methods (such as principal component analysis (PCA) and mutual information analysis) are used to extract features that can characterize the fault from preprocessed data. For example, Fourier transform is used to convert time-domain signals such as temperature and pressure into the frequency domain and extract eigenvalues ​​in the frequency domain. PCA is used to reduce the dimensionality of multiple related operating parameters and extract the main characteristic components.

[0088] 3) Model training and learning: Select an appropriate machine learning algorithm or deep learning model, such as a decision tree, random forest, support vector machine, or long short-term memory network. Use the extracted fault data features as input and the fault type and location as output labels to train the model. Iterative training is performed using a large amount of historical and simulated fault data, adjusting the model parameters to enable the model to accurately identify the fault type and locate the fault location.

[0089] 4) Model Evaluation and Optimization: Use cross-validation, confusion matrix, accuracy, recall, F1 score, and other evaluation metrics to evaluate the performance of the trained fault diagnosis model. Based on the evaluation results, optimize the model by adjusting model parameters, adding training data, and changing the model algorithm to improve the model's diagnostic accuracy and generalization capabilities.

[0090] It should be noted that extreme weather can easily trigger heating system failures. Therefore, extreme weather-related parameters, such as rainfall, snowfall, sleet, temperature, and wind speed, can be incorporated as additional input features into the fault diagnosis model. When collecting historical and simulated operating data, the corresponding weather data is also recorded to establish correlations between weather parameters and heating system failures. Furthermore, data mining techniques, such as association rule mining and cluster analysis, are used to analyze the potential relationships between extreme weather parameters and heating system failure data characteristics. For example, association rule mining can identify frequent patterns of heating network pipeline leakage failures under specific temperature and wind speed conditions. Cluster analysis can cluster failure data under different extreme weather conditions to observe the distribution patterns of fault types and locations. Furthermore, based on the established correlations and fault diagnosis model, when extreme weather is detected, the current weather parameters and real-time heating system operating data can be used to predict the possible fault type and location, and issue early warning information, allowing heating management departments to take appropriate preventive and emergency measures to mitigate the impact of extreme weather on the heating system. For example, before the arrival of extreme cold weather, leakage failures that may occur in heating network pipelines due to low-temperature contraction can be predicted, and inspection and maintenance work can be arranged in advance.

[0091] In this embodiment, S3 includes: obtaining the time when extreme weather occurs based on meteorological data forecast information The operation scheduling time of the heating system is divided into the normal operation period , during the warning operation period , resist during operation and during emergency dispatch ;

[0092] Normal operating conditions are defined as During this period, there was no extreme weather or failure information in the heating system;

[0093] The extreme weather warning operating condition is defined as During this period, there was no extreme weather or failure information in the heating system, but a response plan for the initial occurrence of extreme weather needs to be formulated in advance;

[0094] The resistance operating condition is defined as During this period, the heating system begins to encounter extreme weather and / or fault information, and the pre-planned response plan is implemented to resist and initially meet the missing heat;

[0095] The emergency dispatch condition is defined as During this period, the response plan can no longer meet the missing heat, and it is necessary to further formulate an emergency dispatch plan to maintain the normal operation of the system.

[0096] In actual applications, the transition logic between operating conditions includes the following: the heating system initially operates in normal operating conditions. Upon receiving reliable extreme weather forecast information, it automatically switches to extreme weather warning operating conditions and begins preparing a response plan. If extreme weather occurs on schedule or a fault occurs during this period, it enters the defensive operating condition and implements the response plan. If the response plan fails to resolve the issue and the heating system cannot meet heat demand, it enters the emergency dispatch condition. Once the extreme weather ends, the fault is rectified, and the system operating parameters return to normal, it returns to normal operating conditions.

[0097] In this embodiment, the optimization scheduling model under normal operating conditions aims to minimize the system operating cost under the load demand of each heating station, and outputs the operating output strategy of each heating equipment in the system, which is expressed as:

[0098] ;

[0099] is the operating output of the i-th heating equipment at time t under normal operating conditions; is the unit power operating cost of the i-th heating equipment under normal operating conditions; M is the number of heating equipment.

[0100] It should be noted that under normal operating conditions, the heating system operates according to the original scheduling plan. This is a scheduling plan developed based on analysis of the heating system's long-term operating data and empirical experience, meeting typical heating needs. This plan rationally arranges the output of heating units based on conventional factors such as outdoor temperature and the heating station's heat demand to ensure stable and efficient operation of the heating system and provide users with a steady supply of heat. At this point, all aspects of the heating system operate smoothly within their design parameters, and the hydraulic and thermal balance of the heating network can be maintained through conventional regulatory measures.

[0101] In this embodiment, the establishment of the optimization scheduling model under the extreme weather warning operating condition includes:

[0102] When extreme weather occurs Based on the heat load demand of each thermal power station, and compared with the normal operating conditions Compare the heat load demands of each heating station at the current moment to obtain the heat load demand increment;

[0103] By increasing the operating output of conventional heating units and electric heating units, heat that matches the increase in heat load demand is produced and stored in heat storage devices, heat networks, and buildings;

[0104] With the goal of minimizing the incremental operating costs of conventional heating units, electric heating units, and heat storage devices, an optimal scheduling model under extreme weather warning operating conditions is established, which can be expressed as:

[0105] ;

[0106] It is the operating output increment of conventional heating units under extreme weather warning operating conditions; The unit power operating cost of conventional heating units under extreme weather warning operating conditions; It is the operating output increment of the electric heating unit under extreme weather warning operating conditions; The unit power operating cost of the electric heating unit under extreme weather warning operating conditions; The heat storage increment under extreme weather warning operation conditions; It is the unit heat storage operating cost under extreme weather warning operating conditions.

[0107] It should be noted that when meteorological data predicts that extreme weather is imminent, even though the extreme weather and faults have not yet actually occurred, measures must be taken in advance. The operating output of the heating units can be increased to generate more heat in the heating system. This additional heat is stored in heat storage devices, heating networks, and buildings. Heat storage devices use their own energy storage media, such as hot water and phase change materials, to absorb and store heat. The hot water in the heating network also carries some heat during its flow. At the same time, the walls of buildings and indoor objects also absorb and store a certain amount of heat, acting as small heat storage bodies. In this way, sufficient heat can be stored before extreme weather arrives to prepare for the subsequent increase in heat demand.

[0108] In this embodiment, the establishment of the optimization scheduling model under the operating conditions includes:

[0109] Based on the principle of resisting the heat load shortage of each heating station under operating conditions, the heat stored in the heat storage devices, heating network and buildings is released, while the operating output of the conventional heating units is adjusted to meet the heat load shortage to the maximum extent possible;

[0110] With the goal of minimizing the operating output cost of conventional heating units and the heat release cost of heat storage devices, heat networks, and buildings, an optimal scheduling model under operating conditions is established, which can be expressed as:

[0111] ;

[0112] To cope with the increase in operating output of conventional heating units under operating conditions compared to extreme weather warning operating conditions; To withstand the unit power operating cost of conventional heating units under operating conditions; To resist heat release under operating conditions; To protect against the unit heat release operating cost under operating conditions.

[0113] It should be noted that when the heating system begins to encounter extreme weather and / or fault information under the resistance operation condition, the heat stored in the building, heating network and heat storage device will be used first to supplement and maintain the heat load. The heat stored in the building will be slowly released into the room through the walls, doors and windows and other parts to maintain the indoor temperature. The heat stored in the heating network is transported to each heat user as the hot water circulates. The heat storage device releases the stored heat to the heating network by controlling valves, pumps and other equipment according to the system's heat demand to supplement the heat lost by the heating system due to extreme weather or faults. In this way, the normal operation of the heating system is maintained for a certain period of time to meet the basic heating needs of users.

[0114] For example, during a cold snap, outdoor temperatures plummet, increasing the heat load demanded by the heating system. At this point, the thermal storage device begins releasing hot water into the heating network. While the temperature of the hot water in the network drops, it still maintains a sufficient heat supply. Buildings also begin releasing previously stored heat, slowing the drop in indoor temperatures and thus utilizing the stored heat to supplement and maintain the heat load.

[0115] In this embodiment, the establishment of the optimization scheduling model under the emergency scheduling working condition includes:

[0116] Under the system emergency dispatch condition, the heat load of each heating station is seriously lacking. Through network reconstruction, the heat network is decoupled and the heat network structure is rearranged. By calculating the importance factor of each heat user load under each heating station, the heat user load is divided into important heat load and non-important heat load. The non-important heat load is reduced first, and then the important heat load is reduced.

[0117] With the goal of minimizing the cost of heat network decoupling and heat network structure re-layout and minimizing the heat load reduction, an optimal dispatch model under emergency dispatch conditions is established, which is expressed as:

[0118] ;

[0119] is the decoupling and layout cost of the kth heating network node at time t under emergency dispatch conditions; is the state of the kth heating network node at time t under emergency dispatch conditions; is the cost coefficient for reducing the jth heat load at time t under emergency dispatch conditions; is the jth heat load reduction at time t under emergency dispatch conditions; K is the number of heat network nodes decoupled; N is the amount of heat load reduction.

[0120] It should be noted that during emergency dispatch, when the response plan cannot meet the missing heat demand, emergency dispatch becomes necessary. Network reconfiguration involves changing the hydraulic conditions of the heating network by adjusting valve openings, switching pipe connections, and so on. This allows for a more efficient distribution of heat to various heat user areas, avoiding situations where some areas suffer from severe heat shortages while others suffer from excess heat. Heat load reduction involves appropriately reducing the heat load of non-critical or adjustable heat users, based on actual conditions. For example, this can involve lowering the indoor temperature setpoints of commercial buildings and reducing the heat consumption of industrial users, to ensure the basic heating needs of critical heat users (such as residential buildings, hospitals, and schools). Through a combination of network reconfiguration and heat load reduction, the basic operation of the heating system can be maintained, preventing serious problems such as system failure due to severe heat shortages.

[0121] For example, during extreme snowstorms, some heating system pipes ruptured under the pressure of accumulated snow, resulting in significant heat loss. In this case, valves near the ruptured pipes were closed to divert hot water from the network to other functioning pipes, enabling network reconstruction. At the same time, the heating temperature for some non-critical heat users, such as commercial office buildings, was lowered by approximately 2°C to reduce the heat load and ensure that heating in key areas, such as residential buildings, was not significantly affected.

[0122] In actual applications, various optimization scheduling models are solved to obtain the scheduling strategy set under various operating conditions. The intelligent optimization algorithm used is the particle swarm optimization algorithm. The specific process includes:

[0123] 1) Problem modeling and coding

[0124] Problem modeling: First, it is necessary to determine the relevant objective functions and various constraints, such as equipment operation restrictions and energy balance constraints, based on the optimization scheduling model of each operating condition.

[0125] Encoding: The scheduling strategy is represented as a particle position vector. For example, for a scheduling problem involving multiple devices, the operating parameters of each device (such as power, operating time, etc.) can be used as a dimension of the vector. In this way, the position of a particle represents a complete scheduling strategy. Here, the optimal scheduling strategy for different operating conditions is encoded according to the operating conditions.

[0126] 2) Initialize the particle swarm

[0127] Population size: determines the size of the particle swarm, that is, the number of particles. Generally speaking, the larger the population size, the stronger the algorithm's search capability, but the computational effort also increases accordingly. The appropriate population size is usually chosen based on the complexity of the problem and the computing resources available, with common values ​​ranging from tens to hundreds.

[0128] Particle position and velocity initialization: Randomly initialize the position and velocity of each particle. The particle position should be within the feasible solution space of the problem, and the velocity is usually randomly selected within a small range;

[0129] 3) Fitness function calculation

[0130] For each particle, its position vector is substituted into the objective function of the optimization scheduling model to calculate the corresponding fitness value. The fitness value reflects the quality of the scheduling strategy represented by the particle;

[0131] 4) Particle update

[0132] Velocity Update: Updates the particle's velocity according to the following formula:

[0133] ;

[0134] is the velocity of particle i in the dth dimension at the t+1th iteration; is the inertia weight; 、 is the learning factor; 、 is a random number between [0,1]; is the individual optimal position of particle i in the dth dimension at the tth iteration; is the position of particle i in the dth dimension at the tth iteration; is the global optimal position of the d-th dimension of the entire particle swarm at the t-th iteration;

[0135] Position update: Update the particle's position according to the updated velocity, expressed as:

[0136] ;

[0137] When updating the position, it is necessary to ensure that the particle's position is still within the feasible solution space;

[0138] 5) Optimal solution update

[0139] For each particle, compare its current fitness value with the individual optimal fitness value. If the current fitness value is better, update the individual optimal position and fitness value;

[0140] Compare the individual optimal fitness values ​​of all particles to find the global optimal fitness value and the corresponding global optimal position;

[0141] 6) Termination condition judgment

[0142] Set termination conditions. Common termination conditions include reaching the maximum number of iterations, the change in the global optimal solution being less than a certain threshold, or the computation time exceeding a limit. When the termination conditions are met, the algorithm stops and outputs the global optimal position as the optimal scheduling strategy set. Otherwise, return to step 4 and continue iterating.

[0143] 7) Result analysis and verification

[0144] The obtained optimal scheduling strategy set is analyzed to check whether it meets various constraints and whether it is feasible and effective under actual operating conditions.

[0145] In this embodiment, the establishment of a performance evaluation model for the heating system to resist extreme weather and failures includes:

[0146] A performance evaluation model is established by setting performance evaluation indicators, wherein the performance evaluation indicators include a heat load maintenance indicator, a resistance index, a responsiveness index, and a recovery index.

[0147] In actual applications, the heat load maintenance index is defined as: reflecting the degree of match between the actual heat load provided by the heating system and the heat load required by the user under extreme weather and fault conditions, and measuring the system's ability to meet the user's basic heating needs, expressed as:

[0148] ;

[0149] T is the evaluation period (e.g., the duration of extreme weather or the time from the occurrence to the recovery of a fault); is the actual heat load provided by the system at time t; is the heat load demand value at time t; The closer the index value is to 1, the stronger the heat load maintenance ability is.

[0150] Definition of resilience index: This index measures the heating system's ability to resist interference and maintain a certain level of operation in the event of extreme weather and failures. It reflects the inherent stability and robustness of the system and is expressed as:

[0151] ;

[0152] n is the number of key components of the heating system (such as heat source equipment, heating network pipeline sections, pumping stations, etc.); The actual change in the operating parameters (such as temperature, pressure, flow, etc.) of the i-th component caused by extreme weather or failure; is the maximum change that the operating parameters of the i-th component can withstand; The importance weight of the i-th component is determined according to the component's position in the heating system and its impact on the overall heating (for example, the heat source equipment has a higher weight, while some non-critical branch pipelines have a lower weight). The closer the indicator value is to 1, the stronger the resistance is.

[0153] Responsiveness index definition: reflects the speed at which the heating system takes countermeasures and improves the system's operating status after sensing extreme weather or failures, expressed as:

[0154] ;

[0155] When extreme weather or failure occurs; This is the moment when the system begins to take effective response measures and shows an improvement trend in key operating parameters (such as heating network pressure, heat source heat supply, etc.); It is a set reference time (such as the longest acceptable time without effective response after extreme weather or failure occurs). The closer the indicator value is to 0, the faster the response speed.

[0156] Definition of recovery index: It measures the speed and degree to which the heating system returns to normal operation after the extreme weather ends or the fault is repaired, expressed as:

[0157] ;

[0158] The moment when extreme weather ends or fault repair is completed; The moment when the system is fully restored to normal operation; is the actual heat load provided by the system at time t; It is the heat load that the system should provide under normal operating conditions at time t. The closer the indicator value is to 1, the better the recovery.

[0159] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the systems, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a portion of code, and the module, program segment, or a portion of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0160] In addition, the functional modules in each embodiment of the present invention can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0161] With the above-described preferred embodiments of the present invention as a guide, and with reference to the above description, relevant personnel are fully capable of making various changes and modifications without departing from the technical scope of this invention. The technical scope of this invention is not limited to the contents of the specification and must be determined according to the scope of the claims.

Claims

1. A method for optimizing the scheduling of a heating system considering extreme weather conditions, characterized in that: include: S1. Use the pre-built digital twin model of the heating system to simulate the system's operating status under various extreme weather conditions, analyze the impact of extreme weather on the system's operating conditions, and generate a set of extreme weather operation scenarios for the system; S2. Establish a heating system fault diagnosis model based on the heating system network operation data to obtain system fault information, including: Obtain historical operation data of the entire network when a heating system failure occurs, and obtain simulated operation data when simulating system heating network and equipment failures using the heating system digital twin model; Based on the historical operation data and simulated operation data of the heating system network, after extracting the fault data features and conducting model training and learning, a heating system fault diagnosis model is established to obtain the system fault type and fault location; S3. Based on the system extreme weather operation scenario set and system fault information, the operating conditions of the heating system are divided into normal operating conditions when extreme weather and fault information have not occurred, extreme weather warning operating conditions, resistance operating conditions when encountering extreme weather and / or fault information, and emergency dispatch operating conditions; among them, the time of extreme weather occurrence is known based on meteorological data forecast information. The operation scheduling time of the heating system is divided into the normal operation period , during the warning operation period , resist during operation and during emergency dispatch ; S4. Under normal operating conditions, the heating system will be operated according to the original scheduling plan. Under extreme weather warning operating conditions, the operating output of the heating units will be increased to store heat in heat storage devices, heating networks and buildings in advance. Under defensive operating conditions, the heat stored in buildings, heating networks and heat storage devices will be used to supplement and maintain the heat load. Under system emergency scheduling conditions, network reconstruction and heat load reduction will be carried out. S5. Establish an optimal scheduling model for the heating system under different operating conditions. After obtaining the scheduling strategy set under each operating condition, establish a performance evaluation model for the heating system to resist extreme weather and failures, evaluate the scheduling strategy set of the heating system, and select the optimal scheduling strategy for optimal scheduling of the heating system; The establishment of a performance evaluation model for a heating system to resist extreme weather and failures includes: A performance evaluation model is established by setting performance evaluation indicators, which include heat load maintenance index, resistance index, responsiveness index and recovery index, which are expressed as: ； T is the evaluation period, which can be the duration of extreme weather or the time from the occurrence to the recovery of a fault; is the actual heat load provided by the system at time t; is the heat load demand value at time t; The closer the index value is to 1, the stronger the heat load maintenance capability is; ； n is the number of key components of the heating system, which can be heat source equipment, heating network pipeline sections, and pumping stations; is the actual change in the operating parameters of the i-th component caused by extreme weather or failure. The operating parameters can be temperature, pressure, or flow rate. is the maximum change that the operating parameters of the i-th component can withstand; The importance weight of the i-th component is determined according to the component's position in the heating system and its impact on the overall heating; The closer the indicator value is to 1, the stronger the resistance is; ； When extreme weather or failure occurs; The moment when the system begins to take effective response measures and shows an improvement trend in key operating parameters. The key operating parameters can be the pressure of the heating network and the heat supply of the heat source; The reference time can be set to the longest acceptable time without effective response expected after extreme weather or failure occurs; The closer the indicator value is to 0, the faster the response speed; ； The moment when extreme weather ends or fault repair is completed; The moment when the system is fully restored to normal operation; is the actual heat load provided by the system at time t; is the heat load that the system should provide under normal operating conditions at time t; The closer the indicator value is to 1, the better the recovery.

2. The heating system optimization scheduling method according to claim 1, characterized in that: Said S1 comprises: Use mechanism modeling and data-driven methods to establish a digital twin model of the heating system; Based on rainfall, snowfall, sleet, temperature, and wind speed, various extreme weather types and parameter ranges are defined to generate information on different extreme weather scenarios, which are then input into the heating system digital twin model for simulation. Monitor changes in system heat load supply and demand, changes in network-wide operating parameters under different extreme weather scenarios, and analyze the probability of heat network and equipment failures caused by extreme weather. At the same time, combine the historical operating data of the heating system under extreme weather conditions to generate a set of system extreme weather operation scenarios.

3. The heating system optimization scheduling method according to claim 1, characterized in that: The S3 includes: Normal operating conditions are defined as During this period, there was no extreme weather or failure information in the heating system; The extreme weather warning operating condition is defined as During this period, there was no extreme weather or failure information in the heating system, but a response plan for the initial occurrence of extreme weather needs to be formulated in advance; The resistance operating condition is defined as During this period, the heating system begins to encounter extreme weather and / or fault information, and the pre-planned response plan is implemented to resist and initially meet the missing heat; The emergency dispatch condition is defined as During this period, the response plan can no longer meet the missing heat, and it is necessary to further formulate an emergency dispatch plan to maintain the normal operation of the system.

4. The heating system optimization scheduling method according to claim 1, characterized in that: The optimization scheduling model under normal operating conditions aims to minimize the system operating cost under the load demand of each heating station, and outputs the operating output strategy of each heating equipment in the system, which is expressed as: ； is the operating output of the i-th heating equipment at time t under normal operating conditions; is the unit power operating cost of the i-th heating equipment under normal operating conditions; M is the number of heating equipment.

5. The heating system optimization scheduling method according to claim 1, characterized in that: The establishment of the optimization scheduling model under the extreme weather warning operation condition includes: When extreme weather occurs Based on the heat load demand of each thermal power station, and compared with the normal operating conditions Compare the heat load demands of each heating station at the current moment to obtain the heat load demand increment; By increasing the operating output of conventional heating units and electric heating units, heat that matches the increase in heat load demand is produced and stored in heat storage devices, heat networks, and buildings; With the goal of minimizing the incremental operating costs of conventional heating units, electric heating units, and heat storage devices, an optimal scheduling model under extreme weather warning operating conditions is established, which can be expressed as: ； It is the operating output increment of conventional heating units under extreme weather warning operating conditions; The unit power operating cost of conventional heating units under extreme weather warning operating conditions; It is the operating output increment of the electric heating unit under extreme weather warning operating conditions; The unit power operating cost of the electric heating unit under extreme weather warning operating conditions; The heat storage increment under extreme weather warning operation conditions; It is the unit heat storage operating cost under extreme weather warning operating conditions.

6. The heating system optimization scheduling method according to claim 1, characterized in that: The establishment of the optimization scheduling model under the operating conditions includes: Based on the principle of resisting the heat load shortage of each heating station under operating conditions, the heat stored in the heat storage devices, heating network and buildings is released, while the operating output of the conventional heating units is adjusted to meet the heat load shortage to the maximum extent possible; With the goal of minimizing the operating output cost of conventional heating units and the heat release cost of heat storage devices, heat networks, and buildings, an optimal scheduling model under operating conditions is established, which can be expressed as: ； To cope with the increase in operating output of conventional heating units under operating conditions compared to extreme weather warning operating conditions; To withstand the unit power operating cost of conventional heating units under operating conditions; To resist heat release under operating conditions; To protect against the unit heat release operating cost under operating conditions.

7. The heating system optimization scheduling method according to claim 1, characterized in that: The establishment of the optimal scheduling model under the emergency scheduling condition includes: Under the system emergency dispatch condition, the heat load of each heating station is seriously lacking. Through network reconstruction, the heat network is decoupled and the heat network structure is rearranged. By calculating the importance factor of each heat user load under each heating station, the heat user load is divided into important heat load and non-important heat load. The non-important heat load is reduced first, and then the important heat load is reduced. With the goal of minimizing the cost of heat network decoupling and heat network structure re-layout and minimizing the heat load reduction, an optimal dispatch model under emergency dispatch conditions is established, which is expressed as: ； is the decoupling and layout cost of the kth heating network node at time t under emergency dispatch conditions; is the state of the kth heating network node at time t under emergency dispatch conditions; is the cost coefficient for reducing the jth heat load at time t under emergency dispatch conditions; is the jth heat load reduction at time t under emergency dispatch conditions; K is the number of heat network nodes decoupled; N is the amount of heat load reduction.

Images