Energy efficiency optimization system and method for heat pump system

Abstract

The invention relates to the technical field of heat supply management, and discloses an energy efficiency optimization system and method for a heat pump system, and the method comprises the steps: determining a temperature difference set according to the meteorological data of each sub-residential area, obtaining the indoor temperature data of each sub-residential area, and comparing the indoor temperature data with indoor standard temperature data, a heat supply data chain is constructed based on the comparison result and the temperature difference set, the required heat supply load capacity of the heat pump system is determined based on a random forest model, the standard heat supply load capacity of the heat pump system is obtained based on the preset heat supply requirement, and the standard heat supply load capacity is adjusted according to the heat supply compensation coefficient. When it is judged that the actual heat supply load capacity is not supplemented, the residual heat supply load capacity is stored, when the actual heat supply load capacity needs to be supplemented, the residual heat supply load capacity is released, and the energy efficiency of the heat pump system is optimized by integrating the meteorological data and the indoor temperature data.

Description

Technical Field

[0001] The present invention relates to the technical field of heat supply management, and in particular to an energy efficiency optimization system and method for a heat pump system. Background Art

[0002] With global energy shortages and increasing demands for environmental protection, improving energy efficiency has become a pressing need across all industries, especially in residential heating. Heat pump systems, as an energy system used in residential heating, are responsible for providing real-time heating to residential areas. However, heat pump systems have shortcomings in actual heating. While they can meet basic residential heating needs, they cannot adjust to changes in the weather and indoor temperature. This results in wasted energy or insufficient heating, impacting the overall energy efficiency of the heat pump system.

[0003] Therefore, it is necessary to design an energy efficiency optimization system and method for a heat pump system to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes an energy efficiency optimization system and method for a heat pump system, aiming to solve the problem that the heat pump system cannot be adjusted according to the weather and indoor temperature changes in the residential area, resulting in energy waste or insufficient heating, thereby affecting the overall energy efficiency of the heat pump system.

[0005] The present invention proposes an energy efficiency optimization method for a heat pump system, comprising: Dividing a residential area into a plurality of sub-residential areas, obtaining meteorological data for each sub-residential area, determining a temperature difference set based on the meteorological data for each sub-residential area, obtaining indoor temperature data for each sub-residential area, and comparing the temperature data with indoor standard temperature data, and constructing a heating data chain based on the comparison result and the temperature difference set; Determining, based on the heating data link, a required heating load of the heat pump system based on a random forest model, obtaining a standard heating load of the heat pump system based on a preset heating demand, obtaining all historical heating output information corresponding to the preset heating demand, analyzing all the historical heating output information, calculating a heating compensation coefficient of the heat pump system based on the analysis result, adjusting the standard heating load according to the heating compensation coefficient, and determining an actual heating load; The actual heating load is compared with the required heating load, and whether the actual heating load is to be supplemented is determined based on the comparison result. When it is determined that the actual heating load is not to be supplemented, the remaining heating load is stored, and when the actual heating load needs to be supplemented, the remaining heating load is released.

[0006] Further, when determining the temperature difference set according to the meteorological data of each sub-residential area, it includes: The meteorological data includes average rainfall, average wind speed, and average snowfall, and the meteorological comprehensive value of each sub-residential area is determined according to the average rainfall, the average wind speed, and the average snowfall; The meteorological comprehensive value is obtained by the following formula: ; where E represents the meteorological comprehensive value, V represents the average wind speed, R represents the average rainfall, and S represents the average snowfall; The meteorological comprehensive values of each sub-residential area are grouped, and the temperature difference set includes a first temperature difference set, a second temperature difference set, and a third temperature difference set.

[0007] Further, when grouping the meteorological comprehensive values of each sub-residential area, it includes: A first preset meteorological comprehensive value and a second preset meteorological comprehensive value are preset in advance, and the first preset meteorological comprehensive value is greater than the second preset meteorological comprehensive value; The meteorological comprehensive values of the sub-residential areas greater than or equal to the first preset meteorological comprehensive value are grouped into the first temperature difference set; The meteorological comprehensive values of the sub-residential areas less than the first preset meteorological comprehensive value and greater than the second preset meteorological comprehensive value are grouped into the second temperature difference set; The meteorological comprehensive values of the sub-residential areas less than or equal to the second preset meteorological comprehensive value are grouped into the third temperature difference set.

[0008] Further, when obtaining the indoor temperature data of each sub-residential area, comparing it with the indoor standard temperature data, and constructing a heating data chain based on the comparison result and the temperature difference set, it includes: The indoor temperature data of each sub-residential area is subjected to comparison processing, and the comparison processing includes: The indoor temperature data of the sub-residential areas greater than or less than the indoor standard temperature data is saved; The indoor temperature data of the sub-residential areas equal to the indoor standard temperature data is excluded; Based on the result of the comparison processing, the indoor temperature data of the sub-residential areas after the comparison processing is arranged in numerical order, and the median of the indoor temperature data is obtained; The first temperature difference mean in the first temperature difference set is extracted, the second temperature difference mean in the second temperature difference set is extracted, the third temperature difference mean in the third temperature difference set is extracted, and the average of the first temperature difference mean, the second temperature difference mean, and the third temperature difference mean is calculated; A heating data chain is constructed according to the median and the average.

[0009] Further, when determining the required heating load of the heat pump system based on the heating data chain and the random forest model, it includes: Obtain the historical heating data chain and construct it with the standard heating load as a model data set, and divide the model data set into a training set and a test set; Use cross-validation combined with grid search to find the model parameters of the random forest model, establish the random forest model, use the training set to fit the random forest model, substitute the test set into the random forest model and calculate the correct rate of the required heating load. When the correct rate reaches the preset correct rate threshold, determine the required heating load of the heat pump system according to the heating data chain.

[0010] Further, when obtaining all historical heating output information corresponding to the preset heating demand, analyzing all historical heating output information, and calculating the heating compensation coefficient of the heat pump system based on the analysis results, it includes: Analyze all historical heating output information to determine heating output overflow, normal heating output, and insufficient heating output; Count the historical heating loads corresponding to all heating output overflows and construct an overflow data set, count the historical heating loads corresponding to all insufficient heating outputs and construct an insufficient data set; Calculate the heating compensation coefficient of the heat pump system according to the standard heating load, the overflow data set, and the insufficient data set.

[0011] Further, when calculating the heating compensation coefficient of the heat pump system according to the standard heating load, the overflow data set, and the insufficient data set, it includes: The heating compensation coefficient is obtained from the following formula: ; where Q represents the heating compensation coefficient, m represents the number of historical heating loads in the overflow data set, Ji represents the i-th historical heating load in the overflow data set, n represents the number of historical heating loads in the insufficient data set, Jk represents the k-th historical heating load in the insufficient data set, and J represents the standard heating load.

[0012] Further, when adjusting the standard heating load according to the heating compensation coefficient to determine the actual heating load, it includes: The actual heating load is the product value of the heating compensation coefficient and the standard heating load.

[0013] Further, when comparing the actual heating load and the required heating load and determining whether to supplement the actual heating load according to the comparison result, when it is determined not to supplement the actual heating load, it includes: Obtain the load difference between the required heating load and the actual heating load; When the load difference is positive, it is determined to supplement the actual heating load, and the supplementary heating load is the load difference; When the load difference is negative, it is determined not to supplement the actual heating load.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: By dividing the residential area into multiple sub-residential areas and constructing a heating data chain based on the meteorological data and indoor temperature data of each sub-residential area, the heating demand differences of the heat pump system are effectively captured, ensuring that the heat pump system can accurately capture the changes in meteorology and indoor temperature. Using the random forest model to predict the required heating load ensures the accuracy of its data. Analyzing all historical heating output information to calculate the heating compensation coefficient improves the reliability and stability of the heat pump system's heating. By comparing the actual heating load with the required heating load, it can accurately determine whether heating supplementation is needed, ensuring the energy efficiency of the heat pump system under different climate and indoor temperature changes. By storing and releasing the remaining heating load, the flexibility and regulation ability of the heat pump system are further improved, thereby reducing energy waste, avoiding overheating or insufficient heating, achieving efficient utilization of energy, and further optimizing the energy efficiency of the heat pump system.

[0015] On the other hand, the present application also provides an energy efficiency optimization system for a heat pump system, which is used to apply the above-mentioned energy efficiency optimization method for a heat pump system, including: A data acquisition module, configured to divide the residential area into several sub-residential areas, acquire the meteorological data of the sub-residential areas, determine the temperature difference set according to the meteorological data of each sub-residential area, acquire the indoor temperature data of each sub-residential area, and compare it with the indoor standard temperature data, and construct a heating data chain based on the comparison result and the temperature difference set; An energy efficiency processing module, configured to determine the required heating load of the heat pump system based on the heating data chain and the random forest model, obtain the standard heating load of the heat pump system based on the preset heating demand, acquire all historical heating output information corresponding to the preset heating demand, and analyze all the historical heating output information, calculate the heating compensation coefficient of the heat pump system based on the analysis result, and adjust the standard heating load according to the heating compensation coefficient to determine the actual heating load; The energy efficiency optimization module is configured to compare the actual heating load quantity with the required heating load quantity, determine whether to supplement the actual heating load quantity according to the comparison result, store the remaining heating load quantity when it is determined not to supplement the actual heating load quantity, and release the remaining heating load quantity when it is necessary to supplement the actual heating load quantity.

[0016] It can be understood that the above-provided energy efficiency optimization system and method for a heat pump system have the same beneficial effects, which will not be elaborated here. Description of the Drawings

[0017] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 It is a flowchart of an energy efficiency optimization method for a heat pump system provided by an embodiment of the present invention; Figure 2 It is a functional block diagram of an energy efficiency optimization system for a heat pump system provided by an embodiment of the present invention. Detailed Embodiments

[0018] Hereinafter, the exemplary embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. Hereinafter, the present invention will be described in detail with reference to the drawings and in combination with the embodiments.

[0019] In some embodiments of the present application, referring to Figure 1 as shown, an energy efficiency optimization method for a heat pump system includes: S100: Divide the residential area into several sub-residential areas, obtain the meteorological data of the sub-residential areas, determine the temperature difference set according to the meteorological data of each sub-residential area, obtain the indoor temperature data of each sub-residential area, and compare it with the indoor standard temperature data, and construct a heating data chain based on the comparison result and the temperature difference set; S200: Determine the required heating load of the heat pump system based on the heating data chain and the random forest model, obtain the standard heating load of the heat pump system based on the preset heating demand, obtain all historical heating output information corresponding to the preset heating demand, analyze all historical heating output information, calculate the heating compensation coefficient of the heat pump system based on the analysis results, and adjust the standard heating load according to the heating compensation coefficient to determine the actual heating load; S300: Compare the actual heating load with the required heating load, and judge whether to supplement the actual heating load according to the comparison result. When it is determined not to supplement the actual heating load, store the remaining heating load, and release the remaining heating load when it is necessary to supplement the actual heating load.

[0020] Specifically, the residential area is divided into several sub-residential areas, aiming to measure the possible losses in the heating process according to the meteorological conditions of different sub-residential areas. For example, in the low-rise sub-residential areas, which are blocked by surrounding trees and other low-rise buildings and are less affected by wind speed, while the high-rise sub-residential areas are not blocked by trees and are more affected by high-altitude cold currents and wind speed. The number of sub-residential areas is preferably 10, which can be adjusted according to the actual residential area. By obtaining the meteorological data of each sub-residential area, the heating demands of different sub-residential areas can be accurately analyzed, reducing unnecessary energy waste. By comparing the indoor temperature data with the indoor standard temperature data, the difference in heating can be determined. The indoor standard temperature data is determined according to the "Design Code for Heating, Ventilation and Air Conditioning of Civil Buildings". The heating data chain reflects the influence of meteorology and indoor temperature on the heat pump system, providing a basis for subsequent energy efficiency optimization. The random forest model is an ensemble learning model that can process input variables and accurately predict the required heating load according to the regularity of historical data. The required heating load is determined according to factors such as meteorological data. And obtaining the standard heating load of the heat pump system based on the preset heating demand reflects the standard heating level of the heat pump system. By obtaining all the historical heating output information corresponding to the preset heating demand and analyzing this historical heating output information, the heating compensation coefficient of the heat pump system can be determined. The heating compensation coefficient reflects the fluctuation degree of the heating output during the actual operation of the heat pump system. Adjusting the standard heating load according to the obtained heating compensation coefficient ensures that the actual heating load can accurately match the actual demand, thus optimizing the energy efficiency of the heat pump system. And, by comparing the actual heating load with the required heating load in real time, it is judged whether the actual heating load meets the heating demand of the residential area. When it is determined that the actual heating load does not need to be supplemented, the remaining heating load is stored, and when the actual heating load needs to be supplemented, the remaining heating load is released. It can quickly respond and release the stored heat when the temperature suddenly changes or other demand changes occur, improving the utilization of the remaining heating load, and thus improving the energy efficiency optimization level of the heat pump system.

[0021] It can be understood that determining the heating data chain based on meteorological data and indoor temperature data and judging whether the actual heating load of the heat pump system meets the heating demand avoids the risks of overheating or underheating, minimizes energy consumption to the greatest extent and ensures the heating of the residential area, and stores the remaining heating load in a timely manner, thus optimizing the energy efficiency of the heat pump system.

[0022] In some embodiments of the present application, when determining the temperature difference set according to the meteorological data of each sub-residential area, it includes: the meteorological data includes average rainfall, average wind speed, and average snowfall. Determine the meteorological comprehensive value of each sub-residential area according to the average rainfall, average wind speed, and average snowfall. The meteorological comprehensive value is obtained by the following formula: ; where E represents the meteorological comprehensive value, V represents the average wind speed, R represents the average rainfall, and S represents the average snowfall. Perform set partitioning on the meteorological comprehensive values of each sub-residential area. The temperature difference set includes a first temperature difference set, a second temperature difference set, and a third temperature difference set.

[0023] In some embodiments of the present application, when performing set partitioning on the meteorological comprehensive values of each sub-residential area, it includes: preset a first preset meteorological comprehensive value and a second preset meteorological comprehensive value, and the first preset meteorological comprehensive value is greater than the second preset meteorological comprehensive value. Partition the meteorological comprehensive values of the sub-residential areas greater than or equal to the first preset meteorological comprehensive value into the first temperature difference set, and partition the meteorological comprehensive values of the sub-residential areas less than the first preset meteorological comprehensive value and greater than the second preset meteorological comprehensive value into the second temperature difference set. Partition the meteorological comprehensive values of the sub-residential areas less than or equal to the second preset meteorological comprehensive value into the third temperature difference set.

[0024] Specifically, collect the meteorological data of each sub-residential area. Factors such as average rainfall, average wind speed, and average snowfall will all have a certain impact on the heating demand of the heat pump system, resulting in changes in the temperature maintained by the buildings in the residential area and heat loss, thereby affecting the heating demand of the heat pump system. By calculating the meteorological data, the meteorological comprehensive value of each sub-residential area can be obtained. The meteorological comprehensive value can reflect the comprehensive intensity of the climate conditions in the sub-residential area. For example, the average wind speed is 3 m / s, the average rainfall is 50 cm / year, the average snowfall is 30 cm / year, and the meteorological comprehensive value is 24.47. The higher the meteorological comprehensive value, the more severe the climate conditions in the sub-residential area, indicating that the sub-residential area has a greater impact on the heating of the heat pump system. Performing set partitioning on each sub-residential area according to the meteorological comprehensive value can distinguish different degrees of climate conditions, providing a data basis for subsequent construction of the heating data chain, enabling the heat pump system to flexibly adapt to different climate conditions, not only optimizing the energy efficiency of the heat pump system but also reducing energy consumption.

[0025] In some embodiments of the present application, when obtaining the indoor temperature data of each sub-residential area, comparing it with the indoor standard temperature data, and constructing a heating data chain based on the comparison result and the temperature difference set, it includes: performing comparison processing on the indoor temperature data of each sub-residential area, and the comparison processing includes: saving the indoor temperature data of the sub-residential areas where the indoor temperature data is greater than or less than the indoor standard temperature data, eliminating the indoor temperature data of the sub-residential areas where the indoor temperature data is equal to the indoor standard temperature data, arranging the indoor temperature data of the sub-residential areas after the comparison processing in numerical order, and obtaining the median of the indoor temperature data among them, extracting the first temperature difference mean value in the first temperature difference set, extracting the second temperature difference mean value in the second temperature difference set, extracting the third temperature difference mean value in the third temperature difference set, calculating the average of the first temperature difference mean value, the second temperature difference mean value and the third temperature difference mean value, and constructing a heating data chain according to the median and the average value.

[0026] Specifically, by eliminating the indoor temperature data that meets the indoor standard temperature data, unnecessary analysis of the sub-residential areas with qualified temperatures is avoided, focusing on the sub-residential areas with temperature deviations, which can effectively optimize the energy efficiency of the heat pump system. After the comparison processing of the indoor temperature data, the median among them is extracted. The median is not easily affected by extreme values and represents an average level of the overall temperature demand. Then, combined with the temperature difference mean values of different temperature difference sets, the average value is determined, avoiding the one-size-fits-all heating demand of the heat pump system, thereby obtaining a heating data chain that can comprehensively reflect the heating demand of the residential area, and further optimizing the energy efficiency of the heat pump system.

[0027] In some embodiments of the present application, when determining the required heating load of the heat pump system based on the random forest model according to the heating data chain, it includes: obtaining the historical heating data chain and constructing it with the standard heating load as a model data set, dividing the model data set into a training set and a test set, using cross-validation combined with grid search to find the model parameters of the random forest model, establishing the random forest model, fitting the random forest model with the training set, substituting the test set into the random forest model and calculating the correct rate of the required heating load, and when the correct rate reaches the preset correct rate threshold, determining the required heating load of the heat pump system according to the heating data chain.

[0028] Specifically, obtain the historical heating data chain and construct it with the standard heating load to form a model data set. This data set covers heating data chains from different periods, including data such as historical averages and historical medians, which record the heating conditions of the residential area at different time periods. Divide the model data set into a training set and a test set. Generally, select more than 60% of the data as the training set, and the rest as the test set. Ensure that both the training set and the test set contain data on various heating conditions to improve the generalization ability of the model. And use cross-validation combined with grid search to find the model parameters of the random forest model. Cross-validation divides the data into several parts and trains the model multiple times to verify its stability and performance, while grid search exhaustively searches for parameter combinations in the parameter space to improve the random forest model. Use the training set data to fit the random forest model to reduce the risk of overfitting, thereby improving the accuracy and stability of the model. Input the data of the test set into the already trained random forest model to obtain the correct rate of the required heating load of the model. The correct rate is used to measure the performance of the model, reflects the performance of the model on unknown data, and is an important indicator for evaluating the model performance. During the model training and verification process, continuously adjusting the parameters and verifying the model performance helps the model to stably approach the optimal prediction solution. After the model reaches the preset correct rate threshold, substitute the heating data chain into the random forest model to obtain the required heating load of the heat pump system, further optimizing the energy efficiency of the heat pump system.

[0029] In some embodiments of the present application, when obtaining all historical heating output information corresponding to the preset heating demand and analyzing all the historical heating output information, and calculating the heating compensation coefficient of the heat pump system based on the analysis results, it includes: analyzing all the historical heating output information to determine heating output overflow, normal heating output, and insufficient heating output, counting the historical heating loads corresponding to all heating output overflows and constructing an overflow data set, counting the historical heating loads corresponding to all insufficient heating outputs and constructing an insufficient data set, and calculating the heating compensation coefficient of the heat pump system according to the standard heating load, the overflow data set, and the insufficient data set.

[0030] In some embodiments of the present application, when calculating the heating compensation coefficient of the heat pump system according to the standard heating load, the overflow data set, and the insufficient data set, it includes: the heating compensation coefficient is obtained from the following formula: ; where Q represents the heating compensation coefficient, m represents the number of historical heating loads in the overflow data set, Ji represents the i-th historical heating load in the overflow data set, n represents the number of historical heating loads in the insufficient data set, Jk represents the k-th historical heating load in the insufficient data set, and J represents the standard heating load.

[0031] Specifically, the preset heating demand includes basic demands such as heating time and heating pressure. The standard heating load refers to the heating load corresponding to the preset heating demand, which represents the standard heating level of the heat pump system. The historical heating output information includes heating output overflow, normal heating output, and insufficient heating output. During the actual heating process, the heating of the residential area by the heat pump system is not fixed. By calculating the heating compensation coefficient of the heat pump system based on the standard heating load, the overflow dataset, and the insufficient dataset, the dynamic adjustment of the standard heating load is achieved, reducing the risks of heating output overflow and insufficient heating output.

[0032] In some embodiments of the present application, when adjusting the standard heating load according to the heating compensation coefficient to determine the actual heating load, it includes: the actual heating load is the product value of the heating compensation coefficient and the standard heating load.

[0033] In some embodiments of the present application, when comparing the actual heating load with the required heating load and judging whether to supplement the actual heating load according to the comparison result, when it is determined not to supplement the actual heating load, it includes: obtaining the load difference between the required heating load and the actual heating load. When the load difference is positive, it is determined to supplement the actual heating load, and the supplemented heating load is the load difference. When the load difference is negative, it is determined not to supplement the actual heating load.

[0034] Specifically, by establishing the product relationship between the heating compensation coefficient and the standard heating load, precise control of the actual heating load during the heating process of the heat pump system can be achieved, enabling the actual heating load to meet the preset heating demand. The heating compensation coefficient is calculated based on the overflow dataset and the insufficient dataset, and these data can only reflect the past heating situation of the heat pump system. When actually heating the residential area, even if the standard heating load is adjusted using the heating compensation coefficient, the heating is still affected by factors such as climate conditions, indoor temperature, and user habits during heating, resulting in a gap between the actual heating load and the required heating load. By obtaining the load difference between the required heating load and the actual heating load, it is judged whether to supplement the actual heating load. When the load difference is positive, it means the required heating load is greater than the actual heating load, and the heat pump system needs to supplement heating according to the load difference. Conversely, when the load difference is negative, it means the required heating load is less than the actual heating load, and the heat pump system does not need to supplement the actual heating load. Moreover, the remaining heating load in the heat pump system is stored, effectively saving energy, thereby improving the energy efficiency optimization level of the heat pump system, avoiding unnecessary adjustments, and improving the operating efficiency of the heat pump system.

[0035] In summary, the beneficial effects of the present invention are as follows: By dividing the residential area into multiple sub-residential areas and constructing a heating data chain based on the meteorological data and indoor temperature data of each sub-residential area, the heating demand differences of the heat pump system are effectively captured, ensuring that the heat pump system can accurately capture the changes in meteorology and indoor temperature. Using the random forest model to predict the required heating load, the accuracy of the data is ensured. Analyzing all historical heating output information to calculate the heating compensation coefficient improves the reliability and stability of the heat pump system's heating. By comparing the actual heating load with the required heating load, it can accurately determine whether heating supplementation is needed, ensuring the energy efficiency of the heat pump system under different climate and indoor temperature changes. By storing and releasing the remaining heating load, the flexibility and regulation ability of the heat pump system are further improved, thereby reducing energy waste, avoiding overheating or insufficient heating, achieving efficient utilization of energy, and further optimizing the energy efficiency of the heat pump system.

[0036] In another preferred embodiment based on the above embodiments, referring to Figure 2 as shown, this embodiment provides an energy efficiency optimization system for a heat pump system, which is used to apply the above-mentioned energy efficiency optimization method for a heat pump system, including: A data acquisition module, configured to divide the residential area into several sub-residential areas, acquire the meteorological data of the sub-residential areas, determine the temperature difference set according to the meteorological data of each sub-residential area, acquire the indoor temperature data of each sub-residential area, compare it with the indoor standard temperature data, and construct a heating data chain based on the comparison result and the temperature difference set; An energy efficiency processing module, configured to determine the required heating load of the heat pump system based on the heating data chain and the random forest model, obtain the standard heating load of the heat pump system based on the preset heating demand, acquire all historical heating output information corresponding to the preset heating demand, analyze all historical heating output information, calculate the heating compensation coefficient of the heat pump system based on the analysis result, and adjust the standard heating load according to the heating compensation coefficient to determine the actual heating load; An energy efficiency optimization module, configured to compare the actual heating load with the required heating load, determine whether to supplement the actual heating load according to the comparison result, store the remaining heating load when it is determined not to supplement the actual heating load, and release the remaining heating load when it is necessary to supplement the actual heating load.

[0037] Specifically, the data acquisition module divides the residential area into several sub-residential areas, obtains the meteorological data of each sub-residential area, compares the indoor temperature data with the indoor standard temperature data, and jointly constructs a heating data chain, which can accurately grasp the heating demand of the residential area. The energy efficiency processing module, based on the heating data chain, uses the random forest model to obtain the required heating load of the heat pump system, improving the accuracy of its data. And it analyzes all historical heating output information to calculate the heating compensation coefficient of the heat pump system, and adjusts the standard heating load according to the heating compensation coefficient to determine the actual heating load, improving the pertinence of the heat pump system's energy utilization, thereby optimizing the energy efficiency of the heat pump system. The energy efficiency optimization module then determines whether to supplement the actual heating load based on the comparison result between the actual heating load and the required heating load, and stores the remaining heating load when it is not needed, ensuring that when the subsequent heating demand increases, the remaining heating load can be released in time to supplement the actual heating load. This not only avoids energy waste but also ensures the stable operation and energy-saving effect of the heating system, effectively improving the energy utilization of the heat pump system, thereby optimizing the energy efficiency of the heat pump system.

[0038] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0039] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0040] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions in the process Figure 1One or more processes and / or blocks Figure 1 The functions specified in one or more blocks.

[0041] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 One or more processes and / or blocks Figure 1 The steps of the functions specified in one or more blocks.

[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the specific implementation manners of the present invention can still be modified or equivalently replaced, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.

Claims

1. An energy efficiency optimization method for a heat pump system, characterized in that, Including: Dividing the residential area into several sub-residential areas, obtaining the meteorological data of the sub-residential areas, determining the temperature difference set according to the meteorological data of each sub-residential area, obtaining the indoor temperature data of each sub-residential area, comparing it with the indoor standard temperature data, and constructing a heating data chain based on the comparison result and the temperature difference set; According to the heating data chain, determining the required heating load of the heat pump system based on the random forest model, obtaining the standard heating load of the heat pump system based on the preset heating demand, obtaining all historical heating output information corresponding to the preset heating demand, analyzing all historical heating output information, calculating the heating compensation coefficient of the heat pump system based on the analysis result, and adjusting the standard heating load according to the heating compensation coefficient to determine the actual heating load; Comparing the actual heating load with the required heating load, judging whether to supplement the actual heating load according to the comparison result. When it is determined not to supplement the actual heating load, storing the remaining heating load, and releasing the remaining heating load when it is necessary to supplement the actual heating load.

2. The energy efficiency optimization method for a heat pump system according to claim 1, characterized in that When determining the temperature difference set according to the meteorological data of each sub-residential area, including: The meteorological data includes average rainfall, average wind speed, and average snowfall. Determining the meteorological comprehensive value of each sub-residential area according to the average rainfall, the average wind speed, and the average snowfall; The meteorological comprehensive value is obtained by the following formula: ； Where E represents the meteorological comprehensive value, V represents the average wind speed, R represents the average rainfall, and S represents the average snowfall; Performing set partitioning on the meteorological comprehensive value of each sub-residential area. The temperature difference set includes a first temperature difference set, a second temperature difference set, and a third temperature difference set.

3. The energy efficiency optimization method for a heat pump system according to claim 2, wherein When performing set partitioning on the meteorological comprehensive value of each sub-residential area, including: Presetting a first preset meteorological comprehensive value and a second preset meteorological comprehensive value, and the first preset meteorological comprehensive value is greater than the second preset meteorological comprehensive value; Dividing the meteorological comprehensive value of the sub-residential area greater than or equal to the first preset meteorological comprehensive value into the first temperature difference set; Dividing the meteorological comprehensive value of the sub-residential area less than the first preset meteorological comprehensive value and greater than the second preset meteorological comprehensive value into the second temperature difference set; Dividing the meteorological comprehensive value of the sub-residential area less than or equal to the second preset meteorological comprehensive value into the third temperature difference set.

4. The energy efficiency optimization method for a heat pump system according to claim 3, wherein When obtaining the indoor temperature data of each sub-residential area, comparing it with the indoor standard temperature data, and constructing a heating data chain based on the comparison result and the temperature difference set, including: Performing comparison processing on the indoor temperature data of each sub-residential area. The comparison processing includes: Saving the indoor temperature data of the sub-residential area greater than or less than the indoor standard temperature data; Eliminating the indoor temperature data of the sub-residential area equal to the indoor standard temperature data; Based on the result of the comparison processing, arranging the indoor temperature data of the sub-residential area after the comparison processing in numerical order, and obtaining the median of the indoor temperature data. Extract the first temperature difference mean value from the first set of temperature differences, extract the second temperature difference mean value from the second set of temperature differences, extract the third temperature difference mean value from the third set of temperature differences, and calculate the average of the first temperature difference mean value, the second temperature difference mean value, and the third temperature difference mean value; Construct a heating data chain based on the median and the average.

5. The energy efficiency optimization method for a heat pump system according to claim 4, characterized in that, When determining the required heating load of the heat pump system based on the heating data chain and the random forest model, it includes: Obtain the historical heating data chain and construct it with the standard heating load as a model data set, and divide the model data set into a training set and a test set; Use cross-validation combined with grid search to find the model parameters of the random forest model, establish the random forest model, fit the random forest model with the training set, substitute the test set into the random forest model and calculate the correct rate of the required heating load. When the correct rate reaches the preset correct rate threshold, determine the required heating load of the heat pump system according to the heating data chain.

6. The energy efficiency optimization method for a heat pump system according to claim 5, wherein When obtaining all historical heating output information corresponding to the preset heating demand and analyzing all historical heating output information, and calculating the heating compensation coefficient of the heat pump system based on the analysis results, it includes: Analyze all historical heating output information to determine heating output overflow, normal heating output, and insufficient heating output; Statistically analyze the historical heating loads corresponding to all heating output overflows and construct an overflow data set, and statistically analyze the historical heating loads corresponding to all insufficient heating outputs and construct an insufficient data set; Calculate the heating compensation coefficient of the heat pump system according to the standard heating load, the overflow data set, and the insufficient data set.

7. The energy efficiency optimization method for a heat pump system according to claim 6, characterized in that When calculating the heating compensation coefficient of the heat pump system according to the standard heating load, the overflow data set, and the insufficient data set, it includes: The heating compensation coefficient is obtained from the following formula: ； Where Q represents the heating compensation coefficient, m represents the number of historical heating loads in the overflow data set, Ji represents the i-th historical heating load in the overflow data set, n represents the number of historical heating loads in the insufficient data set, JK represents the K-th historical heating load in the insufficient data set, and J represents the standard heating load.

8. The energy efficiency optimization method for a heat pump system according to claim 7, characterized in that When adjusting the standard heating load according to the heating compensation coefficient to determine the actual heating load, it includes: The actual heating load is the product value of the heating compensation coefficient and the standard heating load.

9. The energy efficiency optimization method for a heat pump system according to claim 8, characterized in that, When comparing the actual heating load with the required heating load and judging whether to supplement the actual heating load according to the comparison result, when it is determined not to supplement the actual heating load, it includes: Obtain the load difference between the required heating load and the actual heating load; When the load difference is positive, it is determined to supplement the actual heating load, and the supplementary heating load is the load difference; When the load difference is negative, it is determined not to supplement the actual heating load.

10. An energy efficiency optimization system for a heat pump system, which is used to apply the energy efficiency optimization method for a heat pump system according to any one of claims 1-9, characterized in that, It includes: A data acquisition module, configured to divide a residential area into a number of sub-residential areas, acquire meteorological data of the sub-residential areas, determine a temperature difference set according to the meteorological data of each sub-residential area, acquire indoor temperature data of each sub-residential area, compare it with indoor standard temperature data, and construct a heating data chain based on the comparison result and the temperature difference set; An energy efficiency processing module, configured to determine the required heating load of a heat pump system based on a random forest model according to the heating data chain, obtain the standard heating load of the heat pump system based on a preset heating demand, acquire all historical heating output information corresponding to the preset heating demand, analyze all the historical heating output information, calculate the heating compensation coefficient of the heat pump system based on the analysis result, and adjust the standard heating load according to the heating compensation coefficient to determine the actual heating load; An energy efficiency optimization module, configured to compare the actual heating load with the required heating load, judge whether to supplement the actual heating load according to the comparison result, store the remaining heating load when it is determined not to supplement the actual heating load, and release the remaining heating load when it is necessary to supplement the actual heating load.

Images