On-demand scheduling control method for heating station of heat supply system containing distributed heat storage tank

Abstract

The invention discloses an on-demand scheduling control method for heating stations of a heat supply system containing distributed heat storage tanks. The on-demand scheduling control method comprises the steps that part of heating stations are selected, and multiple types of mixed heat storage tanks are arranged; constructing a heat supply system cloud edge collaborative architecture containing the distributed heat storage tank; through a plurality of edge computing nodes in the edge layer, operation state data, environment data and heat storage dynamic influence data of each associated heating station and heat storage tank are acquired, and a heat load supply value of each heating station in each time period and a heat load demand value of a subordinate user are predicted and uploaded to the cloud computing layer; heat supply and demand states of all the heating stations are obtained through the cloud computing layer, and heat storage tank heat storage and release mechanisms configured for all the heating stations are established; establishing a cloud computing layer day-ahead global optimization scheduling model by taking the day-ahead multi-period global operation cost minimization of the heat supply system as a target; and establishing an edge layer intra-day optimization scheduling model by taking the highest energy utilization rate, the minimum operation cost of the heat storage tank and the minimum supply-demand deviation of each heating station as targets.

Description

Technical Field

[0001] The present invention belongs to the technical field of heating system scheduling and control, and in particular relates to an on-demand scheduling and control method for a heating power station of a heating system containing a distributed heat storage tank. Background Art

[0002] As heating systems expand and demand for centralized heating increases, the distribution of heat sources may not be adjusted and optimized in a timely manner. This makes it difficult for some remote communities to implement centralized heating, or areas far from the heat source are prone to supply and demand imbalances. Furthermore, in cogeneration centralized heating systems, the cogeneration heat source operates in a power-to-heat mode, which can easily lead to a mismatch between the heat supply and demand at the heating station.

[0003] Currently, the common practice is to configure heat storage tanks and utilize their heat storage and release to achieve a balance between heat supply and demand, ensuring that the heating system can stably meet the needs of heat users and improving energy efficiency. Furthermore, configuring heat storage tanks can make the heating system more flexible, reduce operating costs, and ease the difficulty of regulating the heating system. However, as the scale of the heating system expands and the number of heat storage tanks deployed increases, the system must collect, transmit, and process more and more data, making scheduling and control tasks increasingly complex. This also presents problems such as high computing resource consumption and slow response times.

[0004] Based on the above technical problems, it is necessary to design a new on-demand scheduling control method for a heating system thermal power station containing distributed heat storage tanks. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing technology and provide an on-demand scheduling control method for a thermal power station of a heating system containing a distributed heat storage tank. The method can utilize the cloud-edge collaborative architecture to collaboratively process a large amount of data of the heating system, improve the response speed and effectively utilize computing resources, and establish a cloud computing layer global optimization scheduling model for the day before, with the goal of minimizing the global operating cost, which can optimize the operation of the heating system as a whole, and establish an edge layer intraday optimization scheduling model to combine multiple objectives for rolling optimization instruction output, which can timely adjust and optimize the scheduling strategy according to actual operating data and short-term forecast data within the day, better adapt to the real-time operating status changes of the thermal power station and the heat storage tank, further improve energy utilization efficiency, reduce operating costs, ensure the heating quality of each thermal power station, reduce supply and demand deviations, improve the accuracy and stability of heating, and provide users with better quality heating services.

[0006] In order to solve the above technical problems, the technical solution of the present invention is:

[0007] The present invention provides a method for on-demand dispatching control of a heat supply system thermal power station containing a distributed heat storage tank, which comprises:

[0008] S1. Obtain multi-dimensional factors of the thermal power station's internal and external operations, and select some thermal power stations to deploy various types of mixed heat storage tanks, forming a heating system with distributed heat storage tanks.

[0009] S2. Build a cloud-edge collaborative architecture for the heating system with distributed heat storage tanks, including the edge layer and the cloud computing layer;

[0010] S3. Acquire the operating status data, environmental data, and thermal storage dynamic impact data of each associated thermal power station and thermal storage tank through multiple edge computing nodes in the edge layer, predict the thermal load supply value of each thermal power station and the thermal load demand value of its users in each time period, and upload the acquired data to the cloud computing layer;

[0011] S4. After performing data analysis through the cloud computing layer, the heat supply and demand status of each thermal power station is obtained, including heat supply and demand balance, heat oversupply, and heat undersupply. The heat supply and demand status and heat storage dynamic impact data are taken into consideration to establish a heat storage and release mechanism for the heat storage tanks configured at each thermal power station;

[0012] S5. With the goal of minimizing the global operating cost of the heating system in multiple time periods on the day before, a global optimization scheduling model for the day before cloud computing is established to output the operation strategies of the heat source and each heat storage tank in each time period on the day before.

[0013] S6. Based on the daily operating data of each thermal power station and heat storage tank, combined with the daily ultra-short-term forecast data and the day-ahead scheduling strategy issued by the cloud computing layer, with the goals of maximizing energy utilization, minimizing the operating costs of the heat storage tanks, and minimizing the supply and demand deviation of each thermal power station, an edge layer daily optimization scheduling model is established to correct the rolling optimization instructions of the heat source and each heat storage tank in each time period during the decision output day.

[0014] Furthermore, the S1 includes:

[0015] Obtaining internal and external data of the thermal power station, including geospatial data on where thermal storage tanks can be located, available data on new energy sources, and heat network pipeline layout;

[0016] Obtain the thermal power station's own operating data, including historical fault records of the thermal power station, historical heat supply and demand data, energy consumption data of the thermal power station, heat load ranges of subordinate users, and the types and importance of heat users;

[0017] Based on the internal and external data of the thermal power station and its own operation data, a thermal power station feature library is constructed, and after feature extraction, the key features of the thermal power station are obtained;

[0018] Based on the key features of the heating station, a thermal station portrait label library is generated, including the thermal station geospatial feature label, the new energy availability feature label, the thermal station energy consumption behavior feature label, and the thermal station static attribute label. The weight value of each label is combined to generate a portrait of each thermal station.

[0019] Taking into account the profiles of each thermal power station and the economic cost constraints, some key thermal power stations were selected and the types of heat storage tanks suitable for layout in the key thermal stations were evaluated, including electric heat pump-heat storage tanks, photovoltaic-heat storage tanks, and hot water storage tanks, and finally a heating system with distributed heat storage tanks was formed.

[0020] Furthermore, the S2 includes:

[0021] Connect each heating station, the deployed heat storage tanks, and related sensors to the edge layer, where multiple edge computing nodes are deployed; and connect the edge layer to the cloud computing layer to establish a cloud-edge collaborative interaction mechanism and build a cloud-edge collaborative architecture for the heating system with distributed heat storage tanks.

[0022] Among them, the location, quantity and model of edge computing nodes are optimized according to the scale, distance, number of equipment and data processing volume of each thermal power station.

[0023] Furthermore, the S3 includes:

[0024] Through the multiple edge computing nodes of the edge layer, the water supply temperature, return water temperature, heat flow, water supply pressure, return water pressure, outdoor ambient temperature, and information about the heat users under the jurisdiction of each associated thermal power station are obtained, as well as the heat storage and release status and heat storage and release of the heat storage tank, the dynamic electricity price that affects heat storage, and the dynamic changes in new energy sources;

[0025] Data features that affect the heat load supply value of each heating station and the heat load demand value of the users under its jurisdiction are selected respectively, and model training and learning are carried out to establish a heat load supply value prediction model for each heating station and a heat load demand value prediction model for the users under its jurisdiction, and obtain the heat load supply value of each heating station and the heat load demand value of the users under its jurisdiction in each time period, and upload them to the cloud computing layer together with the obtained data.

[0026] Further, the S4 includes:

[0027] The cloud computing layer analyzes the heat load supply value of each heating station in each time period and the heat load demand value of the users under its jurisdiction, and determines the heat supply and demand status of each heating station, including heat supply and demand balance, heat oversupply and heat undersupply. At the same time, the heat oversupply and heat undersupply time periods of each heating station are identified and used as the heat storage and release adjustment time periods of the heat storage tank;

[0028] When the thermal power station is in a state of over-supply of heat and the heat storage tank has sufficient heat storage space, the heat storage tank is started to store the excess heat. The heat storage speed can be adjusted according to the degree of over-supply of heat and the heat storage capacity of the heat storage tank.

[0029] When the thermal power station is in a state of heat shortage and the heat storage tank has sufficient heat reserve, the heat storage tank is started to release heat to supplement heat to the thermal power station. The heat release rate is adjusted according to the degree of heat shortage and the heat release capacity of the heat storage tank.

[0030] When the thermal power station is in a balance between heat supply and demand, it decides whether to perform heat storage or heat release operations between cells based on the current heat storage status of the heat storage tank and the heat load forecast for a period of time in the future, so as to maintain the heat storage status of the heat storage tank within a preset reasonable range and prepare for future changes in heat supply and demand;

[0031] At the same time, depending on the type of heat storage tank arranged, when the heat storage tank is an electric heat pump-heat storage tank, electric heating and heat storage are carried out using low electricity prices; when the heat storage tank is a photovoltaic-heat storage tank, photovoltaic heating and heat storage are carried out using periods of sufficient sunlight.

[0032] Furthermore, in S5, with the goal of minimizing the global operating cost of the heating system in multiple time periods on the day before, a cloud computing layer day-ahead global optimization scheduling model is established, including:

[0033] Obtain the current operating data of each heating station and heat storage tank, including the supply and return water temperature, supply and return water pressure and heat flow of each heating station, the heat storage capacity of the heat storage tank, and the short-term heat load supply forecast value and heat load demand forecast value of each heating station in combination with the previous day;

[0034] The goal is to minimize the global operating cost of the heating system in multiple periods of the day before. It consists of the heating cost of the heat source, the operating cost of the heat storage tank, and the cloud-edge collaborative data processing cost, which can be expressed as:

[0035]

[0036] C hs,i,t is the heat source heating cost of the i-th thermal power station at time t, including heat source fuel cost, operation and maintenance cost, and start-up and shutdown cost; C ts,i,t is the operating cost of the heat storage tank at the i-th thermal power station at time t, including heat storage cost and heat release cost, which is related to the type of heat storage tank; C ec,i,t is the cloud-edge collaborative data processing cost of the i-th thermal power station at time t, C ec,i,t =η(aD i,t +bS i,t +cR i,t ), η is the calculation cost coefficient, D i,t is the cloud-edge collaborative data processing capacity of the i-th thermal power station at time t, S i,tis the time required for data transmission at the i-th heating station at time t, R i,t is the computing resource amount of the i-th thermal power station at time t, a, b, and c are weight coefficients used to measure the impact of data processing volume, data transmission time, and computing resource amount on cost;

[0037] Set system operation constraints, including: system thermal balance constraints, heat source heating constraints, heat storage tank capacity constraints and heat storage and release power constraints, and heat network safety operation constraints.

[0038] Furthermore, in S6, with the goals of maximizing energy utilization, minimizing the operating cost of the heat storage tank, and minimizing the supply-demand deviation of each thermal power station, an intraday optimization scheduling model for the edge layer is established, which can be expressed as follows:

[0039]

[0040] Q hs,i,t is the actual heat supply of the heat source at the i-th thermal power station at time t; Q tx,i,t is the heat supply of the heat storage tank at the i-th thermal power station at time t; E hs,i,t is the amount of energy consumed by the heat source at the i-th thermal power station at time t; E tx,i,t is the energy consumed by the heat storage tank at the i-th thermal power station at time t, which is related to the type of heat storage tank;

[0041]

[0042] c cha,i,t 、c dis,i,t are the unit heat storage cost and unit heat release cost of the heat storage tank at the i-th thermal power station at time t; P cha,i,t 、P dis,i,t are the heat storage power and heat release power of the heat storage tank at the i-th thermal power station at time t respectively;

[0043]

[0044] Q sup,i,t is the heat load demand of the i-th thermal power station at time t; Q dem,i,t is the actual heat load supply value of the i-th thermal power station at time t;

[0045] The constraints of the marginal layer intraday optimization scheduling model include: energy balance constraint of the heat storage tank, heat storage and release rate constraint of the heat storage tank, heating capacity constraint of the heat source, heat load demand constraint of the heat station and hydraulic balance constraint of the heat network.

[0046] Furthermore, the on-demand dispatch control method for a heating power station in a heating system further includes:

[0047] When an edge computing node reads in real time that a device or heating network failure has occurred at an associated heating station, it indicates that an imbalance in supply and demand has occurred at the heating station and sends a scheduling control signal to the cloud computing layer;

[0048] The cloud computing layer centrally dispatches and manages all heat storage tanks based on the missing heat load supply value of the thermal power station caused by the fault, the heat storage and release status of each heat storage tank in each future period, and the excess heat reserve, to ensure that the heat load demand of each thermal power station and the fault scheduling cost are met and the fault scheduling cost is minimized. The decision output controls at least one heat storage tank to make up for the heat loss and issues scheduling instructions to the edge layer.

[0049] Furthermore, the on-demand dispatch control method for a heating power station in a heating system further includes:

[0050] After the edge layer obtains the rolling optimization instructions of the heat source and each heat storage tank in each time period of the day based on the edge layer's intraday optimization scheduling model, each edge computing node identifies and outputs the control parameters of the corresponding pumps and valves of the thermal power station based on the operating data of the associated thermal power station, the operating data of the heat storage tank and the thermal power station control mechanism model.

[0051] Furthermore, the cloud computing layer's day-ahead global optimization scheduling model also includes consideration of the control costs of the day-ahead flexible heat load and the intraday flexible heat load, and the output also includes scheduling instructions for the day-ahead flexible heat load; the edge layer's intraday optimization scheduling model also includes consideration of the control costs of the intraday flexible heat load, and the output also includes scheduling instructions for the intraday flexible heat load.

[0052] The beneficial effects of the present invention are:

[0053] (1) The present invention obtains multi-dimensional factors of the thermal power station and arranges mixed heat storage tanks to form a heating system with distributed heat storage tanks. This can comprehensively consider the various actual conditions of the thermal power station and select appropriate heat storage tank types and arrangements according to the characteristics of different thermal power stations, thereby improving the flexibility and adaptability of the heating system. By setting up distributed heat storage tanks, heat can be stored in different locations, reducing losses during heat transmission, improving heat utilization efficiency, and better meeting the heating needs of different regions and different users;

[0054] (2) The present invention combines the edge layer and the cloud computing layer by constructing a cloud-edge collaborative architecture, giving full play to the advantages of both. The edge layer can monitor and preliminarily process local thermal power stations and heat storage tanks in real time, as well as perform local data prediction and optimization scheduling, reducing the amount of data transmission, reducing the burden on the cloud computing layer, and improving the response speed of the system. The cloud computing layer can analyze and optimize global data, achieve macro-control of the entire heating system, and improve the overall operating efficiency and management level of the system. This architecture also enhances the reliability and scalability of the system, making it easier to upgrade and maintain the heating system;

[0055] (3) The present invention acquires and uploads data through edge computing nodes, which can provide comprehensive and accurate information support for the system. By acquiring and uploading the operating status data of the thermal power station and heat storage tank, environmental data, and heat storage dynamic impact data in real time, the cloud computing layer can timely understand the operating status of the system and provide a basis for subsequent analysis and decision-making. At the same time, predicting the supply and demand values of the heat load helps to prepare for heat supply scheduling in advance, avoid insufficient or excessive heat supply, and improve the stability and comfort of heat supply;

[0056] (4) The present invention analyzes data through the cloud computing layer and establishes a heat storage and release mechanism, which can reasonably control the charging and releasing of the heat storage tank according to the actual heat supply and demand status of the thermal power station, thereby realizing effective heat allocation. When heat is oversupplied, the excess heat is stored to avoid waste; when heat is undersupplied, the stored heat is released in time to ensure the quality of heating. Considering the dynamic impact data of heat storage makes the heat storage and release mechanism more scientific and reasonable, can adapt to different operating conditions, and improve the use efficiency of the heat storage tank and the stability of the heating system;

[0057] (5) The present invention can optimize the operation of the heating system as a whole by establishing a global optimization scheduling model at the cloud computing layer with the goal of minimizing the global operating cost. By optimizing the operating strategies of the heat source and each heat storage tank in each time period before the day, the output of the heat source and the charging and discharging plan of the heat storage tank can be reasonably arranged, thereby reducing energy consumption and operating costs and improving the economic benefits of the heating system. At the same time, this global optimization scheduling helps to balance the heating demand between different thermal power stations, avoid local overheating or overcooling, and improve the operating efficiency and heating quality of the entire heating system;

[0058] (6) The present invention establishes an intraday optimization scheduling model at the edge layer and combines multiple objectives to output rolling optimization instructions. It can timely adjust and optimize the scheduling strategy based on actual operating data and short-term forecast data within the day. With the goal of maximizing energy utilization, minimizing the operating cost of heat storage tanks, and minimizing the supply and demand deviation of each thermal power station, the heating system can achieve optimized operation on a finer time scale. By continuously correcting and optimizing the scheduling instructions, it can better adapt to the real-time operating status changes of thermal power stations and heat storage tanks, further improve energy utilization efficiency, reduce operating costs, ensure the heating quality of each thermal power station, reduce supply and demand deviations, improve the accuracy and stability of heating, and provide users with better quality heating services.

[0059] 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.

[0060] 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

[0061] 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.

[0062] Figure 1 This is a flow chart of an on-demand dispatch control method for a heating system thermal power station containing a distributed heat storage tank according to the present invention;

[0063] Figure 2 This is a schematic structural diagram of a heating system containing a distributed heat storage tank according to the present invention. DETAILED DESCRIPTION

[0064] 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.

[0065] like Figure 1 、 Figure 2 As shown, this embodiment provides a method for on-demand dispatch control of a heating system thermal power station with a distributed heat storage tank, which includes:

[0066] S1. Obtain multi-dimensional factors of the thermal power station's internal and external operations, and select some thermal power stations to deploy various types of mixed heat storage tanks, forming a heating system with distributed heat storage tanks.

[0067] S2. Build a cloud-edge collaborative architecture for the heating system with distributed heat storage tanks, including the edge layer and the cloud computing layer;

[0068] S3. Acquire the operating status data, environmental data, and thermal storage dynamic impact data of each associated thermal power station and thermal storage tank through multiple edge computing nodes in the edge layer, predict the thermal load supply value of each thermal power station and the thermal load demand value of its users in each time period, and upload the acquired data to the cloud computing layer;

[0069] S4. After performing data analysis through the cloud computing layer, the heat supply and demand status of each thermal power station is obtained, including heat supply and demand balance, heat oversupply, and heat undersupply. The heat supply and demand status and heat storage dynamic impact data are taken into consideration to establish a heat storage and release mechanism for the heat storage tanks configured at each thermal power station;

[0070] S5. With the goal of minimizing the global operating cost of the heating system in multiple time periods on the day before, a global optimization scheduling model for the day before cloud computing is established to output the operation strategies of the heat source and each heat storage tank in each time period on the day before.

[0071] S6. Based on the daily operating data of each thermal power station and heat storage tank, combined with the daily ultra-short-term forecast data and the day-ahead scheduling strategy issued by the cloud computing layer, with the goals of maximizing energy utilization, minimizing the operating costs of the heat storage tanks, and minimizing the supply and demand deviation of each thermal power station, an edge layer daily optimization scheduling model is established to correct the rolling optimization instructions of the heat source and each heat storage tank in each time period during the decision output day.

[0072] In this embodiment, S1 includes:

[0073] Obtaining internal and external data of the thermal power station, including geospatial data on where thermal storage tanks can be located, available data on new energy sources, and heat network pipeline layout;

[0074] Obtain the thermal power station's own operating data, including historical fault records of the thermal power station, historical heat supply and demand data, energy consumption data of the thermal power station, heat load ranges of subordinate users, and the types and importance of heat users;

[0075] Based on the internal and external data of the thermal power station and its own operation data, a thermal power station feature library is constructed, and after feature extraction, the key features of the thermal power station are obtained;

[0076] Based on the key features of the heating station, a thermal station portrait label library is generated, including the thermal station geospatial feature label, the new energy availability feature label, the thermal station energy consumption behavior feature label, and the thermal station static attribute label. The weight value of each label is combined to generate a portrait of each thermal station.

[0077] Taking into account the profiles of each thermal power station and the economic cost constraints, some key thermal power stations were selected and the types of heat storage tanks suitable for layout in the key thermal stations were evaluated, including electric heat pump-heat storage tanks, photovoltaic-heat storage tanks, and hot water storage tanks, and finally a heating system with distributed heat storage tanks was formed.

[0078] In practical applications, geospatial data on where thermal storage tanks can be deployed, both inside and outside the station, is obtained. This includes information on topography, land use type, and building distribution. This provides a geospatial foundation for subsequent thermal storage tank layout planning. For example, some thermal power stations can utilize basements for thermal storage tanks, while others lack internal space and can consider utilizing external space. Some thermal power stations are more suitable for deploying photovoltaic thermal storage tanks, utilizing solar energy resources and assessing solar energy availability based on geographic location and climatic conditions. Other stations are suitable for deploying electric heat pumps, such as air-source heat pumps and ground-source heat pumps, which generate heat and store it in thermal storage tanks. Furthermore, deploying thermal storage tanks requires laying pipelines to connect to the existing heating network. Therefore, consideration must be given to the existing network pipeline layout, including its route, diameter, and burial depth, as well as the feasibility and complexity of laying new pipelines. Some heating stations have a large number of heat users and a large heating area, which makes it easy for supply and demand to be unbalanced. It is necessary to arrange heat storage tanks for such heating stations. Some heating stations have heat users such as hospitals and schools, and heat storage tanks need to be arranged to ensure the reliability and stability of their heating.

[0079] Feature library construction: Organize and categorize the acquired data, building a thermal station feature library based on different themes and data types. This feature library can be stored and managed using a database management system to facilitate data query, update, and maintenance.

[0080] Feature extraction: Data in the feature library is processed using feature engineering techniques from data mining and machine learning. For example, for geospatial data, features such as terrain slope, altitude, and distance to heat sources and users can be extracted. For renewable energy availability data, features such as solar radiation intensity, annual average wind speed, and geothermal energy reserves can be extracted. For thermal power station operating data, features such as heat supply and demand balance, energy consumption rate, and fault frequency can be calculated. Through these feature extraction methods, raw data is transformed into representative and discriminative key features to better describe the characteristics of the thermal power station.

[0081] Generation of a portrait label library: Different types of labels are defined based on the key features of the thermal power station. For example, based on geographic spatial features, geographic spatial feature labels such as "mountainous thermal power station" and "plain thermal power station" are generated; based on the data on the availability of new energy, new energy availability feature labels such as "solar energy-rich thermal power station" and "wind energy exploitable thermal power station" are generated; based on the energy consumption behavior data of the thermal power station, energy consumption feature labels such as "high-energy consumption thermal power station" and "energy-saving thermal power station" are generated; based on the static attributes of the thermal power station, such as scale and service population, static attribute labels such as "large thermal power station" and "small thermal power station" are generated. Each label corresponds to a specific feature value range or condition. By judging and classifying the key features, the thermal power station is labeled with the corresponding label to form a portrait label library.

[0082] Thermal Station Profile Generation: A comprehensive calculation and evaluation of the thermal station's labels is performed, combining the weights of each label. Weights can be determined using multi-criteria decision-making methods such as the Analytic Hierarchy Process (AHP) and Principal Component Analysis (PCA). Each label is weighted according to its importance to the overall characteristics of the thermal station. By multiplying the scores of each label by their weights and summing the results, a comprehensive thermal station profile score is generated. This provides a comprehensive and intuitive description of the thermal station's characteristics and status, generating a profile for each thermal station.

[0083] Key heating station selection: By comprehensively considering the profiles of each heating station and economic cost constraints, multi-objective optimization algorithms, such as the non-dominated sorting genetic algorithm (NSGA-II), are used. Using the station's importance, impact on the heating system, and energy-saving potential as objective functions, and economic cost and resource limitations as constraints, the stations are evaluated and ranked, and a selection of key heating stations is selected. These key heating stations typically play a crucial role in the heating system, and optimizing their configuration and management can effectively improve the performance and efficiency of the entire heating system.

[0084] Thermal storage tank type assessment: For selected key thermal power stations, the appropriate type of thermal storage tank to be deployed is assessed based on their geographic and spatial characteristics, available new energy features, and energy consumption behavior. For example, for thermal power stations with abundant solar energy resources and sufficient electricity supply, photovoltaic-thermal storage tanks can be considered, using solar photovoltaic power generation to heat the thermal storage tanks. For thermal power stations with relatively abundant electricity resources and certain peak-shaving needs, electric heat pump-thermal storage tanks can be selected, using electric heat pumps to convert electrical energy into thermal energy and store it. For traditional thermal power stations that use hot water as a heating medium, hot water thermal storage tanks are a common choice. They can be used to store hot water during low-heat periods and release heat during peak periods to balance the supply and demand of the heating network. Through technical and economic analysis and adaptability assessment of different thermal storage tank types, the most suitable thermal storage tank type for each key thermal power station is determined, ultimately forming a heating system with distributed thermal storage tanks to achieve optimized operation of the heating system and efficient energy utilization.

[0085] In this embodiment, S2 includes:

[0086] Connect each heating station, the deployed heat storage tanks, and related sensors to the edge layer, where multiple edge computing nodes are deployed; and connect the edge layer to the cloud computing layer to establish a cloud-edge collaborative interaction mechanism and build a cloud-edge collaborative architecture for the heating system with distributed heat storage tanks.

[0087] Among them, the location, quantity and model of edge computing nodes are optimized according to the scale, distance, number of equipment and data processing volume of each thermal power station.

[0088] In actual applications, devices are connected to the edge layer: each heating station, thermal storage tank, and related sensors encode and transmit their data information through industrial network protocols such as Modbus and OPC, and then connect to the edge layer. These protocols ensure standardized data communication between different devices, enabling the edge layer to obtain accurate and real-time operational data, including temperature, pressure, and flow rate of the heating station, liquid level and temperature of the thermal storage tank, and environmental parameters monitored by sensors.

[0089] Edge layer connection with the cloud computing layer: The edge layer and cloud computing layer are connected via a high-speed network, such as a fiber optic network or a 5G network. Network communication protocols, such as TCP / IP, are used to ensure reliable data transmission between the edge and cloud computing layers. The edge layer uploads processed or raw data to the cloud computing layer as needed. The cloud computing layer then sends analysis results and control instructions to the edge layer, thus establishing a cloud-edge collaborative interaction mechanism.

[0090] The main considerations for optimizing edge computing node deployment include:

[0091] 1) Thermal power station scale factor: Large thermal power stations typically have more equipment and more complex operating conditions, requiring the processing of large amounts of data. Therefore, it is necessary to deploy high-performance, high-capacity edge computing nodes to ensure timely processing and analysis of various data generated by the thermal power station, such as the operating parameters of multiple heat source equipment and monitoring data of a large number of heat network pipelines. Small thermal power stations, on the other hand, have relatively small amounts of data and can deploy relatively small, low-cost edge computing nodes.

[0092] 2) Distance factor: For thermal power stations that are far away from cloud computing centers, in order to reduce data transmission delays and network bandwidth usage, it is necessary to deploy more powerful edge computing nodes locally, so that they can complete most of the data processing and analysis locally and only upload key results to the cloud computing layer. For thermal power stations that are closer to cloud computing centers, the configuration of edge computing nodes can be appropriately reduced because data can be quickly transmitted to the cloud computing center for processing. For example, by calculating the round-trip time and cost of data transmission, combined with the real-time requirements of the thermal power station, the deployment location and processing capacity of the edge computing nodes can be determined;

[0093] 3) Equipment quantity factor: Thermal power stations with a large number of devices also generate large amounts of data, and the collaborative control requirements between devices are complex. This requires the deployment of multiple edge computing nodes to share data processing tasks, or the deployment of high-performance edge computing nodes to achieve real-time monitoring and precise control of numerous devices. For example, a thermal power station with a large number of pumps, valves, heat exchangers, and sensors requires edge computing nodes to quickly process status information and control instructions from these devices to ensure stable operation and efficient collaboration of the equipment;

[0094] 4) Data processing volume factor: Determine the size of its data processing volume based on the analysis of the historical data and real-time data of the thermal power station. For thermal power stations with large data processing volumes, such as those that require real-time analysis of a large amount of heating network operation data to optimize heating scheduling, edge computing node models with strong computing power and large storage capacity should be selected, and the number of nodes should be reasonably increased to avoid backlogs and delays in data processing. At the same time, considering the real-time requirements of data processing, for thermal power stations that need to complete data processing and respond in a short time, such as those involving emergency fault handling, the performance and deployment location of the edge computing nodes need to be further optimized to meet the needs of rapid processing and decision-making.

[0095] In this embodiment, S3 includes:

[0096] Through the multiple edge computing nodes of the edge layer, the water supply temperature, return water temperature, heat flow, water supply pressure, return water pressure, outdoor ambient temperature, and information about the heat users under the jurisdiction of each associated thermal power station are obtained, as well as the heat storage and release status and heat storage and release of the heat storage tank, the dynamic electricity price that affects heat storage, and the dynamic changes in new energy sources;

[0097] Data features that affect the heat load supply value of each heating station and the heat load demand value of the users under its jurisdiction are selected respectively, and model training and learning are carried out to establish a heat load supply value prediction model for each heating station and a heat load demand value prediction model for the users under its jurisdiction, and obtain the heat load supply value of each heating station and the heat load demand value of the users under its jurisdiction in each time period, and upload them to the cloud computing layer together with the obtained data.

[0098] In this embodiment, the S4 includes:

[0099] The cloud computing layer analyzes the heat load supply value of each heating station in each time period and the heat load demand value of the users under its jurisdiction, and determines the heat supply and demand status of each heating station, including heat supply and demand balance, heat oversupply and heat undersupply. At the same time, the heat oversupply and heat undersupply time periods of each heating station are identified and used as the heat storage and release adjustment time periods of the heat storage tank;

[0100] When the thermal power station is in a state of over-supply of heat and the heat storage tank has sufficient heat storage space, the heat storage tank is started to store the excess heat. The heat storage speed can be adjusted according to the degree of over-supply of heat and the heat storage capacity of the heat storage tank.

[0101] When the thermal power station is in a state of heat shortage and the heat storage tank has sufficient heat reserve, the heat storage tank is started to release heat to supplement heat to the thermal power station. The heat release rate is adjusted according to the degree of heat shortage and the heat release capacity of the heat storage tank.

[0102] When the thermal power station is in a balance between heat supply and demand, it decides whether to perform heat storage or heat release operations between cells based on the current heat storage status of the heat storage tank and the heat load forecast for a period of time in the future, so as to maintain the heat storage status of the heat storage tank within a preset reasonable range and prepare for future changes in heat supply and demand;

[0103] At the same time, depending on the type of heat storage tank arranged, when the heat storage tank is an electric heat pump-heat storage tank, electric heating and heat storage are carried out using low electricity prices; when the heat storage tank is a photovoltaic-heat storage tank, photovoltaic heating and heat storage are carried out using periods of sufficient sunlight.

[0104] It should be noted that when the thermal power station is experiencing a heat oversupply and the heat storage tank has sufficient storage space, the tank is activated to store excess heat. The heat storage rate is adjusted based on the degree of heat oversupply and the heat storage capacity of the heat storage tank. The degree of heat oversupply can be measured by the difference between the supply and demand values; the greater the difference, the greater the oversupply. The heat storage capacity of the heat storage tank is determined by its physical properties, such as the specific heat capacity of the heat storage medium and the tank's volume. Based on these factors, the heat storage rate is adjusted by controlling valves, pumps, and other equipment in the heat storage system to regulate the flow rate and velocity of the heat medium entering the heat storage tank.

[0105] When the thermal power station is experiencing a heat shortage and the heat storage tank has sufficient heat reserves, the tank is activated to release heat to replenish the heat. The heat release rate is also adjusted based on the degree of heat shortage and the heat release capacity of the heat storage tank. The degree of heat shortage is determined by the difference between the demand and supply values; the greater the difference, the greater the shortage. The heat release capacity of the heat storage tank depends on factors such as the temperature of the heat storage medium, the structure of the storage tank, and the performance of the heat release system. By controlling the relevant equipment in the heat release system, such as adjusting the valve opening, the heat medium in the heat storage tank flows to the thermal power station at an appropriate flow rate and flow rate, thereby achieving control over the heat release rate.

[0106] When the heat supply and demand are balanced, the heat storage or heat release operation between cells is determined based on the current heat storage state of the heat storage tank (such as the temperature of the heat storage medium, the liquid level of the heat storage tank and other parameters) and the heat load forecast for a period of time in the future. Heat load forecasting usually uses time series analysis, neural networks and other algorithms to predict future heat load changes based on historical data and current operating trends. If it is predicted that there may be a shortage of heat in the future, and the current heat storage state of the heat storage tank is lower than the preset lower limit of the reasonable range, appropriate heat storage operations are performed; conversely, if it is predicted that there may be an oversupply of heat in the future, and the current heat storage state of the heat storage tank is higher than the preset upper limit of the reasonable range, a small amount of heat release operation is performed to maintain the heat storage state of the heat storage tank within a reasonable range, so as to prepare for future changes in heat supply and demand.

[0107] In this embodiment, in S5, a cloud computing layer day-ahead global optimization scheduling model is established with the goal of minimizing the global operating cost of the heating system in multiple time periods, including:

[0108] Obtain the current operating data of each heating station and heat storage tank, including the supply and return water temperature, supply and return water pressure and heat flow of each heating station, the heat storage capacity of the heat storage tank, and the short-term heat load supply forecast value and heat load demand forecast value of each heating station in combination with the previous day;

[0109] The goal is to minimize the global operating cost of the heating system in multiple periods of the day before. It consists of the heating cost of the heat source, the operating cost of the heat storage tank, and the cloud-edge collaborative data processing cost, which can be expressed as:

[0110]

[0111] C hs,i,t is the heat source heating cost of the i-th thermal power station at time t, including heat source fuel cost, operation and maintenance cost, and start-up and shutdown cost; C ts,i,t is the operating cost of the heat storage tank at the i-th thermal power station at time t, including heat storage cost and heat release cost, which is related to the type of heat storage tank; C ec,i,t is the cloud-edge collaborative data processing cost of the i-th thermal power station at time t, C ec,i,t =η(aD i,t +bS i,t +cR i,t ), η is the calculation cost coefficient, D i,t is the cloud-edge collaborative data processing capacity of the i-th thermal power station at time t, S i,t is the time required for data transmission at the i-th heating station at time t, R i,t is the computing resource amount of the i-th thermal power station at time t, a, b, and c are weight coefficients used to measure the impact of data processing volume, data transmission time, and computing resource amount on cost;

[0112] Set system operation constraints, including: system thermal balance constraints, heat source heating constraints, heat storage tank capacity constraints and heat storage and release power constraints, and heat network safety operation constraints.

[0113] In this embodiment, in S6, with the goals of maximizing energy utilization, minimizing the operating cost of the heat storage tank, and minimizing the supply-demand deviation of each thermal power station, an intraday optimization scheduling model of the edge layer is established, which can be expressed as follows:

[0114]

[0115] Q hs,i,t is the actual heat supply of the heat source at the i-th thermal power station at time t; Q tx,i,t is the heat supply of the heat storage tank at the i-th thermal power station at time t; E hs,i,tis the amount of energy consumed by the heat source at the i-th thermal power station at time t; E tx,i,t is the energy consumed by the heat storage tank at the i-th thermal power station at time t, which is related to the type of heat storage tank;

[0116]

[0117] c cha,i,t 、c dis,i,t are the unit heat storage cost and unit heat release cost of the heat storage tank at the i-th thermal power station at time t; P cha,i,t 、P dis,i,t are the heat storage power and heat release power of the heat storage tank at the i-th thermal power station at time t respectively;

[0118]

[0119] Q sup,i,t is the heat load demand of the i-th thermal power station at time t; Q dem,i,t is the actual heat load supply value of the i-th thermal power station at time t;

[0120] The constraints of the marginal layer intraday optimization scheduling model include: energy balance constraint of the heat storage tank, heat storage and release rate constraint of the heat storage tank, heating capacity constraint of the heat source, heat load demand constraint of the heat station and hydraulic balance constraint of the heat network.

[0121] In this embodiment, the on-demand dispatch control method for a heating system thermal power station further includes:

[0122] When an edge computing node reads in real time that a device or heating network failure has occurred at an associated heating station, it indicates that an imbalance in supply and demand has occurred at the heating station and sends a scheduling control signal to the cloud computing layer;

[0123] The cloud computing layer centrally dispatches and manages all heat storage tanks based on the missing heat load supply value of the thermal power station caused by the fault, the heat storage and release status of each heat storage tank in each future period, and the excess heat reserve, to ensure that the heat load demand of each thermal power station and the fault scheduling cost are met and the fault scheduling cost is minimized. The decision output controls at least one heat storage tank to make up for the heat loss and issues scheduling instructions to the edge layer.

[0124] In actual applications, edge computing nodes analyze and process real-time data based on preset fault detection rules and thresholds. If operating parameters of equipment or the heating network are found to be outside normal ranges, or if specific fault characteristics are present, the heating station is deemed to have experienced a fault and a supply-demand imbalance is detected. At this point, the edge computing node generates a dispatch control signal containing relevant information about the fault, such as its type, location, and potential impact on the heat load supply.

[0125] Scheduling decisions at the cloud computing layer include:

[0126] 1) Calculation of missing heat load supply values: After receiving the dispatch control signal, the cloud computing layer first calculates the missing heat load supply value caused by the fault based on the fault information and the thermal power station's operating model. This calculation process may involve evaluating the heating capacity of the faulty equipment, analyzing the heat loss model of the heating network, and analyzing the overall heating process of the thermal power station to accurately determine the actual heat loss.

[0127] 2) Thermal Tank Status Assessment: The cloud computing layer simultaneously obtains the heat storage and release status of each thermal tank in each future period, as well as the excess heat reserves. This requires communication with the control system of each thermal tank to obtain its real-time parameters such as thermal storage medium temperature, liquid level, thermal storage power, and thermal release power. Combining the physical model of the thermal tank and historical operating data, it predicts the heat storage and release status in each future period.

[0128] 3) Scheduling decision optimization: Based on the principle of ensuring that the heat load demand of each thermal power station is met and the fault scheduling cost is minimized, the cloud computing layer uses an optimization algorithm to centrally schedule and manage all heat storage tanks. The optimization algorithm usually takes into account multiple factors, such as the distance between the heat storage tank and the faulty thermal power station, the remaining heat storage capacity of the heat storage tank, the heat release rate, the energy loss during the scheduling process, and the cost of the scheduling operation (such as equipment operating costs, pipeline transportation costs, etc.). By establishing a mathematical model, these factors are converted into objective functions and constraints, and then optimization methods such as linear programming, nonlinear programming, and dynamic programming are used to solve the optimal scheduling plan, and the decision output controls at least one heat storage tank to make up for the heat loss;

[0129] 4) Scheduling Instruction Generation and Issuance: Based on the optimized scheduling plan, the cloud computing layer generates detailed scheduling instructions, including the number of the thermal storage tank to be activated, the tank's heat storage and release capacity, duration, heat transfer path, and other information. These instructions are then sent via the network to the edge layer, which then forwards them to the corresponding thermal storage tank control system, enabling precise control of the tanks to compensate for the heat loss.

[0130] In this embodiment, the on-demand dispatch control method for a heating system thermal power station further includes:

[0131] After the edge layer obtains the rolling optimization instructions of the heat source and each heat storage tank in each time period of the day based on the edge layer's intraday optimization scheduling model, each edge computing node identifies and outputs the control parameters of the corresponding pumps and valves of the thermal power station based on the operating data of the associated thermal power station, the operating data of the heat storage tank and the thermal power station control mechanism model.

[0132] In practical applications, edge computing nodes use a thermal power station control mechanism model to understand and describe the relationship between pumps, valves, and other equipment within the thermal power station and system operating parameters. This model, based on fundamental principles of thermodynamics and fluid dynamics, establishes mathematical relationships between control parameters such as pump and valve opening and speed, and physical quantities such as flow, pressure, and heat transfer within the thermal network. For example, based on the Bernoulli equation in fluid dynamics and the principles of heat exchange, a quantitative relationship is established between pump speed and hot water flow and heat transfer within the thermal network, as well as between valve opening, pipe resistance, and flow distribution.

[0133] Using the heat source's heating temperature, pressure, and flow rate, the heat storage tank's charge and discharge status and flow rate, and the heat load demand of the heating network as input variables, and control parameters such as pump speed and valve opening as output variables, the edge computing node uses a parameter identification algorithm to calculate the control parameters for the corresponding pumps and valves in the heating station. For example, using optimization algorithms such as the least squares method, the estimated values of the pump and valve control parameters are continuously adjusted to minimize the error between the actual measured values of parameters such as the heating network flow rate and pressure calculated according to the mechanism model. Once the optimal control parameters are identified, the edge computing node outputs them to control the pump and valve equipment in the heating station, achieving precise regulation of the station's operating status, meeting the heat load demand, and optimizing system operating efficiency.

[0134] In this embodiment, the cloud computing layer's day-ahead global optimization scheduling model also includes consideration of the control costs of the day-ahead flexible heat load and the intraday flexible heat load, and the output also includes scheduling instructions for the day-ahead flexible heat load; the edge layer's intraday optimization scheduling model also includes consideration of the control costs of the intraday flexible heat load, and the output also includes scheduling instructions for the intraday flexible heat load.

[0135] 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.

[0136] 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.

[0137] 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 on-demand dispatch control of a heating system thermal power station with a distributed heat storage tank, characterized in that: It includes: S1. Obtain multi-dimensional factors of the thermal power station's internal and external operations, and select some thermal power stations to deploy various types of mixed heat storage tanks, forming a heating system with distributed heat storage tanks. S2. Build a cloud-edge collaborative architecture for the heating system with distributed heat storage tanks, including the edge layer and the cloud computing layer; S3. Acquire the operating status data, environmental data, and thermal storage dynamic impact data of each associated thermal power station and thermal storage tank through multiple edge computing nodes in the edge layer, predict the thermal load supply value of each thermal power station and the thermal load demand value of its users in each time period, and upload the acquired data to the cloud computing layer; S4. After performing data analysis through the cloud computing layer, the heat supply and demand status of each thermal power station is obtained, including heat supply and demand balance, heat oversupply, and heat undersupply. The heat supply and demand status and heat storage dynamic impact data are taken into consideration to establish a heat storage and release mechanism for the heat storage tanks configured at each thermal power station; S5. With the goal of minimizing the global operating cost of the heating system in multiple time periods on the day before, a global optimization scheduling model for the day before cloud computing is established to output the operation strategies of the heat source and each heat storage tank in each time period on the day before. S6. Based on the daily operating data of each thermal power station and heat storage tank, combined with the daily ultra-short-term forecast data and the day-ahead scheduling strategy issued by the cloud computing layer, with the goals of maximizing energy utilization, minimizing the operating costs of the heat storage tanks, and minimizing the supply and demand deviation of each thermal power station, an edge layer daily optimization scheduling model is established to correct the rolling optimization instructions of the heat source and each heat storage tank in each time period during the decision output day.

2. The on-demand dispatch control method for a heating system thermal power station according to claim 1, characterized in that: Said S1 comprises: Obtaining internal and external data of the thermal power station, including geospatial data on where thermal storage tanks can be located, available data on new energy sources, and heat network pipeline layout; Obtain the thermal power station's own operating data, including historical fault records of the thermal power station, historical heat supply and demand data, energy consumption data of the thermal power station, heat load ranges of subordinate users, and the types and importance of heat users; Based on the internal and external data of the thermal power station and its own operation data, a thermal power station feature library is constructed, and after feature extraction, the key features of the thermal power station are obtained; Based on the key features of the heating station, a thermal station portrait label library is generated, including the thermal station geospatial feature label, the new energy availability feature label, the thermal station energy consumption behavior feature label, and the thermal station static attribute label. The weight value of each label is combined to generate a portrait of each thermal station. Taking into account the profiles of each thermal power station and the economic cost constraints, some key thermal power stations were selected and the types of heat storage tanks suitable for layout in the key thermal stations were evaluated, including electric heat pump-heat storage tanks, photovoltaic-heat storage tanks, and hot water storage tanks, and finally a heating system with distributed heat storage tanks was formed.

3. The on-demand dispatch control method for a heating system thermal power station according to claim 1, characterized in that: The S2 includes: Connect each heating station, the deployed heat storage tanks, and related sensors to the edge layer, where multiple edge computing nodes are deployed; and connect the edge layer to the cloud computing layer to establish a cloud-edge collaborative interaction mechanism and build a cloud-edge collaborative architecture for the heating system with distributed heat storage tanks. Among them, the location, quantity and model of edge computing nodes are optimized according to the scale, distance, number of equipment and data processing volume of each thermal power station.

4. The on-demand dispatch control method for a heating system thermal power station according to claim 1, characterized in that: The S3 includes: Through the multiple edge computing nodes of the edge layer, the water supply temperature, return water temperature, heat flow, water supply pressure, return water pressure, outdoor ambient temperature, and information about the heat users under the jurisdiction of each associated thermal power station are obtained, as well as the heat storage and release status and heat storage and release of the heat storage tank, the dynamic electricity price that affects heat storage, and the dynamic changes in new energy sources; Data features that affect the heat load supply value of each heating station and the heat load demand value of the users under its jurisdiction are selected respectively, and model training and learning are carried out to establish a heat load supply value prediction model for each heating station and a heat load demand value prediction model for the users under its jurisdiction, and obtain the heat load supply value of each heating station and the heat load demand value of the users under its jurisdiction in each time period, and upload them to the cloud computing layer together with the obtained data.

5. The on-demand dispatch control method for a heating system thermal power station according to claim 1, characterized in that: The S4 includes: The cloud computing layer analyzes the heat load supply value of each heating station in each time period and the heat load demand value of the users under its jurisdiction, and determines the heat supply and demand status of each heating station, including heat supply and demand balance, heat oversupply and heat undersupply. At the same time, the heat oversupply and heat undersupply time periods of each heating station are identified and used as the heat storage and release adjustment time periods of the heat storage tank; When the thermal power station is in a state of over-supply of heat and the heat storage tank has sufficient heat storage space, the heat storage tank is started to store the excess heat. The heat storage speed can be adjusted according to the degree of over-supply of heat and the heat storage capacity of the heat storage tank. When the thermal power station is in a state of heat shortage and the heat storage tank has sufficient heat reserve, the heat storage tank is started to release heat to supplement heat to the thermal power station. The heat release rate is adjusted according to the degree of heat shortage and the heat release capacity of the heat storage tank. When the thermal power station is in a balance between heat supply and demand, it decides whether to perform heat storage or heat release operations between cells based on the current heat storage status of the heat storage tank and the heat load forecast for a period of time in the future, so as to maintain the heat storage status of the heat storage tank within a preset reasonable range and prepare for future changes in heat supply and demand; At the same time, depending on the type of heat storage tank arranged, when the heat storage tank is an electric heat pump-heat storage tank, electric heating and heat storage are carried out using low electricity prices; when the heat storage tank is a photovoltaic-heat storage tank, photovoltaic heating and heat storage are carried out using periods of sufficient sunlight.

6. The on-demand dispatch control method for a heating system thermal power station according to claim 1, characterized in that: In S5, with the goal of minimizing the global operating cost of the heating system in multiple time periods on the day before, a cloud computing layer day-ahead global optimization scheduling model is established, including: Obtain the current operating data of each heating station and heat storage tank, including the supply and return water temperature, supply and return water pressure and heat flow of each heating station, the heat storage capacity of the heat storage tank, and the short-term heat load supply forecast value and heat load demand forecast value of each heating station in combination with the previous day; The goal is to minimize the global operating cost of the heating system in multiple periods of the day before. It consists of the heating cost of the heat source, the operating cost of the heat storage tank, and the cloud-edge collaborative data processing cost, which can be expressed as: C hs,i,t is the heat source heating cost of the i-th thermal power station at time t, including heat source fuel cost, operation and maintenance cost, and start-up and shutdown cost; C ts,i,t is the operating cost of the heat storage tank at the i-th thermal power station at time t, including heat storage cost and heat release cost, which is related to the type of heat storage tank; C ec,i,t is the cloud-edge collaborative data processing cost of the i-th thermal power station at time t, C ec,i,t =η(aD i,t +bS i,t +cR i,t ), η is the calculation cost coefficient, D i,t is the cloud-edge collaborative data processing capacity of the i-th thermal power station at time t, S i,t is the time required for data transmission at the i-th heating station at time t, R i,t is the computing resource amount of the i-th thermal power station at time t, a, b, and c are weight coefficients used to measure the impact of data processing volume, data transmission time, and computing resource amount on cost; Set system operation constraints, including: system thermal balance constraints, heat source heating constraints, heat storage tank capacity constraints and heat storage and release power constraints, and heat network safety operation constraints.

7. The on-demand dispatch control method for a heating system thermal power station according to claim 1, characterized in that: In S6, with the goals of maximizing energy utilization, minimizing the operating cost of the heat storage tank, and minimizing the supply and demand deviation of each thermal power station, an intraday optimization scheduling model of the edge layer is established, which can be expressed as follows: Q hs,i,t is the actual heat supply of the heat source at the i-th thermal power station at time t; Q tx,i,t is the heat supply of the heat storage tank at the i-th thermal power station at time t; E hs,i,t is the amount of energy consumed by the heat source at the i-th thermal power station at time t; E tx,i,t is the energy consumed by the heat storage tank at the i-th thermal power station at time t, which is related to the type of heat storage tank; c cha,i,t 、c dis,i,t are the unit heat storage cost and unit heat release cost of the heat storage tank at the i-th thermal power station at time t; P cha,i,t 、P dis,i,t are the heat storage power and heat release power of the heat storage tank at the i-th thermal power station at time t respectively; Q sup,i,t is the heat load demand of the i-th thermal power station at time t; Q dem,i,t is the actual heat load supply value of the i-th thermal power station at time t; The constraints of the marginal layer intraday optimization scheduling model include: energy balance constraint of the heat storage tank, heat storage and release rate constraint of the heat storage tank, heating capacity constraint of the heat source, heat load demand constraint of the heat station and hydraulic balance constraint of the heat network.

8. The on-demand dispatch control method for a heating system thermal power station according to claim 1, characterized in that: The on-demand dispatch control method for a heat supply system thermal power station further includes: When an edge computing node reads in real time that a device or heating network failure has occurred at an associated heating station, it indicates that an imbalance in supply and demand has occurred at the heating station and sends a scheduling control signal to the cloud computing layer; The cloud computing layer centrally dispatches and manages all heat storage tanks based on the missing heat load supply value of the thermal power station caused by the fault, the heat storage and release status of each heat storage tank in each future period, and the excess heat reserve, to ensure that the heat load demand of each thermal power station and the fault scheduling cost are met and the fault scheduling cost is minimized. The decision output controls at least one heat storage tank to make up for the heat loss and issues scheduling instructions to the edge layer.

9. The on-demand dispatch control method for a heating system thermal power station according to claim 1, characterized in that: The on-demand dispatch control method for a heat supply system thermal power station further includes: After the edge layer obtains the rolling optimization instructions of the heat source and each heat storage tank in each time period of the day based on the edge layer's intraday optimization scheduling model, each edge computing node identifies and outputs the control parameters of the corresponding pumps and valves of the thermal power station based on the operating data of the associated thermal power station, the operating data of the heat storage tank and the thermal power station control mechanism model.

10. The on-demand dispatch control method for a heating system thermal power station according to claim 1, characterized in that: The cloud computing layer's day-ahead global optimization scheduling model also includes consideration of the control costs of the day-ahead flexible heat load and the intraday flexible heat load, and the output also includes scheduling instructions for the day-ahead flexible heat load; the edge layer's intraday optimization scheduling model also includes consideration of the control costs of the intraday flexible heat load, and the output also includes scheduling instructions for the intraday flexible heat load.

Images