A heating operation dynamic scheduling method and system based on the Internet of Things

Abstract

The present application belongs to the technical field of intelligent heating, and discloses a heating operation dynamic scheduling method and system based on Internet of Things. The present application collects multi-source original data through the arrangement of global Internet of Things sensing devices, and generates standardized heating timing data after preprocessing. The heating load is predicted by using the LSTM-XGBoost model, the hydraulic balance model is used to solve the regulation parameters of each node in combination with the real-time hydraulic working condition, and the optimal output of each unit is distributed according to the heat source operation efficiency. The output parameters of the integrated model are used to generate control instructions and are sent to the field execution mechanism to complete the working condition adjustment. The new operation data after adjustment is compared with the expected target, and the model is iteratively corrected according to the deviation, forming a closed-loop dynamic scheduling cycle. Multi-source complete data supports multi-model collaborative optimization, gets rid of the disadvantages of traditional static fixed value regulation, takes into account the hydraulic safety of the pipe network, the balance of user heating and system energy saving, and can adapt to different heating scenes, realizing intelligent scheduling of the heating system.

Description

Technical Field

[0001] This invention belongs to the field of smart heating and intelligent pipeline scheduling technology, specifically involving a dynamic scheduling method and system for heating operation based on the Internet of Things. Background Technology

[0002] As the coverage of urban centralized heating networks continues to expand, the traditional scheduling model relying on manual fixed-point control and fixed-parameter operation is struggling to meet the actual needs of energy conservation, emission reduction, and balanced heating. Existing heating scheduling schemes mostly employ static set-value control methods, relying solely on historical experience to set heat source output and valve openings. This fails to adapt to real-time hydraulic and thermal conditions of the network, outdoor weather changes, and actual user heating demands, resulting in widespread imbalances such as overheating at the near end and insufficient heating at the far end, leading to persistently high energy consumption in network transmission.

[0003] Currently, the few heating control systems with data acquisition capabilities can only achieve simple data display and lack a complete multi-dimensional data processing chain. On the one hand, the acquired data types are limited, only recording basic network temperature and pressure, lacking related data such as equipment operating status, outdoor weather conditions, and user room temperature distribution. This severe lack of data support dimensions prevents the system from perceiving the actual heating quality at the user end. On the other hand, the raw acquired data suffers from issues such as jumps, disconnections, and missing data, lacking standardized preprocessing and verification mechanisms. Abnormal data directly participates in subsequent calculations, significantly reducing the accuracy and reliability of control calculations. Furthermore, existing systems lack local data caching and breakpoint resumption mechanisms when communication networks are interrupted, making it difficult to guarantee the integrity of critical historical data.

[0004] Furthermore, existing scheduling algorithms have significant limitations. Most schemes only perform short-term load estimation independently, failing to integrate load forecasting, hydraulic balance regulation of the pipeline network, and coordinated allocation of multiple heat sources. This makes it impossible to simultaneously consider pipeline operational safety, user heating comfort, and optimal overall energy consumption. Simultaneously, their control processes are mostly open-loop, single-calculation models, lacking a feedback mechanism for iteratively correcting the scheduling model based on actual control effects after adjustments to operating conditions. This results in a lag in control strategies, hindering continuous, dynamic, and adaptive scheduling. In conclusion, constructing a dynamic heating scheduling scheme capable of comprehensive perception, intelligent decision-making, precise execution, and closed-loop optimization has become a pressing technical challenge in this field. Summary of the Invention

[0005] The purpose of this invention is to solve the problems of imperfect data processing for heating scheduling, lack of linkage among the three types of scheduling models, and absence of a closed-loop adaptive control mechanism in the existing technology, and to provide a dynamic scheduling method and system for heating operation based on the Internet of Things.

[0006] To achieve the above objectives, the present invention employs the following technical solution: The present invention proposes a dynamic scheduling method for heating operation based on the Internet of Things, comprising the following steps: Obtain multi-source raw operating data of the heating system, preprocess the raw operating data to obtain standardized heating time series data; Based on standardized heating time series data, a load prediction model is used to obtain the heat load prediction results for a preset period. Combining the heat load prediction results with real-time hydraulic conditions, the target control parameters of each node are calculated through a hydraulic balance optimization model. Then, based on the operating efficiency of each heat source, the target output allocation results of each heat source are obtained through a heat source scheduling optimization model. A heating control instruction set is generated based on the target control parameters and the target output allocation results of the heat source. The heating conditions are adjusted according to the control instruction set to achieve dynamic scheduling of heating operation.

[0007] Preferably, the multi-source raw operating data of the heating system is collected through Internet of Things (IoT) sensors deployed at various nodes of the heating system; The nodes include heat source outlets, heat exchange stations, pipeline branch nodes, and user terminals; The multi-source raw operating data of the heating system includes pipeline operating parameters, equipment operating status, outdoor environmental weather, and indoor user room temperature; Preferably, the preprocessing of the raw operating data specifically includes: The raw operating data is cleaned to remove jump values ​​and dead values ​​caused by sensor failures; the cleaned data is verified by using the physical relationships between various parameters in the heating system to identify and mark distorted data; when a network interruption is detected, the collected data is cached locally at the edge gateway and resumed after the network is restored.

[0008] Preferably, the load forecasting model is as follows: The model uses a long short-term memory network or an XGBoost model to output short-term heat load forecasts for 24 to 72 hours. The input features of the load forecast model include historical heat load data, weather forecast parameters, and date type features.

[0009] Preferably, the hydraulic balance optimization model calculates the target control parameters for each node, specifically as follows: With the constraints of pipeline pressure safety and user room temperature balance, the optimal opening degree of the regulating valves of each heat exchange station and pipeline is solved.

[0010] Preferably, the step of obtaining the target output allocation result of each heat source based on the operating efficiency of each heat source specifically involves: With the goal of minimizing the total system operating cost, and taking the heat load forecast results, the operating efficiency curves of each heat source, and energy prices as inputs, linear programming or genetic algorithms are used to calculate the optimal output allocation combination of each heat source within a preset time period.

[0011] Preferably, after adjusting the heating conditions according to the control command set, a closed-loop correction step is also included, specifically: The adjusted operating data of the heating system is re-collected, and the adjusted operating data is compared with the expected control target. Based on the comparison results, the model parameters of the load prediction model or hydraulic balance optimization model are corrected, and the corrected model parameters are used in the next round of scheduling.

[0012] Preferably, the implementation of dynamic scheduling of heating operation specifically includes: After the operating conditions are adjusted, the system operation data is collected again, the deviation between the measured data and the expected control is compared, the load prediction or hydraulic balance optimization model is corrected, and all steps are executed cyclically to form adaptive closed-loop control. The calculation involves determining the deviation between the actual operating parameters after adjustment and the expected control target. If the deviation exceeds the preset range, a self-learning mechanism is triggered to adjust the internal parameters of the load prediction model or the hydraulic balance optimization model.

[0013] This invention proposes a dynamic scheduling system for heating operation based on the Internet of Things, comprising: The data preprocessing module is used to acquire multi-source raw operating data of the heating system, preprocess the raw operating data, and obtain standardized heating time series data. The data analysis and calculation module is used to obtain the heat load prediction results for a preset period based on standardized heating time series data and a load prediction model; combining the heat load prediction results with real-time hydraulic conditions, the module calculates the target control parameters of each node through a hydraulic balance optimization model; and then, based on the operating efficiency of each heat source, the module obtains the target output allocation results of each heat source through a heat source scheduling optimization model. The instruction issuing and control module is used to generate a heating control instruction set based on the target control parameters and the target output allocation results of the heat source, and to adjust the heating conditions according to the control instruction set to realize dynamic scheduling of heating operation.

[0014] A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of a dynamic scheduling method for heating operation based on the Internet of Things.

[0015] Compared with the prior art, the present invention has the following beneficial effects: This invention proposes an IoT-based dynamic scheduling method for heating operations. By collecting multi-source, multi-dimensional raw data on heating and performing standardized preprocessing, it overcomes the shortcomings of traditional systems that only collect network temperature and pressure data, missing equipment data, meteorological data, and user room temperature data. It integrates three models—load forecasting, hydraulic balance, and heat source scheduling—into a coordinated operation, unlike existing solutions that only estimate heat load individually and lack multi-objective coordination. First, it predicts subsequent heating demand based on standardized data, then matches the real-time network hydraulic status to solve valve control parameters. Simultaneously, it considers the operational efficiency of each heat source to allocate output, simultaneously addressing network safety, balanced user heating, and energy-saving needs of heat sources, eliminating the biased control caused by a single algorithm. It integrates all model output parameters to generate a complete set of control commands and implements adjustments, abandoning the static scheduling mode that relies on historical experience to set fixed operating parameters. Instead, it relies on real-time updated field data to continuously perform calculations and adjust operating conditions, forming a data-driven dynamic control logic. This improves the practical engineering problems of traditional control lag, network temperature imbalance, and high overall energy consumption, resolving multiple shortcomings of existing scheduling schemes from the data source, algorithm calculation, and on-site execution.

[0016] This invention proposes a dynamic scheduling system for heating operation based on the Internet of Things (IoT). By dividing the system into a data preprocessing module, a data analysis and calculation module, and an instruction issuance and control module, the system adjusts heating conditions according to a set of control instructions, achieving dynamic scheduling of heating operation. The modular approach ensures that each module is independent, facilitating unified management of all modules. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the IoT-based dynamic scheduling method for heating operation according to the present invention.

[0019] Figure 2 This is a diagram of the IoT-based dynamic scheduling system for heating operation according to the present invention.

[0020] Figure 3 This is a schematic diagram of the structure of an electronic device according to the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0022] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0023] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0024] The present invention will now be described in further detail with reference to the accompanying drawings: Addressing the existing problems in the background technology, this invention first connects IoT technology with the theoretical foundation of heating network operation, and then details the construction of a data acquisition system, including optimized layout of acquisition points, multi-source heterogeneous data acquisition, and transmission assurance. Based on this, it focuses on inventing a dynamic scheduling model based on IoT data, encompassing data aggregation and visualization, core algorithms, and closed-loop control processes. This system can effectively improve the energy efficiency, safety, and user satisfaction of heating systems, providing a feasible technical path for the realization of smart heating.

[0025] Example 1 This invention proposes a dynamic scheduling method for heating operation based on the Internet of Things, such as... Figure 1 As shown, it includes the following steps: S1. Obtain multi-source raw operating data of the heating system, preprocess the raw operating data to obtain standardized heating time sequence data; The multi-source raw operating data of the heating system is collected through IoT sensors deployed at each node of the heating system; The nodes include heat source outlets, heat exchange stations, pipeline branch nodes, and user terminals; The multi-source raw operating data of the heating system includes pipeline operating parameters, equipment operating status, outdoor environmental weather, and indoor user room temperature.

[0026] The preprocessing of the raw operating data specifically includes: The raw operating data is cleaned to remove jump values ​​and dead values ​​caused by sensor failures; the cleaned data is verified by using the physical relationships between various parameters in the heating system to identify and mark distorted data; when a network interruption is detected, the collected data is cached locally at the edge gateway and resumed after the network is restored.

[0027] S2. Based on standardized heating time series data, the load prediction model is used to obtain the heat load prediction results for the preset time period; combined with the heat load prediction results and real-time hydraulic conditions, the target control parameters of each node are calculated through the hydraulic balance optimization model, and then the target output allocation results of each heat source are obtained through the heat source scheduling optimization model based on the operating efficiency of each heat source. The load forecasting model is specifically as follows: The model uses a long short-term memory network or an XGBoost model to output short-term heat load forecasts for 24 to 72 hours. The input features of the load forecast model include historical heat load data, weather forecast parameters, and date type features.

[0028] The hydraulic balance optimization model calculates the target control parameters for each node, specifically as follows: With the constraints of pipeline pressure safety and user room temperature balance, the optimal opening degree of the regulating valves of each heat exchange station and pipeline is solved.

[0029] The result of allocating the target output of each heat source based on the operating efficiency of each heat source is as follows: With the goal of minimizing the total system operating cost, and taking the heat load forecast results, the operating efficiency curves of each heat source, and energy prices as inputs, linear programming or genetic algorithms are used to calculate the optimal output allocation combination of each heat source within a preset time period.

[0030] S3. Generate a heating control command set based on the target control parameters and the target output allocation results of the heat source, and adjust the heating conditions according to the control command set to realize dynamic scheduling of heating operation.

[0031] After adjusting the heating conditions according to the control command set, a closed-loop correction step is also included, specifically: The adjusted operating data of the heating system is re-collected, and the adjusted operating data is compared with the expected control target. Based on the comparison results, the model parameters of the load prediction model or hydraulic balance optimization model are corrected, and the corrected model parameters are used in the next round of scheduling.

[0032] The implementation of dynamic scheduling of heating operation specifically includes: After the operating conditions are adjusted, the system operation data is collected again, the deviation between the measured data and the expected control is compared, the load prediction or hydraulic balance optimization model is corrected, and all steps are executed cyclically to form adaptive closed-loop control. The calculation involves determining the deviation between the actual operating parameters after adjustment and the expected control target. If the deviation exceeds the preset range, a self-learning mechanism is triggered to adjust the internal parameters of the load prediction model or the hydraulic balance optimization model.

[0033] This invention is built upon a four-layer IoT architecture and is implemented around the three-step scheduling process described in the claims. It incorporates core improvements such as simultaneous multi-source data processing, linkage of three scheduling models, and closed-loop iterative control. It corrects inconsistencies and overly broad descriptions in the original text that did not match the claims. Each module and step corresponds to the technical features defined in the claims, as detailed below: 1. Internet of Things (IoT) Technology Architecture The IoT system of this invention is divided into four layers: the sensing layer, the network layer, the platform layer, and the application layer. The functions of each layer conform to the complete process of data acquisition, preprocessing, model calculation, and command control as described in the claims. The bottom sensing layer deploys temperature, pressure, flow, heat meters, vibration sensors, and indoor temperature acquisition terminals to collect multi-source raw operating data as defined in the claims. The network layer uses a hybrid transmission of NB-IoT, LoRa, 4G / 5G low-power wide-area wireless technology and fiber optic wired transmission to provide a channel for raw data transmission. The platform layer undertakes preprocessing work such as raw data storage, cleaning, logical verification, and breakpoint caching and resume transmission, outputs standardized heating time series data, and at the same time has built-in three types of models, namely load forecasting, hydraulic balance, and heat source scheduling, to complete intelligent calculations. The application layer integrates command issuance control, operating condition visualization, and fault early warning functions, executes scheduling commands and displays the pipeline network operation status, and ultimately realizes the dynamic closed-loop scheduling described in the claims.

[0034] 2. The core objective of adjusting the operation of the heating network The scheduling process of this invention is designed around three objectives, corresponding one-to-one with the computational logic of the three types of models in the claims: Ensuring stable hydraulic conditions means ensuring that the pressure at each node of the pipeline network is always within a safe range, thereby effectively avoiding potential risks such as system vaporization and water hammer, and providing sufficient available pressure head for heat transfer; Achieve thermal equilibrium: Based on multi-source collected user room temperature data, and with uniform room temperature across the entire network as a constraint, eliminate the thermal imbalance in the pipe network; Achieving on-demand heating and economical operation: combining load forecasting models to predict heating demand, and using heat source scheduling optimization models to allocate the output of each heat source, matching real-time supply and demand, reducing overall energy consumption, corresponding to the solution logic of all models in the second step of the claim.

[0035] 3. Optimization strategy for data collection point layout The layout of data collection points follows the principles of global coverage, highlighting key areas, and cost-effectiveness. These collection points are used to acquire the multi-source raw operational data described in the claims, and their deployment is divided into four categories: Heat source outlet location: Collect the total supply and return water temperature, pressure and flow rate as the input basis for the heat source scheduling model, and use it to calculate the total heat supply and evaluate the heat source operating efficiency; Location of heat exchange stations and relay pump stations: Monitor inlet and outlet parameters and the status of pumps, valves and equipment to provide equipment operating data for hydraulic balance calculations; Key nodes in the pipeline network: Pressure and temperature monitoring points must be set up at pipeline branches, the end of the most unfavorable user loop in hydraulic calculations, the highest point of geographical elevation, and pipe sections that are historically prone to failure. User-end point locations: Select typical users in different buildings, orientations, and floors to install room temperature data acquisition devices to supplement user-side load data and improve the dimensions of multi-source data.

[0036] This data is the ultimate basis for verifying the scheduling effect and realizing true on-demand heating.

[0037] 4. Content and Methods of Multi-Source Heterogeneous Data Acquisition To achieve an accurate depiction of the entire thermal system, the Internet of Things (IoT) system needs to collect massive amounts of data from multiple sources, exhibiting heterogeneity. This data can be categorized into the following main types based on its nature and function.

[0038] Operating parameters form the foundation of system monitoring and mainly consist of high-frequency time-series data. This includes supply and return water temperatures, pressures, and flow rates in the pipeline network, as well as calculated heat and instantaneous power. These data are collected in real time using standard industrial sensors installed on pipelines and equipment, directly reflecting the transmission and distribution of energy.

[0039] Equipment status data focuses on the operational status of key execution units within the system. The start / stop status, operating frequency, opening degree, and fault alarm signals of equipment such as pumps and valves constitute this type of status data. This data is crucial for determining whether the system is operating correctly according to instructions, for fault diagnosis, and for energy efficiency management.

[0040] Environmental and load data serve as important correlated variables, providing external basis for system optimization and scheduling. By accessing the meteorological API interface, accurate meteorological information such as outdoor temperature, wind speed, and solar radiation intensity can be obtained; at the same time, indoor temperature data collected from typical users' homes directly reflects the final heat load demand. Together, these two data constitute the input conditions for load forecasting and dynamic adjustment.

[0041] In addition, in order to improve the system's proactive safety warning capabilities, it is also necessary to introduce abnormal perception data [3]. This type of event data is usually generated discontinuously. For example, by using sound wave or vibration sensors to capture abnormal signals generated by pipeline leaks or partial blockages, early warning can be achieved before the fault expands, thus preventing problems before they occur.

[0042] 5. Data transmission and quality assurance mechanism To ensure reliable transmission and availability of massive amounts of data at higher layers, a hybrid LPWAN + local aggregation solution is adopted: NB-IoT and other wide-area low-power transmission methods are used for nodes in the field without mains power; while industrial Ethernet or LoRa self-organizing networks are used for high-speed aggregation in densely populated areas of heat exchange stations / pump stations, taking into account coverage, power consumption and speed.

[0043] The complete preprocessing workflow consists of three steps, which are the preprocessing methods defined in the claims: Data cleaning: Automatically removes abnormal and dirty data such as jump values ​​and constant dead values ​​caused by sensor malfunctions; Logical verification: Based on the physical formulas of heat, flow rate, and temperature difference, the data is verified for logical consistency, and distorted data is eliminated; Edge caching and breakpoint resume: The edge gateway caches data locally, retains data when the network is interrupted, and automatically resumes transmission after the link is restored, ultimately generating standardized heating time series data with uniform format and reliable values ​​for subsequent model calculations.

[0044] 6. Data aggregation and operational status visualization After massive amounts of data are aggregated to the cloud platform, a digital twin of the heating network, which is mapped in real time to the physical pipeline network, can be constructed by integrating Geographic Information System (GIS) maps or 3D Building Information Modeling (BIM). This digital twin becomes the core cockpit for system operation, transforming abstract physical parameters into intuitive visual information and providing a solid foundation for operation and maintenance decisions.

[0045] In this visualized environment, maintenance personnel can achieve true global awareness. The real-time temperature and pressure field distribution of the entire pipeline network can be clearly presented on a digital map using color gradients or contour lines, allowing operators to grasp the overall thermal and hydraulic conditions at a glance and quickly identify areas of overheating, undercooling, or abnormal pressure.

[0046] The system also features proactive anomaly warning capabilities. The platform sets safety thresholds for key operating parameters. Once the monitored data exceeds the limit, the corresponding device or pipe section will immediately change color in the visualization interface (e.g., from green to red or orange), and automatically trigger audible and visual alarms and push notifications. This intuitive warning mechanism allows faults to be detected and handled promptly in their early stages.

[0047] Furthermore, the platform's powerful data storage and processing capabilities support the tracing of operational data for any historical time period. Operations and maintenance personnel can easily retrieve and compare historical data curves under different dates and operating conditions. This in-depth analysis provides a reliable basis for diagnosing hidden system defects, evaluating the effectiveness of control measures, and further optimizing operational strategies.

[0048] 7. Dynamic Scheduling Core Model and Algorithm The intelligence of dynamic scheduling relies on a series of precise mathematical models and optimization algorithms. These models transform massive amounts of data into scientific decision-making basis, driving the system to achieve a leap from perception to optimization.

[0049] First, accurate short-term heat load forecasting is a crucial forward-looking element of the entire scheduling system. The model integrates historical load data, refined meteorological information, and date characteristics, using LSTM / XGBoost to predict 24-hour heat loads. 72-hour heat load, with advance scheduling of heat source start-up, shutdown, and output.

[0050] Based on this, the hydraulic balance optimization model is dedicated to solving the spatial equilibrium problem within the pipeline network. With the goal of consistent inlet pressure difference or sufficient pressure at the most unfavorable point, the hydraulic model back-calculates the optimal opening degree of each valve, and completes automatic balancing of the entire network with one click.

[0051] For complex systems containing multiple heat sources, heat source scheduling and economic operation models seek optimal solutions from a global perspective. This model aims to minimize the total system operating cost. It comprehensively considers factors such as short-term load forecasts, the different operating efficiency curves of each heat source, and fuel or electricity costs. Through optimization methods such as linear programming or genetic algorithms, it calculates the optimal power allocation combination among heat sources within a specific time period, thereby achieving economical operation at the system level.

[0052] 8. Closed-loop control process of dynamic scheduling system Dynamic scheduling is not a one-time instruction, but a continuous, self-optimizing closed-loop process. Its core process can be summarized as five organic links: perception, analysis, decision-making, execution, and feedback.

[0053] The entire process begins with comprehensive and accurate sensing. The Internet of Things (IoT) system acts as the system's sensory nerves, continuously collecting real-time operational data and indoor temperature from heat sources, pipe networks, heat exchange stations, and user terminals, providing a real and comprehensive data foundation for subsequent intelligent decision-making.

[0054] During the analysis phase, the data aggregated on the platform is given insights. The platform layer invokes core models such as short-term load forecasting, hydraulic optimization, and economic dispatching to perform in-depth calculations and analyses on massive amounts of data, thereby generating optimal control strategies. Specific outputs include the setpoint of the heat source's water supply temperature, the operating frequency of the water pumps, and the target opening degree of each regulating valve.

[0055] Based on the analysis results, the system proceeds to the decision-making stage. For both safety and reliability considerations, the generated control strategy can be configured with two execution modes: one is fully automatic execution by the system to achieve efficient response; the other is pushed to the dispatch center for manual issuance after confirmation by professionals. This flexible design adapts to the safety level requirements of different control scenarios.

[0056] Once a decision is made, it is implemented in the physical system through the execution process. Control commands are sent to actuators such as frequency converters and electric regulating valves installed on-site via reliable network channels, driving the equipment to complete the actual actions, thereby translating the optimization strategies of the digital world into precise adjustments in the physical world.

[0057] Ultimately, a closed loop is formed through feedback. The system immediately collects the adjusted operational data for the next round and compares it with the expected targets to evaluate the control effect. If the effect does not meet expectations, the system will activate a self-learning mechanism to fine-tune the model parameters and immediately start the next optimization cycle. This process repeats continuously, ultimately driving the entire heating system to achieve continuous and lean operation.

[0058] Example 2 This invention proposes a dynamic scheduling system for heating operation based on the Internet of Things, such as... Figure 2 As shown, it includes: The data preprocessing module is used to acquire multi-source raw operating data of the heating system, preprocess the raw operating data, and obtain standardized heating time series data. The data analysis and calculation module is used to obtain the heat load prediction results for a preset period based on standardized heating time series data and a load prediction model; combining the heat load prediction results with real-time hydraulic conditions, the module calculates the target control parameters of each node through a hydraulic balance optimization model; and then, based on the operating efficiency of each heat source, the module obtains the target output allocation results of each heat source through a heat source scheduling optimization model. The instruction issuing and control module is used to generate a heating control instruction set based on the target control parameters and the target output allocation results of the heat source, and to adjust the heating conditions according to the control instruction set to realize dynamic scheduling of heating operation.

[0059] Example 3 Please see Figure 3 As shown, the present invention also provides an electronic device 100 for a dynamic scheduling method of heating operation based on the Internet of Things; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and capable of running on the at least one processor 102, and at least one communication bus 104.

[0060] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the IoT-based dynamic scheduling method for heating operation described in Embodiment 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0061] The at least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor. The processor 102 is the control center of the electronic device 100, connecting various parts of the electronic device 100 via various interfaces and lines.

[0062] The memory 101 in the electronic device 100 stores multiple instructions to implement a dynamic scheduling method for heating operation based on the Internet of Things, and the processor 102 can execute the multiple instructions to achieve the following: Obtain multi-source raw operating data of the heating system, preprocess the raw operating data to obtain standardized heating time series data; Based on standardized heating time series data, a load prediction model is used to obtain the heat load prediction results for a preset period. Combining the heat load prediction results with real-time hydraulic conditions, the target control parameters of each node are calculated through a hydraulic balance optimization model. Then, based on the operating efficiency of each heat source, the target output allocation results of each heat source are obtained through a heat source scheduling optimization model. A heating control instruction set is generated based on the target control parameters and the target output allocation results of the heat source. The heating conditions are adjusted according to the control instruction set to achieve dynamic scheduling of heating operation.

[0063] Example 4 If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0064] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0065] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0066] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0067] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A dynamic scheduling method for heating operation based on the Internet of Things, characterized in that, Includes the following steps: Obtain multi-source raw operating data of the heating system, preprocess the raw operating data to obtain standardized heating time series data; Based on standardized heating time series data, the heat load prediction results for a preset time period are obtained by using a load prediction model. Combining the heat load forecast results with real-time hydraulic conditions, the target control parameters of each node are calculated through the hydraulic balance optimization model. Then, based on the operating efficiency of each heat source, the target output allocation results of each heat source are obtained through the heat source scheduling optimization model. A heating control instruction set is generated based on the target control parameters and the target output allocation results of the heat source. The heating conditions are adjusted according to the control instruction set to achieve dynamic scheduling of heating operation.

2. The IoT-based dynamic scheduling method for heating operation according to claim 1, characterized in that, The multi-source raw operating data of the heating system is collected through IoT sensors deployed at each node of the heating system; The nodes include heat source outlets, heat exchange stations, pipeline branch nodes, and user terminals; The multi-source raw operating data of the heating system includes pipeline operating parameters, equipment operating status, outdoor environmental weather, and indoor user room temperature.

3. The IoT-based dynamic scheduling method for heating operation according to claim 1, characterized in that, The preprocessing of the raw operating data specifically includes: The raw operating data is cleaned to remove jump values ​​and dead values ​​caused by sensor failures; the cleaned data is verified by using the physical relationships between various parameters in the heating system to identify and mark distorted data. When a network interruption is detected, the collected data is cached locally at the edge gateway, and the interrupted transmission is resumed after the network is restored.

4. The dynamic scheduling method for heating operation based on the Internet of Things according to claim 1, characterized in that, The load forecasting model is specifically as follows: The model uses a long short-term memory network or an XGBoost model to output short-term heat load forecasts for 24 to 72 hours. The input features of the load forecast model include historical heat load data, weather forecast parameters, and date type features.

5. The IoT-based dynamic scheduling method for heating operation according to claim 1, characterized in that, The hydraulic balance optimization model calculates the target control parameters for each node, specifically as follows: With the constraints of pipeline pressure safety and user room temperature balance, the optimal opening degree of the regulating valves of each heat exchange station and pipeline is solved.

6. The dynamic scheduling method for heating operation based on the Internet of Things according to claim 1, characterized in that, The result of allocating the target output of each heat source based on the operating efficiency of each heat source is as follows: With the goal of minimizing the total system operating cost, and taking the heat load forecast results, the operating efficiency curves of each heat source, and energy prices as inputs, linear programming or genetic algorithms are used to calculate the optimal output allocation combination of each heat source within a preset time period.

7. The IoT-based dynamic scheduling method for heating operation according to claim 1, characterized in that, After adjusting the heating conditions according to the control command set, a closed-loop correction step is also included, specifically: The adjusted operating data of the heating system is re-collected, and the adjusted operating data is compared with the expected control target. Based on the comparison results, the model parameters of the load prediction model or hydraulic balance optimization model are corrected, and the corrected model parameters are used in the next round of scheduling.

8. The dynamic scheduling method for heating operation based on the Internet of Things according to claim 1, characterized in that, The implementation of dynamic scheduling of heating operation specifically includes: After the operating conditions are adjusted, the system operation data is collected again, the deviation between the measured data and the expected control is compared, the load prediction or hydraulic balance optimization model is corrected, and all steps are executed cyclically to form adaptive closed-loop control. The calculation involves determining the deviation between the actual operating parameters after adjustment and the expected control target. If the deviation exceeds the preset range, a self-learning mechanism is triggered to adjust the internal parameters of the load prediction model or the hydraulic balance optimization model.

9. A dynamic scheduling system for heating operation based on the Internet of Things, characterized in that, include: The data preprocessing module is used to acquire multi-source raw operating data of the heating system, preprocess the raw operating data, and obtain standardized heating time series data. The data analysis and calculation module is used to obtain the heat load prediction results for a preset period based on standardized heating time series data and a load prediction model; combining the heat load prediction results with real-time hydraulic conditions, the module calculates the target control parameters of each node through a hydraulic balance optimization model; and then, based on the operating efficiency of each heat source, the module obtains the target output allocation results of each heat source through a heat source scheduling optimization model. The instruction issuing and control module is used to generate a heating control instruction set based on the target control parameters and the target output allocation results of the heat source, and to adjust the heating conditions according to the control instruction set to realize dynamic scheduling of heating operation.

10. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the IoT-based dynamic scheduling method for heating operation as described in any one of claims 1 to 8.

Images