Park thermal load curve completion method based on RC network thermal dynamic model
By establishing a thermal dynamic model of RC network and optimizing parameters, the problem of incomplete thermal load data in the park is solved, and accurate completion of thermal load data and support for energy management is achieved.
Patent Information
- Application Number
- CN202510255462.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-05
- Publication Date
- 2025-08-05
AI Technical Summary
The thermal load data in the park is incomplete, resulting in inaccurate energy demand forecasts, affecting the effective implementation of energy conservation and carbon reduction strategies.
Establish a thermal dynamic model of the RC network, collect some thermal load data as input benchmarks, use the model to calculate the missing data, and optimize the completion algorithm by adjusting the model parameters until the accuracy requirements are met.
It improves the accuracy of thermal load data and the adaptability of the completion algorithm, and supports comprehensive prediction of thermal loads in the park and energy management optimization.
Smart Images
Figure CN120430894A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of heat load prediction. Specifically, it relates to a method for completing the campus heat load curve based on the RC network thermal dynamic model. Background Art
[0002] The load demand in the campus is large in volume and diverse in types, and there is a certain complementarity in the time distribution of the load. There are more than 15,000 various industrial parks in China, and the carbon emissions of the parks can reach about 31% of the total national emissions. Accurately grasping the heat load data plays an irreplaceable role in realizing efficient energy management, promoting energy conservation and emission reduction measures, and improving environmental comfort.
[0003] However, problems such as insufficient monitoring equipment, loss or damage of data lead to the incompleteness of the basic campus heat load data, which not only restricts the accurate prediction and analysis of energy demand, but also affects the effective formulation and implementation of energy-saving and carbon-reduction strategies.
[0004] Therefore, we propose a method for completing the campus heat load curve based on the RC network thermal dynamic model to improve the basic data for campus heat load analysis. Summary of the Invention
[0005] This application aims to at least solve one of the technical problems existing in the prior art. For this purpose, this application proposes a method for completing the campus heat load curve based on the RC network thermal dynamic model, including the following steps:
[0006] S1. Establish the RC network thermal dynamic model of each building in the campus to simulate the heat transfer process of the building;
[0007] S2. Collect partial heat load data of the buildings in the campus as the input benchmark of the model;
[0008] S3. Use the RC network model to calculate the missing heat load data based on the known heat load data;
[0009] S4. Compare the completed heat load data with the actual measurement data to evaluate the completion effect;
[0010] S5. Adjust the parameters of the RC network model according to the evaluation results and optimize the completion algorithm;
[0011] S6. Repeat steps S3 to S5 until the deviation between the completed data and the actual data meets the preset accuracy requirements;
[0012] S7. Use the optimized model and algorithm to achieve the comprehensive completion of the campus heat load curve.
[0013] In addition, the method for completing the campus heat load curve based on the RC network thermal dynamic model according to the embodiments of this application also has the following additional technical features:
[0014] Preferably, the RC network thermal dynamic model includes multiple RC units for simulating the heat transfer process of a building.
[0015] Preferably, the collecting part of the heat load data includes data obtained from existing monitoring devices.
[0016] Preferably, the metrics used to evaluate the completion effect include root mean square error or mean absolute error.
[0017] Preferably, the optimization algorithms used to adjust the parameters of the RC network model include genetic algorithm or gradient descent algorithm.
[0018] Preferably, the optimization completion algorithm includes machine learning or deep learning algorithms.
[0019] Preferably, the comprehensively completed campus heat load curve is used for campus energy management and energy-saving optimization.
[0020] The present application further provides a device for implementing the above completion method, including a data collection module, a model establishment module, a data calculation module, an effect evaluation module, and a parameter optimization module. The data collection module is used to collect partial heat load data of buildings in the campus; the model establishment module is used to establish an RC network thermal dynamic model; the data calculation module is used to calculate the missing heat load data; the effect evaluation module is used to evaluate the completion effect; the parameter optimization module is used to adjust the model parameters and optimize the completion algorithm.
[0021] The present application further provides a computing system for implementing the above completion method, including a processor and a memory. The processor is used to execute an algorithm for data completion; the memory is used to store an RC network thermal dynamic model, known heat load data, completed heat load data, and software for executing the algorithm.
[0022] The present application further provides a computer program product stored on a computer-readable storage medium for executing the above completion method, which is characterized by including instructions for performing the following steps: receiving an RC network thermal dynamic model and known heat load data; applying a selected algorithm for data completion; using a model evaluation index method to evaluate the completion result; adjusting the algorithm parameters to optimize the completion effect.
[0023] For the campus heat load curve completion method based on the RC network thermal dynamic model according to the embodiments of the present application, the beneficial effects are as follows:
[0024] 1. By using the RC network thermal dynamic model, the heat transfer process of the building is effectively simulated, improving the accuracy of heat load data completion;
[0025] 2. The adaptability and reliability of the completion algorithm are improved through the adjustment and optimization of model parameters;
[0026] 3. Provides data support for comprehensive prediction and analysis of the park's heat load, contributing to energy management and energy-saving optimization;
[0027] 4. It is suitable for parks with incomplete data or insufficient monitoring equipment, and has strong practicality and promotion value. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] In order to more clearly illustrate the technical solutions of the implementation methods of the present application, the following is a brief introduction to the drawings required for use in the implementation methods. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.
[0029] Figure 1 2 is a schematic diagram of a method for completing a campus heat load curve based on an RC network thermal dynamic model according to an embodiment of the present application;
[0030] Figure 2 is a schematic diagram of an RC network model of a single wall of a building according to an embodiment of the present application;
[0031] Figure 3 is a schematic diagram of an RC network model of a single area according to an embodiment of the present application;
[0032] Figure 4 20# plant under different room temperatures according to an embodiment of the present application;
[0033] Figure 5 1 is a schematic diagram of per-unit values of typical heat load curves for each month according to an embodiment of the present application;
[0034] Figure 6 2 is a schematic diagram of a completed heat load curve according to an embodiment of the present application. DETAILED DESCRIPTION
[0035] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.
[0036] The following describes in detail a method for completing the campus heat load curve based on the RC network thermal dynamic model of the present invention through specific embodiments, as Figures 1 - 6 shown, a method for completing the campus heat load curve based on the RC network thermal dynamic model includes the following steps:
[0037] S1. Establish an RC network thermal dynamic model for each building in the campus to simulate the heat transfer process of the building;
[0038] S2. Collect partial heat load data of the buildings in the campus as the input benchmark for the model;
[0039] S3. Use the RC network model to calculate the missing heat load data based on the known heat load data;
[0040] S4. Compare the completed heat load data with the actual measured data to evaluate the completion effect;
[0041] S5. Adjust the parameters of the RC network model according to the evaluation results and optimize the completion algorithm;
[0042] S6. Repeat steps S3 to S5 until the deviation between the completed data and the actual data meets the preset accuracy requirements;
[0043] S7. Use the optimized model and algorithm to achieve a comprehensive completion of the campus heat load curve.
[0044] Specifically, as Figure 2 and Figure 3 shown, the RC network thermal dynamic model includes multiple RC units for simulating the heat transfer process of the building.
[0045] Among them, collecting partial heat load data includes data obtained from existing monitoring equipment.
[0046] Furthermore, the indicators used to evaluate the completion effect include the root mean square error or the mean absolute error.
[0047] Furthermore, the optimization algorithms used to adjust the parameters of the RC network model include the genetic algorithm or the gradient descent algorithm.
[0048] Furthermore, the optimization of the completion algorithm includes machine learning or deep learning algorithms.
[0049] Furthermore, the comprehensively completed campus heat load curve is used for energy management and energy-saving optimization of the campus.
[0050] The present application further provides a device for implementing the completion method, including a data collection module, a model establishment module, a data calculation module, an effect evaluation module, and a parameter optimization module. The data collection module is used to collect partial heat load data of buildings in the park; the model establishment module is used to establish a thermal dynamic model of the RC network; the data calculation module is used to calculate the missing heat load data; the effect evaluation module is used to evaluate the completion effect; the parameter optimization module is used to adjust the model parameters and optimize the completion algorithm.
[0051] The present application further provides a computing system for implementing the completion method, including a processor and a memory. The processor is used to execute an algorithm for data completion; the memory is used to store a thermal dynamic model of the RC network, known heat load data, completed heat load data, and software for executing the algorithm.
[0052] The present application further provides a computer program product, which is stored on a computer-readable storage medium and is used to execute the above-mentioned completion method. It is characterized by including instructions for performing the following steps: receiving a thermal dynamic model of the RC network and known heat load data; applying the selected algorithm for data completion; using the model evaluation index method to evaluate the completion result; adjusting the algorithm parameters to optimize the completion effect.
[0053] Since the basic structures, building materials, and design parameters of the factory buildings in the park are basically the same, Factory Building No. 20 is selected as an example to predict the heating load curve. The thermal resistance, heat capacity, and surface area information of the walls and roofs of Factory Building No. 20 are shown in the following table.
[0054] Thermal Resistance, Heat Capacity and Surface Area of Factory Building (Factory Building No. 20)
[0055] Position East Wall South Wall West Wall North Wall Roof East Window South Window West Window North Window Indoor Air Thermal Resistance 0.648 0.886 0.648 0.521 0.086 2.401 1.742 2.401 1.750 \ Heat Capacity 3.718 17.453 3.718 1.619 54.242 \ \ \ \ 3.157 Surface Area 401.78 545.40 401.78 448.44 3482.10 100.96 139.20 100.96 138.56 \
[0056] According to the building parameters of Factory Building No. 20, the thermal dynamic model prediction method of the RC network is adopted to predict its heat load under three different room temperature requirements of 16°C, 18°C, and 20°C. The prediction curves are as Figure 4 shown.
[0057] From Figure 4 the curves, it can be seen that the heating load of the factory building generally reaches the maximum value at 5:00 - 6:00. After the sun rises, due to the solar radiation effect, the heating load slowly decreases, and the lowest heating load value appears between 13:00 - 14:00.
[0058] At the same time, from the curve shape, it can be seen that under different room temperature requirements, the curve shapes are basically the same, only the heights are different. The curve of 18°C is used as the heating load curve. The per-unit values of the typical heat load curves for each month are as Figure 5 shown.
[0059] Collect heat load data of some buildings in the park as input benchmark for the model;
[0060] When the indoor temperature is controlled at 18℃, the heat load values per unit area in the factory are collected as shown in the following table.
[0061] Heat load per unit area in each month (18℃)
[0062]
[0063]
[0064] Input benchmark data into the RC network model to deduce missing heat load data;
[0065]
[0066]
[0067] The completed heat load curve is as follows Figure 6 As shown in the figure, the completed data is compared with the actual measured data, the deviation is calculated, and based on the deviation analysis, the model parameters are adjusted and the completion algorithm is optimized. The three steps of "inputting the benchmark data into the RC network model and inferring the missing heat load data; comparing the completed data with the actual measured data and calculating the deviation; based on the deviation analysis, adjusting the model parameters and optimizing the completion algorithm" are repeated until the deviation meets the accuracy requirements. The optimized model and algorithm are applied to complete the comprehensive completion of the park's heat load curve.
[0068] The above embodiments are only used to illustrate the specific embodiments of the present invention and are not limited thereto. For those skilled in the art, various similar variations and transformations can be made based on the concept of the present invention, and these variations and transformations should be considered as the protection scope of the present invention.
Claims
1. A method for completing the park heat load curve based on the RC network thermal dynamic model, characterized in that: The following steps are involved: S1. Establish an RC network thermal dynamic model of each building in the park to simulate the heat transfer process of the buildings; S2. Collect heat load data of some buildings in the park as input benchmark for the model; S3. Use the RC network model to estimate the missing heat load data based on the known heat load data; S4. Comparing the completed heat load data with the actual measured data to evaluate the completion effect; S5. Adjust the RC network model parameters based on the evaluation results and optimize the completion algorithm; S6. Repeat steps S3 to S5 until the deviation between the completed data and the actual data meets the preset accuracy requirements; S7. Use the optimized model and algorithm to fully complete the park's heat load curve.
2. The method for completing a park heat load curve based on an RC network thermal dynamic model according to claim 1, wherein: The RC network thermal dynamic model includes a plurality of RC units and is used to simulate the heat transfer process of a building.
3. The method for completing a park heat load curve based on an RC network thermal dynamic model according to claim 1, wherein: The collecting of part of the heat load data includes data obtained from existing monitoring equipment.
4. The method for completing a park heat load curve based on an RC network thermal dynamic model according to claim 1, wherein: The indicators used to evaluate the completion effect include root mean square error or mean absolute error.
5. The method for completing a park heat load curve based on an RC network thermal dynamic model according to claim 1, wherein: The optimization algorithm used to adjust the RC network model parameters includes a genetic algorithm or a gradient descent algorithm.
6. The method for completing a park heat load curve based on an RC network thermal dynamic model according to claim 1, wherein: The optimization and completion algorithm includes a machine learning or deep learning algorithm.
7. The method for completing a park heat load curve based on an RC network thermal dynamic model according to claim 1, wherein: The fully complete park heat load curve is used for energy management and energy-saving optimization of the park.
8. The method for completing a park heat load curve based on an RC network thermal dynamic model according to any one of claims 1 to 7, further comprising a device for implementing the completion method, characterized in that: include: a. Data collection module, used to collect some heat load data of buildings in the park; b. Model building module, used to build the RC network thermal dynamic model; c. Data estimation module, used to estimate missing heat load data; d. Effect evaluation module, used to evaluate the completion effect; e. Parameter optimization module, used to adjust model parameters and optimize the completion algorithm.
9. The method for completing a park heat load curve based on an RC network thermal dynamic model according to claim 1, further comprising a computing system for implementing the completion method, characterized in that: include: a processor for executing an algorithm for data completion; The memory is used to store the RC network thermal dynamic model, known heat load data, completed heat load data, and software for executing the algorithm.
10. The method for completing a campus heat load curve based on an RC network thermal dynamic model according to claim 1, further comprising a computer program product, contained on a computer-readable storage medium, for executing the completion method, characterized in that: Includes instructions for performing the following steps: a. Receive the RC network thermal dynamic model and known heat load data; b. Apply the selected algorithm to complete the data; c. Use the model evaluation index method to evaluate the completion results; d. Adjust algorithm parameters to optimize completion effect.