Multi-dimensional ecological park carbon neutralization dynamic evaluation and path optimization method

Abstract

The invention relates to the technical field of carbon neutralization, in particular to a multi-dimensional ecological park carbon neutralization dynamic evaluation and path optimization method. Thermal load data are collected in real time through a sensor network, a heat energy flow model is constructed, pipe network efficiency fluctuation is analyzed, and energy efficiency loss points are positioned. For the loss point, the pipe network layout is optimized through thermodynamic simulation and reinforcement learning algorithms, and a new configuration scheme is generated. Through iterative optimization and real-time adjustment, the running state of the system can be continuously improved, and carbon emission and running cost are reduced. Meanwhile, the future thermal load distribution trend can be predicted, and a basis is provided for optimization of the next period. According to the method, intelligent management of the park heat energy network is realized, the energy utilization efficiency is improved, and an effective solution is provided for realizing low-carbon operation.

Description

Technical Field

[0001] The present invention belongs to the technical field of carbon neutrality, and specifically relates to a multi-dimensional dynamic evaluation and path optimization method for carbon neutrality in ecological parks. Background Art

[0002] Carbon neutrality is the core of addressing global climate change. As an important carrier of urban sustainable development, the low-carbon transformation of the energy system in ecological parks is particularly crucial. Achieving carbon neutrality in the park requires comprehensive consideration of the optimization of the entire chain of energy supply, transmission, and consumption, and the dynamic evaluation and path optimization method provides systematic technical support for achieving this goal. However, existing methods have significant limitations in dealing with the complexity of the park's energy system, mostly staying at the static analysis level, difficult to adapt to the dynamic changes of heat load and the requirements of multi-energy coordination, and lacking accurate capture of real-time energy efficiency losses. These limitations make it difficult to balance the low-carbon goal and economy in the optimization of the park's heating system.

[0003] The complexity of the heating system in ecological parks stems from the spatio-temporal heterogeneity of heat load distribution, which makes it difficult to accurately model the law of heat energy flow. The unevenness of heat load distribution further exacerbates the fluctuation of the pipe network transmission efficiency, making it difficult to identify the heat energy loss points in real time. The fluctuation of transmission efficiency directly affects the overall energy efficiency of the system, and then leads to a decrease in the accuracy of carbon emission control. Existing thermal network models are mostly based on traditional thermodynamics analysis, lacking deep integration with digital twin technology, and unable to achieve dynamic monitoring of heat energy flow and optimization decision-making.

[0004] Therefore, how to construct a heating power flow analysis method that can dynamically capture the characteristics of heat load distribution, real-time monitor the heat energy flow and loss, and optimize the pipe network layout has become a key issue in the path optimization of carbon neutrality in ecological parks. Summary of the Invention

[0005] The purpose of the present invention is to provide a multi-dimensional dynamic evaluation and path optimization method for carbon neutrality in ecological parks in view of the above deficiencies in the prior art.

[0006] The object of the present invention is achieved through the following technical solutions: A multi-dimensional ecological park carbon neutral dynamic evaluation and path optimization method, comprising the following steps: Obtain real-time data of the heat load in each area of the park, collect temperature, flow rate and pressure information through a sensor network, and combine time series analysis to determine the spatio-temporal heterogeneity characteristics of the heat load distribution; According to the spatio-temporal heterogeneity characteristics of the heat load distribution, construct a heat energy flow model based on digital twin, and use a graph neural network to simulate the dynamic transmission path of heat energy in the pipe network to obtain the real-time state of heat energy flow; Extract the temperature gradient and flow rate change of each node of the pipe network from the real-time state of heat energy flow, calculate the transmission efficiency fluctuation index, judge whether there are nodes with efficiency fluctuations exceeding the preset threshold, and determine the energy efficiency loss points; For the energy efficiency loss points, obtain the geometric parameters and material properties of the corresponding pipe network section, and analyze the distribution law of heat energy loss through thermodynamic simulation to obtain the high-precision spatial positioning of the loss points; According to the high-precision spatial positioning of the loss points, use a reinforcement learning algorithm to optimize the pipe network layout, adjust the pipe diameter and valve opening, and generate an optimized pipe network configuration plan; Through the optimized pipe network configuration plan, update the pipe network parameters in the digital twin model, re-simulate the heat energy flow state, calculate the carbon emissions and operating costs, and judge whether the low-carbon target and economic requirements are met; If the carbon emissions or operating costs exceed the preset threshold, extract new heat load distribution data from the digital twin model, iteratively optimize the pipe network layout, and generate an updated configuration plan; According to the updated configuration plan, adjust the valve and pump station parameters in the pipe network control system in real time, obtain the adjusted heat energy flow data, and verify whether the system operation state reaches the expected optimization effect; Through the verified heat energy flow data, update the prediction model of the heat load distribution, and use a time series prediction algorithm to generate the heat load distribution trend for the next 24 hours to determine the optimization starting point for the next cycle.

[0007] The present invention is further set as follows: The spatio-temporal heterogeneity characteristics of the heat load distribution include the time periodicity and spatial aggregation of the heat load. The real-time state of heat energy flow includes the temperature field distribution and flow rate dynamic change of the pipe network nodes. The high-precision spatial positioning of the energy efficiency loss points is specifically the identification of the local heat loss distribution and loss hot spot areas of the pipe network section. The optimized pipe network configuration plan includes a pipe diameter adjustment plan, a valve opening optimization strategy and a pump station power adjustment plan. The evaluation results of carbon emissions and operating costs include the carbon emission reduction potential and the operating cost savings rate. The updated configuration plan includes the adjustment of the pipe network topology structure and the optimization of control parameters. The prediction model of the heat load distribution includes short-term heat load trend prediction and long-term heat demand pattern analysis.

[0008] The present invention is further configured such that the steps of obtaining real-time data of the heat load in each area of the park, collecting temperature, flow rate, and pressure information through a sensor network, and determining the spatio-temporal heterogeneity characteristics of the heat load distribution by combining time series analysis are specifically as follows: Based on the sensor network arranged in each area of the park, collect real-time data of temperature, flow rate, and pressure, and perform time synchronization and spatial calibration on the multi-sensor data to generate a unified heat load data set; Based on the heat load data set, use the time series decomposition algorithm to separate the trend term, periodic term, and random term of the heat load data, and reveal the time periodic characteristics of the heat load; Based on the time periodic characteristics, use the clustering analysis method to divide the spatial distribution of the heat load into multiple aggregation areas, and generate the spatial aggregation characteristics of the heat load; Integrate the time periodic characteristics and spatial aggregation characteristics, and generate a description of the spatio-temporal heterogeneity characteristics of the heat load distribution through spatio-temporal heterogeneity modeling of the heat load distribution.

[0009] The present invention is further configured such that the steps of constructing a heat energy flow model based on digital twin according to the spatio-temporal heterogeneity characteristics of the heat load distribution, and using a graph neural network to simulate the dynamic transmission path of heat energy in the pipe network to obtain the real-time state of heat energy flow are specifically as follows: Based on the spatio-temporal heterogeneity characteristics of the heat load distribution, construct a digital twin model of heat energy flow, and associate the physical pipe network with the digital model through virtual mapping technology; Based on the digital twin model, use the graph neural network algorithm to abstract the pipe network nodes and connection relationships into a graph structure, and simulate the dynamic transmission path of heat energy in the pipe network; Based on the dynamic transmission path of heat energy, extract the temperature field distribution and flow dynamic change data of the pipe network nodes, and generate the real-time state of heat energy flow; Combine the real-time state of heat energy flow, and verify the accuracy of the model through the thermodynamic equilibrium equation to generate a description of the real-time state of heat energy flow.

[0010] The present invention is further configured such that the steps of extracting the temperature gradient and flow rate change of each node of the pipe network from the real-time state of heat energy flow, calculating the transmission efficiency fluctuation index, determining whether there are nodes with efficiency fluctuations exceeding the preset threshold, and determining the energy efficiency loss points are specifically as follows: Based on the real-time state of heat energy flow, extract the temperature gradient and flow rate change data of each node of the pipe network to generate a description of the thermal characteristics of the pipe network nodes; Based on the description of the thermal characteristics, calculate the transmission efficiency fluctuation index of each node of the pipe network to evaluate the stability of heat energy transmission; Based on the transmission efficiency fluctuation index, set a fluctuation threshold, and determine whether there are nodes with efficiency fluctuations exceeding the preset threshold to generate a candidate set of energy efficiency loss points; Based on the candidate set of energy efficiency loss points, verify the accuracy of the loss points through thermodynamic simulation to generate a high-precision spatial positioning of the energy efficiency loss points.

[0011] The present invention is further configured such that for the energy efficiency loss points, geometric parameters and material properties of the corresponding pipeline sections are obtained, and the distribution law of heat energy loss is analyzed through thermodynamic simulation. The steps for obtaining the high-precision spatial positioning of the loss points are specifically as follows: Based on the high-precision spatial positioning of the energy efficiency loss points, geometric parameters and material properties of the corresponding pipeline sections are obtained, and a basic physical property description of the pipeline section is generated; Based on the basic physical property description, thermodynamic simulation technology is used to analyze the distribution law of heat energy loss within the pipeline section, and a spatial distribution map of heat energy loss is generated; Based on the spatial distribution map of heat energy loss, local heat loss distribution is identified through heat flux density analysis, and a loss hot spot area is generated; By synthesizing the local heat loss distribution and the loss hot spot area, a high-precision spatial positioning description of the loss points is generated.

[0012] The present invention is further configured such that according to the high-precision spatial positioning of the loss points, a reinforcement learning algorithm is used to optimize the pipeline network layout, adjust the pipe diameter and valve opening, and the steps for generating an optimized pipeline network configuration scheme are specifically as follows: Based on the high-precision spatial positioning of the loss points, a reinforcement learning model for pipeline network optimization is constructed, and the optimal solution is explored through the interaction between the agent and the environment; Based on the reinforcement learning model, the pipe diameter and valve opening of the pipeline section are adjusted to optimize the heat energy transmission path, and a preliminary optimization scheme is generated; Based on the preliminary optimization scheme, the optimization effect is verified through thermodynamic simulation, and an optimized pipeline network configuration scheme is generated; Combining the optimized pipeline network configuration scheme, the pipeline network parameters in the digital twin model are updated, and a description of the optimized heat energy flow state is generated.

[0013] The present invention is further configured such that through the optimized pipeline network configuration scheme, the pipeline network parameters in the digital twin model are updated, the heat energy flow state is re-simulated, the carbon emissions and operating costs are calculated, and the steps for determining whether the low-carbon target and economic requirements are met are specifically as follows: Based on the optimized pipeline network configuration scheme, the pipeline network parameters in the digital twin model are updated, and the heat energy flow state is re-simulated; Based on the heat energy flow state, the optimized carbon emissions and operating costs are calculated, and a low-carbon target and economic evaluation result is generated; Based on the evaluation result, it is determined whether the low-carbon target and economic requirements are met. If not, a new optimization requirement is generated; Based on the new optimization requirement, the heat load distribution data is extracted, and a new round of optimization starting point is generated.

[0014] The present invention is further configured such that according to the updated configuration scheme, the valve and pump station parameters in the pipeline network control system are adjusted in real time, the adjusted heat energy flow data is obtained, and the steps for verifying whether the system operation state reaches the expected optimization effect are specifically as follows: Based on the updated configuration scheme, the valve opening and pump station power parameters in the pipeline network control system are adjusted in real time; Based on the adjusted parameters, the heat energy flow data is collected, and a description of the adjusted heat energy flow state is generated; Based on the description of the adjusted heat energy flow state, by comparing with the optimization target, it is verified whether the system operation state reaches the expected optimization effect; Based on the verification result, a system optimization effect report is generated.

[0015] The present invention is further configured such that, based on the verified heat energy flow data, the prediction model of the heat load distribution is updated, and the steps of generating the heat load distribution trend for the next 24 hours by using the time series prediction algorithm and determining the optimization starting point for the next cycle are specifically as follows: updating the prediction model of the heat load distribution based on the verified heat energy flow data; generating the heat load distribution trend for the next 24 hours by using the time series prediction algorithm based on the prediction model; determining the optimization starting point for the next cycle based on the heat load distribution trend and in combination with the current optimization effect; and generating the optimization task description for the next cycle based on the optimization starting point.

[0016] Advantages of the present invention: The present invention collects heat load data in real time through a sensor network, constructs a heat energy flow model, analyzes the fluctuations in the pipe network efficiency, and locates the energy efficiency loss points. For the loss points, the present invention optimizes the pipe network layout by using thermodynamic simulation and reinforcement learning algorithms to generate a new configuration plan. Through iterative optimization and real-time adjustment, the present invention can continuously improve the system operation status, reduce carbon emissions and operation costs. At the same time, the present invention can also predict the future heat load distribution trend to provide a basis for the optimization of the next cycle. This method realizes the intelligent management of the park heat energy network, improves the energy utilization efficiency, and provides an effective solution for realizing low-carbon operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the following drawings without creative efforts.

[0018] Figure 1 is the flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The present invention will be further described in conjunction with the following embodiments.

[0020] By Figure 1It can be seen that the embodiment of the present invention provides a multi-dimensional ecological park carbon neutral dynamic evaluation and path optimization method, including the following steps: obtaining real-time data of the heat load in each area of the park, collecting temperature, flow rate and pressure information through a sensor network, and combining time series analysis to determine the spatio-temporal heterogeneity characteristics of the heat load distribution; constructing a heat energy flow model based on digital twin according to the spatio-temporal heterogeneity characteristics of the heat load distribution, using a graph neural network to simulate the dynamic transmission path of heat energy in the pipe network, and obtaining the real-time state of heat energy flow; extracting the temperature gradient and flow rate change of each node in the pipe network from the real-time state of heat energy flow, calculating the transmission efficiency fluctuation index, judging whether there are nodes with efficiency fluctuations exceeding the preset threshold, and determining the energy efficiency loss points; for the energy efficiency loss points, obtaining the geometric parameters and material properties of the corresponding pipe network section, and analyzing the distribution law of heat energy loss through thermodynamic simulation to obtain the high-precision spatial positioning of the loss points; according to the high-precision spatial positioning of the loss points, using a reinforcement learning algorithm to optimize the pipe network layout, adjusting the pipe diameter and valve opening, and generating an optimized pipe network configuration plan; through the optimized pipe network configuration plan, updating the pipe network parameters in the digital twin model, re-simulating the heat energy flow state, calculating the carbon emissions and operating costs, and judging whether the low-carbon target and economic requirements are met; if the carbon emissions or operating costs exceed the preset threshold, extracting new heat load distribution data from the digital twin model, iteratively optimizing the pipe network layout, and generating an updated configuration plan; according to the updated configuration plan, adjusting the valve and pump station parameters in the pipe network control system in real time, obtaining the adjusted heat energy flow data, and verifying whether the system operation state reaches the expected optimization effect; through the verified heat energy flow data, updating the prediction model of the heat load distribution, using a time series prediction algorithm to generate the heat load distribution trend for the next 24 hours, and determining the optimization starting point for the next cycle. This embodiment realizes the accurate capture of the spatio-temporal heterogeneity of the heat load distribution through the application of a sensor network and time series analysis, and improves the modeling accuracy of the heat energy flow state. This method uses digital twin technology and graph neural network to effectively simulate the dynamic transmission path of heat energy, which helps to identify the energy efficiency loss points and their distribution laws. In addition, the application of the reinforcement learning algorithm makes the optimization of the pipe network layout more scientific, providing a solid foundation for the balance between the low-carbon target and economic requirements. By combining thermodynamic simulation and time series prediction, this method can deeply analyze the interaction between heat energy loss and heat load distribution, and accurately predict the future heat load trend. Using life cycle assessment and cost-benefit analysis, it provides comprehensive technical support for the carbon neutral path optimization of ecological parks, thus promoting the low-carbon transformation and sustainable development of the park heating system.

[0021] In the implementation process, it is first necessary to obtain the real-time data of the heat load in each area of the park, which is completed through a sensor network deployed in the park. The sensor network collects real-time data of temperature, flow rate, and pressure, and performs time synchronization and spatial calibration on the multi-sensor data to generate a unified heat load dataset. Time synchronization uses the GPS-based timestamp alignment technology to ensure that the time reference of all sensor data is consistent; spatial calibration accurately calibrates the sensor positions through the geographic information system to eliminate data deviations caused by installation errors. Subsequently, a time series decomposition algorithm is used to analyze the heat load dataset to separate the trend term, periodic term, and random term. Expressed by the formula: X(t)=T(t)+C(t)+R(t), where X(t) is the original heat load data, T(t) is the trend term, C(t) is the periodic term, and R(t) is the random term. The trend term is extracted by the moving average method, the periodic term identifies the main frequency components through the fast Fourier transform (FFT), and the random term is the remaining part. Based on the time periodicity characteristics, the K-means clustering analysis method is used to divide the spatial distribution of the heat load into multiple aggregation areas to generate the spatial aggregation characteristics of the heat load. Finally, by synthesizing the time periodicity and spatial aggregation characteristics, the spatio-temporal heterogeneity characteristics describing the heat load distribution are generated through spatio-temporal heterogeneity modeling.

[0022] Next, based on the spatio-temporal heterogeneity characteristics of the heat load distribution, a digital-twin-based heat energy flow model is constructed. The physical pipe network is associated with the digital model through virtual mapping technology to establish a digital-twin model of heat energy flow. The core of this model is to map the geometric parameters, material properties, and operating status of the physical pipe network into the digital environment to form a high-precision virtual reproduction. The graph neural network algorithm is used to abstract the pipe network nodes and connection relationships into a graph structure to simulate the dynamic transmission path of heat energy in the pipe network. The input of the graph neural network includes the node feature matrix F and the adjacency matrix A, and the output is the state vector H of each node. Its update formula is: H^(l+1)=σ(A·H^(l)·W^(l)), where H^(l) is the hidden state of the l-th layer, W^(l) is the weight matrix, and σ is the activation function. Based on the dynamic transmission path of heat energy, the temperature field distribution and flow rate dynamic change data of the pipe network nodes are extracted to generate the real-time state of heat energy flow. The accuracy of the model is verified through the thermodynamic equilibrium equation to ensure that the digital-twin model can truly reflect the operating status of the physical pipe network.

[0023] After obtaining the real-time state of heat energy flow, it is necessary to further analyze the fluctuation of the transmission efficiency of each node in the pipe network, determine the energy efficiency loss points, extract the temperature gradient and flow rate change data of each node in the pipe network from the real-time state of heat energy flow, and generate a description of the thermal characteristics of the pipe network nodes. The temperature gradient calculation formula is: ∇T = (T_out - T_in) / L, where T_out is the outlet temperature, T_in is the inlet temperature, and L is the pipe length. The flow rate change calculation formula is: ΔQ = Q_t - Q_(t - 1), where Q_t is the flow rate at the current moment and Q_(t - 1) is the flow rate at the previous moment. Based on the description of thermal characteristics, calculate the transmission efficiency fluctuation index of each node in the pipe network. The transmission efficiency fluctuation index is defined as: η = ΔQ / ΔT, where ΔQ is the flow rate change and ΔT is the temperature gradient change. Set a fluctuation threshold to determine whether there are nodes with efficiency fluctuations exceeding the preset threshold, and generate a candidate set of energy efficiency loss points. Verify the accuracy of the loss points through thermodynamic simulation to generate a high-precision spatial location of the energy efficiency loss points.

[0024] For the energy efficiency loss points, it is necessary to further analyze the distribution law of heat energy loss. Based on the high-precision spatial location of the energy efficiency loss points, obtain the geometric parameters and material properties of the corresponding pipe network segments, and generate a description of the basic physical characteristics of the pipe network segments. The geometric parameters include the pipe diameter D, length L, and wall thickness δ, and the material properties include the thermal conductivity λ and specific heat capacity c. Use thermodynamic simulation technology to analyze the distribution law of heat energy loss in the pipe network segment and generate a spatial distribution map of heat energy loss. The heat energy loss calculation formula is: Q_loss = k·A·(T_1 - T_2), where k is the heat transfer coefficient, A is the heat transfer area, and T_1 and T_2 are the inner and outer surface temperatures respectively. Identify the local heat loss distribution through heat flux density analysis to generate a loss hot spot area. Combine the local heat loss distribution and the loss hot spot area to generate a high-precision spatial location description of the loss points.

[0025] According to the high-precision spatial location of the loss points, use the reinforcement learning algorithm to optimize the pipe network layout, construct a reinforcement learning model for pipe network optimization, and the agent explores the optimal solution by interacting with the environment. The state space of the reinforcement learning model includes the temperature, flow rate, and pressure of each node in the pipe network, the action space includes pipe diameter adjustment, valve opening adjustment, and pump station power change, and the reward function is defined as: R = -α·C - β·E, where C is the operating cost, E is the carbon emissions, and α and β are weight coefficients. Based on the reinforcement learning model, adjust the pipe diameter and valve opening of the pipe network segment, optimize the heat energy transmission path, and generate a preliminary optimization plan. Verify the optimization effect through thermodynamic simulation to generate an optimized pipe network configuration plan. Combine the optimized pipe network configuration plan to update the pipe network parameters in the digital twin model to generate a description of the optimized heat energy flow state.

[0026] The optimized pipeline network configuration plan needs to re - simulate the thermal energy flow state, calculate the carbon emissions and operating costs, update the pipeline network parameters in the digital twin model, and re - simulate the thermal energy flow state. Based on the thermal energy flow state, calculate the optimized carbon emissions and operating costs, and generate the low - carbon target and economic evaluation results. The carbon emissions calculation formula is: E = ∑(Q_i·EF_i), where Q_i is the thermal energy consumption of the i - th section of the pipeline network, and EF_i is the corresponding carbon emission factor. The operating cost calculation formula is: C = ∑(P_i·Q_i), where P_i is the unit operating cost of the i - th section of the pipeline network. Judge whether the low - carbon target and economic requirements are met. If not, generate new optimization requirements. Extract the heat load distribution data and generate a new round of optimization starting points.

[0027] According to the updated configuration plan, adjust the valve and pump station parameters in the pipeline network control system in real - time. Based on the updated configuration plan, adjust the valve opening and pump station power parameters in the pipeline network control system in real - time. Based on the adjusted parameters, collect the thermal energy flow data and generate a description of the adjusted thermal energy flow state. By comparing the optimization objectives, verify whether the system operation state reaches the expected optimization effect. Based on the verification results, generate a system optimization effect report.

[0028] Finally, based on the verified thermal energy flow data, update the prediction model of the heat load distribution. Based on the verified thermal energy flow data, update the prediction model of the heat load distribution. Use the time - series prediction algorithm to generate the heat load distribution trend for the next 24 hours. The prediction algorithm uses the long short - term memory network (LSTM), and its formula is: h_t = f(W_hh·h_(t - 1)+W_xh·x_t + b_h), where h_t is the hidden state at the current moment, W_hh and W_xh are weight matrices, and b_h is the bias term. Based on the heat load distribution trend, combined with the current optimization effect, determine the optimization starting point for the next cycle. Based on the optimization starting point, generate the optimization task description for the next cycle.

[0029] In summary, through the comprehensive application of sensor networks, digital twin technology, graph neural networks, thermodynamic simulation, and reinforcement learning algorithms, the present invention realizes the accurate modeling and optimization of the thermal energy flow state in the park, providing comprehensive technical support for the optimization of the carbon neutralization path in the ecological park.

[0030] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the protection scope of the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the essence and scope of the technical solutions of the present invention.

Claims

1. A multi-dimensional ecological park carbon neutrality dynamic evaluation and path optimization method, characterized in that: It includes the following steps: Obtain the real-time data of the heat load in each area of the park, collect temperature, flow rate and pressure information through a sensor network, and combine time series analysis to determine the spatio-temporal heterogeneity characteristics of the heat load distribution; According to the spatio-temporal heterogeneity characteristics of the heat load distribution, construct a heat energy flow model based on digital twin, use a graph neural network to simulate the dynamic transmission path of heat energy in the pipe network, and obtain the real-time state of heat energy flow; Extract the temperature gradient and flow rate change of each node in the pipe network from the real-time state of heat energy flow, calculate the transmission efficiency fluctuation index, judge whether there are nodes with efficiency fluctuations exceeding the preset threshold, and determine the energy efficiency loss points; For the energy efficiency loss points, obtain the geometric parameters and material properties of the corresponding pipe network segments, and analyze the distribution law of heat energy loss through thermodynamic simulation to obtain the high-precision spatial positioning of the loss points; According to the high-precision spatial positioning of the loss points, use a reinforcement learning algorithm to optimize the pipe network layout, adjust the pipe diameter and valve opening, and generate an optimized pipe network configuration plan; Through the optimized pipe network configuration plan, update the pipe network parameters in the digital twin model, re-simulate the heat energy flow state, calculate the carbon emissions and operating costs, and judge whether the low-carbon target and economic requirements are met; If the carbon emissions or operating costs exceed the preset threshold, extract the new heat load distribution data from the digital twin model, iteratively optimize the pipe network layout, and generate an updated configuration plan; According to the updated configuration plan, adjust the valve and pump station parameters in the pipe network control system in real time, obtain the adjusted heat energy flow data, and verify whether the system operation state reaches the expected optimization effect; Through the verified heat energy flow data, update the prediction model of the heat load distribution, use the time series prediction algorithm to generate the heat load distribution trend for the next 24 hours, and determine the optimization starting point for the next cycle.

2. The multi-dimensional ecological park carbon neutrality dynamic evaluation and path optimization method according to claim 1, characterized in that: The spatio-temporal heterogeneity characteristics of the heat load distribution include the time periodicity and spatial aggregation of the heat load. The real-time state of heat energy flow includes the temperature field distribution and flow rate dynamic changes of the pipe network nodes. The high-precision spatial positioning of the energy efficiency loss points is specifically the local heat loss distribution of the pipe network segments and the identification of the loss hot spot areas. The optimized pipe network configuration plan includes the pipe diameter adjustment plan, valve opening optimization strategy and pump station power adjustment plan. The evaluation results of carbon emissions and operating costs include the carbon emission reduction potential and operating cost savings rate. The updated configuration plan includes the pipe network topology structure adjustment and control parameter optimization. The prediction model of the heat load distribution includes short-term heat load trend prediction and long-term heat demand pattern analysis.

3. A multi-dimensional ecological park carbon neutral dynamic evaluation and path optimization method according to claim 1, characterized in that: The steps to obtain the real-time data of the heat load in each area of the park, collect temperature, flow rate and pressure information through a sensor network, and combine time series analysis to determine the spatio-temporal heterogeneity characteristics of the heat load distribution are specifically as follows: Based on the sensor network arranged in each area of the park, collect the real-time data of temperature, flow rate and pressure, and perform time synchronization and spatial calibration on the multi-sensor data to generate a unified heat load data set; Based on the heat load data set, use the time series decomposition algorithm to separate the trend term, cycle term and random term of the heat load data, and reveal the time periodicity characteristics of the heat load; Based on the time periodicity characteristics, using the clustering analysis method, divide the spatial distribution of heat load into multiple aggregation regions to generate the spatial aggregation characteristics of heat load; Integrate the time periodicity characteristics and spatial aggregation characteristics, and through the spatio-temporal heterogeneity modeling of heat load distribution, generate the spatio-temporal heterogeneity characteristic description of heat load distribution.

4. A multi-dimensional ecological park carbon neutral dynamic evaluation and path optimization method according to claim 1, characterized in that: According to the spatio-temporal heterogeneity characteristics of heat load distribution, the steps to construct a digital twin-based heat energy flow model, use a graph neural network to simulate the dynamic transmission path of heat energy in the pipe network, and obtain the real-time state of heat energy flow are as follows: Based on the spatio-temporal heterogeneity characteristics of heat load distribution, construct a digital twin model of heat energy flow, and associate the physical pipe network with the digital model through virtual mapping technology; Based on the digital twin model, use the graph neural network algorithm to abstract the pipe network nodes and connection relationships into a graph structure, and simulate the dynamic transmission path of heat energy in the pipe network; Based on the dynamic transmission path of heat energy, extract the temperature field distribution and flow dynamic change data of the pipe network nodes to generate the real-time state of heat energy flow; Combined with the real-time state of heat energy flow, verify the accuracy of the model through the thermodynamic equilibrium equation to generate the real-time state description of heat energy flow.

5. A multi-dimensional ecological park carbon neutral dynamic evaluation and path optimization method according to claim 1, characterized in that: The steps to extract the temperature gradient and flow change of each node of the pipe network from the real-time state of heat energy flow, calculate the transmission efficiency fluctuation index, judge whether there are nodes with efficiency fluctuations exceeding the preset threshold, and determine the energy efficiency loss points are as follows: Based on the real-time state of heat energy flow, extract the temperature gradient and flow change data of each node of the pipe network to generate the thermal characteristics description of the pipe network nodes; Based on the thermal characteristics description, calculate the transmission efficiency fluctuation index of each node of the pipe network to evaluate the stability of heat energy transmission; Based on the transmission efficiency fluctuation index, set the fluctuation threshold, judge whether there are nodes with efficiency fluctuations exceeding the preset threshold, and generate a candidate set of energy efficiency loss points; Based on the candidate set of energy efficiency loss points, verify the accuracy of the loss points through thermodynamic simulation to generate the high-precision spatial positioning of the energy efficiency loss points.

6. A multi-dimensional ecological park carbon neutrality dynamic evaluation and path optimization method according to claim 1, characterized in that: For the energy efficiency loss points, the steps to obtain the geometric parameters and material properties of the corresponding pipe network section, and analyze the distribution law of heat energy loss through thermodynamic simulation to obtain the high-precision spatial positioning of the loss points are as follows: Based on the high-precision spatial positioning of the energy efficiency loss points, obtain the geometric parameters and material properties of the corresponding pipe network section to generate the basic physical characteristics description of the pipe network section; Based on the basic physical characteristics description, use thermodynamic simulation technology to analyze the distribution law of heat energy loss in the pipe network section to generate the spatial distribution map of heat energy loss; Based on the spatial distribution map of heat energy loss, identify the local heat loss distribution through heat flux density analysis to generate the loss hot spot area; Integrate the local heat loss distribution and the loss hot spot area to generate the high-precision spatial positioning description of the loss points.

7. A multi-dimensional ecological park carbon neutrality dynamic evaluation and path optimization method according to claim 1, characterized in that: According to the high-precision spatial positioning of the loss points, the steps to optimize the pipe network layout using the reinforcement learning algorithm, adjust the pipe diameter and valve opening, and generate an optimized pipe network configuration plan are as follows: Based on the high-precision spatial positioning of the loss points, construct a reinforcement learning model for pipe network optimization, and explore the optimal solution through the interaction between the agent and the environment; Based on the reinforcement learning model, adjust the pipe diameter and valve opening of the pipe network section, optimize the heat energy transmission path, and generate a preliminary optimization plan; Based on the preliminary optimization plan, verify the optimization effect through thermodynamic simulation and generate an optimized pipe network configuration plan; Combined with the optimized pipe network configuration plan, update the pipe network parameters in the digital twin model to generate a description of the optimized heat energy flow state.

8. A multi-dimensional ecological park carbon neutral dynamic evaluation and path optimization method according to claim 1, characterized in that: The steps of updating the pipe network parameters in the digital twin model through the optimized pipe network configuration plan, re-simulating the heat energy flow state, calculating the carbon emissions and operating costs, and determining whether the low-carbon target and economic requirements are met are as follows: Based on the optimized pipe network configuration plan, update the pipe network parameters in the digital twin model and re-simulate the heat energy flow state; Based on the heat energy flow state, calculate the optimized carbon emissions and operating costs to generate a low-carbon target and economic evaluation result; Based on the evaluation result, determine whether the low-carbon target and economic requirements are met. If not, generate new optimization requirements; Based on the new optimization requirements, extract the heat load distribution data to generate a new round of optimization starting point.

9. A multi-dimensional ecological park carbon neutral dynamic evaluation and path optimization method according to claim 1, characterized in that: The steps of adjusting the valve and pump station parameters in the pipe network control system in real time according to the updated configuration plan, obtaining the adjusted heat energy flow data, and verifying whether the system operation state reaches the expected optimization effect are as follows: Based on the updated configuration plan, adjust the valve opening and pump station power parameters in the pipe network control system in real time; Based on the adjusted parameters, collect the heat energy flow data to generate a description of the adjusted heat energy flow state; Based on the description of the adjusted heat energy flow state, verify whether the system operation state reaches the expected optimization effect by comparing the optimization objectives; Based on the verification result, generate a system optimization effect report.

10. A multi-dimensional ecological park carbon neutrality dynamic evaluation and path optimization method according to claim 1, characterized in that: The steps of updating the prediction model of the heat load distribution through the verified heat energy flow data, using the time series prediction algorithm to generate the heat load distribution trend for the next 24 hours, and determining the optimization starting point for the next cycle are as follows: Based on the verified heat energy flow data, update the prediction model of the heat load distribution; Based on the prediction model, use the time series prediction algorithm to generate the heat load distribution trend for the next 24 hours; Based on the heat load distribution trend, combined with the current optimization effect, determine the optimization starting point for the next cycle; Based on the optimization starting point, generate a description of the optimization task for the next cycle.

Images