Heating optimization method, apparatus, device, storage medium and product
By combining user behavior and real-time weather data to adjust the weighting coefficients, and using sensitivity analysis and an optimized long short-term memory network algorithm to construct a heating assessment model, the problem of low accuracy in heating assessment models is solved, and efficient optimization and precise control of the heating system are achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- PETROCHINA SHENZHEN NEW ENERGY RESEARCH INSTITUTE CO LTD
- Filing Date
- 2024-11-28
- Publication Date
- 2026-05-29
Smart Images
Figure CN122107446A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of smart heating technology, and in particular to a heating optimization method, apparatus, equipment, storage medium, and product. Background Technology
[0002] Extracting valuable information from historical data and constructing appropriate heating forecasting models is of great significance for heating companies to improve heating quality and energy efficiency. Existing technologies improve the accuracy of heating demand assessment models, thereby achieving precise heating for the system. However, the selection of weighting coefficients is influenced by various factors, including building structure, user behavior, and weather conditions. Inappropriate weighting coefficient settings can lead to inaccurate indoor temperature data calculations, thus affecting the accuracy of the heating assessment model. Summary of the Invention
[0003] The main objective of this application is to provide a heating optimization method, apparatus, equipment, storage medium, and product, which aims to solve the technical problem of how to optimize the operation of the heating system by improving the accuracy of the heating assessment model.
[0004] To achieve the above objectives, this application proposes a heating optimization method, the method comprising:
[0005] Based on user behavior data and real-time weather data, the weighting coefficients of temperature measurement points are adjusted to obtain the adjusted weighting coefficients.
[0006] Based on the adjusted weighting coefficients, sensitivity analysis was used to analyze the factors affecting heating assessment and to obtain the factors with the greatest impact on heating assessment.
[0007] A heating assessment model is constructed based on the optimized long short-term memory network algorithm and the user behavior data.
[0008] The user behavior data, the real-time weather data, and the factors with the greatest impact on the heating assessment are input into the heating assessment model to obtain the assessment results, and the heating control parameters and operating parameters are optimized based on the assessment results.
[0009] In one embodiment, the step of analyzing the influencing factors of heating assessment using sensitivity analysis based on the adjusted weighting coefficients to obtain the factor with the greatest influence on heating assessment includes:
[0010] Based on the adjusted weighting coefficients, the temperature fusion value is calculated by weighted summation of the user behavior data;
[0011] Based on the temperature fusion value and sensitivity analysis method, the sensitivity of the influencing factors is calculated according to the initial values of the influencing factors of heating assessment and the initial values of heating demand load. The influencing factors of heating assessment include user behavior types and weather parameter types.
[0012] Based on the sensitivity of the influencing factors and the preset sensitivity threshold, important influencing factors for heating assessment are selected from the influencing factors of heating assessment.
[0013] The factor with the greatest impact on the heating assessment was selected from the important factors affecting the heating assessment.
[0014] In one embodiment, after the steps of inputting the user behavior data, the real-time weather data, and the factors with the greatest impact on heating assessment into the heating assessment model to obtain assessment results, and optimizing heating control parameters and operating parameters based on the assessment results, the method further includes:
[0015] Adjust the heating output based on the assessment results and the real-time weather data;
[0016] Adjust the heating operation parameters based on the assessment results and the actual operating status of the heating system.
[0017] The actual temperature at the temperature measuring point is monitored in real time, and the temperature error is calculated when the actual temperature is inconsistent with the target temperature.
[0018] Based on the evaluation results and the temperature error, adjust the heating operation parameters.
[0019] In one embodiment, before the step of constructing a heating assessment model based on the user behavior data using an optimized long short-term memory network algorithm, the method further includes:
[0020] Based on the bat algorithm, an improved bat algorithm is obtained by optimizing the update methods of bat frequency, position, and speed;
[0021] The parameters of the Long Short-Term Memory (LSTM) network algorithm are optimized using the improved bat algorithm to obtain the optimized LSM network algorithm.
[0022] In one embodiment, before the step of adjusting the weighting coefficients of temperature measurement points based on user behavior data and real-time weather data to obtain the adjusted weighting coefficients, the method further includes:
[0023] Multiple temperature measurement points are set up, and user behavior data is collected by smart devices through these multiple temperature measurement points within a preset period.
[0024] Obtain real-time weather data from meteorological services within a preset period;
[0025] The user behavior data and the real-time weather data are preprocessed, including data cleaning and normalization.
[0026] In one embodiment, the step of constructing a heating assessment model based on the user behavior data using an optimized long short-term memory network algorithm includes:
[0027] The user behavior data and the real-time weather data are used as time series data;
[0028] The time series data is preliminarily analyzed using time series analysis techniques to obtain the characteristics of the time series data;
[0029] Extract time series features from the time series data;
[0030] Based on the characteristics and features of the time series data, design the network structure of the optimized Long Short-Term Memory network algorithm;
[0031] A heating assessment model is constructed based on the network structure and the factors that have the greatest impact on the heating load assessment.
[0032] Furthermore, to achieve the above objectives, this application also proposes a heating optimization device, which includes:
[0033] The weight adjustment module is used to adjust the weight coefficients of temperature measurement points based on user behavior data and real-time weather data, and obtain the adjusted weight coefficients.
[0034] The factor screening module is used to analyze the factors affecting the heating assessment based on the adjusted weight coefficients using a sensitivity analysis method, and to obtain the factors with the greatest impact on the heating assessment.
[0035] The model building module is used to build a heating assessment model based on the user behavior data, using an optimized long short-term memory network algorithm.
[0036] The parameter optimization module is used to input the user behavior data, the real-time weather data, and the factors with the greatest impact on the heating assessment into the heating assessment model, obtain the assessment results, and optimize the heating control parameters and operating parameters based on the assessment results.
[0037] In addition, to achieve the above objectives, this application also proposes a heating optimization device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the heating optimization method as described above.
[0038] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the heating optimization method described above.
[0039] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the heating optimization method described above.
[0040] The technical solution proposed in this application adjusts the weighting coefficients of temperature measuring points based on user behavior data and real-time weather data to obtain adjusted weighting coefficients. Based on these adjusted weighting coefficients, sensitivity analysis is used to analyze the influencing factors of heating assessment, identifying the factors with the greatest impact on heating assessment. A heating assessment model is constructed based on an optimized Long Short-Term Memory (LSTM) network algorithm and user behavior data. The user behavior data, real-time weather data, and the factors with the greatest impact on heating assessment are input into the heating assessment model to obtain assessment results. Heating control parameters and operating parameters are then optimized based on these results. Because this application adjusts the weighting coefficients by combining user behavior data and real-time weather data, thereby constructing a heating assessment model and optimizing heating parameters, the accuracy of the heating assessment model is improved, and the operation of the heating system is optimized. Attached Figure Description
[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0043] Figure 1 This is a flowchart illustrating an embodiment of the heating optimization method of this application.
[0044] Figure 2 This is a schematic diagram of the steps in the heating optimization method of this application;
[0045] Figure 3 This is a flowchart illustrating Embodiment 2 of the heating optimization method of this application;
[0046] Figure 4 This is a flowchart illustrating Embodiment 3 of the heating optimization method of this application;
[0047] Figure 5This is a schematic diagram of the module structure of the heating optimization device according to an embodiment of this application;
[0048] Figure 6 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the heating optimization method in the embodiments of this application.
[0049] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0050] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.
[0051] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.
[0052] Existing technologies improve the accuracy of heating demand assessment by refining the assessment model, thereby achieving precise heating of the heating system. However, the selection of weighting coefficients is affected by a variety of factors, including building structure, heat user behavior, and weather conditions. Inappropriate weighting coefficient settings can lead to inaccurate calculation of indoor temperature data, which in turn affects the accuracy of the heating assessment model.
[0053] Therefore, in order to overcome the above-mentioned defects, this application provides a solution that combines user behavior data and real-time weather data to adjust the weighting coefficients, thereby constructing a heating assessment model to optimize heating parameters, improving the accuracy of the heating assessment model and optimizing the operation of the heating system.
[0054] It should be noted that the executing entity of each embodiment of this application can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or heating optimization device capable of realizing the above functions. The following embodiments will be described using a heating optimization device as an example.
[0055] Based on this, the embodiments of this application provide a heating optimization method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the heating optimization method of this application.
[0056] In this embodiment, the heating optimization method includes steps S10 to S40:
[0057] Step S10: Adjust the weight coefficients of temperature measurement points based on user behavior data and real-time weather data to obtain the adjusted weight coefficients.
[0058] It should be noted that user behavior data refers to user behavior data related to the heating system in daily life, such as room temperature adjustment, window opening and closing, and outdoor activity patterns. Real-time weather data refers to current or recent weather conditions, such as temperature, humidity, and wind speed. Temperature measurement points refer to the points in the heating system used to measure temperature. In data analysis, weighting coefficients are used to represent the degree of influence of different factors or data points on the final result.
[0059] Based on user behavior data, we can understand users' behavioral habits, such as indoor activity time and temperature preferences. The heating system can adjust the inlet temperature in real time. For example, it can raise the indoor temperature in advance before users get up, or lower the heating temperature after users leave home; it can automatically reduce the heating power at night when users are used to lower temperatures, and automatically increase the heating power in the morning when users are used to higher temperatures.
[0060] By combining real-time weather data, the heating system can predict and respond to weather changes in real time, such as a sudden drop or rise in temperature. It can adjust the heating parameters in advance according to the weather forecast to ensure that the indoor temperature is raised in time when cold weather arrives, or the heating is appropriately reduced when the temperature rises.
[0061] In addition, by combining user behavior data and real-time weather data, the heating system can more accurately control the output of heating equipment, such as boilers and heat pumps. It can adjust the operating status of heating equipment based on real-time data to avoid overheating or overcooling and ensure that the temperature entering the house is always kept within the ideal range.
[0062] Understandably, adjusting the weighting coefficients of temperature measurement points based on user behavior data and real-time weather data means that the system will dynamically adjust the importance of each temperature measurement point in evaluating the heating effect according to changes in external conditions.
[0063] For example, the dynamic adjustment calculation of the weighting coefficients can be as follows:
[0064] wi(t)=f(Bj(t),Wl(t)) (1)
[0065] Specifically,
[0066]
[0067] In the formula, w i (t) represents the weighting coefficient of the i-th measurement point at time t, B j (t) represents the data for the j-th user behavior at time t, and α represents user behavior B. j The influence factor of (t) is n, which is the total number of measurement points.
[0068] Understandably, in order to ensure that all weight coefficients are within a certain range, it is necessary to normalize the weight coefficients.
[0069] For example, the normalization calculation of the weight coefficients can be as follows:
[0070]
[0071] In the formula, w i (t) is the weighting coefficient of the i-th measurement point at time t.
[0072] Step S20: Based on the adjusted weighting coefficients, a sensitivity analysis method is used to analyze the influencing factors of heating assessment and obtain the factors with the greatest influence on heating assessment.
[0073] It should be noted that sensitivity analysis is an important tool for studying system uncertainty and its influencing factors.
[0074] It should be understood that various factors can significantly impact heating performance during heating assessments. Therefore, sensitivity analysis can be used to evaluate the degree of influence of these factors on the assessment, thereby identifying the most influential factors.
[0075] Step S30: Based on the optimized Long Short-Term Memory network algorithm, construct a heating assessment model according to the user behavior data.
[0076] It should be noted that Long Short-Term Memory (LSTM) is a type of recurrent neural network that is particularly suitable for processing and predicting time series data.
[0077] Understandably, an optimized Long Short-Term Memory (LSTM) network algorithm is used to build a heating assessment model based on collected user behavior data. This model will predict future heating demand or assess current heating effectiveness based on historical data such as users' heating preferences and usage habits.
[0078] For example, the parameter optimization calculation for a long short-term memory network can be:
[0079] θ opt =IBA(θ0) (4)
[0080] In the formula, θ opt θ0 represents the optimized long short-term memory network parameters, while θ0 represents the initial long short-term memory network parameters.
[0081] Furthermore, an optimized Long Short-Term Memory (LSTM) network algorithm can be obtained based on the bat algorithm. Therefore, before step S30, the following steps are also included:
[0082] Based on the bat algorithm, an improved bat algorithm is obtained by optimizing the update methods of bat frequency, position, and speed;
[0083] The parameters of the Long Short-Term Memory (LSTM) network algorithm are optimized using the improved bat algorithm to obtain the optimized LSM network algorithm.
[0084] It should be noted that the Bat Algorithm (BA) is based on iterative optimization techniques. It initializes a set of random solutions and then searches for the optimal solution through iteration. In addition, it generates new local solutions around the optimal solution by randomly flying around it, thereby strengthening the local search.
[0085] It should be understood that, based on the bat algorithm, an improved strategy is proposed, mainly optimizing the update methods for the frequency, position, and speed of the bats, thus obtaining an improved bat algorithm. This improvement enables the algorithm to explore the solution space more efficiently during the search process, avoids premature convergence, and enhances global search capabilities.
[0086] For example, the improved bat algorithm calculation formula is as follows:
[0087] f i =f min +(f max -f min rand (5)
[0088] In the formula, f i f is the frequency of the i-th bat. max f is the maximum frequency. min The minimum frequency.
[0089] Bat position and speed update formula:
[0090] v i (t+1)=v i (t)+(x i (t)-x * )·f i (6)
[0091] x i (t+1)=x i (t)+v i (t+1) (7)
[0092] In the formula, v i (t) represents the velocity of the i-th bat at time t, x * This represents the position of the current optimal solution.
[0093] Then, the parameters of the Long Short-Term Memory (LSTM) network algorithm are optimized using an improved bat algorithm. Algorithm optimization can be achieved by adjusting key parameters such as the number of hidden layers, the number of neurons, and the learning rate. During optimization, the LTM network parameters are treated as "position" vectors in the bat algorithm, and the optimal parameter combination is found through the flight search of bats. The improved bat algorithm guides the search process towards a better parameter configuration through its optimized frequency, position, and speed update strategies until a preset stopping condition is reached. Finally, the optimized LTM network algorithm is obtained.
[0094] Step S40: Input the user behavior data, the real-time weather data, and the factors with the greatest impact on heating assessment into the heating assessment model to obtain the assessment results, and optimize the heating control parameters and operating parameters based on the assessment results.
[0095] Understandably, user behavior data, real-time weather data, and the factors with the greatest impact on heating assessment identified through sensitivity analysis are first input into a pre-built and trained heating assessment model. After the model runs, it outputs an assessment result that reflects the overall effectiveness of the heating system under current conditions, as well as potential problems or areas for improvement. Based on the assessment result, the control and operating parameters of the heating system are optimized and adjusted.
[0096] It should be noted that control parameters may include temperature settings, the operating frequency of the circulating pump, etc., while operating parameters may involve the output power of the heat source, the flow distribution of the heating network, etc.
[0097] Furthermore, it is understandable that optimizing heating control and operating parameters is a continuous iterative and optimization process that requires constantly collecting new data, updating the model, and adjusting parameters based on evaluation results.
[0098] For ease of understanding, please refer to Figure 2 This explanation is provided, but does not limit the scope of this application. Figure 2 This is a flowchart illustrating the steps of the heating optimization method in this application. The steps of heating optimization can be as follows:
[0099] 1. Data Acquisition and Preprocessing: Multiple indoor temperature measurement points are set up at different heat users in the heating system, and indoor temperature measurement values are acquired at multiple times within a preset period. The acquired data is then preprocessed.
[0100] 2. Dynamic adjustment of weighting coefficients: The weighting coefficients of each indoor temperature measuring point are dynamically adjusted based on user behavior and weather conditions. For example, if a user keeps the window open for a long time, the indoor temperature will drop, and the weighting coefficient of that measuring point should be increased accordingly. The weighting coefficients are dynamically calculated and updated based on the latest user behavior and weather data.
[0101] 3. Temperature fusion value calculation: Based on the dynamically adjusted weighting coefficients, the indoor temperature fusion value of each indoor temperature measuring point is calculated;
[0102] 4. Sensitivity Analysis and Screening of Important Influencing Factors: Sensitivity analysis is used to analyze various influencing factors affecting the assessment of heating demand load, and important influencing factors are screened out. Based on the results of the sensitivity analysis, the factors with the greatest impact on heating demand are selected as the key considerations for model input.
[0103] 5. Algorithm Improvement and Optimization: An improved bat algorithm is used to optimize the parameters of the Long Short-Term Memory Network algorithm. The optimized Long Short-Term Memory Network algorithm is then used to train a model of heating demand load.
[0104] 6. Heating demand load assessment model construction: Based on the optimized long short-term memory network algorithm, a heating demand load assessment model is constructed. Real-time user behavior data, weather data, and the most influential factors are input into the model to conduct real-time assessment of heating demand load.
[0105] 7. Parameter adjustment and optimization: Adjust the operating parameters of the heating system based on the evaluation results, and dynamically adjust the output of the heating system.
[0106] This embodiment adjusts the weighting coefficients of temperature measurement points based on user behavior data and real-time weather data to obtain adjusted weighting coefficients. Based on these adjusted weighting coefficients, sensitivity analysis is used to analyze the influencing factors of heating assessment, identifying the factors with the greatest impact on heating assessment. A heating assessment model is constructed based on an optimized Long Short-Term Memory (LSTM) network algorithm and user behavior data. The user behavior data, real-time weather data, and the factors with the greatest impact on heating assessment are input into the heating assessment model to obtain assessment results. Heating control parameters and operating parameters are then optimized based on these results. Because this application adjusts the weighting coefficients by combining user behavior data and real-time weather data, thereby constructing a heating assessment model and optimizing heating parameters, the accuracy of the heating assessment model is improved, and the operation of the heating system is optimized.
[0107] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S20 may include steps S201 to S204:
[0108] Step S201: Based on the adjusted weighting coefficients, calculate the temperature fusion value by weighted summation of the user behavior data.
[0109] It should be noted that the temperature fusion value is a temperature index calculated by integrating multiple factors. It aims to reflect the most suitable or expected temperature level in an environment or system, determined based on specific weights and various influencing factors (such as user behavior, weather conditions, system performance, etc.).
[0110] For example, the temperature fusion value can be calculated as follows:
[0111]
[0112] In the formula, T fused (t) represents the combined indoor temperature value at time t, w i (t) represents the weighting coefficient of the i-th measurement point at time t, T' i (t) represents the normalized indoor temperature measurement value (user behavior data) at time t for the i-th measuring point.
[0113] Step S202: Based on the temperature fusion value and sensitivity analysis method, calculate the sensitivity of the influencing factors according to the initial values of the influencing factors of heating assessment and the initial values of heating demand load. The influencing factors of heating assessment include user behavior types and weather parameter types.
[0114] It is understandable that user behavior types can include opening and closing windows, using electric heaters, and frequent indoor activities; weather parameters can include outdoor temperature, wind speed, humidity, etc.
[0115] It should be understood that, based on temperature fusion values and sensitivity analysis methods, the impact of user behavior types and weather parameter types on heating demand load in the heating system can be comprehensively assessed. By quantifying the initial values of each influencing factor and calculating its sensitivity coefficient, it is possible to determine which factors have a significant impact on the performance of the heating system.
[0116] For example, sensitivity analysis calculations can be performed as follows:
[0117]
[0118] In the formula, S l Let Y be the initial value of the output variable, and X be the sensitivity of the l-th influencing factor. l This is the initial value for the l-th influencing factor.
[0119] Step S203: Based on the sensitivity of the influencing factors and the preset sensitivity threshold, select the important influencing factors for heating assessment from the influencing factors for heating assessment.
[0120] Understandably, by using the sensitivity of influencing factors and preset sensitivity thresholds, factors affecting heating assessment can be screened to determine which factors are important. This process involves comparing the sensitivity of each influencing factor with the preset threshold. If the sensitivity coefficient of an influencing factor is higher than the threshold, it is considered an important influencing factor in the heating assessment.
[0121] For example, the sensitivity analysis calculation in the sensitivity analysis and screening of important influencing factors is as follows:
[0122]
[0123] In the formula, H load This is the initial value of the heating demand load.
[0124] The calculation for selecting key influencing factors is as follows:
[0125] Select l where S l >threshold (11)
[0126] In the formula, l is the index of the influencing factor, and threshold is the preset sensitivity threshold.
[0127] Step S204: Select the factor with the greatest impact on the heating assessment from the important influencing factors of the heating assessment.
[0128] It should be understood that after identifying the important influencing factors in heating assessment, it is necessary to further select the factors with the greatest impact. This usually involves ranking or comparing the selected important factors to determine which one or more factors have the most significant impact on the performance of the heating system.
[0129] This embodiment calculates a temperature fusion value by weighting and summing user behavior data based on adjusted weighting coefficients. Based on the temperature fusion value and sensitivity analysis, it calculates the sensitivity of influencing factors according to the initial values of heating assessment influencing factors and the initial value of heating demand load. Based on the sensitivity of influencing factors and a preset sensitivity threshold, it selects important influencing factors from the heating assessment influencing factors, and then selects the factor with the greatest influence from among the important influencing factors. This improves the accuracy of data fusion, achieves more precise and efficient heating assessment, and enhances the overall performance and energy utilization efficiency of the heating system.
[0130] In the second embodiment, before step S10, the method further includes:
[0131] Multiple temperature measurement points are set up, and user behavior data is collected by smart devices through these multiple temperature measurement points within a preset period.
[0132] Obtain real-time weather data from meteorological services within a preset period;
[0133] The user behavior data and the real-time weather data are preprocessed, including data cleaning and normalization.
[0134] Understandably, data collection and preprocessing steps are necessary to comprehensively evaluate the performance of the heating system and accurately identify key influencing factors. Multiple indoor temperature measurement points are set up at different heat users within the heating system, and indoor temperature measurements (user behavior data) are acquired at multiple times within a preset period. Daily behavioral data of users can be collected through smart devices (smart meters and smart switches), real-time weather data can be obtained from meteorological services, and the collected data is cleaned and normalized to ensure accuracy and consistency.
[0135] For example, the indoor temperature measurement value can be calculated as follows:
[0136] T i (t)for i=1,2,...,n and t=t1,t2,...,t m (12)
[0137] In the formula, T i (t) represents the indoor temperature measurement value at time t of the i-th measuring point, where i ranges from 1 to n, and t ranges from t1 to t2. m Where n is the total number of measuring points, t m The total number of measurement times, t = t1, t2, ..., t m For the measurement time.
[0138] User behavior data is calculated as follows:
[0139] B j (t)for j=1,2,...,k and t=t1,t2,...,t m (13)
[0140] In the formula, B j (t) represents the data of the j-th user behavior at time t, where t = t1, t2, ..., tm are the measurement times.
[0141] Real-time weather data is calculated as follows:
[0142] W l (t)for l=1,2,...,p and t=t1,t2,...,t m (14)
[0143] In the formula, W l(t) represents the data of the l-th weather parameter at time t, where l ranges from 1 to p, and t ranges from t1, t2, ..., tp. m Where p is the total number of weather parameter types, and t = t1, t2, ..., t m This represents the total number of measurement moments.
[0144] This embodiment sets up multiple temperature measurement points and uses smart devices to collect user behavior data within a preset period. Real-time weather data is obtained from meteorological services within the preset period. The user behavior data and real-time weather data are preprocessed, including data cleaning and normalization, so as to provide a comprehensive and accurate information foundation for heating assessment, effectively improve data quality, and thus ensure the accuracy and reliability of heating assessment and optimization.
[0145] Based on the first embodiment of this application, in the third embodiment of this application, the content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 After step S30, steps S311 to S314 may also be included:
[0146] Step S311: Adjust the heating output based on the evaluation results and the real-time weather data.
[0147] Understandably, based on the assessment results and real-time weather data, the output of the heating system can be finely adjusted. This may include adjusting the firepower of the heating boiler, changing the water flow rate in the heating pipes, and adjusting the opening of the radiators.
[0148] For example, the output adjustment calculation of the heating system can be:
[0149] Q output (t)=PID(T target (t)-T actual (t),H load (t)) (15)
[0150] In the formula, Q output (t) represents the output of the heating system at time t, where T is the output of the heating system at time t. target (t) represents the target indoor temperature at time t, in H. load (t) represents the heating demand load at time t.
[0151] Step S312: Adjust the heating operation parameters based on the evaluation results and the actual operating status of the heating system.
[0152] Understandably, based on the assessment results and the current operating status of the heating system, by deeply analyzing the assessment results and combining them with factors such as real-time weather and user behavior, it is possible to accurately identify and optimize potential performance bottlenecks and make timely adjustments to heating operation parameters (heating temperature, flow rate, pressure, etc.).
[0153] Step S313: Monitor the actual temperature of the temperature measuring point in real time, and calculate the temperature error when the actual temperature is inconsistent with the target temperature.
[0154] It is understandable that real-time monitoring of each temperature measuring point in the heating system is necessary to ensure stable system operation. During the monitoring process, if a deviation is found between the actual temperature and the preset target temperature, the magnitude of the temperature error is quickly determined using precise mathematical methods.
[0155] Step S314: Adjust the heating operation parameters based on the evaluation results and the temperature error.
[0156] For example, the calculation formula for the heating assessment model is as follows:
[0157] X input (t)=[X user (t),X weather (t)] (16)
[0158] In the formula, X input (t) represents the model input data at time t.
[0159]
[0160] In the formula, P control (t) represents the heating control parameters at time t, P current (t) represents the heating operation parameters at the current time t.
[0161] Heating adjustment calculations can be performed as follows:
[0162]
[0163] In the formula, Q output Q(t) represents the heat output of the heating system at time t. demand (t) represents the heat demand at time t, and e(t) represents the temperature error at time t, i.e., the difference between the target temperature and the actual temperature; K i These are integral control parameters; This is the integral of the temperature error.
[0164] Temperature error is calculated as follows:
[0165] e(t) = T target (t)-T actual (t) (19)
[0166] In the formula, T target (t) represents the target temperature at time t.
[0167] The calculation comparing the actual temperature and the target temperature is as follows:
[0168] ΔT(t)=T actual (t)-T target (t) (20)
[0169] In the formula, ΔT(t) is the difference between the actual temperature and the target temperature at time t.
[0170] P control (t)=P current (t)+f adjust (ΔT(t)) (21)
[0171] In the formula, f adjust This is a function for adjusting heating operation parameters.
[0172] This embodiment adjusts the heating output based on the evaluation results and real-time weather data, adjusts the heating operation parameters based on the evaluation results and the actual operating status of the heating system, monitors the actual temperature of the temperature measuring points in real time, calculates the temperature error when the actual temperature is inconsistent with the target temperature, and adjusts the heating operation parameters based on the evaluation results and the temperature error. This allows for flexible adjustment of the heating output, ensuring that the heating efficiency matches the demand, finely adjusting the operation parameters, improving the heating stability, and achieving dynamic optimization of the heating system.
[0173] In the third embodiment, S30 includes:
[0174] The user behavior data and the real-time weather data are used as time series data;
[0175] The time series data is preliminarily analyzed using time series analysis techniques to obtain the characteristics of the time series data;
[0176] Extract time series features from the time series data;
[0177] Based on the characteristics and features of the time series data, design the network structure of the optimized Long Short-Term Memory network algorithm;
[0178] A heating assessment model is constructed based on the network structure and the factors that have the greatest impact on the heating load assessment.
[0179] It should be noted that a time series refers to a sequence of data in which the values of the same statistical indicator are arranged in chronological order of their occurrence. Time series data essentially reflects the trend of one or more random variables changing over time. Time series techniques, such as the Autoregressive Integrated Moving Average (ARIMA) model, focus on the analysis and application of time series data, aiming to extract potential patterns, trends, and periodic components from the data in order to predict future data or make decisions.
[0180] It should be understood that data processing based on time series analysis techniques is used to more accurately predict and assess heating demand load. First, user behavior data and real-time weather data are integrated into time series data. Next, time series analysis techniques are used to conduct preliminary analysis of the integrated data to reveal its inherent characteristics and patterns. Then, key time series features are extracted from the time series data; these features reflect the core information and trends of the data.
[0181] After obtaining the characteristics and features of the time series data, we designed and optimized the network structure of the Long Short-Term Memory (LSTM) network algorithm. Through this network structure, and in conjunction with the factors that have the greatest impact on the heating load assessment, we constructed a heating assessment model.
[0182] This embodiment uses user behavior data and real-time weather data as time series data. It performs preliminary analysis on the time series data using time series analysis technology to obtain the characteristics of the time series data, extracts time series features from the time series data, and designs an optimized network structure for the Long Short-Term Memory (LSTM) network algorithm based on the characteristics and features of the time series data. Based on the network structure and the factors that have the greatest impact on heating load assessment, a heating demand load assessment model is constructed, thereby accurately capturing data characteristics and features, improving prediction accuracy, and enhancing the response speed of the heating system.
[0183] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the heating optimization method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.
[0184] This application also provides a heating optimization device, please refer to... Figure 5 The heating optimization device includes:
[0185] The weight adjustment module 10 is used to adjust the weight coefficients of temperature measuring points based on user behavior data and real-time weather data, and obtain the adjusted weight coefficients.
[0186] The factor screening module 20 is used to analyze the factors affecting the heating assessment based on the adjusted weight coefficients using a sensitivity analysis method, and to obtain the factors with the greatest impact on the heating assessment.
[0187] Model building module 30 is used to build a heating assessment model based on the user behavior data using an optimized long short-term memory network algorithm.
[0188] The parameter optimization module 40 is used to input the user behavior data, the real-time weather data, and the factors with the greatest impact on the heating assessment into the heating assessment model, obtain the assessment results, and optimize the heating control parameters and operating parameters based on the assessment results.
[0189] The heating optimization device provided in this application, employing the heating optimization method in the above embodiments, can solve the technical problem of how to optimize the operation of the heating system by improving the accuracy of the heating assessment model. Compared with the prior art, the beneficial effects of the heating optimization device provided in this application are the same as those of the heating optimization method provided in the above embodiments, and other technical features in the heating optimization device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.
[0190] This application provides a heating optimization device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the heating optimization method in Embodiment 1 above.
[0191] The following is for reference. Figure 6 The diagram illustrates a structural schematic suitable for implementing the heating optimization device in the embodiments of this application. The heating optimization device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Desserts), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The heating optimization device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.
[0192] like Figure 6As shown, the heating optimization device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the heating optimization device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the heating optimization equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows heating optimization equipment with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented alternatively.
[0193] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.
[0194] The heating optimization device provided in this application, employing the heating optimization method described in the above embodiments, can solve the technical problem of how to optimize the operation of the heating system by improving the accuracy of the heating assessment model. Compared with the prior art, the beneficial effects of the heating optimization device provided in this application are the same as those of the heating optimization method provided in the above embodiments, and other technical features of the heating optimization device are the same as those disclosed in the previous embodiment method, and will not be repeated here.
[0195] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.
[0196] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
[0197] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the heating optimization method in the above embodiments.
[0198] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0199] The aforementioned computer-readable storage medium may be included in the heating optimization equipment; or it may exist independently and not assembled into the heating optimization equipment.
[0200] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the heating optimization equipment, the heating optimization equipment: adjusts the weight coefficients of temperature measuring points based on user behavior data and real-time weather data to obtain adjusted weight coefficients; analyzes the influencing factors of heating assessment using a sensitivity analysis method based on the adjusted weight coefficients to obtain the factors with the greatest influence on heating assessment; constructs a heating assessment model based on user behavior data using an optimized long short-term memory network algorithm; inputs user behavior data, real-time weather data, and the factors with the greatest influence on heating assessment into the heating assessment model to obtain assessment results; and optimizes heating control parameters and operating parameters based on the assessment results.
[0201] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0202] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0203] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.
[0204] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described heating optimization method. This program can solve the technical problem of how to optimize the operation of the heating system by improving the accuracy of the heating assessment model. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the heating optimization method provided in the above embodiments, and will not be repeated here.
[0205] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the heating optimization method described above.
[0206] The computer program product provided in this application can solve the technical problem of how to optimize the operation of a heating system by improving the accuracy of a heating assessment model. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the heating optimization method provided in the above embodiments, and will not be repeated here.
[0207] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.
Claims
1. A heating optimization method, characterized in that, The method includes the following steps: Based on user behavior data and real-time weather data, the weighting coefficients of temperature measurement points are adjusted to obtain the adjusted weighting coefficients. Based on the adjusted weighting coefficients, sensitivity analysis was used to analyze the factors affecting heating assessment and to obtain the factors with the greatest impact on heating assessment. A heating assessment model is constructed based on the optimized long short-term memory network algorithm and the user behavior data. The user behavior data, the real-time weather data, and the factors with the greatest impact on the heating assessment are input into the heating assessment model to obtain the assessment results, and the heating control parameters and operating parameters are optimized based on the assessment results.
2. The heating optimization method as described in claim 1, characterized in that, The step of analyzing the influencing factors of heating assessment using sensitivity analysis based on the adjusted weighting coefficients to obtain the factor with the greatest influence on heating assessment includes: Based on the adjusted weighting coefficients, the temperature fusion value is calculated by weighted summation of the user behavior data; Based on the temperature fusion value and sensitivity analysis method, the sensitivity of the influencing factors is calculated according to the initial values of the influencing factors of heating assessment and the initial values of heating demand load. The influencing factors of heating assessment include user behavior types and weather parameter types. Based on the sensitivity of the influencing factors and the preset sensitivity threshold, important influencing factors for heating assessment are selected from the influencing factors of heating assessment. The factor with the greatest impact on the heating assessment was selected from the important factors affecting the heating assessment.
3. The heating optimization method as described in claim 1, characterized in that, After the steps of inputting the user behavior data, the real-time weather data, and the factors with the greatest impact on heating assessment into the heating assessment model to obtain assessment results, and optimizing heating control parameters and operating parameters based on the assessment results, the method further includes: Adjust the heating output based on the assessment results and the real-time weather data; Adjust the heating operation parameters based on the assessment results and the actual operating status of the heating system. The actual temperature at the temperature measuring point is monitored in real time, and the temperature error is calculated when the actual temperature is inconsistent with the target temperature. Based on the evaluation results and the temperature error, adjust the heating operation parameters.
4. The heating optimization method as described in claim 1, characterized in that, Before the step of constructing a heating assessment model based on the user behavior data using the optimized long short-term memory network algorithm, the method further includes: Based on the bat algorithm, an improved bat algorithm is obtained by optimizing the update methods of bat frequency, position, and speed; The parameters of the Long Short-Term Memory (LSTM) network algorithm are optimized using the improved bat algorithm to obtain the optimized LSM network algorithm.
5. The heating optimization method as described in claim 1, characterized in that, Before the step of adjusting the weighting coefficients of temperature measurement points based on user behavior data and real-time weather data to obtain the adjusted weighting coefficients, the method further includes: Multiple temperature measurement points are set up, and user behavior data is collected by smart devices through these multiple temperature measurement points within a preset period. Obtain real-time weather data from meteorological services within a preset period; The user behavior data and the real-time weather data are preprocessed, including data cleaning and normalization.
6. The heating optimization method as described in claim 1, characterized in that, The step of constructing a heating assessment model based on the user behavior data using the optimized long short-term memory network algorithm includes: The user behavior data and the real-time weather data are used as time series data; The time series data is preliminarily analyzed using time series analysis techniques to obtain the characteristics of the time series data; Extract time series features from the time series data; Based on the characteristics and features of the time series data, design the network structure of the optimized Long Short-Term Memory network algorithm; A heating assessment model is constructed based on the network structure and the factors that have the greatest impact on the heating load assessment.
7. A heating optimization device, characterized in that, The heating optimization device includes: The weight adjustment module is used to adjust the weight coefficients of temperature measurement points based on user behavior data and real-time weather data, and obtain the adjusted weight coefficients. The factor screening module is used to analyze the factors affecting the heating assessment based on the adjusted weight coefficients using a sensitivity analysis method, and to obtain the factors with the greatest impact on the heating assessment. The model building module is used to build a heating assessment model based on the user behavior data, using an optimized long short-term memory network algorithm. The parameter optimization module is used to input the user behavior data, the real-time weather data, and the factors with the greatest impact on the heating assessment into the heating assessment model, obtain the assessment results, and optimize the heating control parameters and operating parameters based on the assessment results.
8. A heating optimization device, characterized in that, The heating optimization device includes: a memory, a processor, and a heating optimization program stored in the memory and executable on the processor, wherein the heating optimization program, when executed by the processor, implements the heating optimization method as described in any one of claims 1 to 6.
9. A storage medium, characterized in that, The storage medium stores a heating optimization program, which, when executed by a processor, implements the heating optimization method as described in any one of claims 1 to 6.
10. A computer program product, characterized in that, The computer program product includes a heating optimization program, which, when executed by a processor, implements the heating optimization method as described in any one of claims 1 to 6.