Heat supply resource distribution method and system based on gas heat supply global data analysis

Abstract

The invention provides a heat supply resource allocation method and system based on fuel gas heat supply global data analysis, and relates to the technical field of intelligent heat supply. A primary heat supply network and a secondary heat supply network in a heat supply global are determined, a first gating unit and a second gating unit are introduced, and a demand prediction model is constructed; and performing data validity and heat supply demand decision on the input data set, determining demand prediction data, performing heat supply resource allocation under the primary heat supply network and the secondary heat supply network by taking pipeline minimization heat loss as a constraint, and determining a resource allocation strategy, thereby solving the problem of scene variability in the prior art, and improving the resource allocation efficiency. According to the method, the technical problems that the precision of supply and demand prediction is insufficient, and the precision of heat supply resource allocation and the scene integrating degree are insufficient due to error superposition under complex staggering of heat supply networks are solved, and accurate supply and demand prediction and reasonable resource allocation in variable scenes are achieved by optimizing the demand prediction and resource allocation process.

Description

Technical Field

[0001] The present application relates to the field of smart heating technology, and specifically to a heating resource allocation method and system based on global data analysis of gas heating. Background Art

[0002] With the acceleration of urbanization, the demand for heating is growing. With the introduction of artificial intelligence, the multiple challenges of traditional heating systems such as low energy efficiency, waste of resources and environmental pollution, which often rely on fixed resource allocation strategies and lack flexibility and real-time performance, have been solved to a certain extent, resulting in heat being unable to effectively meet the changing demand in different regions. At the same time, new challenges have been introduced.

[0003] This includes how to effectively integrate multi-dimensional data, process information flows in real time, and quickly respond and adjust to dynamically changing demand situations. In addition, climate change and external environmental factors have an increasingly significant impact on heating demand, making it difficult to accurately predict and allocate resources, resulting in heat losses and reduced user satisfaction.

[0004] In summary, the existing technology still has certain technical limitations. The variability of the scenarios makes the prediction accuracy of supply and demand insufficient. In addition, the superposition of errors under the complex interweaving of the heating network leads to insufficient accuracy and scenario fit in the allocation of heating resources. Summary of the invention

[0005] The present application provides a heating resource allocation method and system based on global data analysis of gas heating, which is used to solve the technical problems that the variability of scenarios existing in the prior art leads to insufficient accuracy in forecasting supply and demand, and the error superposition under the complex interweaving of the heating network, resulting in insufficient accuracy and scenario fit of heating resource allocation.

[0006] In view of the above problems, the present application provides a heating resource allocation method and system based on global data analysis of gas heating.

[0007] In a first aspect, the present application provides a heating resource allocation method based on global data analysis of gas heating, the method comprising: Determine the primary heat network and the secondary heat network under the whole heat supply area, wherein the primary heat network is from the gas facility side to the heat power station side, and the secondary heat network is from the heat power station side to the demand side; A first gating unit and a second gating unit are introduced to construct a demand forecasting model, wherein the first gating unit is used to control the flow of reset information at the previous moment, and the second gating unit is used to control the flow of transmission information at the previous moment; Acquire an input data set, perform data validation and heating demand decision-making in combination with the demand forecasting model, and determine demand forecasting data, wherein the input data set includes real-time heating data, preset time zone heating data, and external factors; Based on the demand forecast data, heating resources are allocated under the primary heating network and the secondary heating network with the pipeline minimization heat loss as a constraint, and a resource allocation strategy is determined.

[0008] In a second aspect, the present application provides a heating resource allocation system based on global data analysis of gas heating, the system comprising: A heat network determination module, which is used to determine the primary heat network and the secondary heat network under the entire heating area, wherein the primary heat network is from the gas facility side to the heat station side, and the secondary heat network is from the heat station side to the demand side; A model building module, the model building module is used to introduce a first gating unit and a second gating unit to build a demand forecasting model, wherein the first gating unit is used to control the flow of reset information at the previous moment, and the second gating unit is used to control the flow of transmission information at the previous moment; A demand forecasting module, the demand forecasting module is used to obtain an input data set, perform data validation and heating demand decision-making in combination with the demand forecasting model, and determine demand forecasting data, wherein the input data set includes real-time heating data, preset time zone heating data and external factors; A resource allocation module is used to allocate heating resources between the primary heating network and the secondary heating network based on the demand forecast data and with the pipeline minimizing heat loss as a constraint, and to determine a resource allocation strategy.

[0009] In a third aspect, an electronic device comprises: a processor, wherein the processor is coupled to a memory, wherein the memory is used to store a program, and when the program is executed by the processor, the system executes the steps of the method described in the first aspect.

[0010] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored on the storage medium, and when the computer program is executed by a processor, the method steps described in the first aspect are implemented.

[0011] One or more technical solutions provided in this application have at least the following technical effects or advantages: The embodiment of the present application provides a heating resource allocation method based on gas heating global data analysis, determines the primary heating network and the secondary heating network under the entire heating domain, introduces the first gating unit and the second gating unit, builds a demand prediction model, performs data validation and heating demand decision on the input data set, determines the demand prediction data, and allocates heating resources under the primary heating network and the secondary heating network with the constraint of minimizing heat loss in the pipeline, and determines the resource allocation strategy, which solves the variability of scenarios existing in the prior art, resulting in insufficient accuracy in supply and demand prediction, and the technical problem that the accuracy of heating resource configuration and the degree of fit with the scenario are insufficient due to the superposition of errors under the complex interlacing of the heating network. By optimizing the demand prediction and resource allocation process, accurate supply and demand prediction and reasonable resource allocation in variable scenarios are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flow chart of a heating resource allocation method based on global data analysis of gas heating is provided for this application; Figure 2 A schematic diagram of the heating resource allocation system structure based on global data analysis of gas heating is provided for this application; Figure 3 A structural schematic diagram of an electronic device is provided for the present application. DETAILED DESCRIPTION

[0013] The present application provides a heating resource allocation method and system based on global data analysis of gas heating, determines the primary heating network and the secondary heating network under the global heating area, introduces the first gating unit and the second gating unit, builds a demand prediction model, performs data validation and heating demand decision-making on the input data set, determines the demand prediction data, and allocates heating resources under the primary heating network and the secondary heating network with the constraint of minimizing heat loss in the pipeline, and determines the resource allocation strategy, which is used to solve the variability of scenarios existing in the prior art, resulting in insufficient accuracy in the prediction of supply and demand, and the technical problem that the accuracy of heating resource configuration and the degree of fit with the scenarios are insufficient, and the errors are superimposed under the complex interlacing of the heating network.

[0014] Embodiment 1 like Figure 1 As shown, the present application provides a heating resource allocation method based on global data analysis of gas heating, the method comprising: S1: Determine the primary heat network and the secondary heat network under the whole heat supply area, wherein the primary heat network is from the gas facility side to the heat station side, and the secondary heat network is from the heat station side to the demand side; In modern heating systems, the key to ensuring efficient energy management is to rationally divide the primary and secondary heat networks. The primary heat network refers to the heat energy transmission network from the gas facility side (such as a natural gas power plant or boiler room) to the thermal power station side (such as a centralized heating station). The primary heat network is mainly responsible for transmitting the generated heat to the thermal power station in a high temperature and high pressure state, minimizing heat loss and ensuring the stability of heat energy during long-distance transmission.

[0015] Furthermore, once the heat reaches the thermal power station, it will enter the secondary heat network, which is the heating system from the thermal power station side to the final demand side (such as residential, commercial buildings, etc.). The secondary heat network is designed to distribute heat to each user at an appropriate temperature and pressure, ensuring timely response to user needs and flexibility in heating. At this time, the thermal power station converts the high-temperature hot water transmitted in the primary heat network into heating parameters suitable for various users, thereby achieving effective distribution of heat.

[0016] Due to the differences in the specific structures of the heat networks, the distribution of the pipes in the primary heat network is relatively gradual and mostly directly connected, while the distribution of the pipes in the secondary heat network is more complex and has many branches. By subdividing, it is convenient to perform adaptive resource allocation processing based on the specific distribution characteristics of the heat network in the future to improve the adaptability and ensure that the best heat energy distribution and loss minimization can be achieved under different load conditions. Through scientific resource allocation, the heating system can be optimized in a dynamic environment.

[0017] S2: Introduce a first gating unit and a second gating unit to construct a demand forecasting model, wherein the first gating unit is used to control the flow of reset information at the previous moment, and the second gating unit is used to control the flow of transmission information at the previous moment; Specifically, the main function of the first gating unit is to control the reset information flow of the previous moment, that is, in the demand forecasting process, it is responsible for screening and resetting those data inputs that are no longer relevant or important. When the heating demand environment changes, such as sudden fluctuations in user demand, the first gating unit can quickly identify and adjust the internal state of the model to suppress the impact of outdated information. This dynamic reset mechanism ensures that the model always makes predictions based on the latest and most relevant data, thereby improving the real-time and accuracy of the prediction.

[0018] The second gating unit focuses on controlling the flow of information transmitted at the previous moment, that is, selectively retaining important information for continued use in subsequent calculations. Specifically, when receiving new input data, the second gating unit will evaluate the importance of the information at the previous moment and decide which information should be passed to the next stage of prediction. In this way, the model can retain the effective information flow, thereby constructing a more accurate heating demand forecast.

[0019] Combined with these two gating units, the demand forecasting model can achieve efficient information management and efficient and accurate demand forecasting. In the embodiment of the present application, the gated loop algorithm principle, such as the long short-term memory network, is combined to realize the functions of these two units, which can enhance the model's ability to process time series data. Not only does it improve the prediction accuracy of heating demand, but it also reduces the computational burden caused by data redundancy, making the system more flexible and efficient when dealing with complex environmental changes, so that the heating demand forecasting model can be quickly adjusted in a dynamically changing environment, improving the accuracy of demand forecasting to optimize the configuration of thermal energy resources, and thus improving the efficiency of the entire heating system and user satisfaction.

[0020] Wherein, the construction of the demand forecasting model, step S2 of the present application further includes: Call historical heating data and perform data cleaning and normalization to divide and determine the first sample and the second sample that have a mapping relationship; based on the first sample, construct the first gating unit by training a first reset function, wherein the first reset function is generated based on the supervised learning of the first sample; based on the second sample, construct the second gating unit by training a second transfer function, wherein the second transfer function is generated based on the supervised learning of the second sample; and generate the demand forecasting model by running the first gating unit and the second gating unit in parallel.

[0021] In the embodiment of the present application, the historical heating data is a record of heating distribution for the entire heating area. Due to accuracy and data format issues of the data, in order to ensure the quality and consistency of the input data, the historical heating data is cleaned and normalized in advance.

[0022] Specifically, the main purpose of data cleaning is to remove incomplete, duplicate or noisy data to ensure that the model training is based on high-quality information. For example, processing missing values, deleting outliers or unifying data formats, etc. Normalization converts values ​​of different ranges to the same scale to avoid certain features from having an undue impact on model training.

[0023] Next, the cleaned and normalized data is divided into a first sample and a second sample. Specifically, for the first heating record, in the current scenario, the data is divided and mapped based on whether to reset the data or continue to use the data, and the first sample and the second sample are added respectively.

[0024] In an embodiment of the present application, the first reset function is used to determine the reset probability of new input data. As the sample training progresses, the system is generated based on sample supervised learning, that is, based on the relationship captured by the training samples.

[0025] The first sample is usually used to train the first reset function, focusing on capturing the instantaneous changes and dynamic characteristics of heating demand, while the second sample is used to train the second transfer function, aiming to capture the continuous characteristics and long-term dependencies in the time series.

[0026] Through the supervised learning method, the first reset function trained based on the first sample is used to construct the first gating unit, which is responsible for dynamically adjusting the state of the model and timely resetting the no longer relevant information. This reset mechanism helps to enhance the model's sensitivity to sudden changes in demand and improve the timeliness of prediction.

[0027] At the same time, the second transfer function based on the second sample training is used to construct the second gating unit, whose main function is to selectively retain important information to ensure that valid data is passed in the next prediction. The parallel operation of these two gating units enables the model to flexibly process time series data, thereby performing well in short-term and long-term demand forecasting.

[0028] Finally, by integrating the first gating unit and the second gating unit, the generated demand forecasting model has powerful data processing capabilities, which can achieve accurate data processing and forecasting when faced with complex and dynamic heating demands.

[0029] S3: obtaining an input data set, combining the demand forecasting model to perform data validation and heating demand decision-making, and determining demand forecasting data, wherein the input data set includes real-time heating data, preset time zone heating data and external factors; The input dataset mainly consists of three parts: real-time heating data, preset time zone heating data and external factors, which provides a comprehensive perspective for demand forecasting.

[0030] Real-time heating data refers to the current operating status of the heating system, including real-time heat demand of users, flow and temperature of the pipe network, etc. These data are collected in real time through monitoring sensors and data acquisition systems, and directly reflect the instantaneous load changes of the heating system, which can provide the latest input for the model.

[0031] The preset time zone heating data is the heating data for the preset time zone forward from the current moment. It has a time-regular heating data and usually includes the heating demand characteristics in different time periods. It helps the model understand the cyclical characteristics of heating demand and facilitates trend prediction based on previous heating demand.

[0032] External factors include various environmental factors that affect heating demand, such as weather conditions, holidays, economic activities, etc. For example, cold weather may lead to a surge in heat demand, while during holidays, demand in some areas may drop significantly. Incorporating these external factors into the model can help improve the accuracy of demand forecasting.

[0033] In the embodiment of the present application, based on the first gate control unit and the second gate control unit, the real-time heating data and the preset time zone heating data are reset and analyzed and transferred, and the external factors are combined to make predictions and determine the allocation standard on the demand side. This can effectively improve the accuracy and flexibility of demand prediction, so that the heating system can realize intelligent scheduling decisions in a dynamically changing environment, thereby improving overall energy efficiency and user satisfaction.

[0034] Wherein, the step S3 of determining demand forecast data in this application further includes: The input data set is transmitted to the demand prediction model; based on the first gating unit resetting the data and processing it, the second gating unit locates the transmitted data and retains it, the units interact and perform demand prediction, and determine the demand prediction data.

[0035] First, the input data set is transmitted to the demand forecasting model, and the first gating unit and the second gating unit in the model run in parallel. The role of the first gating unit is to locate and reset the data. Specifically, it evaluates the relevance of the current input data and dynamically resets unnecessary information based on the state of the model. For example, when new real-time heating data indicates a change in demand, the first gating unit can promptly suppress outdated data input, thereby ensuring that the model only makes predictions based on the latest and most relevant data.

[0036] At the same time, the second gating unit is responsible for locating and retaining important historical information. It selectively passes on information that is helpful for prediction by analyzing the data of the previous moment. This process ensures that the model can effectively use long-term dependent data to enhance the understanding of heating demand.

[0037] In an embodiment of the present application, under the model training mechanism, the reset probability is determined by the first reset function. Preferably, a first critical probability value can be preset, such as 70%, and the first gating unit will reset the data portion that is higher than the first critical probability value; the transfer probability is determined by the second transfer function. Similarly, a second critical probability value can be preset, and the second gating unit will transfer data that is higher than the second critical probability value.

[0038] Furthermore, based on the interaction between the first gating unit and the second gating unit, demand forecasting is performed under valid data to generate required demand forecasting data. Through parallel operation, the dynamic reset of the first gating unit and the information transfer of the second gating unit can be combined to form a comprehensive and accurate demand forecast.

[0039] Among them, step S3 of the present application also includes: the preset time zone heating data is determined by pushing forward the preset time zone with the real-time moment node; wherein, when the output of the first reset function is closer to 0, the feature neglect degree of the preset time zone heating data is higher; when the output of the second transfer function is closer to 1, the feature transfer degree of the preset time zone heating data is higher.

[0040] Specifically, the preset time zone heating data is used to analyze the real-time and effectiveness of the model output. In the real-time operation of the model, these data are based on the real-time node to push forward the preset time zone and perform auxiliary analysis to ensure that the data is referenceable. Specifically, when the output value of the first reset function approaches 0, it means that the feature neglect degree of the preset time zone heating data is higher, that is, the model tends to rely more on the current real-time data; on the contrary, when the output value of the second transfer function approaches 1, it means that the feature transfer degree of the preset time zone heating data is higher, that is, the model relies more on this part to form a prediction.

[0041] For example, when making long-term predictions, trend characteristics based on heating data in a preset time zone can effectively assist in subsequent trend predictions, with a lower reliance on real-time data; when making short-term predictions, it may be more dependent on real-time data, and through flexible processing, the accuracy of the prediction can be effectively improved.

[0042] The dynamic adjustment mechanism provided in the embodiment of the present application enables the model to flexibly adapt to the changing heating environment, thereby improving the accuracy and reliability of the prediction, allowing the system to still make accurate demand predictions under complex conditions, and providing a scientific basis for the effective allocation of heating resources.

[0043] S4: Based on the demand forecast data and with the minimization of heat loss in pipelines as a constraint, allocate heating resources in the primary heating network and the secondary heating network, and determine a resource allocation strategy.

[0044] Specifically, in the process of allocating heating resources and transmitting resources, the longer the distance, the greater the heat loss. The pipeline heat loss is constrained to minimize the heat loss to ensure the efficient operation of the heating system. Pipeline heat loss refers to the energy loss caused by heat dissipation when heat passes through the transmission pipeline. In order to reduce this loss, the heating system needs to optimize the allocation and scheduling process.

[0045] In the embodiment of the present application, the demand forecast data is the resource allocation standard on the demand side. Considering that the pipelines are complicated and have many intersections in the actual allocation and scheduling process, in order to determine the optimal allocation path and the supply amount of each supply end under the demand forecast data, the primary heat network and the secondary heat network are combined to make a recursive decision. That is, based on the actual pipeline distribution, the allocation amount of each pipeline node is calculated step by step from the demand side, and the pipeline transmission loss is considered at the same time to ensure the scenario fit of the resource allocation strategy.

[0046] Wherein, the heating resource allocation between the primary heating network and the secondary heating network is performed, and step S4 of the present application further includes: Identify the demand forecast data, execute resource allocation on the thermal power station side under the secondary thermal network, and determine the secondary thermal network strategy, wherein the pipeline bifurcation node is used as a decision-making basis; identify the thermal power station surplus, take the demand of the thermal power station as the target, and based on the proximity principle, perform resource allocation on the gas facility side under the primary thermal network, and determine the primary thermal network strategy; integrate the primary thermal network strategy with the secondary thermal network strategy to generate the resource allocation strategy.

[0047] In the process of allocating heating resources, the demand forecast data is identified and based on this, a targeted analysis of the distribution status of the secondary and primary heating networks is carried out.

[0048] Specifically, the secondary heat network, that is, from the heat station side to the demand side, has complex pipeline distribution and many branches, so the allocation process decision is made based on the multi-step recursion on the demand side. At this time, the pipeline bifurcation node is used as the decision-making basis. The pipeline bifurcation node is usually an important intersection of heat transmission, and the heat supply direction can be flexibly adjusted according to demand. For example, when the heat demand in a certain area suddenly increases, the system can respond quickly and ensure that the heat can be supplied to users with higher demand in a timely manner by adjusting the flow direction and distribution ratio of the pipeline. In this way, the system can ensure the efficient distribution of heat in the secondary heat network, minimize heat loss, and improve user satisfaction.

[0049] Furthermore, by identifying the primary heating network strategy, the required heat supply of each heating station is determined, and at the same time, it is determined whether the heating station has energy surplus, where the energy surplus here refers to the energy used for real-time supply in addition to the backup energy. Based on the required heat supply of each heating station and the corresponding energy surplus, the amount of energy that needs to be dispatched to the heating station is determined to ensure that its supply capacity matches user demand.

[0050] In this process, the demand of the thermal power station will be used as the target of resource allocation. Since the pipeline distribution of the first thermal network, that is, from the gas facility side to the thermal power station side, is relatively simple, with fewer branches and mostly direct connections, the transmission path is determined based on the principle of proximity to reduce the heat loss that may occur during the transmission process, and the allocation strategy from the gas facility side to the thermal power station side is determined as the second thermal network strategy.

[0051] Furthermore, the first heating network strategy and the second heating network strategy are integrated as the resource allocation strategy, so that the allocation of heating resources is optimal from demand to dynamic scheduling, maximizing the rationality of resource allocation and improving resource utilization.

[0052] Wherein, to execute the resource allocation at the heating station side under the secondary heating network, step S4 of the present application further includes: Determine a first proximal node, wherein the first proximal node is a distributed pipeline bifurcation node close to the demand side; traverse the demand forecast data to determine the node resource requirement of the first proximal node; determine multiple levels of proximal nodes under the primary heating network, perform iterative recursion based on the node resource requirement, and determine a pipeline allocation plan as the primary heating network strategy.

[0053] Specifically, in the resource allocation process of the secondary heating network, the first proximal node refers to the distributed pipeline bifurcation node close to the demand side, which is usually the direct source of the user's heating demand. By superimposing the needs of each bifurcation end user, the node resource demand of each first proximal node is determined. Preferably, the first proximal node corresponding to each user side is allocated based on the principle of proximity.

[0054] Furthermore, the distributed pipeline intersection node close to the first proximal node is used as the second proximal node, and the node resource requirements are determined by superposition. The above steps are repeated recursively to determine the node resource requirements under the multi-level proximal nodes until the resource requirements of each thermal power station are determined. In summary, the heating system can ensure efficient distribution of heat, minimize heat loss, and respond to user needs in a timely manner.

[0055] After determining the resource allocation strategy, step S4 of the present application further includes: The resource allocation strategy is identified, and a pipeline transfer distance between each allocation end is determined; based on the pipeline transfer distance, a heat loss is determined; and based on the heat loss, the resource allocation strategy is compensated.

[0056] First, identify the resource allocation strategy, which involves the resource flow of multi-level nodes between different thermal power stations and users, as well as the resource flow from the gas facility side to the thermal power station side, and determine a heating network view covering the entire area.

[0057] Further determine the pipeline transfer distance between each distribution end. This distance refers to the length of the pipeline that heat needs to pass through from one distribution end (such as a thermal power station or branch node) to another distribution end, because the longer the transfer distance, the greater the possibility of heat loss during the transfer process. Based on the pipeline transfer distance, further calculate the heat loss.

[0058] Among them, heat loss is mainly affected by many factors, including: pipe material: pipes of different materials have differences in heat conduction; pipe diameter: the larger the diameter, the more heat may flow, but it may also increase heat dissipation; temperature difference: the temperature difference inside and outside the pipe directly affects the dissipation of heat, etc.

[0059] Exemplarily, in combination with the heat conduction formula, based on parameters such as the transfer distance, pipeline characteristics and temperature differences, the heat loss of each section of the pipeline is obtained, and the resource allocation strategy is compensated to ensure that the end user can obtain the expected heat supply without being affected by the heat loss during the transportation process.

[0060] Exemplary compensation strategies may include: increasing heat supply: in resource allocation, appropriately increasing the heat supply of certain nodes to compensate for the heat lost during transportation; optimizing pipeline layout: optimizing pipeline sections with high heat loss, reducing their length or adding insulation measures to fundamentally reduce heat loss, etc. In summary, the heating system can ensure optimal configuration in the heat distribution process, minimize heat loss, and improve overall energy efficiency.

[0061] The heating resource allocation method based on gas heating global data analysis provided by this application has the following technical effects: 1. By dividing the heat network based on the gas facility side to the heat station side and the heat station side to the demand side, targeted allocation process decisions can be made according to the distribution characteristics of the heat network pipelines to improve the effectiveness and adaptability of the decision.

[0062] 2. Introduce the gated loop principle to reset no longer relevant information in a timely manner for dynamic scenarios and transmit relevant information to increase sensitivity to sudden changes in demand, improve the flexibility of analysis and the timeliness and accuracy of prediction, thereby improving the targetedness of predictions in short-term and long-term demand forecasts.

[0063] 3. Based on the pipeline distribution characteristics of the first heating network and the second heating network, targeted dynamic allocation decisions are made. At the same time, combined with the actual transmission heat loss, strategy compensation correction is carried out to improve the accuracy of the resource allocation strategy.

[0064] Embodiment 2 Based on the same inventive concept as the heating resource allocation method based on global data analysis of gas heating in the aforementioned embodiment, Figure 2 As shown, the present application provides a heating resource allocation system based on global data analysis of gas heating, the system comprising: A heat network determination module 11, the heat network determination module 11 is used to determine the primary heat network and the secondary heat network under the whole heat supply area, wherein the primary heat network is from the gas facility side to the heat power station side, and the secondary heat network is from the heat power station side to the demand side; A model building module 12, wherein the model building module 12 is used to introduce a first gating unit and a second gating unit to build a demand forecasting model, wherein the first gating unit is used to control the flow of reset information at the previous moment, and the second gating unit is used to control the flow of transmission information at the previous moment; The demand forecasting module 13 is used to obtain an input data set, perform data validation and heating demand decision-making in combination with the demand forecasting model, and determine demand forecasting data, wherein the input data set includes real-time heating data, preset time zone heating data and external factors; The resource allocation module 14 is used to allocate heating resources between the primary heating network and the secondary heating network based on the demand forecast data and with the pipeline minimization heat loss as a constraint, and determine a resource allocation strategy.

[0065] Among them, the model construction module 12 is also used to perform the following steps: calling historical heating data and performing data cleaning and normalization, dividing and determining the first sample and the second sample that have a mapping relationship; based on the first sample, by training the first reset function, constructing the first gating unit, wherein the first reset function is generated based on the supervised learning of the first sample; based on the second sample, by training the second transfer function, constructing the second gating unit, wherein the second transfer function is generated based on the supervised learning of the second sample; and parallelizing the first gating unit and the second gating unit to generate the demand forecasting model.

[0066] Among them, the demand prediction module 13 is also used to perform the following steps: transmitting the input data set to the demand prediction model; resetting and processing data based on the first gating unit, locating and transmitting data and retaining it by the second gating unit, the units interact and perform demand prediction, and determine the demand prediction data.

[0067] Among them, the preset time zone heating data is determined by the real-time moment node and the preset time zone is pushed forward; when the output of the first reset function is closer to 0, the feature neglect degree of the preset time zone heating data is higher; when the output of the second transfer function is closer to 1, the feature transfer degree of the preset time zone heating data is higher.

[0068] Among them, the resource allocation module 14 is also used to perform the following steps: identify the demand forecast data, execute the resource allocation on the thermal power station side under the secondary thermal network, and determine the secondary thermal network strategy, wherein the pipeline bifurcation node is used as the decision-making basis; identify the thermal power station surplus, take the demand of the thermal power station as the target, and based on the proximity principle, perform the resource allocation on the gas facility side under the primary thermal network, and determine the primary thermal network strategy; integrate the primary thermal network strategy with the secondary thermal network strategy to generate the resource allocation strategy.

[0069] Among them, the resource allocation module 14 is also used to perform the following steps: determine a first proximal node, wherein the first proximal node is a distributed pipeline bifurcation node close to the demand side; traverse the demand forecast data to determine the node resource requirements of the first proximal node; determine the multi-level proximal nodes under the primary heating network, iterate and recursively based on the node resource requirements, and determine the pipeline allocation plan as the primary heating network strategy.

[0070] The resource allocation module 14 is further used to perform the following steps: identifying the resource allocation strategy, determining the pipeline transfer distance between each allocation end; determining the heat loss based on the pipeline transfer distance; and compensating the resource allocation strategy based on the heat loss.

[0071] Embodiment 3 Based on the same inventive concept as the heating resource allocation method based on global data analysis of gas heating in the aforementioned embodiment, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method in embodiment one is implemented.

[0072] Through the above detailed description of the heating resource allocation method based on global data analysis of gas heating, those skilled in the art can clearly understand the heating resource allocation method and system based on global data analysis of gas heating in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0073] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0074] refer to Figure 3 An electronic device describing an embodiment of the present application. Based on the same inventive concept as the method for allocating heating resources based on global data analysis of gas heating in the aforementioned embodiment, the present application also provides an electronic device, comprising: a processor, the processor is coupled to a memory, the memory is used to store a program, and when the program is executed by the processor, the system executes the steps of the method described in embodiment one.

[0075] The electronic device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. The communication interface 303, the processor 302, and the memory 301 may be interconnected via the bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0076] The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0077] The communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), wired access network, etc.

[0078] The memory 301 may be a ROM or other type of static storage device that can store static information and instructions, a RAM or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via a bus architecture 304. The memory may also be integrated with the processor.

[0079] The memory 301 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the computer-executable instructions stored in the memory 301, thereby realizing the heating resource allocation method based on gas heating global data analysis provided in the above embodiment of the present application.

[0080] Although the present application has been described in conjunction with specific features and embodiments thereof, it will be apparent that various modifications and combinations thereof can be made without departing from the spirit and scope of the present application.

[0081] Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A heating resource allocation method based on global data analysis of gas heating, characterized in that: The method comprises: Determine the primary heat network and the secondary heat network under the whole heat supply area, wherein the primary heat network is from the gas facility side to the heat power station side, and the secondary heat network is from the heat power station side to the demand side; A first gating unit and a second gating unit are introduced to construct a demand forecasting model, wherein the first gating unit is used to control the flow of reset information at the previous moment, and the second gating unit is used to control the flow of transmission information at the previous moment; Acquire an input data set, perform data validation and heating demand decision-making in combination with the demand forecasting model, and determine demand forecasting data, wherein the input data set includes real-time heating data, preset time zone heating data, and external factors; Based on the demand forecast data, heating resources are allocated under the primary heating network and the secondary heating network with the pipeline minimization heat loss as a constraint, and a resource allocation strategy is determined.

2. The method for allocating heating resources based on global data analysis of gas heating according to claim 1, characterized in that: The constructing of the demand forecasting model comprises: Call historical heating data and perform data cleaning and normalization to divide and determine the first sample and the second sample that have a mapping relationship; Based on the first sample, constructing the first gating unit by training a first reset function, wherein the first reset function is generated based on supervised learning of the first sample; Based on the second sample, constructing the second gating unit by training a second transfer function, wherein the second transfer function is generated based on supervised learning of the second sample; The first gating unit and the second gating unit are operated in parallel to generate the demand prediction model.

3. The method for allocating heating resources based on global data analysis of gas heating according to claim 2, characterized in that: The determining of demand forecast data includes: transmitting the input data set to the demand forecasting model; Based on the first gating unit resetting data and processing, the second gating unit positioning transfer data and retaining it, the units interact and perform demand forecasting to determine the demand forecasting data.

4. The method for allocating heating resources based on global data analysis of gas heating according to claim 3, characterized in that: The preset time zone heating data is determined by pushing forward the preset time zone at the real-time time node; Among them, when the output of the first reset function is closer to 0, the characteristic neglect degree of the preset time zone heating data is higher; when the output of the second transfer function is closer to 1, the characteristic transfer degree of the preset time zone heating data is higher.

5. The method for allocating heating resources based on global data analysis of gas heating according to claim 1, characterized in that: Allocating heating resources between the primary heating network and the secondary heating network includes: Identify the demand forecast data, execute the resource allocation of the heating station side under the secondary heating network, and determine the secondary heating network strategy, wherein the pipeline bifurcation node is used as a decision basis; Identify the surplus of the heat station, take the demand of the heat station as the target, and allocate the resources of the gas facilities under the primary heat network based on the principle of proximity, and determine the primary heat network strategy; The primary heating network strategy and the secondary heating network strategy are integrated to generate the resource allocation strategy.

6. The method for allocating heating resources based on global data analysis of gas heating according to claim 5, characterized in that: Executing the resource allocation at the heating station side under the secondary heating network includes: Determine a first proximal node, wherein the first proximal node is a distributed pipeline bifurcation node close to the demand side; Traversing the demand forecast data to determine the node resource demand of the first proximal node; Determine the multi-level proximal nodes under the primary heating network, perform iterative recursion based on the node resource requirements, and determine a pipeline allocation plan as the primary heating network strategy.

7. The method for allocating heating resources based on global data analysis of gas heating according to claim 1, characterized in that: After determining the resource allocation strategy, include: Identify the resource allocation strategy and determine the pipeline transmission distance between each allocation end; Determining heat loss based on the pipeline transfer distance; Based on the heat loss, the resource allocation strategy is compensated.

8. A heating resource allocation system based on global data analysis of gas heating, characterized in that: The system is used to execute the heating resource allocation method based on gas heating global data analysis according to any one of claims 1 to 7, and the system comprises: A heat network determination module, which is used to determine the primary heat network and the secondary heat network under the entire heating area, wherein the primary heat network is from the gas facility side to the heat station side, and the secondary heat network is from the heat station side to the demand side; A model building module, the model building module is used to introduce a first gating unit and a second gating unit to build a demand forecasting model, wherein the first gating unit is used to control the flow of reset information at the previous moment, and the second gating unit is used to control the flow of transmission information at the previous moment; A demand forecasting module, the demand forecasting module is used to obtain an input data set, perform data validation and heating demand decision-making in combination with the demand forecasting model, and determine demand forecasting data, wherein the input data set includes real-time heating data, preset time zone heating data and external factors; A resource allocation module is used to allocate heating resources between the primary heating network and the secondary heating network based on the demand forecast data and with the pipeline minimizing heat loss as a constraint, and to determine a resource allocation strategy.

9. An electronic device, characterized in that: include: A processor, the processor is coupled to a memory, the memory is used to store a program, when the program is executed by the processor, the system is enabled to perform the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method steps according to any one of claims 1 to 7 are implemented.

Images