Thermal load analysis system based on cloud computing

Abstract

The invention relates to the technical field of industrial internet, and particularly discloses a thermal load analysis system based on cloud computing, which comprises a central processing module used for uniformly scheduling cloud computing resources and coordinating multiple tasks and data flow management; the data acquisition module is used for acquiring parameters related to the thermal load; the data processing module is used for preprocessing data, calculating instantaneous thermal load and historical thermal load evaluation coefficients and generating a collection strategy adjustment instruction; the data storage module is used for storing real-time data, historical data and evaluation reports; the data analysis module is used for carrying out thermal load abnormity diagnosis; and the data analysis result generation module is used for generating a thermal load evaluation report. According to the method, intelligent management of thermal load analysis is realized, and the system operation efficiency and the data processing efficiency are remarkably improved through intelligent resource scheduling and flow batch cooperative processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial internet, more specifically, the present application relates to a heat load analysis system based on cloud computing. BACKGROUND

[0002] In the field of energy management technology, heat load analysis is of great significance to achieve precise energy consumption control and system optimization. Heat load refers to the total amount of heat provided to maintain a specific environment or process requirement, and its accurate analysis directly affects the operating efficiency and economy of the energy system. The heat load analysis system monitors and analyzes temperature, flow and other operating parameters in real time, providing data support and decision-making basis for the optimized operation of the energy system. With the development of cloud computing technology, heat load analysis systems based on cloud platforms have become an effective technical means for industrial energy saving and intelligent building management.

[0003] In the prior art, a heat load monitoring system based on a cloud platform is disclosed in Chinese patent CN201910123456.7. The system collects temperature, flow and other operating parameters through a distributed sensor network, stores data using a traditional relational database, and generates load trend reports using basic statistical methods such as moving average algorithm. Another similar solution is the intelligent building heat load analysis platform disclosed in CN202010654321.2, which uses an edge computing architecture, uploads data to the cloud platform after preprocessing at the local gateway node, uses traditional statistical methods such as ARIMA time series analysis for load prediction, and provides basic energy efficiency evaluation functions.

[0004] However, the existing heat load analysis system has some defects and shortcomings in actual application, the main defects are as follows: 1. Inadequate resource scheduling mechanism leading to low utilization: the system lacks central scheduling management mechanism, each computing module runs independently, and cannot realize dynamic allocation and collaborative management of cloud computing resources. This leads to low resource utilization, both resource idling and processing bottleneck when handling high concurrency data, and cannot be flexibly scaled according to actual load, seriously affecting the overall operation efficiency and performance of the system.

[0005] 2. Performance bottleneck caused by separation of stream and batch processing architecture: a single processing mode is adopted, which cannot distinguish the different technical requirements of real-time stream processing and batch computing. This architecture design leads to large delay when processing real-time data, while batch computing tasks cannot fully utilize distributed cluster resources, which cannot meet the dual requirements of real-time and processing efficiency of heat load analysis, limiting the performance of the system in large-scale application scenarios. SUMMARY

[0006] In order to overcome the above-mentioned defects of the prior art, the present application provides a heat load analysis system based on cloud computing, which solves the problems raised in the above background art through the following scheme.

[0007] To achieve the above object, the present application provides the following technical scheme: a heat load analysis system based on cloud computing, comprising: A central processing module is configured to uniformly schedule cloud computing resources, cooperatively process multiple tasks, and manage data streams. A data acquisition module is configured to acquire parameters related to heat load, standardize and condition analog signals, and perform analog-to-digital conversion, and finally transmit digital data to a data processing module while accepting and executing data acquisition strategy adjustment instructions issued by the data processing module. A data processing module is configured to preprocess data, calculate instantaneous heat load based on the preprocessed data, and periodically calculate historical heat load evaluation coefficients, and generate data acquisition strategy adjustment instructions based on data quality analysis results and abnormal diagnosis results and issue them to the data acquisition module. A data storage module is configured to store real-time data, historical data, and evaluation reports, and support multi-dimensional query and call of historical data. A data analysis module is configured to analyze processed data, running energy efficiency coefficient, and running stability coefficient, and perform heat load abnormal diagnosis. An analysis result generation module is configured to generate quantitative heat load evaluation reports based on heat load evaluation coefficients and abnormal diagnosis results.

[0008] The technical effects and advantages of the present application are as follows: 1. Intelligent resource scheduling improves system performance: The present application realizes the unified scheduling and intelligent allocation of cloud computing resources through the resource abstraction layer and task scheduler of the central processing module, effectively solving the problem of low resource utilization rate of existing systems. The central processing module pools physical resources and dynamically allocates them to each module, automatically adjusts resource allocation strategies according to real-time load conditions, and significantly improves the resource utilization efficiency and overall performance of the system.

[0009] 2. Stream-batch collaborative processing optimizes computing efficiency: The present application adopts a separate architecture design of stream processing and batch processing, realizes high-speed processing of real-time data through an independent stream processing unit, and completes periodic computing tasks with a batch processing unit, overcoming the single processing mode defect of existing systems. This design can meet different needs of real-time processing and batch computing, greatly improving the data processing efficiency and performance of the system. BRIEF DESCRIPTION OF DRAWINGS

[0010] Figure 1 The module structure diagram of the system of the present application. DETAILED DESCRIPTION

[0011] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0012] Reference Figure 1 The cloud computing-based heat load analysis system shown in the figure comprises a central processing module, a data acquisition module, a data processing module, a data storage module, a data analysis module and an analysis result generation module.

[0013] The central processing module is connected with the data acquisition module, the data processing module, the data storage module, the data analysis module and the analysis result generation module respectively, the data acquisition module is connected with the data processing module, the data processing module is connected with the data storage module and the data analysis module respectively, and the data storage module is connected with the data analysis module and the analysis result generation module.

[0014] It should be noted that the connection modes between the modules in the system of the present application include but are not limited to physical connection, electrical connection, wired network connection, wireless network connection, data interface connection and logical function connection.

[0015] In a preferred embodiment of the present application, the central processing module is used for unified scheduling of cloud computing resources, cooperative processing of multiple tasks and data flow management.

[0016] The central processing module comprises: A resource abstraction layer is used for pooling physical computing, storage and network resources into virtualized resource units. A task scheduler is used for allocating computing resources to each module and managing task execution priority. A data manager is used for controlling data flow and storage strategy in the system.

[0017] The central processing module as the core control unit of the system adopts a hierarchical architecture to realize cooperative management of each module through physical connection and logical connection. On the physical connection level, high-speed Ethernet interface and TCP or IP protocol are adopted for data transmission; on the logical connection level, message queue and remote procedure call are adopted to realize instruction issuing and state monitoring.

[0018] The resource abstraction layer connects with the underlying physical server through virtualization technology, pools CPU, memory, storage and network resources, and generates virtualized resource units that can be dynamically allocated; real-time resource utilization data is collected, and resource state signals are sent to the task scheduler through logical connection; software-defined network technology is used to allocate independent network channels for each virtual resource unit.

[0019] The task scheduler uses scheduling algorithms such as multi-level feedback queue to receive resource requests from each module, including computing, storage and network bandwidth requirements, through logical connection; it interacts with the cloud computing platform management interface through physical connection and sends resource allocation instructions; it maintains a task priority mapping table internally and dynamically adjusts resource allocation strategies according to task urgency, thereby supporting the "management task execution priority" function.

[0020] The data manager realizes data flow control through a dual connection method: it directly interacts with the data storage module through physical connection to control data read and write operations; it receives data feature signals from the data processing module through logical connection to develop data distribution strategies; it uses data lineage tracking technology to establish a data flow map through metadata management, and real-time monitors data transmission paths and processing status to execute the "control data flow and storage strategy" function.

[0021] The interaction between the units of the central processing module is as follows: the resource abstraction layer exchanges resource state information with the task scheduler through shared memory; the task scheduler sends data scheduling instructions to the data manager through remote procedure call; the data manager feeds back storage resource usage to the resource abstraction layer through message queue. This composite connection architecture ensures real-time and reliability of the system when processing high-concurrency data, while ensuring accuracy of resource scheduling and efficiency of data flow control.

[0022] In a preferred embodiment of the present application, the data acquisition module is used to acquire parameters related to thermal load, and to standardize and convert analog signals to digital signals, and finally transmit digital data to the data processing module, while accepting and executing data acquisition strategy adjustment instructions issued by the data processing module.

[0023] The data acquisition module comprises: a sensor for acquiring parameters related to thermal load; a signal conditioning unit for amplifying, filtering and standardizing sensor signals; a data conversion unit for converting analog signals to digital signals; a communication unit for transmitting collected data to the data processing module, while receiving and executing data acquisition strategy adjustment instructions issued by the data processing module.

[0024] The data acquisition module serves as a system perception layer and a signal conversion hub, adopts a distributed sensor network architecture, and realizes comprehensive acquisition and standardized processing of heat load related parameters through physical and logical connection combination.

[0025] The sensor unit is composed of multiple types of sensors: temperature sensors acquire supply medium temperature and return medium temperature, flow sensors measure medium flow, and power sensors acquire total input power of the system. All sensors are physically connected with the signal conditioning unit through 4-20 mA current signals or Modbus protocol.

[0026] The signal conditioning unit amplifies weak current signals through an instrument amplifier, eliminates power frequency and high frequency noise through multiple active filters, completes signal standardization through current conversion, and transmits the processed analog signals to the data conversion unit through electrical connection.

[0027] The data conversion unit adopts a high-precision analog-to-digital conversion chip to digitize the standardized analog signals at a maximum sampling frequency of 1 kHz, and further eliminates noise during conversion using digital filtering technology to ensure data accuracy. Finally, clean digital signals are sent to the communication unit through internal interfaces.

[0028] The communication unit adopts a dual-mode architecture of industrial Ethernet and wireless transmission, and establishes a high-reliability logical connection with the data processing module through TCP / IP protocol. The communication unit not only packages and uploads the collected digital signals and device status information to the data processing module at regular intervals, but also receives real-time collection strategy adjustment instructions from the data processing module and dynamically optimizes the data collection process according to the instructions.

[0029] The interaction between the data acquisition module and the central processing module is realized through its task scheduler: the central processing module uniformly allocates network bandwidth and computing resources to the communication unit, and coordinates data flow through the data manager to realize resource scheduling and macro management of the collection process.

[0030] In a preferred embodiment of the present application, the data processing module is used for pre-processing data, calculating instantaneous heat load based on pre-processed data, and periodically calculating historical heat load evaluation coefficients. Data acquisition strategy adjustment instructions are generated based on data quality analysis results and abnormal diagnosis results and then issued to the data acquisition module.

[0031] The data processing module comprises: a pre-processing unit for data cleaning and filtering; a stream processing unit for calculating instantaneous heat load based on a stream processing framework; a batch processing unit for periodically calculating historical heat load evaluation coefficients based on a batch processing framework; A strategy generation unit is configured to generate a data collection strategy adjustment instruction based on the data quality analysis result and the anomaly diagnosis result, and deliver the data collection strategy adjustment instruction to the data collection module.

[0032] The data processing module is a core computing engine of the system, responsible for converting the raw electrical signals uploaded by the data collection module into thermal load parameters with explicit physical meaning.

[0033] The preprocessing unit directly receives the raw digital signals from the communication unit of the data collection module through physical connection, and its core function is to complete data cleaning and filtering. In the data cleaning link, the preprocessing unit can identify and eliminate illegal values and null values generated by sensor transient faults or network jitter, and use linear interpolation of valid data before and after to fill in, ensuring the integrity of the data. In the data filtering link, sliding weighted average filtering or Kalman filtering algorithm is used to effectively suppress high-frequency noise and smooth the data curve, thereby significantly improving the signal-to-noise ratio. The cleaned data after preprocessing is pushed to two downstream pathways through logical connection: one way is to transmit in real time to the stream processing unit in a high-throughput and low-delay manner; the other way is to archive to the time series database of the data storage module in time batches for periodic calling by the batch processing unit.

[0034] The stream processing unit is built based on a stream processing framework and continuously consumes real-time clean data streams in the message queue through logical connection. Its core task is to calculate the instantaneous thermal load value in real time through the built-in instantaneous thermal load calculation formula based on the principle of energy conservation.

[0035] The instantaneous thermal load calculation formula is as follows: ;

[0036] Wherein: is the instantaneous thermal load, with the unit of kW; is the specific heat capacity of the medium at constant pressure, with the unit of kJ / (kg·℃), which can be obtained by looking up the table; is the medium density, with the unit of kg / m³, which can be obtained by looking up the table; is the volumetric flow measured by the flow meter, with the unit of m³ / h; and are the supply medium temperature and the return medium temperature, respectively, with the unit of ℃.

[0037] The calculation is continuously performed within a time window, and the result is written to the time series database of the data storage module through physical network connection.

[0038] The batch processing unit periodically starts calculation tasks based on the batch processing framework. It retrieves clean data and instantaneous heat load calculation results from the data warehouse of the data storage module through logical connections, and calculates the historical heat load evaluation coefficient according to the predefined heat load evaluation coefficient calculation formula.

[0039] The formula for calculating the heat load assessment factor is as follows: In this embodiment, it should be noted that the calculation formula for the heat load assessment coefficient K is as follows: ;

[0040] in: and These are the weighting coefficients for the operating energy efficiency coefficient E and the operating stability coefficient S, respectively. It is recommended that their initial values ​​be set to 0.6 and 0.4, respectively, to indicate a greater emphasis on energy efficiency. The weights can be dynamically adjusted through the task scheduler of the central processing module according to the specific project priority.

[0041] 1. The operating energy efficiency coefficient E is calculated using the following formula: ;

[0042] in: This is the average instantaneous heat load within a calculation cycle, expressed in kW. This data comes from the calculation results of the stream processing unit and is stored in the time-series database. The average total input power of the system during the calculation period is expressed in kW. This data is the average power of all energy consumed to generate the heat load and is collected by the data acquisition module. This is a reference energy efficiency ratio; this value is stored as system data in the data warehouse.

[0043] The closer E is to 1, the closer the actual energy efficiency of the system is to the design ideal value.

[0044] 2. Operational stability coefficient The calculation formula is as follows: ;

[0045] in: To calculate all instantaneous heat load values ​​within the calculation period The standard deviation of , in kW; To calculate all instantaneous heat load values ​​within the calculation period The average value is expressed in kW. Known as the coefficient of variation, it is a standardized indicator that measures the volatility of data, eliminating the influence of the magnitude of the mean itself on the judgment of volatility.

[0046] The smaller the coefficient of variation, the more stable the heat load.

[0047] It is necessary to supplement the embodiment that a calculation period can be one day, i.e. 24 hours.

[0048] The strategy generation unit receives the data quality analysis results from the preprocessing unit in real time through logical connection, including signal-to-noise ratio, data integrity and abnormal value frequency and the like. The strategy generation unit is built-in with a strategy rule engine, and when it is monitored that the data quality indicators exceed the preset threshold, an acquisition strategy adjustment instruction is automatically generated. The instruction includes dynamically adjusting the sampling frequency, triggering the sensor calibration program or switching the standby communication channel and the like, and is issued to the communication unit of the data acquisition module through logical connection.

[0049] All processing processes are uniformly scheduled by the central processing module: the task scheduler dynamically allocates computing resources, allocates high-priority resources for real-time flow processing tasks, and allocates elastic resources for batch processing tasks and strategy generation tasks; the data manager controls the data flow, and the processed instantaneous load data and historical heat load evaluation coefficients are synchronously pushed to the data storage module for archiving through the internal physical network and logical API call, and trigger the prediction and diagnosis tasks of the data analysis module, forming a closed-loop processing flow.

[0050] In a preferred embodiment of the application, the data storage module is used for storing real-time data, historical data and evaluation reports, and supports multi-dimensional query and call of historical data.

[0051] The data storage module comprises: A time series database is used for storing real-time monitoring data and instantaneous heat load calculation results; A data warehouse is used for storing historical data, historical operation energy efficiency coefficients, operation stability coefficients, heat load evaluation coefficients and evaluation reports, and supports multi-dimensional query and call of historical data.

[0052] The data storage module serves as the data hub of the system, responsible for hierarchical storage and efficient management of full-life-cycle data, and the time series database and the data warehouse work cooperatively with other modules of the system through physical and logical dual connection modes.

[0053] The time series database directly receives real-time data streams from the flow processing unit through physical network connection, including instantaneous heat load, temperature, flow and the like, adopts a columnar storage structure and an efficient compression algorithm, supports millisecond-level data writing and query, and automatically labels the data with device ID, parameter type and the like to support multi-dimensional fast query.

[0054] The data warehouse extracts, transforms and loads historical data from the time series database periodically, and integrates the thermal load evaluation coefficient generated by the batch processing unit and the final analysis report of the analysis result generation module. The data warehouse provides standardized historical data sets to the batch processing unit through a timing trigger to drive its periodic computing tasks.

[0055] The data manager of the central processing module realizes dynamic data management through logical connection: formulates a cold and hot data separation strategy, retains real-time data in the time series database, and automatically archives historical data to the data warehouse; allocates CPU and memory resources for distributed computing tasks of the data warehouse; monitors the health status of the storage node, and automatically triggers the elastic expansion process when the storage pressure exceeds the threshold.

[0056] The data storage module provides raw materials for the data analysis module by receiving preprocessed data from the data processing module, and finally feeds back the evaluation results to the data analysis result generation module, forming a complete data closed loop to ensure data consistency and processing efficiency in each link.

[0057] In a preferred embodiment of the present application, the data analysis module is used to analyze the processed data, the operation energy efficiency coefficient and the operation stability coefficient, and perform thermal load anomaly diagnosis.

[0058] The data analysis module serves as the intelligent analysis center of the system, and realizes the function of thermal load anomaly diagnosis by deeply mining the processed data and the thermal load evaluation coefficient. The data analysis module subscribes to real-time data streams from the time series database through an API interface, and calls the historical thermal load evaluation coefficient sequence in the data warehouse; a multi-dimensional anomaly detection model is established based on pattern recognition technology and statistical process control method to continuously monitor the numerical fluctuations of the operation energy efficiency coefficient, the operation stability coefficient and the thermal load evaluation coefficient.

[0059] When the numerical values of the operation energy efficiency coefficient, the operation stability coefficient and the thermal load evaluation coefficient fluctuate, the operation energy efficiency coefficient, the operation stability coefficient and the thermal load evaluation coefficient are compared with their respective abnormal threshold values, and the abnormal state of the system is identified based on the comparison results, and the abnormal diagnosis result is output.

[0060] It should be noted that the diagnosis result includes the following three cases: When the numerical value of the operation energy efficiency coefficient of the system exceeds the abnormal threshold value, it is preliminarily determined that the system operation energy efficiency is abnormal; When the numerical value of the operation stability coefficient of the system exceeds the abnormal threshold value, it is preliminarily determined that the system operation stability is abnormal; When the numerical values of the operation energy efficiency coefficient and the operation stability coefficient of the system exceed the abnormal threshold values, it is preliminarily determined that the system operation energy efficiency and operation stability are abnormal.

[0061] The operation energy efficiency coefficient abnormal threshold is set to 0.65, which is based on engineering practice, economic criticality and equipment health considerations; the operation stability coefficient abnormal threshold is set to 0.7, which is based on corresponding volatility, control failure and equipment life considerations.

[0062] The entire data analysis process interacts closely with the central processing module: the task scheduler dynamically allocates computing resources; the data manager optimizes data flow.

[0063] In a preferred embodiment of the present application, the analysis result generation module is used to generate a quantitative heat load assessment report based on the heat load assessment coefficient and the abnormal diagnosis result.

[0064] The analysis result generation module serves as the decision support output of the system, responsible for converting the analysis results into operational reports.

[0065] The analysis result generation module obtains the heat load assessment coefficient and the abnormal diagnosis result from the data warehouse through the data interface; based on the value of the heat load assessment coefficient, a system state mapping model is established to divide the heat load assessment coefficient into four assessment levels, generate a quantitative heat load assessment report containing the system energy efficiency level and the operation stability, and generate a system health state label based on time series analysis; after the report and the label are generated, they are pushed to the central processing module for visualization through the interface, and are archived and stored in the data warehouse.

[0066] It needs to be supplemented in this embodiment that the four assessment levels and their corresponding system operation states are: K≥0.85: excellent, the system is in a high-efficiency and stable operation state; 0.70≤K<0.85: good, the system is running normally, but there is room for optimization; 0.60≤K<0.70: qualified, the system energy efficiency is low or there is certain fluctuation, which needs to be concerned about its development trend; K<0.60: poor, the system performance is seriously deteriorated, the energy efficiency is low or the operation is extremely unstable, and immediate intervention diagnosis is needed.

[0067] The entire module interacts with the central processing module: the task scheduler allocates computing resources for report generation; the data manager optimizes query performance and monitors data flow. The resource abstraction layer provides virtualized resource support, dynamically adjusting memory and storage allocation according to load conditions.

[0068] The analysis result generation module generates visual reports by receiving data analysis data and applying evaluation algorithms, and realizes resource elastic allocation under central scheduling, forming a complete analysis-evaluation-decision support closed loop.

[0069] Secondly: the embodiment of the present application discloses only the structure related to the embodiment of the present application, other structures can refer to the general design, and in the case of no conflict, the same embodiment and different embodiments of the present application can be combined with each other; Finally: the above only describes the preferred embodiments of the present application and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A cloud computing-based thermal load analysis system, characterized by, The application relates to a heat load evaluation system, which comprises the following modules: a central processing module for unified scheduling of cloud computing resources, cooperative processing of multiple tasks and data flow management; a data acquisition module for acquiring parameters related to heat load, standardizing and conditioning analog signals and performing analog-digital conversion, and finally transmitting digital data to a data processing module while accepting and executing data acquisition strategy adjustment instructions issued by the data processing module; a data processing module for pre-processing data, calculating instantaneous heat load based on pre-processed data and periodically calculating a historical heat load evaluation coefficient, generating data acquisition strategy adjustment instructions based on data quality analysis results and abnormal diagnosis results and issuing the instructions to the data acquisition module; a data storage module for storing real-time data, historical data and evaluation reports and supporting multi-dimensional query and calling of historical data; a data analysis module for analyzing processed data, running energy efficiency coefficient and running stability coefficient and performing heat load abnormal diagnosis; an analysis result generation module for generating a quantitative heat load evaluation report based on the heat load evaluation coefficient and the abnormal diagnosis results. 2.The cloud computing-based thermal load analysis system of claim 1, wherein: The central processing module comprises: a resource abstraction layer for pooling physical computing, storage and network resources into virtualized resource units; a task scheduler for allocating computing resources to each module and managing task execution priority; a data manager for controlling data flow and storage strategy in the system. 3.The cloud computing-based thermal load analysis system of claim 1, wherein: The data acquisition module comprises: a sensor for acquiring parameters related to heat load; a signal conditioning unit for amplifying, filtering and standardizing sensor signals; a data conversion unit for converting analog signals into digital signals; a communication unit for transmitting acquired data to the data processing module and receiving and executing acquisition strategy adjustment instructions issued by the data processing module.

4. The cloud computing based thermal load analysis system as claimed in claim 1, wherein: The data processing module comprises: a pre-processing unit for data cleaning and filtering; a stream processing unit for calculating instantaneous heat load based on a stream processing framework; a batch processing unit for periodically calculating a historical heat load evaluation coefficient based on a batch processing framework; a strategy generation unit for generating data acquisition strategy adjustment instructions based on data quality analysis results and abnormal diagnosis results and issuing the instructions to the data acquisition module.

5. The cloud computing based thermal load analysis system as claimed in claim 1, wherein: The data storage module comprises: a time series database for storing real-time monitoring data and instantaneous heat load calculation results; a data warehouse for storing historical data, historical running energy efficiency coefficient, running stability coefficient, heat load evaluation coefficient and evaluation reports and supporting multi-dimensional query and calling of historical data.

6. The cloud computing based thermal load analysis system according to claim 1, wherein: The data analysis module is used for comparing the running energy efficiency coefficient and the running stability coefficient with their respective abnormal threshold values, identifying the abnormal state of the system based on the comparison results and outputting abnormal diagnosis results.

7. The cloud computing-based thermal load analysis system of claim 1, wherein: The analysis result generation module is used for generating a quantitative heat load evaluation report based on the heat load evaluation coefficient and the abnormal diagnosis results. 8.The cloud computing-based thermal load analysis system of claim 1, wherein: The parameters related to heat load include temperature, flow and power. 9.The cloud computing-based thermal load analysis system of claim 5, wherein: The heat load evaluation coefficient is obtained by weighting the running energy efficiency coefficient and the running stability coefficient.

Images