Heat exchange system optimization method and system based on big data analysis

Abstract

The invention discloses a heat exchange system optimization method and system based on big data analysis, and belongs to the technical field of heat exchange system optimization processing, and the method comprises the following steps: analyzing a computing resource demand evaluation index of each data flow, carrying out resource limitation, and according to the computing resource demand evaluation index of each data flow, carrying out resource optimization; and analyzing the real-time data flow fluctuation coefficient and the system computing power evaluation index, adjusting the sampling frequency of each data flow, predicting the thermal load of the heat exchange system, and dynamically adjusting the heat exchange system. According to the invention, by evaluating the computing resource demand and carrying out reasonable resource limitation, delay or errors caused by resource competition during data processing of different data streams are avoided, the processing stability and efficiency of each data stream are guaranteed, the data acquisition quality and the resource utilization efficiency are improved, the resource configuration is optimized, the energy utilization efficiency is improved, and the resource utilization efficiency is improved. The energy consumption is reduced, and the stability, accuracy and economical efficiency of operation of the heat exchange system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of heat exchange system optimization processing, and in particular to a heat exchange system optimization method and system based on big data analysis. Background Art

[0002] With the intensification of the energy crisis and the increasing severity of environmental pollution, improving energy efficiency and reducing energy consumption have become the focus. In the industrial field, the heat exchange system is an important equipment for energy recovery and utilization. Heat load prediction is a key technology for optimizing the operation of the heat exchange system. By predicting the heat load required by the system in the future, it helps the system adjust the operating parameters in advance, optimize resource allocation, and improve the system's operating efficiency and economy.

[0003] Currently, the heating amount is predicted according to the target temperature, and the random forest algorithm is used to screen and reduce the dimension of the features; then the data is standardized; and then a heat load prediction model based on the long-term and short-term time series network is established. The model captures the long-term and short-term feature information through convolutional layers and loop layers, and then introduces the concept of loop skip layer to capture longer-term feature information. At the same time, the autoregressive algorithm is used to add linear processing capabilities to the model, which enhances the robustness of the model.

[0004] However, in the data collection of the heat load prediction link of the existing heat exchange system, there are problems with the timeliness and accuracy of data collection due to the fluctuation of data volume. In addition, in data processing, there is also the problem of unbalanced consumption of computing resources of different data streams, which easily leads to interference between multiple tasks, making the system inefficient when processing large amounts of data, and even causing data processing errors, which in turn affects the accuracy of heat load prediction and the optimized operation effect of the entire heat exchange system. Summary of the invention

[0005] In order to overcome the problems existing in the prior art, the first aspect of the present invention provides a heat exchange system optimization method based on big data analysis, including the following steps: S1, recording each heat load prediction data stream of the heat exchange system as each data stream, performing computing resource demand evaluation of each data stream, analyzing the computing resource demand evaluation index of each data stream, and thereby performing resource limitation.

[0006] S2, based on the computing resource demand evaluation indicators of each data flow, and synchronously analyzing the real-time data flow fluctuation coefficient and system computing power evaluation indicators, generates adaptive sampling frequency control instructions to adjust the sampling frequency of each data flow.

[0007] S3, collecting data based on the adjusted sampling frequency, thereby predicting the heat load of the heat exchange system.

[0008] S4, dynamically adjusting the heat exchange system according to the heat load prediction result of the heat exchange system.

[0009] The second aspect of the present invention provides an optimization system for a heat exchange system based on big data analysis, including:

[0010] A computing resource requirement assessment module, which is used to record the heat load prediction data streams of the heat exchange system as each data stream, perform the computing resource requirement assessment of each data stream, analyze the computing resource requirement assessment indicators of each data stream, and thus perform resource limitation.

[0011] A sampling frequency adjustment module, which is used to generate an adaptive sampling frequency control instruction according to the computing resource requirement assessment indicators of each data stream, and synchronously analyze the real-time data flow fluctuation coefficient and the system computing power assessment indicator, and perform the sampling frequency adjustment of each data stream.

[0012] A heat load prediction module, which is used to collect data based on the adjusted sampling frequency, and thus perform the heat load prediction of the heat exchange system.

[0013] A heat exchange system dynamic adjustment module, which is used to perform the dynamic adjustment of the heat exchange system according to the heat load prediction result of the heat exchange system.

[0014] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0015] 1. The optimization method for the heat exchange system based on big data analysis provided by the present invention, by evaluating the computing resource requirements and performing reasonable resource limitation, avoids delays or errors caused by resource competition during data processing of different data streams, and ensures the stability and efficiency of the processing of each data stream. At the same time, the sampling frequency is adjusted according to the computing resource requirement assessment indicators, the real-time data flow fluctuation coefficient and the system computing power assessment indicator. It can not only increase the sampling frequency when the data changes rapidly to obtain more accurate and timely data, but also reduce the sampling frequency when the data is stable to avoid resource waste, effectively improving the quality of data collection and the resource utilization efficiency. Data is collected and the heat load is predicted based on the adjusted sampling frequency, and the system is dynamically adjusted according to the prediction result, optimizing the resource allocation, improving the energy utilization efficiency, reducing the energy consumption, and enhancing the stability, accuracy and economy of the operation of the heat exchange system.

[0016] 2. By analyzing the computing resource requirement assessment indicators of each data stream and thus performing resource limitation, on the one hand, accurate resource limitation can avoid the disorderly competition and unreasonable consumption of system resources, prevent processing delays or errors caused by insufficient resources, and improve the efficiency and accuracy of data processing. On the other hand, it helps to improve the overall operation stability of the system. Different data streams operate in their respective exclusive resource environments, with less interference between each other, making the system more reliable when processing complex tasks and large amounts of data, providing a solid data foundation for key links such as subsequent heat load prediction and system dynamic adjustment, and ultimately optimizing the overall performance of the heat exchange system.

[0017] 3. By adjusting the sampling frequency of each data stream, when the data of the data stream changes rapidly, increasing the sampling frequency can obtain richer and more timely data, ensuring the timeliness and accuracy of the data, providing more accurate data support for the heat load prediction, and thus improving the accuracy of the prediction. When the data of the data stream changes relatively stably, reducing the sampling frequency can avoid unnecessary resource waste, reasonably optimize the system resource configuration, reduce the system operation burden, and improve the overall operation efficiency of the system.

[0018] 4. By dynamically adjusting the heat exchange system according to the heat load prediction results of the heat exchange system, the present invention effectively improves the energy utilization efficiency, reduces the system operation cost, helps to maintain the stability of the system operation, can timely adjust the system state according to the environmental changes and the fluctuations of the heat load demand, reduces the operation fluctuations of the system caused by sudden load changes, prolongs the service life of the equipment, and reduces the equipment maintenance cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of an optimization method for a heat exchange system based on big data analysis provided by the present invention.

[0020] Figure 2 It is a schematic structural diagram of an optimization system for a heat exchange system based on big data analysis provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] Referring to Figure 1 As shown, the present invention provides an optimization method for a heat exchange system based on big data analysis in the first aspect, including the following steps:

[0023] S1. Denote the heat load prediction data streams of the heat exchange system as each data stream, perform the calculation resource requirement assessment of each data stream, analyze the calculation resource requirement assessment indexes of each data stream, and thus perform resource limitation.

[0024] In this embodiment, the heat load prediction data streams of the heat exchange system specifically include: the historical data of the heat load of the heat exchange system, the operation data of the heat exchange system, and the meteorological data of the area where the heat exchange system is located.

[0025] In this embodiment, the process of analyzing the calculation resource requirement assessment indexes of each data stream and thus performing resource limitation is as follows:

[0026] Obtain the historical resource parameters of each data stream, and analyze the evaluation indicators of the computing resource requirements of each data stream.

[0027] Extract the demand quantities corresponding to each demand evaluation index interval stored in the database, and map and extract the demand quantity corresponding to the interval where the computing resource demand evaluation index of each data stream is located, which is recorded as the computing resource demand quantity of each data stream.

[0028] Perform resource limitation according to the computing resource demand quantity of each data stream.

[0029] It should be noted that the computing resource demand quantity refers to the number of allocated CPU cores and the amount of memory.

[0030] In a specific embodiment, taking the data stream of the historical heat load data of the heat exchange system as an example, assume that the evaluation index of the computing resource requirement of the data stream of the historical heat load data of the heat exchange system is 8 during multiple previous heat load predictions. The corresponding computing resource demand quantity extracted from the database is that 8 additional CPU cores and 16 GB of memory need to be allocated. Based on this, the system performs resource limitation on this data stream and specifically allocates these 8 CPU cores and 16 GB of memory to the data stream processing task of the historical heat load data of the heat exchange system.

[0031] In the specific embodiment, through resource limitation, other data streams are prevented from occupying these allocated computing resources, ensuring that each data stream has sufficient and stable computing resource support during subsequent data processing, avoiding data processing delays or errors caused by resource competition, and ensuring that related operations such as heat load prediction can be carried out efficiently and accurately.

[0032] It should be noted that if a certain data stream occupies more computing resources than its set computing resource demand quantity during actual calculation, its calculation task will be stopped.

[0033] In this embodiment, the evaluation indicators of the computing resource requirements of each data stream are analyzed, and the specific analysis process is as follows:

[0034] Obtain the historical resource parameters of each data stream, including the mean value of the historical data volume, the mean value of the historical data processing frequency, the mean value of the number of historical data types, and the mean value of the historical data transmission bandwidth of each data stream.

[0035] It should be noted that the historical resource parameters of each data stream refer to the average value of the resource parameters recorded each time during previous heat load predictions of each data stream.

[0036] It should be understood that the historical resource parameters of each data stream are collected from the system program logs. Among them, the number of data types refers to the total number of data types included in the data stream. In a specific embodiment, the data types include but are not limited to numerical type, character type, and date type.

[0037] Obtain reference historical resource parameters.

[0038] The reference historical resource parameters include the mean value of the reference historical data volume, the mean value of the reference historical data processing frequency, the mean value of the number of reference historical data types, and the mean value of the reference historical data transmission bandwidth.

[0039] According to the historical resource parameters of each data stream and the reference historical resource parameters, comprehensively analyze and process to obtain the evaluation index of the computing resource requirements for each data stream.

[0040] The evaluation index of the computing resource requirements for each data stream represents the quantitative result of the combined influence of the mean value of the historical data volume, the mean value of the historical data processing frequency, the mean value of the number of historical data types, and the mean value of the historical data transmission bandwidth of each data stream on the degree of computing resource requirements for the data stream.

[0041] In a specific embodiment, the method for specifically obtaining the evaluation index of the computing resource requirements for each data stream is as follows:

[0042]

[0043] Among them, A i is the evaluation index of the computing resource requirements for the i-th data stream, a i is the mean value of the historical data volume of the i-th data stream, b i is the mean value of the historical data processing frequency of the i-th data stream, c i is the mean value of the number of historical data types of the i-th data stream, d i is the mean value of the historical data transmission bandwidth of the i-th data stream, a0 is the mean value of the reference historical data volume, b0 is the mean value of the reference historical data processing frequency, c0 is the mean value of the number of reference historical data types, d0 is the mean value of the reference historical data transmission bandwidth, x1 is the weight value of the mean value of the historical data volume, x2 is the weight value of the mean value of the historical data processing frequency, x3 is the weight value of the mean value of the number of historical data types, x4 is the weight value of the mean value of the historical data transmission bandwidth, i is the number of each data stream, i = 1, 2,..., n, and n is the number of data streams.

[0044] It should be noted that the value ranges of the historical data volume mean weight, historical data processing frequency mean weight, historical data type number mean weight, and historical data transmission bandwidth mean weight are all between 0 and 1. When used, the preset values can be directly extracted from the database. The specific extraction method is as follows: for example, construct a mapping set by respectively combining the historical data volume mean, historical data processing frequency mean, historical data type number mean, and historical data transmission bandwidth mean with their corresponding weights. When used, input the obtained historical data volume mean, historical data processing frequency mean, historical data type number mean, and historical data transmission bandwidth mean into the mapping set, so as to extract the historical data volume mean weight, historical data processing frequency mean weight, historical data type number mean weight, and historical data transmission bandwidth mean weight.

[0045] It should also be noted that the calculation resource requirement evaluation indicators for each data stream obtained by analyzing and processing the historical resource parameters of each data stream take into account the mutual correlation between these parameters. For example, when the historical data volume mean is large, in order to ensure processing timeliness, the historical data processing frequency mean often needs to be increased; the larger the historical data type number mean, the more the data diversity and complexity increase, which will cause the historical data volume mean to rise under the same number of records. A high historical data processing frequency mean requires that the historical data transmission bandwidth mean be large enough, otherwise it will affect the processing efficiency; and when the historical data type number mean is large, due to the more complex data transmission protocol and coding method, it will also have a higher requirement for the historical data transmission bandwidth mean.

[0046] S2. According to the calculation resource requirement evaluation indicators of each data stream, and synchronously analyzing the real-time data traffic fluctuation coefficient and the system computing power evaluation indicator, generate an adaptive sampling frequency control instruction to adjust the sampling frequency of each data stream.

[0047] In this embodiment, the specific analysis process of the real-time data traffic fluctuation coefficient is as follows:

[0048] Extract the initial sampling frequency and data acquisition verification duration of each data stream.

[0049] Perform data acquisition for each data stream at the initial sampling frequency of each data stream within the data acquisition verification duration, so as to obtain the data fluctuation parameters of each data stream.

[0050] The data fluctuation parameters of each data stream include the average packet arrival interval, total number of packets, peak data rate, and average data rate of each data stream.

[0051] It should be noted that the data fluctuation parameters of each data flow can be obtained through the system program log collection, where the average data packet arrival interval refers to the average time interval between consecutive arrival data packets. The shorter the interval, the faster the data flow speed, and the more severe the fluctuation may be. The peak data rate refers to the highest rate in the data flow during the data collection verification period. The higher the peak rate, the greater the fluctuation may be.

[0052] The reference data fluctuation parameters stored in the database are extracted, including the reference average data packet arrival interval, the reference total number of data packets, the reference peak data rate, and the reference average data rate.

[0053] The real-time data flow fluctuation coefficient of each data flow is obtained by analyzing and processing the data fluctuation parameters of each data flow.

[0054] The real-time data flow fluctuation coefficient of each data flow represents the quantitative result of the influence of the average arrival interval of data packets, the total number of data packets, the peak data rate and the average data rate of each data flow on the data flow fluctuation state.

[0055] In a specific embodiment, the real-time data flow fluctuation coefficient of each data flow is obtained in the following specific method:

[0056]

[0057] Among them, B i is the real-time data flow fluctuation coefficient of the i-th data flow, α i is the average arrival interval of packets of the ith data stream, β i is the total number of packets of the ith data flow, γ i is the peak data rate of the ith data stream, δ i is the average data rate of the i-th data flow, α0 is the average arrival interval of reference data packets, β0 is the total number of reference data packets, γ0 is the reference peak data rate, δ0 is the reference average data rate, y1 is the weight of the average arrival interval of data packets, y2 is the weight of the total number of data packets, y3 is the weight of the peak data rate, y4 is the weight of the average data rate, i is the number of each data flow, i = 1, 2, ..., n, n is the number of data flows, and e is a natural constant.

[0058] It should be noted that the average packet arrival interval weight, the total number of packet weight, the peak data rate weight and the average data rate weight all have value ranges between 0 and 1. When used, the preset values ​​can be directly extracted from the database. The specific extraction method can be to construct a mapping set with the average packet arrival interval, the total number of packet weight, the peak data rate and the average data rate respectively and the corresponding average packet arrival interval weight, the total number of packet weight, the peak data rate weight and the average data rate weight. When used, the real-time average packet arrival interval, the total number of packet weight, the peak data rate and the average data rate are input into the corresponding mapping set, so as to extract the average packet arrival interval weight, the total number of packet weight, the peak data rate weight and the average data rate weight.

[0059] It should be noted that the real-time data flow fluctuation coefficient of each data flow is obtained by analyzing and processing the data fluctuation parameters of each data flow, taking into account the correlation between these parameters. For example, when the average arrival interval of data packets is short, it means that the amount of data arriving per unit time increases. In this case, the total number of data packets usually increases accordingly; at the same time, the rate of data transmission changes more frequently, so that the peak data rate may increase, and the average data rate will also be affected and increased. On the contrary, if the average arrival interval of data packets is long, the growth rate of the total number of data packets will slow down or even decrease, data transmission will be relatively stable, and both the peak data rate and the average data rate may decrease. In addition, the increase in the total number of data packets may cause data transmission congestion when conditions such as transmission bandwidth remain unchanged, which will extend the average arrival interval of data packets, thereby affecting the peak data rate and the average data rate, resulting in peak rate limitation, average rate fluctuation, etc.; and when the peak data rate is high, it often means that data transmission is extremely fast in a certain period of time, which may cause the average arrival interval of data packets to be greatly shortened in the period of time, while promoting the total number of data packets to increase rapidly in a short period of time, and the average data rate will also increase accordingly.

[0060] In this embodiment, the system computing power evaluation index and the specific analysis method are as follows:

[0061] The system's CPU idle rate, remaining memory, and GPU idle rate are extracted from the system program log, and the system computing power evaluation indicators are obtained through analysis.

[0062] It should be noted that the CPU idle rate refers to the proportion of CPU computing power that is not currently in use, the remaining memory refers to the memory capacity in the system that has not been occupied, and the GPU idle rate refers to the proportion of GPU computing power that is not currently in use.

[0063] The system computing power evaluation index represents the quantization result of the combined influence degree of the CPU idle rate, the remaining memory amount, and the GPU idle rate of the system on the remaining computing power state of the system.

[0064] In a specific embodiment, the method for specifically obtaining the system computing power evaluation index is as follows:

[0065] Extract the reference CPU idle rate, the reference remaining memory amount, and the reference GPU idle rate stored in the database.

[0066] Perform normalization processing on the CPU idle rate, the remaining memory amount, and the GPU idle rate of the system. Divide the CPU idle rate of the system by the reference CPU idle rate to obtain the normalized value of the CPU idle rate; similarly, divide the remaining memory amount of the system by the reference remaining memory amount to obtain the normalized value of the remaining memory amount; then divide the GPU idle rate of the system by the reference GPU idle rate to obtain the normalized value of the GPU idle rate. Next, extract the preset CPU idle rate weight, remaining memory amount weight, and GPU idle rate weight from the database. Then, multiply the normalized values of the CPU idle rate, the remaining memory amount, and the GPU idle rate by the corresponding weights respectively, that is, multiply the normalized value of the CPU idle rate by the CPU idle rate weight, multiply the normalized value of the remaining memory amount by the remaining memory amount weight, and multiply the normalized value of the GPU idle rate by the GPU idle rate weight. After that, sum up these product results to obtain a comprehensive value. Finally, take the exponential of this comprehensive value with e as the base, and use the result after this exponential operation as the system computing power evaluation index.

[0067] In this embodiment, the method for specifically representing the system computing power evaluation index is as follows:

[0068]

[0069] Among them, C is the system computing power evaluation index, ε is the CPU idle rate of the system, ζ is the remaining memory amount of the system, η is the GPU idle rate of the system, ε0 is the reference CPU idle rate, ζ0 is the reference remaining memory amount, η0 is the reference GPU idle rate, z1 is the CPU idle rate weight, z2 is the remaining memory amount weight, z3 is the GPU idle rate weight, and e is the natural constant.

[0070] It should be understood that the CPU idle rate weight, the remaining memory amount weight, and the GPU idle rate weight can be directly extracted from the database. For example, the extraction method is to construct mapping sets for the CPU idle rate, the remaining memory amount, and the GPU idle rate and the CPU idle rate weight, the remaining memory amount weight, and the GPU idle rate weight respectively. When in use, input the real-time obtained CPU idle rate, remaining memory amount, and GPU idle rate into the mapping sets to obtain the CPU idle rate weight, the remaining memory amount weight, and the GPU idle rate weight.

[0071] In this embodiment, the sampling frequency of each data stream is adjusted. The specific analysis process is as follows:

[0072] Extract the first correction factor of the sampling frequency of each data stream according to the calculation resource requirement evaluation index of each data stream. The specific extraction method is: extract the first correction factor of the sampling frequency corresponding to each calculation resource requirement evaluation index interval stored in the database, and map and extract the first correction factor of the sampling frequency corresponding to the interval where the calculation resource requirement evaluation index of each data stream is located, which is denoted as the first correction factor of the sampling frequency of each data stream.

[0073] It should be noted that the larger the calculation resource requirement evaluation index, the greater the calculation resource requirement evaluation index, which means that the demand for calculation resources during data stream processing is higher. In order to reduce the computing power consumption of the system, the sampling frequency should be smaller, and the corresponding first correction factor of the sampling frequency extracted should be smaller.

[0074] Extract the second correction factor of the sampling frequency according to the system computing power evaluation index. The specific extraction method is: extract the second correction factor of each frequency corresponding to each system computing power evaluation index interval stored in the database, and map and extract the second correction factor of the frequency corresponding to the interval where the system computing power evaluation index is located, which is denoted as the second correction factor of the sampling frequency.

[0075] It should be noted that the larger the system computing power evaluation index, the more sufficient the remaining computing power available for data processing in the system. In order to make more full use of system resources and ensure the timeliness and accuracy of data collection, the corresponding second correction factor of the sampling frequency extracted should be larger. Because a higher sampling frequency can obtain more data. On the premise that the system computing power is guaranteed, processing these increased data will not cause the system to be overloaded, but instead helps to improve the accuracy and reliability of data processing.

[0076] Based on the real-time data flow fluctuation coefficient of each data stream, the first correction factor of the sampling frequency of each data stream, and the second correction factor of the sampling frequency, comprehensively analyze and process to obtain the sampling adjustment index of each data stream.

[0077] The sampling adjustment index of each data stream represents the quantitative result of the combined influence of the real-time data flow fluctuation coefficient of each data stream, the first correction factor of the sampling frequency of each data stream, and the second correction factor of the sampling frequency on the sampling frequency adjustment requirement degree of each data stream.

[0078] The sampling adjustment index of each data stream. The specific acquisition method is as follows: perform a multiplication operation on the real-time data flow fluctuation coefficient of each data stream, the first correction factor of the sampling frequency of each data stream, and the second correction factor of the sampling frequency, and use the finally obtained product result as the sampling adjustment index of each data stream.

[0079] In a specific embodiment, the sampling adjustment indexes of each data stream are specifically represented as follows:

[0080]

[0081] Among them, D i is the sampling adjustment index of the i-th data stream, B i is the real-time data flow fluctuation coefficient of the i-th data stream, is the first correction factor of the sampling frequency of the i-th data stream, σ C is the second correction factor of the sampling frequency, i is the number of each data stream, i = 1, 2,..., n, and n is the number of data streams.

[0082] Extract the preset sampling adjustment index threshold in the database.

[0083] Subtract the sampling adjustment index threshold from the sampling adjustment indexes of each data stream to obtain the sampling adjustment deviation indexes of each data stream.

[0084] It should be understood that the sampling adjustment deviation indexes of the data streams can be greater than zero, less than zero, or equal to zero.

[0085] Extract the sampling frequency adjustment values of each data stream according to the sampling adjustment deviation indexes of each data stream.

[0086] In a specific embodiment, the extraction method is as follows: Extract the sampling frequency adjustment values corresponding to each sampling adjustment deviation index interval stored in the database, and map and extract the sampling frequency adjustment values corresponding to the interval where the sampling adjustment deviation index of each data stream is located, which are denoted as the sampling frequency adjustment values of each data stream.

[0087] It should be understood that when the sampling adjustment deviation index of a data stream is greater than zero, it indicates that the data of this data stream changes relatively fast after comprehensive analysis, and the existing sampling frequency cannot meet the data processing requirements. It is necessary to increase the sampling frequency to obtain more accurate and timely data. At this time, the corresponding extracted sampling frequency adjustment value should be greater than zero, and the larger the sampling adjustment deviation index, the larger the extracted sampling frequency adjustment value should be, so as to more effectively adapt to the changes of the data stream and ensure the quality of data collection and the accuracy of subsequent heat load prediction.

[0088] When the sampling adjustment deviation index of a data stream is less than zero, it indicates that the data of this data stream changes relatively stably after comprehensive analysis, and the existing sampling frequency of this data stream exceeds the actual requirements of system resources and data processing, which may cause unnecessary resource waste. At this time, the corresponding extracted sampling frequency adjustment value should be less than zero, and the larger the absolute value of the sampling adjustment deviation index, the larger the absolute value of the extracted sampling frequency adjustment value should be, so as to reduce the sampling frequency, reasonably optimize the system resource configuration, and reduce resource waste.

[0089] Adjust the sampling frequency of each data stream according to the initial sampling frequency of each data stream and the sampling frequency adjustment value of each data stream.

[0090] In a specific embodiment, taking the data stream of the historical heat load of the heat exchange system as an example, assume that the initial sampling frequency of the data stream of the historical heat load of the heat exchange system is 10 Hz. The preset sampling adjustment index threshold in the database is 5. After analysis, the sampling adjustment index of this data stream is 8. Subtract the sampling adjustment index threshold from the sampling adjustment index (i.e., 8 - 5 = 3) to obtain the sampling adjustment deviation index of this data stream as 3.

[0091] Assume that the sampling frequency adjustment value corresponding to the sampling adjustment deviation index 3 stored in the database is to increase by 2 Hz. Then, according to the initial sampling frequency and the sampling frequency adjustment value of this data stream, adjust the sampling frequency to 12 Hz (i.e., 10 + 2 = 12).

[0092] S3. Perform data acquisition based on the adjusted sampling frequency, and thus perform the heat load prediction of the heat exchange system.

[0093] In this embodiment, for the heat load prediction of the heat exchange system, the specific analysis method is as follows:

[0094] Within the preset monitoring period, perform data acquisition based on the adjusted sampling frequency to obtain the historical heat load data of the heat exchange system and the operation data of the heat exchange system.

[0095] Among them, the historical heat load data of the heat exchange system includes the historical heat load average value and the historical heat load change rate of the heat exchange system.

[0096] It should be understood that the historical heat load average value and the historical heat load change rate affect each other and are closely related. When the historical heat load change rate is positive and large, it indicates that the heat load shows a rapid upward trend, which will gradually increase the subsequent historical heat load average value; conversely, if the historical heat load change rate is negative and the absolute value is large, it means that the heat load drops rapidly, and then the historical heat load average value will decrease accordingly.

[0097] The operation data of the heat exchange system includes the average temperature difference between the inlet and outlet of the heat exchanger, the average pressure difference between the inlet and outlet of the heat exchanger, and the heat exchange efficiency of the heat exchanger.

[0098] It should be understood that the heat exchange efficiency of the heat exchanger refers to the ratio of the actual heat exchange amount of the heat exchanger to the theoretical maximum heat exchange amount. The higher the efficiency, the better the heat exchange performance of the heat exchanger.

[0099] Analyze and process the historical heat load data of the heat exchange system and the operation data of the heat exchange system to obtain the predicted index value of the heat load of the heat exchanger.

[0100] The method for specifically obtaining the predicted index value of the heat exchanger heat load is as follows:

[0101] According to the historical data analysis of the heat load of the heat exchange system, the first predicted index value of the heat exchanger heat load is obtained. The first predicted index value of the heat exchanger heat load represents the quantitative data of the combined influence degree of the historical heat load mean value and the historical heat load change rate of the heat exchange system on the heat exchanger heat load. The method for obtaining it is as follows: Extract the historical heat load mean value and the reference historical heat load change rate stored in the database of the reference heat exchange system.

[0102] Normalize the historical heat load mean value in the historical data of the heat load of the heat exchange system. Divide the historical heat load mean value by the reference historical heat load mean value to obtain the normalized value of the historical heat load mean value. Then perform the same operation on the historical heat load change rate. Divide the historical heat load change rate by the reference historical heat load change rate to obtain the normalized value of the historical heat load change rate. Extract the pre-set weight value of the historical heat load mean value and the weight value of the historical heat load change rate in the database. Multiply the normalized value of the historical heat load mean value by the weight value of the historical heat load mean value, multiply the normalized value of the historical heat load change rate by the weight value of the historical heat load change rate, and finally add the results of these two multiplications. Add 1 to the sum obtained and input it into the logarithmic function with the base of e, and take the calculation result of the logarithmic function as the first predicted index value of the heat exchanger heat load.

[0103] In a specific embodiment, the first predicted index value of the heat exchanger heat load is expressed as follows:

[0104]

[0105] Among them, F is the first predicted index value of the heat exchanger heat load, is the historical heat load mean value of the heat exchange system, λ is the historical heat load change rate of the heat exchange system, is the reference historical heat load mean value, λ0 is the reference historical heat load change rate, z3 is the weight value of the historical heat load mean value, and z4 is the weight value of the historical heat load change rate.

[0106] It should be noted that the weight value of the historical heat load mean value and the weight value of the historical heat load change rate are pre-set in the database, and their value ranges are between 0 and 1. For example, the extraction method is to construct a mapping set with the historical heat load mean value and the historical heat load change rate and the weight value of the historical heat load mean value and the weight value of the historical heat load change rate respectively. When in use, input the real-time obtained historical heat load mean value and historical heat load change rate into the mapping set, so as to extract the weight value of the historical heat load mean value and the weight value of the historical heat load change rate.

[0107] According to the operation data analysis of the heat exchange system, the second index value of the heat exchanger heat load prediction is obtained. The second index value of the heat exchanger heat load prediction represents the quantification result of the combined influence degree of the average temperature difference between the inlet and outlet of the heat exchanger, the average pressure difference between the inlet and outlet of the heat exchanger, and the heat exchange efficiency of the heat exchanger on the operation state of the heat exchange system.

[0108] The specific method for obtaining the second index value of the heat exchanger heat load prediction is as follows:

[0109] Extract the average temperature difference between the inlet and outlet of the reference heat exchanger, the average pressure difference between the inlet and outlet of the reference heat exchanger, and the heat exchange efficiency of the reference heat exchanger stored in the database.

[0110] Extract the weight value of the average temperature difference between the inlet and outlet of the heat exchanger, the weight value of the average pressure difference between the inlet and outlet of the heat exchanger, and the weight value of the heat exchange efficiency of the heat exchanger preset in the database.

[0111]

[0112] Wherein, G is the second index value of the heat exchanger heat load prediction, f is the average temperature difference between the inlet and outlet of the heat exchanger, g is the average pressure difference between the inlet and outlet of the heat exchanger, h is the heat exchange efficiency of the heat exchanger, f0 is the average temperature difference between the inlet and outlet of the reference heat exchanger, g0 is the average pressure difference between the inlet and outlet of the reference heat exchanger, h0 is the heat exchange efficiency of the reference heat exchanger, is the weight value of the average temperature difference between the inlet and outlet of the heat exchanger, is the weight value of the average pressure difference between the inlet and outlet of the heat exchanger, is the weight value of the heat exchange efficiency of the heat exchanger, and e is the natural constant.

[0113] It should be understood that the average temperature difference between the inlet and outlet of the heat exchanger directly reflects the temperature transfer situation between the hot and cold fluids during the heat exchange process. The larger the average temperature difference, the stronger the heat transfer driving force of the heat exchanger, and the higher the heat exchange efficiency. The average pressure difference between the inlet and outlet reflects the resistance situation of the fluid during its flow inside the heat exchanger. The larger the average pressure difference, the greater the fluid flow resistance, which may lead to a decrease in the fluid flow rate and thus affect the heat exchange efficiency. The heat exchange efficiency is jointly affected by the average temperature difference between the inlet and outlet and the average pressure difference between the inlet and outlet. Under other unchanged conditions, an increase in the average temperature difference between the inlet and outlet usually improves the heat exchange efficiency, while an increase in the average pressure difference between the inlet and outlet may reduce the heat exchange efficiency.

[0114] It should be noted that the weight values of the average temperature difference at the inlet and outlet of the heat exchanger, the weight values of the average pressure difference at the inlet and outlet of the heat exchanger, and the weight values of the heat exchange efficiency of the heat exchanger all have a value range of 0 to 1. When in use, the preset values can be directly extracted from the database. For example, the extraction method is to construct a mapping set with the average temperature difference at the inlet and outlet of the heat exchanger, the average pressure difference at the inlet and outlet of the heat exchanger, and the heat exchange efficiency of the heat exchanger, and the corresponding weight values of the average temperature difference at the inlet and outlet of the heat exchanger, the weight values of the average pressure difference at the inlet and outlet of the heat exchanger, and the weight values of the heat exchange efficiency of the heat exchanger. When in use, the average temperature difference at the inlet and outlet of the heat exchanger, the average pressure difference at the inlet and outlet of the heat exchanger, and the heat exchange efficiency of the heat exchanger are input into the mapping set, so as to extract the corresponding weight values of the average temperature difference at the inlet and outlet of the heat exchanger, the weight values of the average pressure difference at the inlet and outlet of the heat exchanger, and the weight values of the heat exchange efficiency of the heat exchanger.

[0115] Multiply the first index value of the heat exchanger heat load prediction and the second index value of the heat exchanger heat load prediction by the corresponding first index weight value of the heat exchanger heat load prediction and the second index weight value of the heat exchanger heat load prediction respectively, and then add the products to obtain the heat exchanger heat load prediction index value.

[0116] In a specific embodiment, the heat exchanger heat load prediction index value is specifically expressed as follows:

[0117] H = F * ω1 + G * ω2,

[0118] Wherein, H is the heat exchanger heat load prediction index value, F is the first index value of the heat exchanger heat load prediction, G is the second index value of the heat exchanger heat load prediction, ω1 is the first index weight value of the heat exchanger heat load prediction, and ω2 is the second index weight value of the heat exchanger heat load prediction.

[0119] It should be noted that the value ranges of the first index weight value of the heat exchanger heat load prediction and the second index weight value of the heat exchanger heat load prediction are both 0 - 1. When in use, the preset values can be directly extracted from the database. For example, the extraction method is to construct a mapping set with the first index value of the heat exchanger heat load prediction and the second index value of the heat exchanger heat load prediction, and the corresponding first index weight value of the heat exchanger heat load prediction and the second index weight value of the heat exchanger heat load prediction. When in use, the first index value of the heat exchanger heat load prediction and the second index value of the heat exchanger heat load prediction are input into the mapping set, so as to obtain the corresponding weight values.

[0120] Extract the heat load prediction value of the area where the heat exchanger is located according to the heat exchanger heat load prediction index value, thereby completing the heat load prediction of the heat exchange system.

[0121] It should be noted that the predicted heat load value of the area where the heat exchanger is located is extracted according to the predicted heat load index value of the heat exchanger, and the extraction process is as follows: Extract the predicted heat load values corresponding to the intervals of each predicted heat load index value stored in the database, and map and extract the predicted heat load value corresponding to the interval where the predicted heat load index value of the heat exchanger is located, which is denoted as the predicted heat load value of the area where the heat exchanger is located.

[0122] S4. Perform dynamic adjustment of the heat exchange system according to the predicted heat load result of the heat exchange system.

[0123] In this embodiment, the dynamic adjustment of the heat exchange system is performed according to the predicted heat load result of the heat exchange system, and the specific analysis method is as follows:

[0124] Obtain the meteorological data of the area where the heat exchange system is located, including the average temperature and average humidity of the area where the heat exchange system is located.

[0125] It should be noted that the meteorological data of the area where the heat exchange system is located is the meteorological data of the target time period of the predicted heat load of the area where the heat exchange system is located, and can be directly collected from the geographic information system.

[0126] Analyze and process the meteorological data of the area where the heat exchange system is located to obtain the meteorological characterization coefficient of the area where the heat exchange system is located.

[0127] The method for specifically obtaining the meteorological characterization coefficient of the area where the heat exchange system is located is as follows: Extract the average reference temperature and average reference humidity stored in the database.

[0128] Perform normalization processing on the average temperature in the meteorological data of the area where the heat exchange system is located. Divide the average temperature of the area where the heat exchange system is located by the average reference temperature to obtain the normalized value of the average temperature; then perform the same operation on the average humidity. Divide the average humidity of the area where the heat exchange system is located by the average reference humidity to obtain the normalized value of the average humidity. Extract the preset weight of the average temperature and the weight of the average humidity stored in the database. Multiply the normalized value of the average temperature by the weight of the average temperature, multiply the normalized value of the average humidity by the weight of the average humidity, add these product results, add 1 to the obtained sum, input it into the logarithmic function with base 10, and use the output result of this function as the meteorological characterization coefficient of the area where the heat exchange system is located.

[0129] The specific representation method of the meteorological characterization coefficient of the area where the heat exchange system is located is as follows:

[0130]

[0131] Among them, K is the meteorological characterization coefficient of the area where the heat exchange system is located, p is the average temperature of the area where the heat exchange system is located, q is the average humidity of the area where the heat exchange system is located, p0 is the average reference temperature, q0 is the average reference humidity, z5 is the weight of the average temperature, and z6 is the weight of the average humidity.

[0132] It should be understood that the value ranges of the temperature mean weight and the humidity mean weight are both between 0 and 1. When in use, the preset values can be directly extracted. For example, the extraction method is to construct corresponding mapping sets for the temperature mean and the humidity mean with the temperature mean weight and the humidity mean weight respectively. When in use, the collected temperature mean and humidity mean are input into the mapping sets one by one, so as to extract the temperature mean weight and the humidity mean weight.

[0133] Extract the ideal heat load of the area where the heat exchange system is located according to the meteorological characterization coefficient of the area where the heat exchange system is located. The extraction method is as follows: extract the ideal heat load corresponding to each meteorological characterization coefficient interval in the database, and map and extract the ideal heat load corresponding to the interval where the meteorological characterization coefficient of the area where the heat exchange system is located is located, which is recorded as the ideal heat load of the area where the heat exchange system is located.

[0134] Subtract the ideal heat load of the area where the heat exchange system is located from the predicted value of the heat load of the area where the heat exchanger is located to obtain the heat load prediction deviation value of the area where the heat exchange system is located.

[0135] The heat load prediction deviation value of the area where the heat exchange system is located may be greater than zero, less than zero or equal to zero.

[0136] Take the heat load prediction deviation value of the area where the heat exchange system is located as the heat load prediction result of the heat exchange system.

[0137] Extract the heat exchanger adjustment parameters according to the heat load prediction deviation value of the area where the heat exchange system is located.

[0138] It should be noted that when the heat load prediction deviation value of the area where the heat exchange system is located is greater than zero, it means that the currently predicted heat load exceeds the ideal heat load of this area. To prevent waste of resources, the corresponding heat exchanger adjustment parameters extracted should be less than zero, and the greater the heat load prediction deviation value of the area where the heat exchange system is located, the higher the degree of exceeding the ideal heat load, and the greater the absolute value of the heat exchanger adjustment parameters should be. When the heat load prediction deviation value of the area where the heat exchange system is located is less than zero, it means that the currently predicted heat load has not reached the ideal level and the predicted heat load is less. The corresponding heat exchanger adjustment parameters extracted should be greater than zero, and the greater the absolute value of the heat load prediction deviation value of the area where the heat exchange system is located, the more obvious the gap between the heat load and the ideal value, and the greater the heat exchanger adjustment parameters should be.

[0139] The heat exchanger adjustment parameters include the expansion valve opening adjustment value and the frequency conversion pump speed.

[0140] Extract the initial parameters of the heat exchanger.

[0141] Perform dynamic adjustment of the heat exchange system according to the initial parameters of the heat exchanger and the heat exchanger adjustment parameters.

[0142] In a specific embodiment, it is assumed that the initial opening degree of the expansion valve of the heat exchanger is 50%, and the rotational speed of the variable-frequency pump is 1000 revolutions per minute. After calculation, the predicted deviation value of the heat load in the area where the heat exchange system belongs is greater than zero, which is 10 kW. According to the rules, the extracted adjustment value of the expansion valve opening degree is -10%, and the adjustment value of the rotational speed of the variable-frequency pump is -200 revolutions per minute. Then, based on the initial parameters of the heat exchanger and these adjustment parameters, dynamic adjustment is carried out. After adjustment, the opening degree of the expansion valve becomes 50% + (-10%) = 40%, and the rotational speed of the variable-frequency pump becomes 1000 + (-200) = 800 revolutions per minute. Through dynamic adjustment, the refrigerant flow rate and circulating power are reduced, resource waste when the predicted heat load value is higher than the ideal value is avoided, and it is ensured that the heat exchange system can operate more efficiently and reasonably.

[0143] Refer to Figure 2 As shown, the second aspect of the present invention provides an optimization system for a heat exchange system based on big data analysis, including:

[0144] A computing resource requirement assessment module, which is used to record each heat load prediction data stream of the heat exchange system as each data stream, perform the computing resource requirement assessment of each data stream, analyze the computing resource requirement assessment indicators of each data stream, and thus perform resource limitation.

[0145] A sampling frequency adjustment module, which is used to generate an adaptive sampling frequency control instruction according to the computing resource requirement assessment indicators of each data stream, and synchronously analyze the real-time data flow fluctuation coefficient and the system computing power assessment indicators, and perform the sampling frequency adjustment of each data stream.

[0146] A heat load prediction module, which is used to collect data based on the adjusted sampling frequency, and thus perform the heat load prediction of the heat exchange system.

[0147] A heat exchange system dynamic adjustment module, which is used to perform dynamic adjustment of the heat exchange system according to the heat load prediction result of the heat exchange system.

[0148] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0149] The present invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each flow and / or block in the flowchart illustrations and / or block diagrams, and combinations of flows and / or blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing apparatus create means for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 one or more blocks for implementing the specified functions.

[0150] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 one or more blocks for implementing the specified functions.

[0151] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 one or more blocks for implementing the specified functions.

[0152] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0153] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. Optimization method for heat exchange system based on big data analysis, characterized in that, It includes the following steps: S1. Denote the heat load prediction data streams of the heat exchange system as each data stream, perform the calculation resource requirement assessment of each data stream, analyze the calculation resource requirement assessment indicators of each data stream, and thus perform resource limitation; S2. According to the calculation resource requirement assessment indicators of each data stream, and synchronously analyze the real-time data flow fluctuation coefficient and the system computing power assessment indicator, generate an adaptive sampling frequency control instruction, and adjust the sampling frequency of each data stream; S3. Perform data collection based on the adjusted sampling frequency, and thus perform the heat load prediction of the heat exchange system; S4. Perform dynamic adjustment of the heat exchange system according to the heat load prediction result of the heat exchange system.

2. The optimization method of the heat exchange system based on big data analysis according to claim 1, characterized in that: The heat load prediction data streams of the heat exchange system specifically include: the heat load historical data of the heat exchange system, the operation data of the heat exchange system, and the meteorological data of the area where the heat exchange system is located.

3. The optimization method of the heat exchange system based on big data analysis according to claim 1, characterized in that: The process of analyzing the calculation resource requirement assessment indicators of each data stream and thus performing resource limitation is as follows: Obtain the historical resource parameters of each data stream, and analyze the calculation resource requirement assessment indicators of each data stream; Extract the demand quantities corresponding to each demand assessment indicator interval stored in the database, and map and extract the demand quantities corresponding to the interval where the calculation resource requirement assessment indicator of each data stream is located, and denote them as the calculation resource demand quantities of each data stream; Perform resource limitation according to the calculation resource demand quantities of each data stream.

4. The optimization method of the heat exchange system based on big data analysis according to claim 3, characterized in that: The specific analysis process of the calculation resource requirement assessment indicators of each data stream is as follows: Obtain the historical resource parameters of each data stream, including the average value of the historical data volume of each data stream, the average value of the historical data processing frequency, the average value of the number of historical data types, and the average value of the historical data transmission bandwidth; Obtain the reference historical resource parameters; Comprehensively analyze and process according to the historical resource parameters of each data stream and the reference historical resource parameters to obtain the calculation resource requirement assessment indicators of each data stream; The calculation resource requirement assessment indicators of each data stream represent the quantitative result of the combined influence of the average value of the historical data volume of each data stream, the average value of the historical data processing frequency, the average value of the number of historical data types, and the average value of the historical data transmission bandwidth on the calculation resource requirement degree of the data stream.

5. The optimization method of the heat exchange system based on big data analysis according to claim 1, wherein: The specific analysis process of the real-time data flow fluctuation coefficient is as follows: Extract the initial sampling frequency and data collection verification duration of each data stream; Perform data collection of each data stream at the initial sampling frequency of each data stream within the data collection verification duration, so as to obtain the data fluctuation parameters of each data stream; The data fluctuation parameters of each data stream include the average arrival interval of data packets of each data stream, the total number of data packets, the peak data rate, and the average data rate; Analyze and process according to the data fluctuation parameters of each data stream to obtain the real-time data flow fluctuation coefficient of each data stream; The real-time data flow fluctuation coefficient of each data stream represents the quantitative result of the combined influence of the average arrival interval of data packets of each data stream, the total number of data packets, the peak data rate, and the average data rate on the data flow fluctuation state.

6. The optimization method of the heat exchange system based on big data analysis according to claim 1, characterized in that: The specific analysis method of the system computing power assessment indicator is as follows: Extract the CPU idle rate, the remaining memory, and the GPU idle rate of the system from the system program log, and analyze to obtain the system computing power assessment indicator; The system computing power evaluation index represents the quantization result of the combined influence degree of the CPU idle rate, the remaining memory amount, and the GPU idle rate of the system on the remaining computing power state of the system.

7. The optimization method of the heat exchange system based on big data analysis according to claim 1, wherein: The adjustment of the sampling frequency of each data stream is carried out, and the specific analysis process is as follows: Extract the first correction factor of the sampling frequency of each data stream according to the computing resource demand evaluation index of each data stream; Extract the second correction factor of the sampling frequency according to the system computing power evaluation index; Based on the real-time data flow fluctuation coefficient of each data stream, the first correction factor of the sampling frequency of each data stream, and the second correction factor of the sampling frequency, comprehensively analyze and process to obtain the sampling adjustment index of each data stream; Extract the preset sampling adjustment index threshold in the database; Subtract the sampling adjustment index threshold from the sampling adjustment index of each data stream to obtain the sampling adjustment deviation index of each data stream; Extract the sampling frequency adjustment value of each data stream according to the sampling adjustment deviation index of each data stream; Adjust the sampling frequency of each data stream according to the initial sampling frequency of each data stream and the sampling frequency adjustment value of each data stream.

8. The optimization method of the heat exchange system based on big data analysis according to claim 1, characterized in that: The heat load prediction of the heat exchange system is carried out, and the specific analysis method is as follows: Within a preset monitoring period, perform data collection based on the adjusted sampling frequency to obtain the heat load historical data of the heat exchange system and the operation data of the heat exchange system; Among them, the heat load historical data of the heat exchange system includes the historical heat load average value and the historical heat load change rate of the heat exchange system; The operation data of the heat exchange system includes the average temperature difference between the inlet and outlet of the heat exchanger, the average pressure difference between the inlet and outlet of the heat exchanger, and the heat exchange efficiency of the heat exchanger; Based on the heat load historical data of the heat exchange system and the operation data of the heat exchange system, analyze and process to obtain the heat load prediction index value of the heat exchanger; Extract the heat load prediction value of the area where the heat exchanger is located according to the heat load prediction index value of the heat exchanger, thereby completing the heat load prediction of the heat exchange system.

9. The optimization method of the heat exchange system based on big data analysis according to claim 1, wherein: The dynamic adjustment of the heat exchange system is carried out according to the heat load prediction result of the heat exchange system, and the specific analysis method is as follows: Obtain the meteorological data of the area where the heat exchange system is located, including the average temperature and average humidity of the area where the heat exchange system is located; Analyze and process the meteorological data of the area where the heat exchange system is located to obtain the meteorological characterization coefficient of the area where the heat exchange system is located; Extract the ideal heat load of the area where the heat exchange system is located according to the meteorological characterization coefficient of the area where the heat exchange system is located; Subtract the ideal heat load of the area where the heat exchange system is located from the heat load prediction value of the area where the heat exchanger is located to obtain the heat load prediction deviation value of the area where the heat exchange system is located; Use the heat load prediction deviation value of the area where the heat exchange system is located as the heat load prediction result of the heat exchange system; Extract the heat exchanger adjustment parameters according to the heat load prediction deviation value of the area where the heat exchange system is located; The heat exchanger adjustment parameters include the expansion valve opening adjustment value and the variable frequency pump speed; Extract the initial parameters of the heat exchanger; Perform dynamic adjustment of the heat exchange system according to the initial parameters of the heat exchanger and the heat exchanger adjustment parameters.

10. A system applying the optimization method of the heat exchange system based on big data analysis according to any one of claims 1-9, characterized in that, Include: A computing resource demand evaluation module, which is used to record each heat load prediction data stream of the heat exchange system as each data stream, perform the computing resource demand evaluation of each data stream, analyze the computing resource demand evaluation index of each data stream, and thus perform resource limitation; The sampling frequency adjustment module is used to evaluate the computing resource requirements of each data stream, synchronously analyze the real-time data flow fluctuation coefficient and the system computing power evaluation index, generate an adaptive sampling frequency control instruction, and adjust the sampling frequency of each data stream; The heat load prediction module is used to collect data based on the adjusted sampling frequency, and thus predict the heat load of the heat exchange system; The heat exchange system dynamic adjustment module is used to dynamically adjust the heat exchange system according to the heat load prediction result of the heat exchange system.

Images