Planning design and optimized operation method for heat supply system with introduced long-distance heat source

Abstract

The invention discloses a planning design and optimized operation method for a heat supply system introducing a long-distance heat source, which comprises the following steps: acquiring basic data of the long-distance heat source to be introduced into the heat supply system in a heating season, and analyzing the operation mode change and dynamic characteristic change of a heat supply network of the existing heat supply system after the long-distance heat source is introduced; performing quantitative analysis and comparison on the plurality of heat supply network planning and design schemes in combination with external heat supply industry evolution data in a heat supply season to obtain an optimal heat supply network planning and design scheme; spatial characteristic data and time characteristic data related to the heat supply system are obtained, a space-time model of the heat supply system is established, and heat load prediction of each heat supply network area is carried out in combination with the heat load multi-dimensional influence data; and according to the heat load prediction value of each heat supply network area, combining the multi-dimensional heat supply loss, the heat source output characteristic and the heat supply network heat transmission and distribution characteristic of the long-distance heat source and the traditional heat source, and considering a heat source optimization operation target and a heat supply network regulation and control target, establishing a multi-time scale optimization operation model, and obtaining a corresponding optimization operation strategy.

Description

Technical Field

[0001] The present invention belongs to the field of smart heating technology, and specifically relates to a planning, design and optimized operation method of a heating system that introduces a long-distance heat source. Background Art

[0002] With the acceleration of urbanization and the continuous expansion of centralized heating areas, the production capacity of existing local heat sources has become insufficient to meet the rapidly growing heat load demand. In this context, the introduction of external long-distance heat sources has become a necessary means to provide large-scale and stable heat input. This not only alleviates the heating pressure of local heat sources but also improves the stability and reliability of heating system operation.

[0003] However, once external long-distance heat sources are introduced into the existing heating network, the entire heating system's pipe network layout, operating mode, and the coordinated heating mechanism of the heat sources will undergo dynamic changes. The current technical problems mainly include two aspects: First, how to measure the impact of the introduction of long-distance heat sources on the operation of the existing heating network during the non-heating season, and then scientifically guide the planning and design of the heating network to obtain reasonable planning and design plans for each heat source and pipeline network; Secondly, based on planning and design, long-distance heat sources and local heat sources form a multi-heat source joint heating mode during the heating season, which makes the operation and control mechanism of the heating system more complicated. It is necessary to comprehensively consider multi-dimensional influencing factors such as various heat sources, various heating network areas, and external time and space dynamic changes, how to effectively utilize the operating characteristics of each heat source, and explore multi-source complementary operation modes and equipment control strategies under different heating periods and different heating network area heat load demands.

[0004] In response to the above technical problems, it is urgent to design a new heating system planning and design and optimized operation method that introduces long-distance heat sources to solve the shortcomings of the existing technology. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing technology and provide a method for planning, designing and optimizing the operation of a heating system that introduces a long-distance heat source. The method can effectively analyze the impact of the introduction of the long-distance heat source on the operation of the heating network, quantitatively analyze and obtain the optimal planning and design scheme of the heating network, and based on the optimal planning scheme of the heating network, predict the heat load of each heating network area and establish a multi-time scale optimization operation model, thereby improving the collaborative efficiency of the heat source, reducing operating costs, reducing manual intervention and ensuring the quality of heating services.

[0006] In order to solve the above technical problems, the technical solution of the present invention is: The present invention provides a method for planning, designing and optimizing the operation of a heating system that introduces a long-distance heat source, which includes: S1. Obtain basic data on the long-distance heat source to be introduced into the heating system during the heating season, and analyze changes in the operation mode and dynamic characteristics of the existing heating system's heat network after the introduction of the long-distance heat source; S2. Based on the changes in the operation mode and dynamic characteristics of the heating network, and combined with the external heating industry evolution data during the heating season, quantitatively analyze and compare multiple preset heating network planning and design schemes to obtain a heating network planning and design scheme; S3. Acquire spatial and temporal characteristic data related to the heating system, establish a spatiotemporal model of the heating system, obtain the heating network structure and operating parameters that change over time, and then, combined with the multi-dimensional impact data of the heat load, perform heat load forecasts for each heating network area; S4. Based on the predicted heat load values ​​of each heating network area, combined with the multi-dimensional heat supply losses of long-distance heat sources and traditional heat sources, heat source output characteristics and heat transmission and distribution characteristics of the heating network, while considering the heat source optimization operation objectives and heating network regulation objectives, a multi-time scale optimization operation model is established to obtain the optimization operation strategies under different time scales.

[0007] Furthermore, the S1 specifically includes: Obtain basic data on the long-distance heat source to be introduced into the heating system during the heating season, including: heating capacity, outlet temperature, outlet pressure, pipeline length, diameter, insulation thickness, burial depth, terrain elevation along the route, heat load adjustment range, location of connection point with the existing heating network, and interface pipe diameter; Collect existing heating network data, including the topology of the heating network, the pressure and temperature of each node in the heating network, the flow rate of each pipe section, and the parameters of key equipment in the heating network; Based on the basic data of long-distance heat sources and the collected data of existing heating networks, a heating system simulation model is established to analyze the changes in the heating network zoning, heating network structure, pressure distribution changes at each node of the heating network, temperature distribution changes, flow distribution changes at each pipe section, and hydraulic stability of the existing heating system after the introduction of the long-distance heat source. In addition, the response time and fluctuation amplitude of the heating network pressure and temperature during the dynamic process of commissioning and exiting the long-distance heat source are evaluated.

[0008] Furthermore, the S2 specifically includes: Obtain data on the evolution of external heating services during the heating period, including data on the evolution of heating area, growth in heat users, energy price fluctuations, and new station commissioning during the planning period; Based on the external heating business evolution data during the heating period, the changes in heat load demand during the heating period are analyzed. At the same time, the heat supply and demand balance is analyzed by combining the heating capacity of long-distance heat sources and traditional heat sources; According to the changes in the operation mode and dynamic characteristics of the heat network after the introduction of long-distance heat sources, set the constraints for the safe and stable operation of each heat source and the heat network; Based on the results of heat supply and demand balance analysis, and the safe operation constraints of various heat sources and heat networks, various heat network planning and design schemes, including heat source combinations and pipe network layouts, are pre-set for different periods of the heating season. A multi-index comprehensive evaluation system is constructed, and a multi-criteria decision analysis method is used to quantitatively analyze and compare various heat network planning and design schemes to obtain the optimal planning and design scheme, guide the timing of the withdrawal and commissioning of long-distance heat sources and traditional heat sources, the preliminary output plan of each heat source, the layout of the pipeline direction, and the pipeline route design scheme.

[0009] Furthermore, the new station commissioning data includes heat user, network access area, heat use location, heating company, heat supply form, and heat use type; The multi-index comprehensive evaluation system includes technical indicators, economic indicators and environmental indicators.

[0010] Furthermore, in S3, establishing a spatiotemporal model of the heating system specifically includes: Acquire spatial characteristic data and temporal characteristic data related to the heating system; the spatial characteristic data represents the spatial coupling effects between heating networks and heating stations; the temporal characteristic data represents the temporal evolution of the operation and structure of the heating system's heat sources, heating networks, and heating stations; Using a first machine learning algorithm to train the spatial feature data to extract spatial features; Using a second machine learning algorithm to train the time feature data to extract time features; The extracted spatial and temporal features are integrated to establish a spatiotemporal model of the heating system.

[0011] Furthermore, in S3, the heat load forecasting of each heating network area specifically includes: The heating network structure and operating parameters of the heating system that change over time are obtained based on the spatiotemporal model of the heating system. The data are combined with meteorological data, building characteristic data of heat users in each heating network area, user behavior data, new station commissioning data, and historical heat load data to form a heat load impact data set for each heating network area. After preprocessing and feature extraction of the heat load impact data set of each heating network area, it is input into the hybrid learning algorithm for training and learning, and a heat load prediction model for each heating network area is established to predict the heat load of each heating network area at different times in the future.

[0012] Furthermore, the S4 specifically includes: Based on the next day's heat load forecast for each heating network region, combined with the multi-dimensional heating losses and heat source output characteristics of long-distance heat sources and traditional heat sources, and with the goal of minimizing operating costs and heat load supply and demand deviation, a day-ahead optimization scheduling model was established to obtain the load allocation strategy for long-distance heat sources and traditional heat sources at each time period on the day-ahead. Based on the predicted and measured daily heat load values ​​of each heating network area and the heat transmission and distribution characteristics of each heat source to each related heating network area, the operating parameters of long-distance heat sources and traditional heat sources are adjusted and corrected while ensuring the heat load demand of each heating network area. With the goal of minimizing the adjustment and correction cost and the fluctuation of heating network parameters, an intraday optimization scheduling model is established to obtain the operating guidance curves of long-distance heat sources and traditional heat sources at various time periods within the day. Based on the operating guidance curves of long-distance heat sources and traditional heat sources at different time periods during the day, combined with the preset control temperature targets of each heating network area, a real-time optimization control model is established to generate hourly valve parameter control strategies for each heating network area.

[0013] Furthermore, the multi-dimensional heating loss includes: heat loss caused by heat leakage in the heating network, water replenishment heat loss caused by water leakage in the heating network and excess heat loss in space; the excess heat loss in space refers to uneven heating loss between buildings in the heating network and uneven loss among users in the building.

[0014] Furthermore, the analysis of the heat transmission and distribution characteristics of each heat source to each associated heating network area includes: using the heat source temperature rise curve to calculate the transmission delay time from the temperature change of each heat source to the response of the corresponding thermal power station in each heating network area, and adjusting the operating parameters of each heat source in advance.

[0015] Furthermore, the heating system planning, design and optimized operation method also includes: analyzing the problems existing in the heating network and establishing corresponding heating network transformation strategies based on the heat loss caused by heat leakage in the heating network, the water replenishment heat loss caused by water leakage in the heating network and the excess heat loss in space.

[0016] The present invention adopts the above technical solution, which has at least the following beneficial effects: (1) The present invention obtains the basic data of the long-distance heat source to be introduced into the heating system during the heating season and analyzes the changes in the operation mode and dynamic characteristics of the existing heating network after the introduction of the long-distance heat source. It can clearly determine the synergistic matching degree between the long-distance heat source and the existing heating network, and identify the changes in the operation mode and dynamic characteristics of the heating network in advance, providing a basis for subsequent planning and control strategies. (2) The present invention quantitatively analyzes and compares a variety of pre-set heating network planning and design schemes based on changes in the operation mode and dynamic characteristics of the heating network, combined with external heating business evolution data during the heating season, to obtain the optimal heating network planning and design scheme; it can combine external heating business data to ensure that the planning scheme remains reasonable for a period of time in the future, and through comprehensive quantitative evaluation of multiple indicators, obtain the optimal planning and design scheme; (3) The present invention obtains spatial characteristic data and temporal characteristic data related to the heating system, establishes a spatiotemporal model of the heating system, obtains the heating network structure and operating parameters of the heating system that change over time, and then combines the multi-dimensional impact data of the heat load to predict the heat load of each heating network area. It can capture spatial coupling characteristics, optimize regional coordinated regulation, characterize the time evolution law, and adapt to dynamic operation scenarios, so that the heat load prediction results are more consistent with the physical laws and time dimension changes of the actual operation of the heating network, and improve the response capability to complex scenarios. (4) The present invention is based on the predicted value of the heat load of each heating network area, combined with the multi-dimensional heat loss of long-distance heat sources and traditional heat sources, the heat source output characteristics and the heat distribution characteristics of the heating network, and takes into account the heat source optimization operation objectives and the heating network control objectives. A multi-time scale optimization operation model is established to obtain the optimization operation strategy under different time scales; it can realize load distribution based on multi-dimensional data, fine-grained control to adapt to short-term load changes and hourly valve control to achieve precise heating, improve the collaborative efficiency of heat sources, reduce operating costs, reduce manual intervention and ensure the quality of heating services.

[0017] Other features and advantages will be described in the following description, and in part will become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0018] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 This is a flow chart of a method for planning, designing, and optimizing the operation of a heating system that introduces a long-distance heat source according to the present invention; Figure 2 Flowchart for the heat network planning and design of the present invention; Figure 3 Schematic diagram of the hierarchical structure of the multi-index comprehensive evaluation system of the present invention; Figure 4 A schematic diagram of the principle of establishing a spatiotemporal model of a heating system according to the present invention; Figure 5 A flow chart of establishing a multi-time scale optimization operation model for the present invention. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0022] like Figure 1 As shown, this embodiment provides a method for planning, designing, and optimizing the operation of a heating system that introduces a long-distance heat source, which includes: S1. Obtain basic data on the long-distance heat source to be introduced into the heating system during the heating season, and analyze changes in the operation mode and dynamic characteristics of the existing heating system's heat network after the introduction of the long-distance heat source; S2. Based on changes in the operation mode and dynamic characteristics of the heating network, and combined with the external heating industry evolution data during the heating season, quantitatively analyze and compare multiple preset heating network planning and design schemes to obtain the optimal heating network planning and design scheme; S3. Acquire spatial and temporal characteristic data related to the heating system, establish a spatiotemporal model of the heating system, obtain the heating network structure and operating parameters that change over time, and then, combined with the multi-dimensional impact data of the heat load, perform heat load forecasts for each heating network area; S4. Based on the predicted heat load values ​​of each heating network area, combined with the multi-dimensional heat supply losses of long-distance heat sources and traditional heat sources, heat source output characteristics and heat transmission and distribution characteristics of the heating network, while considering the heat source optimization operation objectives and heating network regulation objectives, a multi-time scale optimization operation model is established to obtain the optimization operation strategies under different time scales.

[0023] In this embodiment, the S1 specifically includes: Obtain basic data on the long-distance heat source to be introduced into the heating system during the heating season, including: heating capacity, outlet temperature, outlet pressure, pipeline length, diameter, insulation thickness, burial depth, terrain elevation along the route, heat load adjustment range, location of connection point with the existing heating network, and interface pipe diameter; Collect existing heating network data, including the topology of the heating network, the pressure and temperature of each node in the heating network, the flow rate of each pipe section, and the parameters of key equipment in the heating network; Based on the basic data of long-distance heat sources and the collected data of existing heating networks, a heating system simulation model is established to analyze the changes in the heating network zoning, heating network structure, pressure distribution changes at each node of the heating network, temperature distribution changes, flow distribution changes at each pipe section, and hydraulic stability of the existing heating system after the introduction of the long-distance heat source. In addition, the response time and fluctuation amplitude of the heating network pressure and temperature during the dynamic process of commissioning and exiting the long-distance heat source are evaluated.

[0024] In one specific embodiment of the present invention, with the increasing heat load demand in a certain city, the existing traditional heat sources are unable to meet the demand. This is especially true during cold weather when the network heats up, resulting in a significant shortfall between supply and demand. Therefore, an external heat source is required to be introduced and used in conjunction with the existing traditional heat source for heat supply. This external heat source is transported to the main urban area via a long-distance heat transmission network, where it is exchanged at a pressure isolation station before being supplied to the urban area. This long-distance heat transmission network is characterized by varying terrain, resulting in complex pipeline routing and operating conditions.

[0025] In addition, the heating system also involves multiple gas boiler rooms; the entire heating system supplies heat to each heating network area based on external heat sources and gas boiler rooms. At the same time, the heating network areas are divided according to parameters such as the heating network pipeline structure layout and the location of the heating station, pressure isolation station, heat source location, and heating capacity of the heating system. The heating area and heat consumption of each heating network area are different.

[0026] When building a heating system simulation model, graphical configuration is used to establish the topological connection logic relationships between heat sources, pipeline networks, and heat exchange stations. Parameters are used to specifically describe the spatial location and structural information of equipment such as heat sources, boilers, pipelines, elbows, water pumps, and heat exchange stations. The heat network model is built based on the mechanism models for controlling heat sources, thermal power stations, boilers, valves, pipelines, buildings, and other components, as well as the actual layout of the heat network, ensuring structural consistency with the actual heat network. The simulation model can also simulate changes in supply and return water temperature, pressure, flow rate, specific friction resistance, and heat source parameters, as well as analyze the operational status of the pipeline network after the introduction of a long-distance heat source.

[0027] It should be noted that the pressure distribution changes: compare the pressure distribution of each node in the heating network before and after the introduction of the long-distance heat source, and evaluate whether there is a pressure over-limit or under-limit situation. For example, analyze whether the pressure of certain nodes exceeds the design pressure of the pipeline, or whether the pressure at certain user ends is lower than the minimum pressure to meet the heating demand. Flow distribution changes: analyze the flow distribution changes of each pipe section of the heating network after the introduction of the long-distance heat source, and judge whether it will cause hydraulic imbalance. The degree of hydraulic imbalance can be evaluated by calculating the flow ratio of each pipe section. Temperature distribution changes: compare the temperature distribution of each node in the heating network before and after the introduction of the long-distance heat source, and analyze the impact of temperature changes on the heating effect.

[0028] Hydraulic stability assessment: Calculate the damping ratio, critical flow rate, and other indicators of the heating network to assess the hydraulic stability of the heating network after the introduction of the long-distance heat source. If the damping ratio is less than 0.3, it indicates that the heating network may be at risk of hydraulic oscillation and appropriate measures need to be taken to optimize it. Response time assessment: Evaluate the response time of the heating network pressure and temperature during dynamic processes such as the connection and switching of long-distance heat sources to determine whether it meets the requirements for safe system operation. The response time is generally required to be no more than 10 minutes. Fluctuation amplitude analysis: Analyze the fluctuation amplitude of pressure and temperature during dynamic processes to assess whether it will have adverse effects on equipment and users. For example, the pressure fluctuation amplitude should not exceed 20% of the pipeline design pressure.

[0029] like Figure 2 As shown, in this embodiment, S2 specifically includes: Obtaining external heating business evolution data during the heating period, including heating area evolution data, heat user growth data, energy price fluctuation data, and new station commissioning data during the planning period; the new station commissioning data includes heat users, network area, heat use locations, heating companies, heat supply forms, and heat use types; Based on the external heating business evolution data during the heating period, the changes in heat load demand during the heating period are analyzed. At the same time, the heat supply and demand balance is analyzed by combining the heating capacity of long-distance heat sources and traditional heat sources; According to the changes in the operation mode and dynamic characteristics of the heat network after the introduction of long-distance heat sources, set the constraints for the safe and stable operation of each heat source and the heat network; Based on the results of heat supply and demand balance analysis, and the safe operation constraints of various heat sources and heat networks, various heat network planning and design schemes, including heat source combinations and pipe network layouts, are pre-set for different periods of the heating season. A multi-index comprehensive evaluation system is constructed, including technical indicators, economic indicators and environmental indicators, and a multi-criteria decision analysis method is used to quantitatively analyze and compare various heat network planning and design schemes to obtain the optimal planning and design scheme, guide the timing of the withdrawal and commissioning of long-distance heat sources and traditional heat sources, the preliminary output plan of each heat source, the layout of the pipeline direction, and the pipeline route design scheme.

[0030] Set constraints for safe and stable operation of each heat source and heat network, including: Upper limit of heating temperature of heat source equipment: The outlet temperature of the heat source equipment cannot exceed the design value, otherwise it may damage the equipment components and accelerate the aging of the pipeline; Operating temperature range of heat source equipment: During the operation of the equipment, the temperature of key internal components must be maintained within a reasonable range; Upper limit of pressure of heat source equipment: The outlet pressure of the heat source cannot exceed the tolerance range of the equipment and pipeline. Overpressure may cause serious accidents such as explosion; Lower limit of pressure of heat source equipment: Some heat source equipment cannot operate normally below a certain pressure; Maximum load of heat source equipment: The heating capacity of the heat source is limited and cannot exceed its rated heating load; Minimum load of heat source equipment: Some heat source equipment has a minimum stable operating load. Below this load, the equipment operation is unstable; The upper limit of the node pressure in the heating network: the pressure of each node in the heating network cannot exceed the pressure bearing capacity of the pipeline and equipment. Excessive pressure may cause the pipeline to rupture; the lower limit of the node pressure in the heating network: in order to ensure the normal circulation of the heating network and the heating effect at the user end, the pressure of each node must be higher than a certain value; the maximum flow rate of the heating network: the heating network pipeline has a maximum allowable flow rate limit. Exceeding this flow rate will increase the resistance of the pipeline network and may cause hydraulic imbalance; the flow distribution of the heating network: ensure that the flow distribution of each branch of the heating network is reasonable to avoid hydraulic imbalance such as overheating at the near end and overcooling at the far end; the upper limit of the water supply temperature of the heating network: if the water supply temperature of the heating network is too high, it may cause damage to the pipeline insulation layer and user-end equipment, and also waste energy; the lower limit of the return water temperature of the heating network: if the return water temperature is too low, it means that the heat is not fully utilized, which will reduce the heating efficiency; if the return water temperature is too high, it may affect the operation of the heat source equipment, so the return water temperature must be controlled within an appropriate range.

[0031] Construct a multi-indicator comprehensive evaluation system: technical indicators, economic indicators and environmental indicators; technical indicators include hydraulic stability, supply and demand balance, response speed and pipeline transportation efficiency; economic indicators include investment and construction costs, operating costs; environmental indicators include carbon emission intensity.

[0032] A multi-criteria decision analysis method is used to quantitatively analyze and compare various heating network planning and design schemes to obtain the optimal planning and design scheme. The specific implementation is the hierarchical analysis method, which includes: 1) If Figure 3 As shown in the figure, a multi-index comprehensive evaluation system hierarchy is established. Target layer: The ultimate goal is to "select the best heating network planning and design scheme"; Criteria layer: Technical indicators include hydraulic stability, supply and demand balance, response speed and pipeline network transmission efficiency; economic indicators include investment and construction costs, and operating costs; environmental indicators include carbon emission intensity; Scheme layer: different heating network planning and design schemes; 2) Quantitative calculation of indicators For each heat network planning and design scheme, calculate its index values ​​in technical, economic, environmental and social benefits, among which Represents the mth indicator value of the nth option, forming a decision matrix, which is expressed as: ; 3) Weight determination For k solutions, construct a judgment matrix , Represent the comparison result of the importance of scheme i relative to scheme j, and calculate the relative importance weight of each scheme in the scheme layer relative to the target layer; 4) After ranking the heating network planning and design schemes according to their relative importance weights, the optimal design scheme is selected.

[0033] like Figure 4 As shown, in this embodiment, in S3, establishing the spatiotemporal model of the heating system specifically includes: Acquire spatial characteristic data and temporal characteristic data related to the heating system; the spatial characteristic data represents the spatial coupling effects between heating networks and heating stations; the temporal characteristic data represents the temporal evolution of the operation and structure of the heating system's heat sources, heating networks, and heating stations; Using a first machine learning algorithm to train the spatial feature data to extract spatial features; Using a second machine learning algorithm to train the time feature data to extract time features; The extracted spatial and temporal features are integrated to establish a spatiotemporal model of the heating system.

[0034] In practical applications, due to the spatial coupling between heating network regions and heating stations, changes in the operating status of one network region can affect other structurally coupled heating network regions. Similarly, within a network region with multiple heating stations, adjusting the heat distribution of one station can affect the heat output of other stations. Furthermore, over time, weather changes, heating demand fluctuates, and the network structure can change due to external factors (such as abnormal fault information and the introduction of heat sources), requiring adaptive changes in the operation of heat sources, heating networks, and heating stations.

[0035] The spatial feature data is trained using a first machine learning algorithm to extract spatial features, including: 1) Algorithm selection: Graph neural network algorithms were selected. Because the spatial structure of the heating network and thermal power stations can be viewed as a graph (nodes represent heating network nodes or thermal power stations, and edges represent the connections between them), graph neural network algorithms are well suited to processing this topologically structured data and mining spatial coupling correlations. 2) Model Construction and Training: Organize the preprocessed spatial feature data into a graph-structured data format and input it into the selected algorithm model. Define an appropriate loss function and optimizer, train the model using the backpropagation algorithm, and adjust the model parameters to enable the model to learn the spatial coupling characteristics between the heating network and the heating stations. 3) Feature Extraction and Screening: After training is complete, learned and abstracted spatial feature vectors are extracted from the model. These feature vectors represent information such as the spatial coupling relationship between the heating network and heating stations, and the impact of spatial layout on operational status. Feature selection methods (such as variance selection and correlation analysis) can be further used to screen out representative spatial features that contribute significantly to the model, reducing feature dimensionality and improving model efficiency and generalization.

[0036] The time feature data is trained using a second machine learning algorithm to extract time features, including: 1) Algorithm selection: The recurrent neural network algorithm is suitable for processing time series data and can capture long-term dependencies in time series; 2) Model Construction and Training: Organize the preprocessed temporal feature data into a sequence in chronological order, dividing it into training, validation, and test sets. Construct a recurrent neural network algorithm model, setting appropriate hyperparameters such as the number of network layers and hidden units. Input the training data into the model, and update the model parameters using a stochastic gradient descent optimization algorithm by minimizing the loss function. This allows the model to learn the temporal evolution of the heating system's heat source, heating network, and heating station operations and structure. 3) Feature Extraction and Dimensionality Reduction: After training, time feature vectors are extracted from the algorithm model. These vectors contain information about the dynamic changes in the time series. To reduce feature dimensionality, dimensionality reduction methods such as principal component analysis and linear discriminant analysis can be used. While retaining key information, the number of features can be reduced, improving computational efficiency.

[0037] The process of establishing a spatiotemporal model includes: 1) Feature Fusion The extracted spatial feature vector and temporal feature vector are fused. A weighted fusion method can be used to assign different weights to the spatial and temporal features according to their importance, thus obtaining a comprehensive feature vector containing spatiotemporal information. 2) Model construction Select an appropriate model architecture: Select a spatiotemporal convolutional network that can process spatiotemporal feature data simultaneously and explore the interaction between spatial and temporal dimensions in the heating system; Model training and optimization: Using the fused spatiotemporal feature data as input, we define the corresponding objective function (the mean square error between the predicted and true values) and optimization algorithm (particle swarm optimization) to train the model. By continuously adjusting the model parameters, the model can accurately learn the spatiotemporal characteristics of the heating system, improving the model's prediction and analysis capabilities in both spatiotemporal and temporal dimensions. Model evaluation and validation: Evaluation metrics (such as root mean square error and mean absolute error) are used to measure model performance. Based on the evaluation results, the model is optimized to ensure good generalization and accurate reflection of the spatiotemporal characteristics of the heating system.

[0038] In this embodiment, in S3, the heat load forecasting of each heating network area specifically includes: The heating network structure and operating parameters of the heating system that change over time are obtained based on the spatiotemporal model of the heating system. The data are combined with meteorological data, building characteristic data of heat users in each heating network area, user behavior data, new station commissioning data, and historical heat load data to form a heat load impact data set for each heating network area. After preprocessing and feature extraction of the heat load impact data set of each heating network area, it is input into the hybrid learning algorithm for training and learning, and a heat load prediction model for each heating network area is established to predict the heat load of each heating network area at different times in the future.

[0039] In actual applications, a hybrid learning algorithm is used for training and learning. When establishing the heat load prediction model for each heat network area, the XGBoost extreme gradient boosting algorithm and the SVM support vector machine algorithm are used for training and learning respectively to obtain the first and second prediction results of the heat load. After setting the weights of the first and second prediction results according to the deviation range between the heat load prediction value and the true value, the final heat load prediction value is calculated based on the first and second prediction results of the heat load and the corresponding weights.

[0040] like Figure 5 As shown, in this embodiment, the S4 specifically includes: Based on the next day's heat load forecast for each heating network region, combined with the multi-dimensional heating losses and heat source output characteristics of long-distance heat sources and traditional heat sources, and with the goal of minimizing operating costs and heat load supply and demand deviation, a day-ahead optimization scheduling model was established to obtain the load allocation strategy for long-distance heat sources and traditional heat sources at each time period on the day-ahead. Based on the predicted and measured daily heat load values ​​of each heating network area and the heat transmission and distribution characteristics of each heat source to each related heating network area, the operating parameters of long-distance heat sources and traditional heat sources are adjusted and corrected while ensuring the heat load demand of each heating network area. With the goal of minimizing the adjustment and correction cost and the fluctuation of heating network parameters, an intraday optimization scheduling model is established to obtain the operating guidance curves of long-distance heat sources and traditional heat sources at various time periods within the day. Based on the operating guidance curves of long-distance heat sources and traditional heat sources at different time periods during the day, combined with the preset control temperature targets of each heating network area, a real-time optimization control model is established to generate hourly valve parameter control strategies for each heating network area.

[0041] In practical applications, with the goal of minimizing operating costs and minimizing the deviation between heat load supply and demand, a day-ahead optimal scheduling model is established, which can be expressed as: ; 、 are the weight coefficients of the operating cost target and the heat load supply and demand deviation target respectively; T is the scheduling period; S is the number of heat sources; is the unit operating cost of heat source s, which is related to the fuel cost and heat delivery cost of the heat source; is the heat supply of heat source s at time t; is the heat load supply and demand deviation value at time t, , is the heating efficiency of heat source s; is the heat loss of heat source s; N is the number of heating network areas; is the predicted heat load value of heating network area n at time t.

[0042] With the goal of minimizing the adjustment correction cost and the fluctuation of heating network parameters, an intraday optimization scheduling model is established, which is expressed as: ; To adjust the target weight coefficient of the completion cost; is the adjustment cost coefficient of heat source s; is the output power of heat source s at time t; is the water supply temperature fluctuation value at time t in the heating network; is the return water temperature fluctuation value of the heating network at time t; Based on the operating guidance curves of long-distance heat sources and traditional heat sources at various time periods within the day, combined with the preset control temperature targets for each heating network area, a real-time optimization control model is established. This includes: based on the operating guidance curves of long-distance heat sources and traditional heat sources at various time periods within the day, analyzing the secondary water supply temperature or secondary supply and return average temperature target values ​​at different times in each heating network area, combining the plate heat exchanger heat transfer characteristics and valve adjustment characteristics of each heating network area (plate heat exchanger heat transfer is related to primary side flow, secondary side flow, primary / secondary side inlet and outlet temperatures, and valve opening is related to flow), analyzing the identification relationship between valve opening and heating network temperature target values, obtaining the valve opening value for each heating network area, minimizing the deviation between the measured temperature and the target temperature, and issuing the value for execution to achieve real-time optimization control of the system; Among them, according to the total heat supply of the heat source and the heat load of each heating network area, the flow rate and temperature required by each heating network area are calculated, which can be expressed as: ; is the flow rate of each heating network area; is the specific heat capacity of hot water; 、 They are the secondary water supply temperature and return water temperature of each heating network area respectively; is the target temperature value of each heating network area at time t; is the reference temperature; is the temperature adjustment correction factor; is the design outdoor temperature; is the outdoor temperature at time t.

[0043] In this embodiment, the multi-dimensional heating loss includes: heat loss caused by heat leakage in the heating network, water replenishment heat loss caused by water leakage in the heating network, and excess heat loss in space; the excess heat loss in space refers to the uneven heating loss between buildings in the heating network and the uneven loss among users in the building.

[0044] In this embodiment, the analysis of the heat transmission and distribution characteristics of each heat source to each associated heating network area includes: using the heat source temperature rise curve to calculate the transmission delay time from the temperature change of each heat source to the response of the corresponding thermal power station in each heating network area, and adjusting the operating parameters of each heat source in advance.

[0045] In this embodiment, the heating system planning, design and optimized operation method also includes: analyzing the problems existing in the heating network and establishing corresponding heating network transformation strategies based on the heat loss caused by heat leakage in the heating network, the water replenishment heat loss caused by water leakage in the heating network and the excess heat loss in space.

[0046] It should be noted that heat source heat loss includes heat loss caused by pipeline heat leakage and water replenishment heat loss caused by pipeline water leakage; factors that have a greater impact on heat loss include the loss of pipeline insulation, aging pipelines, water seepage in pipe wells, flooding, and shallow pipeline burial depth; strengthen the management of thermal pipelines, gradually eliminate old pipelines, deal with problematic pipelines, and reduce heat loss. Excessive spatial heat loss is due to the uneven distribution of flow to each user due to the layout and resistance of the pipeline network. It mainly includes uneven losses between buildings in the pipeline network and uneven users within the building. The main reason is the lack of effective balancing and regulation. Advanced control devices can be installed to achieve automatic regulation, such as self-operated balancing control valves, pressure equalizing tank equipment, etc., and the balancing and regulation efforts can be strengthened to reduce uneven heat loss and reduce energy consumption in the transmission and distribution system.

[0047] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the systems, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a portion of code, and the module, program segment, or a portion of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0048] In addition, the functional modules in each embodiment of the present invention can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk, or an optical disk.

[0049] With the above-described preferred embodiments of the present invention as a guide, and with reference to the above description, relevant personnel are fully capable of making various changes and modifications without departing from the technical scope of this invention. The technical scope of this invention is not limited to the contents of the specification and must be determined according to the scope of the claims.

Claims

1. A method for planning, designing and optimizing the operation of a heating system that introduces a long-distance heat source, characterized in that: It includes: S1. Obtain basic data on the long-distance heat source to be introduced into the heating system during the heating season, and analyze changes in the operation mode and dynamic characteristics of the existing heating system's heat network after the introduction of the long-distance heat source; S2. Based on the changes in the operation mode and dynamic characteristics of the heating network, and combined with the external heating industry evolution data during the heating season, quantitatively analyze and compare multiple preset heating network planning and design schemes to obtain a heating network planning and design scheme; S3. Acquire spatial and temporal characteristic data related to the heating system, establish a spatiotemporal model of the heating system, obtain the heating network structure and operating parameters that change over time, and then, combined with the multi-dimensional impact data of the heat load, perform heat load forecasts for each heating network area; S4. Based on the predicted heat load values ​​of each heating network area, combined with the multi-dimensional heat supply losses of long-distance heat sources and traditional heat sources, heat source output characteristics and heat transmission and distribution characteristics of the heating network, while considering the heat source optimization operation objectives and heating network regulation objectives, a multi-time scale optimization operation model is established to obtain the optimization operation strategies under different time scales.

2. The method for planning, designing and optimizing operation of a heating system according to claim 1, characterized in that: Said S1 specifically includes: Obtain basic data on the long-distance heat source to be introduced into the heating system during the heating season, including: heating capacity, outlet temperature, outlet pressure, pipeline length, diameter, insulation thickness, burial depth, terrain elevation along the route, heat load adjustment range, location of connection point with the existing heating network, and interface pipe diameter; Collect existing heating network data, including the topology of the heating network, the pressure and temperature of each node in the heating network, the flow rate of each pipe section, and the parameters of key equipment in the heating network; Based on the basic data of long-distance heat sources and the collected data of existing heating networks, a heating system simulation model is established to analyze the changes in the heating network zoning, heating network structure, pressure distribution changes at each node of the heating network, temperature distribution changes, flow distribution changes in each pipe section, and hydraulic stability of the existing heating system after the introduction of the long-distance heat source. In addition, the response time and fluctuation amplitude of the heating network pressure and temperature during the dynamic process of commissioning / exiting the long-distance heat source are evaluated.

3. The method for planning, designing and optimizing operation of a heating system according to claim 1, characterized in that: The S2 specifically includes: Obtain data on the evolution of external heating services during the heating period, including data on the evolution of heating area, growth in heat users, energy price fluctuations, and new station commissioning during the planning period; Based on the external heating business evolution data during the heating period, the changes in heat load demand during the heating period are analyzed. At the same time, the heat supply and demand balance is analyzed by combining the heating capacity of long-distance heat sources and traditional heat sources; According to the changes in the operation mode and dynamic characteristics of the heat network after the introduction of long-distance heat sources, set the constraints for the safe and stable operation of each heat source and the heat network; Based on the results of heat supply and demand balance analysis, and the safe operation constraints of various heat sources and heat networks, various heat network planning and design schemes, including heat source combinations and pipe network layouts, are pre-set for different periods of the heating season. A multi-index comprehensive evaluation system is constructed, and a multi-criteria decision analysis method is used to quantitatively analyze and compare various heat network planning and design schemes to obtain the optimal planning and design scheme, guide the timing of the withdrawal and commissioning of long-distance heat sources and traditional heat sources, the preliminary output plan of each heat source, the layout of the pipeline direction, and the pipeline route design scheme.

4. The method for planning, designing and optimizing operation of a heating system according to claim 3, characterized in that: The new station commissioning data includes heat user, network area, heat use location, heating company, heat supply form, and heat use type; The multi-index comprehensive evaluation system includes technical indicators, economic indicators and environmental indicators.

5. The method for planning, designing and optimizing operation of a heating system according to claim 1, characterized in that: In S3, establishing a spatiotemporal model of the heating system specifically includes: Acquire spatial characteristic data and temporal characteristic data related to the heating system; the spatial characteristic data represents the spatial coupling effects between heating networks and heating stations; the temporal characteristic data represents the temporal evolution of the operation and structure of the heating system's heat sources, heating networks, and heating stations; Using a first machine learning algorithm to train the spatial feature data to extract spatial features; Using a second machine learning algorithm to train the time feature data to extract time features; The extracted spatial and temporal features are integrated to establish a spatiotemporal model of the heating system.

6. The method for planning, designing and optimizing operation of a heating system according to claim 1, characterized in that: In S3, the heat load forecasting of each heating network area specifically includes: The heating network structure and operating parameters of the heating system that change over time are obtained based on the spatiotemporal model of the heating system. The data are combined with meteorological data, building characteristic data of heat users in each heating network area, user behavior data, new station commissioning data, and historical heat load data to form a heat load impact data set for each heating network area. After preprocessing and feature extraction of the heat load impact data set of each heating network area, it is input into the hybrid learning algorithm for training and learning, and a heat load prediction model for each heating network area is established to predict the heat load of each heating network area at different times in the future.

7. The method for planning, designing and optimizing operation of a heating system according to claim 1, characterized in that: The S4 specifically includes: Based on the next day's heat load forecast for each heating network region, combined with the multi-dimensional heating losses and heat source output characteristics of long-distance heat sources and traditional heat sources, and with the goal of minimizing operating costs and heat load supply and demand deviation, a day-ahead optimization scheduling model was established to obtain the load allocation strategy for long-distance heat sources and traditional heat sources at each time period on the day-ahead. Based on the predicted and measured daily heat load values ​​of each heating network area and the heat transmission and distribution characteristics of each heat source to each related heating network area, the operating parameters of long-distance heat sources and traditional heat sources are adjusted and corrected while ensuring the heat load demand of each heating network area. With the goal of minimizing the adjustment and correction cost and the fluctuation of heating network parameters, an intraday optimization scheduling model is established to obtain the operating guidance curves of long-distance heat sources and traditional heat sources at various time periods within the day. Based on the operating guidance curves of long-distance heat sources and traditional heat sources at different time periods during the day, combined with the preset control temperature targets of each heating network area, a real-time optimization control model is established to generate hourly valve parameter control strategies for each heating network area.

8. The method for planning, designing and optimizing operation of a heating system according to claim 7, characterized in that: The multi-dimensional heating losses include: heat loss caused by heat leakage in the heating network, water replenishment heat loss caused by water leakage in the heating network and excess heat loss in space; the excess heat loss in space refers to the uneven heating loss between buildings in the heating network and the uneven loss to users within the building.

9. The method for planning, designing and optimizing operation of a heating system according to claim 7, characterized in that: The analysis of the heat transmission and distribution characteristics of each heat source to each associated heat network area includes: using the heat source temperature rise curve to calculate the transmission delay time from the temperature change of each heat source to the response of the corresponding thermal power station in each heat network area, and adjusting the operating parameters of each heat source in advance.

10. The method for planning, designing and optimizing operation of a heating system according to claim 8, characterized in that: The heating system planning, design and optimized operation method also includes: analyzing the problems existing in the heating network and establishing corresponding heating network transformation strategies based on the heat loss caused by heat leakage in the heating network, the water replenishment heat loss caused by water leakage in the heating network and the excess heat loss in space.

Images