Heating and ventilation energy consumption analysis method, system and device based on data center and medium

Abstract

The invention provides a heating and ventilation energy consumption analysis method, system and device based on a data center and a medium, and relates to the technical field of energy consumption analysis, and the method comprises the steps: monitoring the energy consumption data of heating and ventilation equipment in real time, carrying out the statistical analysis of the energy consumption data according to the time, the equipment type and the regional dimension, and generating an energy consumption report, comparing the energy consumption data in the energy consumption report with a preset energy consumption index, and judging whether the energy consumption data is normal or not; environmental parameters in the machine room are monitored in real time, and when the environmental parameters exceed a preset normal range, the operation state of the heating and ventilation equipment is automatically adjusted; and training an energy consumption prediction model based on historical data related to the energy consumption of the heating and ventilation equipment in the machine room and a machine learning algorithm, and predicting the energy consumption of the future heating and ventilation equipment by using the trained energy consumption prediction model. The method, the system, the device and the medium can solve the problems that a traditional data center heating and ventilation system is high in energy consumption, poor in dynamic load adaptability and low in efficiency due to manual dependence.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption analysis, and particularly to a method, system, device and medium for analyzing the heating, ventilation and air conditioning (HVAC) energy consumption based on a data center. Background Art

[0002] In recent years, with the rapid development of cloud computing, big data and Internet of Things technologies, the scale of data centers has been continuously expanding, and the operation cost of computer rooms has also increased accordingly. The energy consumption problem of data centers has become increasingly prominent, and the energy consumption of HVAC equipment (such as air conditioners, cooling pumps, cooling towers, etc.) accounts for a quite large proportion. In order to ensure the normal operation of network and security equipment in the computer room, these equipment often operate at high power to meet the low-temperature environment requirements of the computer room. However, in fact, the network and security equipment can operate normally with less cooling capacity, and the air-conditioning refrigeration equipment can meet the cooling demand in a lower power mode, resulting in waste of energy due to the excess generated cooling capacity.

[0003] Traditional data center cooling methods mainly rely on air-cooled or water-cooled systems. The air-cooled system sends cold air into the computer room through a fan to take away the heat generated by the equipment. The water-cooled system uses water as a cooling medium and transports cold water to the heat exchanger in the computer room through a circulation pump. After absorbing the heat generated by the equipment, it returns to the cooling tower for heat dissipation. However, these traditional cooling methods have many limitations: First, traditional cooling methods often require high-power equipment to provide sufficient cooling capacity, resulting in high energy consumption; Second, it is difficult for traditional cooling methods to dynamically adjust the cooling capacity according to the actual load changes, which is likely to cause energy waste. Finally, although the operation and maintenance personnel can calculate the optimal operation mode through the performance test of the air-conditioning system, the processing process has no unified processing standard, and the amount of data involved is large. Manual processing is prone to data calculation errors, time-consuming and inefficient. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a method, system, device and medium for analyzing the HVAC energy consumption based on a data center in view of the above deficiencies of the prior art, so as to solve the problems of high energy consumption, poor adaptability to dynamic load and low efficiency caused by manual dependence in the traditional data center HVAC system.

[0005] In the first aspect, the present invention provides a method for analyzing the HVAC energy consumption based on a data center, the method comprising:

[0006] Real-time monitoring the energy consumption data of HVAC equipment, statistically analyzing the energy consumption data according to time, equipment type and regional dimensions, generating an energy consumption report, and comparing the energy consumption data in the energy consumption report with a preset energy consumption index to determine whether the energy consumption data is normal;

[0007] Real-time monitor the environmental parameters in the computer room. When the environmental parameters exceed the preset normal range, automatically adjust the operating state of the HVAC equipment;

[0008] Based on the historical data related to the energy consumption of the HVAC equipment in the computer room and the machine learning algorithm, train an energy consumption prediction model, and use the trained energy consumption prediction model to predict the future energy consumption of the HVAC equipment;

[0009] Compare the actual energy consumption of each of the multiple HVAC equipment with the predicted theoretical energy consumption, calculate the energy consumption deviation, rank the multiple HVAC equipment according to the total energy consumption within a preset time period, and generate corresponding energy-saving strategies based on the ranking and energy consumption deviation.

[0010] Furthermore, the energy consumption data includes power consumption data and water resource consumption data. Real-time monitor the energy consumption data of the HVAC equipment, statistically analyze the energy consumption data according to time, equipment type, and regional dimensions, generate an energy consumption report, and compare the energy consumption data in the energy consumption report with the preset energy consumption indicators to determine whether the energy consumption data is normal. Specifically, it includes:

[0011] Real-time collect the power consumption data and water resource consumption data of the HVAC equipment through pre-installed smart meters and flow sensors;

[0012] Statistically analyze the collected power consumption data and water resource consumption data according to time, equipment type, and regional dimensions to generate the energy consumption report;

[0013] Take the equipment of different equipment types in different regions in the energy consumption report as target equipment respectively, compare the power consumption data of the target equipment with the lower limit and upper limit of the power consumption index corresponding to the target equipment respectively. If the power consumption data of the target equipment is less than the lower limit of the power consumption index or the power consumption data of the target equipment is greater than the upper limit of the power consumption index, it is determined that the power consumption data of the target equipment is abnormal. Otherwise, it is determined that the power consumption data of the target equipment is normal;

[0014] Take different regions in the energy consumption report as target regions respectively, summarize the water resource consumption data of the target regions, and compare the summarized water resource consumption data of the target regions with the lower limit and upper limit of the water resource consumption index corresponding to the target regions respectively. If the summarized water resource consumption data of the target region is less than the lower limit of the water resource consumption index or the summarized water resource consumption data of the target region is greater than the upper limit of the water resource consumption index, it is determined that the water resource consumption data of the target region is abnormal. Otherwise, it is determined that the water resource consumption data of the target region is normal.

[0015] Further, the method further includes:

[0016] Calculating the average value and standard deviation of the historical power consumption data according to the historical power consumption data of the target device under different working conditions;

[0017] Taking the average value of the historical power consumption data as an intermediate reference value, and determining the lower limit value and upper limit value of the power consumption index corresponding to the target device based on the standard deviation of the historical power consumption data;

[0018] Calculating the average value and standard deviation of the historical water resource consumption data according to the historical water resource consumption data of the target area under different working conditions;

[0019] Taking the average value of the historical water resource consumption data as an intermediate reference value, and determining the lower limit value and upper limit value of the water resource consumption index corresponding to the target area based on the standard deviation of the historical water resource consumption data.

[0020] Further, the environmental parameters include temperature and humidity. When the environmental parameters in the machine room are monitored in real time and exceed the preset normal range, the operating state of the HVAC equipment is automatically adjusted, specifically including:

[0021] Real-time collecting the temperature and humidity in the machine room;

[0022] When the temperature exceeds the maximum value of the preset normal temperature range, sending a first control instruction to the air conditioner unit so that the air conditioner unit adjusts the compressor frequency, fan speed, and refrigerant flow rate of the air conditioner unit according to the first control instruction;

[0023] When the humidity exceeds the maximum value of the preset normal humidity range, sending a second control instruction to the dehumidifier so that the dehumidifier adjusts the compressor frequency, fan speed, and condensing pipe temperature of the dehumidifier according to the second control instruction.

[0024] Further, the adjustment formula for the compressor frequency is:

[0025]

[0026] where f1 represents the required compressor frequency, f0 represents the air conditioner standard frequency, Q0 represents the reference refrigerating capacity, and Q1 represents the target refrigerating capacity determined according to the machine room temperature;

[0027] The adjustment formula for the fan speed is:

[0028]

[0029] where n1 represents the adjusted fan speed and n0 represents the initial fan speed;

[0030] The adjustment formula for the refrigerant flow rate is as follows:

[0031]

[0032] Wherein, m1 represents the required refrigerant flow rate, and m0 represents the initial refrigerant flow rate.

[0033] Furthermore, the energy consumption deviation includes an absolute energy consumption deviation and a relative energy consumption deviation. Compare the actual energy consumption and the predicted theoretical energy consumption of each of the multiple HVAC devices, calculate the energy consumption deviation, rank the multiple HVAC devices according to the total energy consumption within a preset time period, and generate corresponding energy-saving strategies based on the ranking and the energy consumption deviation. Specifically, it includes:

[0034] Compare the actual energy consumption and the predicted theoretical energy consumption of each of the multiple HVAC devices, and calculate the absolute energy consumption deviation and the relative energy consumption deviation;

[0035] Calculate the total energy consumption of each of the multiple HVAC devices within a preset time period;

[0036] Rank the multiple HVAC devices in descending order according to the total energy consumption;

[0037] Determine the equipment to be energy-saving based on the absolute energy consumption deviation, relative energy consumption deviation, and the ranking of each HVAC device;

[0038] According to the relationship between temperature and energy consumption, find the temperature setting value when the energy consumption of the equipment to be energy-saving is the smallest, and generate a corresponding energy-saving strategy based on the temperature setting value.

[0039] Furthermore, the step of finding the temperature setting value when the energy consumption of the equipment to be energy-saving is the smallest according to the relationship between temperature and energy consumption specifically includes:

[0040] Establish a relationship model between temperature and energy consumption;

[0041] Determine the current temperature setting value and the corresponding actual energy consumption of the equipment to be energy-saving;

[0042] Obtain the preset temperature adjustment range and temperature adjustment step size of the equipment to be energy-saving;

[0043] Starting from the current temperature setting value, gradually adjust the temperature setting value according to the temperature adjustment step size until reaching the maximum value of the temperature adjustment range;

[0044] Substitute each new temperature setting value into the relationship model and calculate the corresponding predicted energy consumption;

[0045] Compare the predicted energy consumption at each new temperature setting value, find the new temperature setting value with the minimum predicted energy consumption, and use it as the temperature setting value when the energy consumption of the energy-saving device is minimized.

[0046] In a second aspect, the present invention provides a heating, ventilation, and air conditioning (HVAC) energy consumption analysis system based on a data center, including:

[0047] An energy consumption monitoring module, configured to monitor the energy consumption data of HVAC equipment in real time, statistically analyze the energy consumption data according to time, equipment type, and regional dimensions, generate an energy consumption report, and compare the energy consumption data in the energy consumption report with a preset energy consumption index to determine whether the energy consumption data is normal;

[0048] An environmental parameter monitoring module, connected to the energy consumption monitoring module, configured to monitor the environmental parameters in the computer room in real time, and automatically adjust the operating state of the HVAC equipment when the environmental parameters exceed the preset normal range;

[0049] An energy consumption prediction module, connected to the environmental parameter monitoring module, configured to train an energy consumption prediction model based on historical data related to the energy consumption of HVAC equipment in the computer room and a machine learning algorithm, and use the trained energy consumption prediction model to predict the future energy consumption of the HVAC equipment;

[0050] An energy-saving strategy module, connected to the energy consumption prediction module, configured to compare the actual energy consumption and the predicted theoretical energy consumption of each of multiple HVAC equipment, calculate the energy consumption deviation, rank the multiple HVAC equipment according to the total energy consumption of the multiple HVAC equipment within a preset time period, and generate corresponding energy-saving strategies according to the ranking and the energy consumption deviation.

[0051] In a third aspect, the present invention provides a heating, ventilation, and air conditioning (HVAC) energy consumption analysis device based on a data center, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to implement the heating, ventilation, and air conditioning (HVAC) energy consumption analysis method according to the first aspect described above.

[0052] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the heating, ventilation, and air conditioning (HVAC) energy consumption analysis method according to the first aspect described above.

[0053] The present invention provides a method, system, device and medium for analyzing the heating, ventilation and air conditioning (HVAC) energy consumption based on a data center. First, the energy consumption data of HVAC equipment is monitored in real time, and the energy consumption data is statistically analyzed according to time, equipment type and regional dimension to generate an energy consumption report. Then, the energy consumption data in the energy consumption report is compared with a preset energy consumption index to determine whether the energy consumption data is normal. Next, the environmental parameters in the computer room are monitored in real time. When the environmental parameters exceed the preset normal range, the operating state of the HVAC equipment is automatically adjusted. Furthermore, an energy consumption prediction model is trained based on the historical data related to the HVAC equipment energy consumption in the computer room and machine learning algorithms, and the trained energy consumption prediction model is used to predict the future energy consumption of the HVAC equipment. Finally, the actual energy consumption of each of the multiple HVAC equipment is compared with the predicted theoretical energy consumption, the energy consumption deviation is calculated, and the multiple HVAC equipment are ranked according to the total energy consumption within a preset time period. In addition, corresponding energy-saving strategies are generated based on the ranking and energy consumption deviation. By monitoring the energy consumption data of HVAC equipment in real time, statistically analyzing it according to time, equipment type and regional dimension, and comparing it with the preset energy consumption index at the same time, the present invention can timely detect abnormal energy consumption and provide a strong basis for energy-saving decision-making. At the same time, by monitoring the environmental parameters of the computer room in real time and automatically adjusting the equipment operating state when the parameters exceed the normal range, the present invention significantly enhances the system's adaptability to dynamic load changes, effectively reduces the dependence on manual intervention, and improves the overall management efficiency. In addition, by using historical data and machine learning algorithms to train the energy consumption prediction model, the present invention can accurately predict future energy consumption. On this basis, by comparing the actual energy consumption with the theoretical energy consumption, calculating the energy consumption deviation and ranking the equipment, and then generating targeted energy-saving strategies, the energy consumption can be further accurately reduced and the operation and maintenance efficiency can be improved. This solves the problems of high energy consumption, poor adaptability to dynamic load and low efficiency caused by manual dependence in the traditional data center HVAC system. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flowchart of a method for analyzing the HVAC energy consumption based on a data center according to Embodiment 1 of the present invention;

[0055] Figure 2 It is a schematic structural diagram of a system for analyzing the HVAC energy consumption based on a data center according to Embodiment 2 of the present invention;

[0056] Figure 3 It is a schematic structural diagram of a device for analyzing the HVAC energy consumption based on a data center according to Embodiment 3 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] To enable those skilled in the art to better understand the technical solutions of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0058] It is understood that the specific embodiments and accompanying drawings described herein are only for explaining the present invention and not for limiting the present invention.

[0059] It is understood that, without conflict, the various embodiments in the present invention and the various features in the embodiments may be combined with each other.

[0060] It is understood that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings of the present invention, and the parts unrelated to the present invention are not shown in the accompanying drawings.

[0061] It is understood that each unit and module involved in the embodiments of the present invention may correspond to only one entity structure, or may be composed of multiple entity structures, or multiple units and modules may also be integrated into one entity structure.

[0062] It is understood that the terms "first", "second", etc. in the embodiments of the present invention are used to distinguish different objects or to distinguish different processes for the same object, rather than to describe a specific order of the objects.

[0063] It is understood that, without conflict, the functions and steps marked in the flowcharts and block diagrams of the present invention may occur in a different order from that marked in the accompanying drawings.

[0064] It is understood that in the flowcharts and block diagrams of the present invention, the possible system architectures, functions, and operations of the systems, devices, equipment, and methods according to the various embodiments of the present invention are shown. Among them, each block in the flowchart or block diagram may represent a unit, module, program segment, or code, which contains executable instructions for implementing the specified function. Moreover, each block or combination of blocks in the block diagram and flowchart may be implemented by a hardware-based system for implementing the specified function, or may be implemented by a combination of hardware and computer instructions.

[0065] It is understood that the units and modules involved in the embodiments of the present invention may be implemented in software or in hardware. For example, the units and modules may be located in the processor.

[0066] Embodiment 1:

[0067] This embodiment provides a method for analyzing the heating, ventilation, and air conditioning (HVAC) energy consumption based on a data center. As Figure 1 shown, the method includes:

[0068] Step S101: Monitor the energy consumption data of HVAC equipment in real time, statistically analyze the energy consumption data according to time, equipment type, and regional dimensions, generate an energy consumption report, and compare the energy consumption data in the energy consumption report with a preset energy consumption index to determine whether the energy consumption data is normal.

[0069] In this embodiment, the HVAC equipment includes air conditioning units, dehumidifiers, cooling towers, cooling pumps, chiller hosts, chilled water pumps, fans, etc., which are used to adjust and control the indoor environment. The energy consumption report includes information such as the statistical time period, equipment type, area, energy consumption value, and average energy consumption. By comparing the energy consumption data in the energy consumption report with the preset energy consumption indicators, it is possible to accurately determine whether the energy consumption is abnormal.

[0070] Optionally, the energy consumption data includes power consumption data and water resource consumption data. The energy consumption data of the HVAC equipment is monitored in real time, statistically analyzed according to the time, equipment type, and area dimensions to generate an energy consumption report, and the energy consumption data in the energy consumption report is compared with the preset energy consumption indicators to determine whether the energy consumption data is normal. Specifically, it includes:

[0071] The power consumption data and water resource consumption data of the HVAC equipment are collected in real time through pre-installed smart meters and flow sensors;

[0072] The collected power consumption data and water resource consumption data are statistically analyzed according to the time, equipment type, and area dimensions to generate the energy consumption report;

[0073] The equipment of different equipment types in different areas in the energy consumption report is respectively used as the target equipment, and the power consumption data of the target equipment is compared with the lower limit value and the upper limit value of the power consumption index corresponding to the target equipment. If the power consumption data of the target equipment is less than the lower limit value of the power consumption index or the power consumption data of the target equipment is greater than the upper limit value of the power consumption index, it is determined that the power consumption data of the target equipment is abnormal; otherwise, it is determined that the power consumption data of the target equipment is normal;

[0074] Each area in the energy consumption report is respectively used as the target area, the water resource consumption data of the target area is summarized, and the summarized water resource consumption data of the target area is compared with the lower limit value and the upper limit value of the water resource consumption index corresponding to the target area. If the summarized water resource consumption data of the target area is less than the lower limit value of the water resource consumption index or the summarized water resource consumption data of the target area is greater than the upper limit value of the water resource consumption index, it is determined that the water resource consumption data of the target area is abnormal; otherwise, it is determined that the water resource consumption data of the target area is normal.

[0075] In this embodiment, the smart meter is preferably a high-precision smart meter, which is installed on the power supply line of the HVAC equipment and used to measure the power consumption data of the HVAC equipment, while the flow sensor is installed on the water pipeline system, make-up water pipe, or inlet and outlet water pipes of the HVAC equipment and used to monitor the water resource consumption data in real time.

[0076] In this embodiment, after collecting the power and water resource consumption data of the HVAC equipment, the collected power and water resource consumption data are first converted into digital signals. Then, according to the equipment identifier, the equipment information table is associated to obtain the equipment type information. Based on this information, the energy consumption data of different types of equipment are grouped and statistically analyzed, and an energy consumption report is generated according to the results of the statistical analysis.

[0077] In this embodiment, the lower limit value of the power consumption index is determined based on the statistical characteristics of historical power consumption data. This lower limit value comprehensively considers the possible fluctuation range of power consumption during the normal operation of the target equipment, as well as actual situations such as equipment aging and future load expectations. It indicates that under normal circumstances, considering the fluctuations in historical data, the power consumption of the equipment is unlikely to be lower than this value. If it is lower than this lower limit, it may mean that the operating state of the target equipment is abnormal, such as partial function failure of the equipment or too small a load, or it may be that special energy-saving measures have been taken resulting in a significant reduction in power consumption. The upper limit value of the power consumption index considers the upper limit of the power consumption fluctuation of the target equipment under different working conditions, as well as factors such as equipment aging and future load increase. It indicates that under normal circumstances, the power consumption of the target equipment generally will not exceed this value. If the actual power consumption is higher than this upper limit, it may imply that the target equipment has an excessive load, a malfunction, or an error in data measurement, etc. Similarly, the water resource consumption index is also calculated based on the historical water resource consumption data of the target area. This lower limit value indicates that under normal circumstances, considering the fluctuations in historical water resource consumption and actual situations, the water resource consumption in this target area is unlikely to be lower than this value. If it is lower than the lower limit, it may indicate abnormal statistical data, extremely effective water-saving measures implemented in the target area, or water leakage not included in the statistics, etc. The upper limit value of the water resource consumption index considers the upper limit of the historical water resource consumption fluctuation of the target area and actual situations. It represents that under normal circumstances, the water resource consumption in this target area generally should not exceed this value. When the actual water resource consumption is higher than this upper limit, it may mean that the water demand in the target area has suddenly increased, the water-using equipment has malfunctioned, or there is a deviation in the statistical data.

[0078] Optionally, the method further includes:

[0079] Calculating the average value and standard deviation of the historical power consumption data according to the historical power consumption data of the target equipment under different working conditions;

[0080] Taking the average value of the historical power consumption data as the intermediate reference value, and determining the lower limit value and upper limit value of the power consumption index corresponding to the target equipment based on the standard deviation of the historical power consumption data;

[0081] Calculating the average value and standard deviation of the historical water resource consumption data according to the historical water resource consumption data of the target area under different working conditions;

[0082] Taking the average value of the historical water resource consumption data as an intermediate reference value, determine the lower limit value and the upper limit value of the water resource consumption index corresponding to the target area based on the standard deviation of the historical water resource consumption data.

[0083] Specifically, the lower limit value of the power consumption index corresponding to the target device is calculated according to the following formula:

[0084]

[0085] where P min represents the lower limit value of the power consumption index, represents the average value of the historical water resource consumption data, k1 represents the adjustment coefficient, and σ P represents the standard deviation of the historical water resource consumption data;

[0086] Specifically, the upper limit value of the power consumption index corresponding to the target device is calculated according to the following formula:

[0087]

[0088] where P max represents the upper limit value of the power consumption index, and k2 represents the adjustment coefficient;

[0089] Specifically, the lower limit value of the water resource consumption index corresponding to the target area is calculated according to the following formula:

[0090]

[0091] where W min represents the lower limit value of the water resource consumption index, represents the average value of the historical water resource consumption data, k3 represents the adjustment coefficient, and σ W represents the standard deviation of the historical water resource consumption data.

[0092] Specifically, the upper limit value of the water resource consumption index corresponding to the target area is calculated according to the following formula:

[0093]

[0094] where W max represents the upper limit value of the water resource consumption index, and k4 represents the adjustment coefficient.

[0095] Step S102: Real-time monitor the environmental parameters in the computer room, and automatically adjust the operating state of the HVAC equipment when the environmental parameters exceed the preset normal range.

[0096] In this embodiment, the environmental parameters in the computer room are monitored in real time to ensure that the computer room environment meets the equipment operation requirements. When the environmental parameters exceed the normal range, the operation status of the HVAC equipment is automatically adjusted to quickly restore the computer room environment to the normal level.

[0097] Optionally, the environmental parameters include temperature and humidity. The real-time monitoring of the environmental parameters in the computer room and the automatic adjustment of the operation status of the HVAC equipment when the environmental parameters exceed the preset normal range specifically include:

[0098] Collect the temperature and humidity in the computer room in real time;

[0099] When the temperature exceeds the maximum value of the preset normal temperature range, send a first control command to the air conditioner unit so that the air conditioner unit adjusts the compressor frequency, fan speed, and refrigerant flow rate of the air conditioner unit according to the first control command;

[0100] When the humidity exceeds the maximum value of the preset normal humidity range, send a second control command to the dehumidifier so that the dehumidifier adjusts the compressor frequency, fan speed, and condensing pipe temperature of the dehumidifier according to the second control command.

[0101] In this embodiment, environmental parameter sensors are arranged in the computer room, including temperature sensors and humidity sensors, for collecting the temperature and humidity in the computer room in real time. When the temperature sensor detects that the temperature in the computer room is higher than the maximum value of the normal temperature range, the system will automatically send a first control command to the air conditioner unit, requiring to increase the cooling capacity and lower the temperature in the computer room. After receiving the command, the air conditioner unit adjusts the compressor frequency, fan speed, and refrigerant flow rate. When the humidity sensor detects that the humidity in the computer room is higher than the maximum value of the normal humidity range, the system will automatically send a second control command to the dehumidifier, requiring to start and increase the dehumidification amount to lower the humidity in the computer room. After receiving the command, the dehumidifier adjusts the compressor frequency, fan speed, and condensing pipe temperature. This automatic adjustment function can effectively ensure the stability of the computer room environment, provide good environmental conditions for the normal operation of the HVAC equipment, reduce the occurrence of equipment failures and performance degradation caused by environmental factors, and improve the reliability and service life of the equipment.

[0102] Optionally, the adjustment formula for the compressor frequency is:

[0103]

[0104] where f1 represents the required compressor frequency, f0 represents the air conditioner standard frequency, Q0 represents the reference cooling capacity, and Q1 represents the target cooling capacity determined according to the computer room temperature;

[0105] The adjustment formula for the fan speed is:

[0106]

[0107] Among them, n1 represents the adjusted fan speed, and n0 represents the initial fan speed;

[0108] The adjustment formula for the refrigerant flow rate is:

[0109]

[0110] Among them, m1 represents the required refrigerant flow rate, and m0 represents the initial refrigerant flow rate.

[0111] In this embodiment, by adjusting the compressor frequency, the fan speed, and the refrigerant flow rate, the purpose of increasing the cooling capacity can be achieved.

[0112] In this embodiment, before sending the second control instruction to the dehumidifier, the target dehumidification amount D1 can be determined according to the excess situation of the humidity; then the required compressor frequency f d1 and the adjusted fan speed n d1 can be calculated; then according to the non-linear relationship between the dehumidification amount D and the condensing pipe temperature T c , the target condensing pipe temperature T c1 can be calculated; when the dehumidifier receives the second control instruction, it automatically adjusts the compressor frequency to f d1 , adjusts the fan speed to n d1 , and adjusts the condensing pipe temperature to T v1 .

[0113] Step S103: Train an energy consumption prediction model based on historical data related to the energy consumption of HVAC equipment in the computer room and a machine learning algorithm, and use the trained energy consumption prediction model to predict the future energy consumption of HVAC equipment.

[0114] In this embodiment, by collecting a large amount of historical energy consumption data and various influencing factor data related thereto, and using the powerful data mining and analysis capabilities of the machine learning algorithm, these data are deeply learned and analyzed, so as to establish an energy consumption prediction model that can accurately reflect the energy consumption change law. By using the trained energy consumption prediction model to predict the future HVAC energy consumption, it can help the operation and maintenance personnel understand the energy demand situation in advance. The operation and maintenance personnel can discover potential energy consumption problems and energy-saving opportunities in advance, formulate targeted energy-saving measures and equipment maintenance plans, optimize energy use, improve energy utilization efficiency, and achieve the goal of energy conservation and emission reduction. In addition, the energy consumption prediction results can also provide an important reference basis for the planning and decision-making of the data center, help the management personnel reasonably plan the construction and expansion of the data center, optimize the equipment configuration and layout, and improve the overall operation efficiency and economic benefits of the data center.

[0115] Step S104: Compare the actual energy consumption of each of the multiple HVAC devices with the predicted theoretical energy consumption, calculate the energy consumption deviation, rank the multiple HVAC devices according to their total energy consumption within a preset time period, and generate corresponding energy-saving strategies based on the ranking and energy consumption deviation.

[0116] In this embodiment, by comparing the actual energy consumption with the theoretical energy consumption, calculating the energy consumption deviation and ranking the devices, and then generating targeted energy-saving strategies, it is possible to further achieve precise reduction of energy consumption and significant improvement of operation and maintenance efficiency.

[0117] Optionally, the energy consumption deviation includes an absolute energy consumption deviation and a relative energy consumption deviation. The step of comparing the actual energy consumption of each of the multiple HVAC devices with the predicted theoretical energy consumption, calculating the energy consumption deviation, ranking the multiple HVAC devices according to their total energy consumption within a preset time period, and generating corresponding energy-saving strategies based on the ranking and energy consumption deviation specifically includes:

[0118] Compare the actual energy consumption of each of the multiple HVAC devices with the predicted theoretical energy consumption, and calculate the absolute energy consumption deviation and the relative energy consumption deviation;

[0119] Calculate the total energy consumption of each of the multiple HVAC devices within a preset time period;

[0120] Rank the multiple HVAC devices in descending order according to the total energy consumption;

[0121] Determine the devices to be energy-saving based on the absolute energy consumption deviation, relative energy consumption deviation, and the ranking of each HVAC device;

[0122] According to the relationship between temperature and energy consumption, find the temperature setting value when the energy consumption of the device to be energy-saving is the smallest, and generate corresponding energy-saving strategies based on the temperature setting value.

[0123] Specifically, the calculation formula for the absolute energy consumption deviation is as follows:

[0124]

[0125] where deviation represents the absolute energy consumption deviation, y actual represents the actual energy consumption, represents the theoretical energy consumption.

[0126] Specifically, the calculation formula for the relative energy consumption deviation is as follows:

[0127]

[0128] where Relative represents the relative energy consumption deviation.

[0129] Specifically, the total energy consumption of each of the HVAC devices within a preset time period can be calculated in the form of time integration:

[0130]

[0131] Among them, E i represents the total energy consumption of the HVAC device within the preset time period [t1, t2], P i (t) represents the power of the i-th HVAC device at time t, and dt is the differential symbol.

[0132] In this embodiment, by analyzing the absolute energy consumption deviation, relative energy consumption deviation, and ranking of each HVAC device, the devices to be energy-saving can be determined. Specifically, the HVAC devices with high energy consumption and large energy consumption deviation can be given priority as the objects to be considered for energy-saving. For example, the HVAC devices with an absolute energy consumption deviation greater than a preset first threshold, a relative energy consumption deviation greater than a preset second threshold, and a ranking within a preset third threshold range (such as the top 20% or a specific value) can be used as the devices to be energy-saving, and targeted energy-saving measures can be formulated preferentially.

[0133] In addition, for HVAC devices with a large energy consumption deviation but relatively low total energy consumption, they may not be high-energy-consuming devices, but their energy consumption deviation is still significant. In this case, it is possible to focus on checking whether the operating state of the HVAC device is abnormal and take corresponding measures to bring its energy consumption back to the normal level. This not only helps to improve the operating efficiency of the device but also avoids unnecessary energy waste.

[0134] Finally, according to the characteristics and energy consumption status of different HVAC devices, we can comprehensively generate an overall energy-saving strategy covering aspects such as equipment operation optimization and energy management to reduce the overall energy consumption level and achieve more efficient and sustainable energy utilization.

[0135] Optionally, finding the temperature setting value when the energy consumption of the device to be energy-saving is minimized according to the relationship between temperature and energy consumption specifically includes:

[0136] Establishing a relationship model between temperature and energy consumption;

[0137] Determining the current temperature setting value and the corresponding actual energy consumption of the device to be energy-saving;

[0138] Obtaining the preset temperature adjustment range and temperature adjustment step size of the device to be energy-saving;

[0139] Starting from the current temperature setting value, gradually adjusting the temperature setting value according to the temperature adjustment step size until the maximum value of the temperature adjustment range is reached;

[0140] Substitute each new temperature setting value into the relationship model and calculate the corresponding predicted energy consumption.

[0141] Compare the predicted energy consumption under each new temperature setting value, find the new temperature setting value with the minimum predicted energy consumption, and use it as the temperature setting value when the energy consumption of the device to be energy-saving is minimized.

[0142] In this embodiment, the formula of the relationship model between temperature and energy consumption is as follows:

[0143] E = aT + b

[0144] Where, T represents temperature, E represents energy consumption, a represents the influence degree of temperature T on energy consumption E, and b represents the constant term.

[0145] In this embodiment, by observing the change trend of the predicted energy consumption as the temperature is adjusted, the temperature setting value that can minimize the predicted energy consumption is found, and an energy-saving strategy is generated based on this, such as adjusting the temperature setting value, operating time, or other operating parameters of the device.

[0146] In a specific embodiment, the HVAC energy consumption analysis method based on a data center is applied to an HVAC energy consumption analysis system based on a data center. The system includes an energy consumption monitoring module, an environmental parameter monitoring module, an energy consumption prediction module, and an energy-saving strategy module. The descriptions of each part are as follows:

[0147] (1) Energy consumption monitoring module: used to monitor the energy consumption data of HVAC equipment in real time, statistically analyze the energy consumption data according to time, equipment type, and regional dimensions, generate an energy consumption report, and judge whether the energy consumption is normal by comparing it with the preset energy consumption index;

[0148] Specifically, the energy consumption monitoring module installs high-precision intelligent electric meters on the power supply lines of HVAC equipment, which are respectively used to measure the power consumption data of cooling towers, cooling pumps, cooling hosts, chilled water pumps, and fans. In the water pipeline system of the fans, flow sensors are installed at the positions of the cooling tower make-up water pipe, the inlet and outlet pipes of the cooling pump, the inlet and outlet pipes of the cooling host, and the inlet and outlet pipes of the chilled water pump, which are used to monitor the water resource consumption data in real time. The intelligent electric meters and flow sensors collect the power and water resource consumption data in real time and convert them into digital signals, and transmit the collected data to the data acquisition terminal. The data acquisition terminal caches the data and waits for further transmission;

[0149] At the data acquisition terminal, associate the device information table according to the device identifier, obtain the device type information, group and count the energy consumption data of different types of devices, generate an energy consumption report based on the statistically analyzed data. The report content includes the statistical time period, device type, region, energy consumption value, and average energy consumption information. Collect the historical energy consumption data of the data acquisition terminal, analyze the energy consumption of different device types and regions under different working conditions, and calculate the energy consumption index based on the historical data. The specific calculation steps of the energy consumption index are as follows:

[0150] S1. Power consumption index: Collect the historical power consumption data of a certain HVAC device under different working conditions, denoted as P1, P2,..., P n , calculate the average value of the historical power consumption data Then calculate the standard deviation of the data Take the average value as the intermediate reference value of the energy consumption index, and then determine the lower limit value P min and the upper limit value P max , the lower limit value the upper limit value where k1 and k2 represent adjustment coefficients used to adjust the deviation degree of the lower limit value and the upper limit value from the average value;

[0151] S2. Water resource consumption index: Collect the historical water resource consumption data of this region at different times and under different working conditions, denoted as W1, W2,..., W m , calculate the average value of the historical water resource consumption data Then calculate the standard deviation of the data Based on the average value, determine the lower limit value W min and the upper limit value W max , the lower limit value the upper limit value where k3 and k4 represent adjustment coefficients used to adjust the deviation degree of the lower limit value and the upper limit value from the average value;

[0152] S3. Real-time obtain the power consumption data P of a certain HVAC device current , calculate the difference ΔP between the current power consumption and the lower limit value min =P current -P min , and the difference ΔP from the upper limit value max =P max -P current , when ΔP min <0, it indicates that the current power consumption is lower than the lower limit value. When ΔP max <0, it indicates that the current power consumption is higher than the upper limit value;

[0153] S4. Real-time obtain the water resource consumption data W of a certain regioncurrent , calculate the difference ΔW between the current water resource consumption and the lower limit value min = W current - W min , and the difference ΔW from the upper limit value max = W max - W current , when ΔW min < 0, it indicates that the current water resource consumption is lower than the lower limit value. When ΔW max < 0, it indicates that the current water resource consumption is higher than the upper limit value.

[0154] It should be noted that the lower limit value of the power consumption index is determined based on the statistical characteristics of historical power consumption data, representing the average value of historical power consumption data, reflecting the average level of power consumption of the HVAC equipment under various operating conditions in the past. σ P represents the standard deviation, measuring the degree of data dispersion. This lower limit value comprehensively considers the possible fluctuation range of power consumption during the normal operation of the equipment, as well as actual situations such as equipment aging and future load expectations. It means that under normal circumstances, considering the fluctuations in historical data, it is unlikely that the power consumption of the equipment will be lower than this value. If it is lower than this lower limit, it may mean that the operating state of the HVAC equipment is abnormal, such as partial function failure of the equipment or too small a load, or it may be due to the adoption of special energy-saving measures resulting in a significant reduction in power consumption. The upper limit value of the power consumption index takes into account the upper limit of power consumption fluctuations under different operating conditions of the equipment, as well as factors such as equipment aging and future load increase. It means that under normal circumstances, the power consumption of the equipment generally will not exceed this value. If the actual power consumption is higher than this upper limit, it may imply that the equipment load is too large, there is a fault, or there is an error in data measurement, etc.

[0155] Similarly, the water resource consumption index is also calculated based on the historical water resource consumption data of the region. This lower limit value means that under normal circumstances, considering the fluctuations in historical water resource consumption and actual situations, it is unlikely that the water resource consumption in this region will be lower than this value. If it is lower than the lower limit, it may indicate abnormal statistical data, extremely effective water-saving measures implemented in the region, or there is a leak that has not been included in the statistics, etc. The upper limit value of the water resource consumption index takes into account the upper limit of fluctuations in historical water resource consumption in the region and actual situations. It represents that under normal circumstances, the water resource consumption in this region generally should not exceed this value. When the actual water resource consumption is higher than this upper limit, it may mean that the water demand in the region has suddenly increased, there is a fault in the water-using equipment, or there is a deviation in the statistical data.

[0156] (2) Environmental parameter monitoring module: used to monitor the environmental parameters in the computer room in real time, ensure that the computer room environment meets the equipment operation requirements, and automatically adjust the operation state of the HVAC equipment when the environmental parameters exceed the normal range;

[0157] Specifically, the environmental parameter monitoring module arranges environmental parameter sensors in the computer room and around each HVAC device, including temperature sensors and humidity sensors, for collecting equipment operation environmental parameters, including the computer room temperature and humidity. According to the preset normal range threshold, it conducts real-time analysis on the collected environmental parameter data. When the temperature sensor detects that the temperature in the computer room is higher than the upper limit (i.e., the maximum value) of the normal range (i.e., the normal temperature range), it sends a control instruction (i.e., the first control instruction) to the air conditioning unit to increase the cooling capacity to lower the computer room temperature. After receiving the control instruction, the air conditioning unit adjusts the compressor frequency, fan speed, and refrigerant flow rate. Suppose the cooling capacity of the air conditioner at the standard frequency f0 is Q0, and the target cooling capacity is determined to be Q1 according to the computer room temperature situation. Then the calculation formula for the required compressor frequency is as follows:

[0158]

[0159] Among them, f1 represents the required compressor frequency. Based on the required compressor frequency, the refrigeration capacity is increased. Given that the initial fan speed is n0 and the corresponding cooling capacity is Q0, in order to achieve the target cooling capacity Q1, the specific calculation formula for the adjusted fan speed is as follows:

[0160]

[0161] Among them, n1 represents the adjusted fan speed. Based on the adjusted fan speed, the air circulation is accelerated to enhance the refrigeration effect. Suppose the refrigeration capacity per unit mass of refrigerant is q, the initial refrigerant flow rate is m0, and the corresponding cooling capacity is Q0. Then the specific calculation formula for the required refrigerant flow rate is as follows:

[0162]

[0163] Among them, m1 represents the required refrigerant flow rate. Based on the adjustment of the compressor frequency, fan speed, and refrigerant flow rate, the purpose of increasing the cooling capacity is achieved;

[0164] When the humidity is adjusted, when the humidity sensor detects that the humidity in the computer room is higher than the upper limit of the normal range (i.e., the normal humidity range), it sends a control instruction (i.e., the second control instruction) to the dehumidifier. After receiving the instruction, the dehumidifier adjusts the operating parameters of the dehumidifier to lower the computer room humidity. If the dehumidification capacity of the dehumidifier at the standard frequency f d0 is D0, and the target dehumidification capacity is determined to be D1 according to the humidity exceeding the standard situation. Based on the required compressor frequency f d1 is calculated to improve the dehumidification capacity. Given that the initial fan speed is n d0 , based on the adjusted fan speed n d1, accelerate air circulation, improve the dehumidification efficiency, and fit the dehumidification capacity D and the temperature T of the condensing pipe c The specific calculation formula is as follows:

[0165]

[0166] Among them, a, b, and c represent fitting coefficients, reflects the non-linear influence of the temperature T of the condensing pipe c on the dehumidification capacity D. As the temperature of the condensing pipe changes, the condensation mechanism of water vapor on the surface of the condensing pipe will change, resulting in a non-linear response of the dehumidification capacity. bT c reflects the linear influence of the temperature T of the condensing pipe c on the dehumidification capacity D. Given that the dehumidification capacity at the current temperature T of the condensing pipe is D0 and the target dehumidification capacity is D2, then the target temperature T of the condensing pipe c0 The specific calculation formula is as follows: c1 The specific calculation formula is as follows:

[0167]

[0168] Among them, represents the non-linear influence of the temperature of the condensing pipe on the dehumidification capacity at the target temperature T of the condensing pipe c1 bT c1 represents the linear influence of the temperature of the condensing pipe on the dehumidification capacity at the target temperature T of the condensing pipe c1 After receiving the instruction, the dehumidifier automatically adjusts the compressor frequency, fan speed, and temperature parameter of the condensing pipe of the dehumidifier to achieve the purpose of increasing the dehumidification capacity.

[0169] (3) Energy consumption prediction module: used to predict future HVAC energy consumption based on historical data and machine learning algorithms using a trained model;

[0170] Specifically, the energy consumption prediction module collects historical data related to the energy consumption of HVAC equipment in the computer room, including but not limited to equipment operation time, indoor and outdoor temperature, humidity, equipment load rate, refrigerant flow rate, and pressure data. These data are used as input features of the model, and at the same time, the corresponding energy consumption values are collected as output labels. The data is processed for data anomalies and missing values, and the data is normalized. The processed data is divided into a training set, a validation set, and a test set to establish an energy consumption prediction model. The specific steps for establishing the energy consumption prediction model are as follows:

[0171] S1. Set the initial coefficients of the linear regression model, use the input feature data in the training set, and calculate the predicted energy consumption value according to the linear regression model. Suppose there are X m samples in the training set, and each sample has X n features. For the i-th sample, its vector feature is xi1 , x i2 ,..., x in Then, the specific calculation formula for predicting the energy consumption value is as follows:

[0172]

[0173] Wherein, represents the predicted energy consumption value of the i-th sample, x i1 , x i2 ,..., x in represents the n feature values of the i-th sample, β0, β1, β2, β n represents the coefficients of the model;

[0174] S2. Compare the predicted value with the corresponding actual energy consumption value in the training set, and measure the difference between the predicted value and the actual energy consumption value through a loss function. Use the mean square error as the loss function. The loss value reflects the fitting degree of the current model to the training data. A small loss value indicates that the predicted value of the model is relatively close to the actual energy consumption value. Then, the specific calculation formula for the loss value is as follows:

[0175]

[0176] Wherein, y i represents the actual energy consumption value of the i-th sample;

[0177] S3. Based on the loss function, use the backpropagation algorithm to calculate the gradient of the loss function with respect to the model coefficients. The specific calculation formula is as follows:

[0178]

[0179] Wherein, β j represents the gradient of the model coefficients. When j = 0, x i0 = 1. The gradient represents the change direction and rate of the loss function at the current parameter values. By calculating the gradient, it can be known in which direction to update the parameters to minimize the loss function;

[0180] S4. According to the calculated gradient, update the coefficients of the model according to the rules of the optimization algorithm. The specific calculation formula is as follows:

[0181]

[0182] Update the model parameter β by subtracting the product of the learning rate α and the gradient j . The learning rate α controls the step size of each parameter update;

[0183] S5. Continuously execute steps S1 - S4 until the training stop condition is met.

[0184] (4) Energy-saving strategy module: Compare the actual energy consumption with the theoretical energy consumption, calculate the energy consumption deviation, rank the devices according to the energy consumption level, and generate an energy-saving strategy based on the energy consumption analysis results.

[0185] Specifically, the energy-saving strategy module predicts the energy consumption by using a trained linear regression model to obtain the theoretical energy consumption value. Collect the actual energy consumption data y of the corresponding device under the same operating conditions from the actual energy consumption monitoring. actual , For each data point, calculate the absolute energy consumption deviation. The specific calculation formula is as follows:

[0186]

[0187] Among them, deviation represents the absolute energy consumption deviation. Calculate the relative energy consumption deviation based on the absolute energy consumption deviation. The specific calculation formula is as follows:

[0188]

[0189] Among them, Relative represents the relative energy consumption deviation. Obtain the total energy consumption data E of different devices within the time period [t1, t2]. i , Use a sorting algorithm to sort the total energy consumption data E of the devices i from high to low. The total energy consumption data E of the devices i is calculated by time integration. The specific calculation formula is as follows:

[0190]

[0191] Among them, P i (t) represents the power of the HVAC device i at time t. t1 represents the starting time point of energy consumption calculation, t2 represents the ending time point of energy consumption calculation, dt is the differential symbol, representing the small change in time t. According to the historical data and the energy consumption prediction model, based on the energy-saving strategy of temperature adjustment, analyze the relationship between temperature T and energy consumption E. Assume the linear relationship between temperature T and energy consumption E is E = aT + b. Among them, a represents the influence degree of temperature T on energy consumption E, that is, the change in energy consumption per unit change in temperature, and b represents the constant term, representing the basic energy consumption independent of temperature. Based on the linear relationship, the influence of temperature change on energy consumption can be analyzed, and energy can be saved by adjusting the temperature setting value. Record the current temperature setting value T current and the corresponding energy consumption E current , Determine the range and step size of temperature adjustment. According to the environmental conditions, set the temperature adjustment range as [T min , T max , and the step size is ΔT. Starting from the current temperature T current , gradually adjust the temperature setting value T according to the set step size.new , calculate the predicted energy consumption E at each new temperature new , and the specific calculation formula is as follows:

[0192] E new = a(T current +ΔT)+b

[0193] Among them, observe the change trend of the energy consumption E as the temperature is adjusted, plot the relationship diagram of the temperature T new and E new , find the temperature setting value T new that minimizes the energy consumption E new . During the adjustment process, record each T optimal and its corresponding E new . Compare the values of different E new , find the T new corresponding to the minimum value, and ensure that the adjusted temperature setting value T optimal meets the operating requirements of the equipment. optimal

[0194] It should be noted that the present invention can monitor the environmental parameters in the computer room in real time, such as temperature and humidity, and ensure that the computer room environment meets the operating requirements of the equipment. When the environmental parameters exceed the normal range, the system can automatically adjust the operating state of the HVAC equipment to quickly restore the computer room environment to the normal level. When the temperature sensor detects that the temperature in the computer room is higher than the upper limit of the normal range, the system will automatically send a command to the air conditioner unit control system to increase the cooling capacity and lower the temperature of the computer room. When the humidity sensor detects that the humidity in the computer room is higher than the upper limit of the normal range, the system will automatically send a command to the dehumidifier control system to start and increase the dehumidification amount to lower the humidity of the computer room. This automatic adjustment function can effectively ensure the stability of the computer room environment, provide good environmental conditions for the normal operation of the equipment, reduce the occurrence of equipment failures and performance degradation caused by environmental factors, and improve the reliability and service life of the equipment. At the same time, by using the trained energy consumption prediction model to predict the future HVAC energy consumption, it can help the operation and maintenance personnel understand the energy demand situation in advance, reasonably arrange the energy procurement plan, and reduce the energy procurement cost.

[0195] ​The method for analyzing the heating, ventilation and air conditioning (HVAC) energy consumption based on a data center provided by an embodiment of the present invention first monitors the energy consumption data of HVAC equipment in real time, statistically analyzes the energy consumption data according to time, equipment type and regional dimensions to generate an energy consumption report, and compares the energy consumption data in the energy consumption report with a preset energy consumption index to determine whether the energy consumption data is normal; then monitors the environmental parameters in the computer room in real time, and automatically adjusts the operating state of the HVAC equipment when the environmental parameters exceed the preset normal range; further trains an energy consumption prediction model based on historical data related to the HVAC equipment energy consumption in the computer room and a machine learning algorithm, and uses the trained energy consumption prediction model to predict the future energy consumption of the HVAC equipment; finally, compares the actual energy consumption of each of the multiple HVAC equipment with the predicted theoretical energy consumption, calculates the energy consumption deviation, ranks the multiple HVAC equipment according to the total energy consumption of the multiple HVAC equipment within a preset time period, and generates a corresponding energy-saving strategy according to the ranking and the energy consumption deviation. By monitoring the energy consumption data of HVAC equipment in real time, statistically analyzing it according to time, equipment type and regional dimensions, and comparing it with the preset energy consumption index, the present invention can timely detect abnormal energy consumption and provide a strong basis for energy-saving decision-making. At the same time, by monitoring the environmental parameters in the computer room in real time and automatically adjusting the equipment operating state when the parameters exceed the normal range, the present invention significantly enhances the system's adaptability to dynamic load changes, effectively reduces the dependence on manual intervention, and improves the overall management efficiency. In addition, by using historical data and machine learning algorithms to train an energy consumption prediction model, the present invention can accurately predict future energy consumption. On this basis, by comparing the actual energy consumption with the theoretical energy consumption, calculating the energy consumption deviation and ranking the equipment, and then generating a targeted energy-saving strategy, it can further accurately reduce energy consumption and improve the operation and maintenance efficiency. It solves the problems of high energy consumption, poor adaptability to dynamic loads and low efficiency caused by manual dependence in traditional data center HVAC systems.

[0196] Embodiment 2:

[0197] As Figure 2 shown, this embodiment provides a system for analyzing the HVAC energy consumption based on a data center, which is used to execute the method for analyzing the HVAC energy consumption based on a data center as described above, and includes:

[0198] An energy consumption monitoring module 11, which is used to monitor the energy consumption data of HVAC equipment in real time, statistically analyze the energy consumption data according to time, equipment type and regional dimensions to generate an energy consumption report, and compare the energy consumption data in the energy consumption report with a preset energy consumption index to determine whether the energy consumption data is normal;

[0199] An environmental parameter monitoring module 12, which is connected to the energy consumption monitoring module 11, and is used to monitor the environmental parameters in the computer room in real time, and automatically adjust the operating state of the HVAC equipment when the environmental parameters exceed the preset normal range;

[0200] An energy consumption prediction module 13, connected to the environmental parameter monitoring module 12, is configured to train an energy consumption prediction model based on historical data related to the energy consumption of HVAC equipment in the computer room and machine learning algorithms, and use the trained energy consumption prediction model to predict the future energy consumption of HVAC equipment;

[0201] An energy-saving strategy module 14, connected to the energy consumption prediction module 13, is configured to compare the actual energy consumption of each of multiple HVAC equipment with the predicted theoretical energy consumption, calculate the energy consumption deviation, rank the multiple HVAC equipment according to the total energy consumption of the multiple HVAC equipment within a preset time period, and generate corresponding energy-saving strategies according to the ranking and energy consumption deviation.

[0202] Optionally, the energy consumption data includes power consumption data and water resource consumption data, and the energy consumption monitoring module 11 includes:

[0203] A water and electricity consumption data acquisition unit, configured to collect the power consumption data and water resource consumption data of HVAC equipment in real time through pre-installed smart meters and flow sensors;

[0204] An energy consumption report generation unit, configured to perform statistical analysis on the collected power consumption data and water resource consumption data according to time, equipment type, and regional dimensions, and generate the energy consumption report;

[0205] A first comparison and judgment unit, configured to use the equipment of different equipment types in different regions in the energy consumption report as target equipment respectively, compare the power consumption data of the target equipment with the lower limit value and the upper limit value of the power consumption index corresponding to the target equipment respectively. If the power consumption data of the target equipment is less than the lower limit value of the power consumption index or the power consumption data of the target equipment is greater than the upper limit value of the power consumption index, it is determined that the power consumption data of the target equipment is abnormal, otherwise, it is determined that the power consumption data of the target equipment is normal;

[0206] A second comparison and judgment unit, configured to use different regions in the energy consumption report as target regions respectively, summarize the water resource consumption data of the target regions, and compare the summarized water resource consumption data of the target regions with the lower limit value and the upper limit value of the water resource consumption index corresponding to the target regions respectively. If the summarized water resource consumption data of the target region is less than the lower limit value of the water resource consumption index or the summarized water resource consumption data of the target region is greater than the upper limit value of the water resource consumption index, it is determined that the water resource consumption data of the target region is abnormal, otherwise, it is determined that the water resource consumption data of the target region is normal.

[0207] Optionally, the energy consumption monitoring module 11 further includes:

[0208] A first calculation unit, configured to calculate an average value and a standard deviation of the historical power consumption data according to the historical power consumption data of the target device under different working conditions;

[0209] A first determination unit, configured to use the average value of the historical power consumption data as an intermediate reference value, and determine a lower limit value and an upper limit value of the power consumption index corresponding to the target device based on the standard deviation of the historical power consumption data;

[0210] A second calculation unit, configured to calculate an average value and a standard deviation of the historical water resource consumption data according to the historical water resource consumption data of the target area under different working conditions;

[0211] A second determination unit, configured to use the average value of the historical water resource consumption data as an intermediate reference value, and determine a lower limit value and an upper limit value of the water resource consumption index corresponding to the target area based on the standard deviation of the historical water resource consumption data.

[0212] Optionally, the environmental parameters include temperature and humidity, and the environmental parameter monitoring module 12 includes:

[0213] A temperature and humidity acquisition unit, configured to acquire the temperature and humidity in the computer room in real time;

[0214] A first control unit, configured to send a first control instruction to the air conditioner unit when the temperature exceeds the maximum value of the preset normal temperature range, so that the air conditioner unit adjusts the compressor frequency, the fan speed, and the refrigerant flow rate of the air conditioner unit according to the first control instruction;

[0215] A second control unit, configured to send a second control instruction to the dehumidifier when the humidity exceeds the maximum value of the preset normal humidity range, so that the dehumidifier adjusts the compressor frequency, the fan speed, and the condensing tube temperature of the dehumidifier according to the second control instruction.

[0216] Optionally, the adjustment formula for the compressor frequency is:

[0217]

[0218] Wherein, f1 represents the required compressor frequency, f0 represents the air conditioner standard frequency, Q0 represents the reference refrigerating capacity, and Q1 represents the target refrigerating capacity determined according to the computer room temperature;

[0219] The adjustment formula for the fan speed is:

[0220]

[0221] Wherein, n1 represents the adjusted fan speed, and n0 represents the initial fan speed;

[0222] The adjustment formula for the refrigerant flow rate is as follows:

[0223]

[0224] where m1 represents the required refrigerant flow rate, and m0 represents the initial refrigerant flow rate.

[0225] Optionally, the energy consumption deviation includes an absolute energy consumption deviation and a relative energy consumption deviation. The energy-saving strategy module 14 includes:

[0226] An energy consumption deviation calculation unit for comparing the actual energy consumption of each of the multiple HVAC devices with the predicted theoretical energy consumption, and calculating the absolute energy consumption deviation and the relative energy consumption deviation;

[0227] A total energy consumption calculation unit for calculating the total energy consumption of each of the multiple HVAC devices within a preset time period;

[0228] A device ranking unit for ranking the multiple HVAC devices in descending order of the total energy consumption;

[0229] A device to be energy-saving determination unit for determining the device to be energy-saving based on the absolute energy consumption deviation, the relative energy consumption deviation, and the ranking of each of the HVAC devices;

[0230] A temperature setpoint optimization unit for finding the temperature setpoint at which the energy consumption of the device to be energy-saving is minimized based on the relationship between temperature and energy consumption, and generating a corresponding energy-saving strategy based on the temperature setpoint.

[0231] Optionally, the temperature setpoint optimization unit includes:

[0232] A relationship model establishment unit for establishing a relationship model between temperature and energy consumption;

[0233] A third determination unit for determining the current temperature setpoint and the corresponding actual energy consumption of the device to be energy-saving;

[0234] A first acquisition unit for acquiring the preset temperature adjustment range and temperature adjustment step size of the device to be energy-saving;

[0235] An adjustment unit for starting from the current temperature setpoint and gradually adjusting the temperature setpoint in accordance with the temperature adjustment step size until the maximum value of the temperature adjustment range is reached;

[0236] A predicted energy consumption calculation unit for substituting each new temperature setpoint into the relationship model and calculating the corresponding predicted energy consumption;

[0237] A comparison and optimization unit is configured to compare the predicted energy consumption at each new temperature setting value, find the new temperature setting value with the minimum predicted energy consumption, and use it as the temperature setting value when the energy consumption of the device to be energy-saving is minimized.

[0238] Embodiment 3:

[0239] Reference Figure 3 , this embodiment provides a heating, ventilation and air conditioning (HVAC) energy consumption analysis device based on a data center, including a memory 21 and a processor 22. A computer program is stored in the memory 21, and the processor 22 is configured to run the computer program to execute the HVAC energy consumption analysis method based on the data center in Embodiment 1.

[0240] Among them, the memory 21 is connected to the processor 22. The memory 21 can be a flash memory, a read-only memory, or other memories, and the processor 22 can be a central processing unit or a single-chip microcomputer.

[0241] Embodiment 4:

[0242] This embodiment provides a computer-readable storage medium with a computer program stored thereon. When the computer program is executed by a processor, it implements the HVAC energy consumption analysis method based on the data center in Embodiment 1 above.

[0243] The computer-readable storage medium includes volatile or non-volatile, removable or non-removable media implemented in any method or technology for storing information such as computer-readable instructions, data structures, computer program modules, or other data. The computer-readable storage medium includes, but is not limited to, RAM (Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory, or other memory technologies, CD-ROM (Compact Disc Read-Only Memory), digital versatile disc (DVD), or other optical disc storage, magnetic cassette, tape, magnetic disk storage, or any other medium that can be used to store the desired information and can be accessed by a computer.

[0244] In summary, the HVAC energy consumption analysis method, system, device and medium based on the data center provided by the embodiments of the present invention first monitor the energy consumption data of HVAC equipment in real time, statistically analyze the energy consumption data according to time, equipment type and regional dimensions, generate an energy consumption report, and compare the energy consumption data in the energy consumption report with a preset energy consumption index to determine whether the energy consumption data is normal; then monitor the environmental parameters in the computer room in real time, and automatically adjust the operating state of the HVAC equipment when the environmental parameters exceed the preset normal range; then train an energy consumption prediction model based on the historical data related to the energy consumption of the HVAC equipment in the computer room and a machine learning algorithm, and use the trained energy consumption prediction model to predict the future energy consumption of the HVAC equipment; finally, compare the actual energy consumption of each of the multiple HVAC equipment with the predicted theoretical energy consumption, calculate the energy consumption deviation, rank the multiple HVAC equipment according to the total energy consumption of the multiple HVAC equipment within a preset time period, and generate corresponding energy-saving strategies according to the ranking and energy consumption deviation. By monitoring the energy consumption data of HVAC equipment in real time, statistically analyzing it according to time, equipment type and regional dimensions, and comparing it with the preset energy consumption index at the same time, the present invention can timely detect abnormal energy consumption and provide a strong basis for energy-saving decision-making. At the same time, by monitoring the environmental parameters of the computer room in real time and automatically adjusting the operating state of the equipment when the parameters exceed the normal range, the present invention significantly enhances the adaptability of the system to dynamic load changes, effectively reduces the dependence on manual intervention, and improves the overall management efficiency. In addition, by using historical data and machine learning algorithms to train an energy consumption prediction model, the present invention can accurately predict future energy consumption. On this basis, by comparing the actual energy consumption with the theoretical energy consumption, calculating the energy consumption deviation and ranking the equipment, and then generating targeted energy-saving strategies, the energy consumption can be further accurately reduced and the operation and maintenance efficiency can be improved. It solves the problems of high energy consumption, poor adaptability to dynamic loads and low efficiency caused by manual dependence in traditional data center HVAC systems.

[0245] It can be understood that the above embodiments are merely exemplary embodiments adopted to illustrate the principle of the present invention, but the present invention is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also regarded as the protection scope of the present invention.

Claims

1. A HVAC energy consumption analysis method based on a data center, characterized in that: The method comprises: Real-time monitoring of the energy consumption data of HVAC equipment, statistical analysis of the energy consumption data by time, equipment type and region, generating energy consumption reports, and comparing the energy consumption data in the energy consumption reports with preset energy consumption indicators to determine whether the energy consumption data is normal; Real-time monitoring of environmental parameters in the computer room, and automatically adjusting the operating status of the HVAC equipment when the environmental parameters exceed the preset normal range; Train the energy consumption prediction model based on the historical data related to the energy consumption of HVAC equipment in the computer room and the machine learning algorithm, and use the trained energy consumption prediction model to predict the energy consumption of HVAC equipment in the future; Compare the actual energy consumption of each of the multiple HVAC devices with the predicted theoretical energy consumption, calculate the energy consumption deviation, rank the multiple HVAC devices according to their total energy consumption within a preset time period, and generate a corresponding energy-saving strategy based on the ranking and the energy consumption deviation.

2. The method according to claim 1, characterized in that The energy consumption data includes power consumption data and water resource consumption data. The real-time monitoring of the energy consumption data of HVAC equipment is to statistically analyze the energy consumption data according to time, equipment type and regional dimensions to generate an energy consumption report, and compare the energy consumption data in the energy consumption report with the preset energy consumption index to determine whether the energy consumption data is normal, specifically including: Collect electricity consumption data and water consumption data of HVAC equipment in real time through pre-installed smart meters and flow sensors; Performing statistical analysis on the collected power consumption data and water resource consumption data according to time, equipment type and regional dimensions to generate the energy consumption report; The devices of different types in different areas in the energy consumption report are respectively taken as target devices, and the power consumption data of the target devices are respectively compared with the lower limit value and the upper limit value of the power consumption index corresponding to the target devices. If the power consumption data of the target device is less than the lower limit value of the power consumption index or the power consumption data of the target device is greater than the upper limit value of the power consumption index, it is judged that the power consumption data of the target device is abnormal; otherwise, it is judged that the power consumption data of the target device is normal; Different areas in the energy consumption report are respectively used as target areas, and the water resource consumption data of the target areas are summarized. The summarized water resource consumption data of the target areas are compared with the lower limit value and the upper limit value of the water resource consumption index corresponding to the target areas. If the summarized water resource consumption data of the target area is less than the lower limit value of the water resource consumption index or the summarized water resource consumption data of the target area is greater than the upper limit value of the water resource consumption index, it is judged that the water resource consumption data of the target area is abnormal; otherwise, it is judged that the water resource consumption data of the target area is normal.

3. The method according to claim 2, characterized in that The method further comprises: Calculate the average value and standard deviation of the historical power consumption data according to the historical power consumption data of the target device under different working conditions; Taking the average value of the historical power consumption data as an intermediate reference value, and determining the lower limit value and the upper limit value of the power consumption indicator corresponding to the target device based on the standard deviation of the historical power consumption data; Calculate the average value and standard deviation of the historical water resource consumption data according to the historical water resource consumption data of the target area under different working conditions; The average value of the historical water resource consumption data is used as an intermediate reference value, and the lower limit value and the upper limit value of the water resource consumption index corresponding to the target area are determined based on the standard deviation of the historical water resource consumption data.

4. The method according to claim 1, characterized in that: The environmental parameters include temperature and humidity. The real-time monitoring of the environmental parameters in the computer room and automatically adjusting the operating state of the HVAC equipment when the environmental parameters exceed a preset normal range specifically include: Collect the temperature and humidity in the equipment room in real time; When the temperature exceeds the maximum value of the preset normal temperature range, a first control instruction is sent to the air-conditioning unit, so that the air-conditioning unit adjusts the compressor frequency, fan speed and refrigerant flow of the air-conditioning unit according to the first control instruction; When the humidity exceeds the maximum value of the preset normal humidity range, a second control instruction is sent to the dehumidifier so that the dehumidifier adjusts the compressor frequency, fan speed and condenser temperature of the dehumidifier according to the second control instruction.

5. The method according to claim 4, characterized in that The adjustment formula of the compressor frequency is: Among them, f1 represents the required compressor frequency, f0 represents the standard frequency of the air conditioner, Q0 represents the reference cooling capacity, and Q1 represents the target cooling capacity determined according to the room temperature; The adjustment formula of the fan speed is: Among them, n1 represents the adjusted fan speed, and n0 represents the initial fan speed; The adjustment formula of the refrigerant flow is: Among them, m1 represents the required refrigerant flow rate, and m0 represents the initial refrigerant flow rate.

6. The method according to claim 1, characterized in that The energy consumption deviation includes an absolute energy consumption deviation and a relative energy consumption deviation. The actual energy consumption of each of the multiple HVAC devices is compared with the predicted theoretical energy consumption, the energy consumption deviation is calculated, and the multiple HVAC devices are ranked according to their total energy consumption within a preset time period, and a corresponding energy-saving strategy is generated according to the ranking and the energy consumption deviation, specifically including: Comparing the actual energy consumption of each of the plurality of HVAC equipment with the predicted theoretical energy consumption, and calculating the absolute energy consumption deviation and the relative energy consumption deviation; Calculating the total energy consumption of each of the plurality of HVAC equipment within a preset time period; Ranking the plurality of HVAC equipment in order of total energy consumption from high to low; Determine the equipment to be energy-efficient according to the absolute energy consumption deviation, relative energy consumption deviation and ranking of each of the HVAC equipment; According to the relationship between temperature and energy consumption, the temperature setting value when the energy consumption of the device to be energy-saving is minimized is found, and a corresponding energy-saving strategy is generated based on the temperature setting value.

7. The method according to claim 6, characterized in that The step of finding the temperature setting value when the energy consumption of the device to be energy-saving is minimum according to the relationship between temperature and energy consumption specifically includes: Establish a relationship model between temperature and energy consumption; Determine the current temperature setting value of the equipment to be energy-saving and the corresponding actual energy consumption; Obtaining a preset temperature adjustment range and a temperature adjustment step length of the device to be energy-saving; Starting from the current temperature setting value, gradually adjusting the temperature setting value according to the temperature adjustment step until the maximum value of the temperature adjustment range is reached; Substituting each new temperature setting value into the relationship model to calculate the corresponding predicted energy consumption; The predicted energy consumption under each new temperature setting value is compared, and the new temperature setting value with the minimum predicted energy consumption is found and used as the temperature setting value when the energy consumption of the equipment to be energy-saving is the minimum.

8. A HVAC energy consumption analysis system based on a data center, characterized in that: include: The energy consumption monitoring module is used to monitor the energy consumption data of HVAC equipment in real time, perform statistical analysis on the energy consumption data by time, equipment type and region, generate energy consumption reports, and compare the energy consumption data in the energy consumption reports with preset energy consumption indicators to determine whether the energy consumption data is normal; An environmental parameter monitoring module, connected to the energy consumption monitoring module, is used to monitor the environmental parameters in the computer room in real time, and automatically adjust the operating state of the HVAC equipment when the environmental parameters exceed a preset normal range; An energy consumption prediction module, connected to the environmental parameter monitoring module, is used to train an energy consumption prediction model based on historical data related to the energy consumption of HVAC equipment in the computer room and a machine learning algorithm, and use the trained energy consumption prediction model to predict the energy consumption of the HVAC equipment in the future; An energy-saving strategy module is connected to the energy consumption prediction module, and is used to compare the actual energy consumption of each of the multiple HVAC devices with the predicted theoretical energy consumption, calculate the energy consumption deviation, and rank the multiple HVAC devices according to their total energy consumption within a preset time period, and generate a corresponding energy-saving strategy based on the ranking and energy consumption deviation.

9. A HVAC energy consumption analysis device based on a data center, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement the HVAC energy consumption analysis method based on a data center as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the HVAC energy consumption analysis method based on a data center is implemented as described in any one of claims 1-7.

Images