Efficient machine room intelligent control system suitable for intelligent building

Abstract

The invention provides an efficient machine room intelligent control system suitable for an intelligent building, and relates to the technical field of energy conservation. The temperature control quantity of an intelligent building machine room special airflow channel and a machine room environment airflow channel is obtained through a processing module and an adjusting module, and a temperature characteristic identification model during operation of an intelligent building machine room is constructed according to the temperature control quantity. Adjusting the thermal response deviation in the temperature feature identification model during the operation of the intelligent building machine room through the temperature correction coefficient; correcting an adaptive compensation value in the intelligent building machine room cooling side energy consumption model during energy consumption adjustment through a correction module; and the feedback control module is used for performing feedback control on the working state of the machine room of the intelligent building. The dynamic adaptability of intelligent control of the intelligent building machine room can be improved under the influence of deviation overrun of the control response when the intelligent building machine room is subjected to intelligent control.

Description

TECHNICAL FIELD

[0001] The application relates to the field of energy saving, in particular to a high-efficiency machine room intelligent control system suitable for intelligent buildings. BACKGROUND

[0002] Energy saving refers to a series of technologies and methods aimed at reducing energy consumption and improving energy efficiency. By optimizing energy use and improving equipment efficiency, energy consumption and related costs can be reduced, and environmental impact can be reduced. Common forms include high-efficiency equipment, intelligent control systems, heat recovery technology, and energy management systems. These technologies not only help reduce energy costs, but also reduce greenhouse gas emissions and promote sustainable development.

[0003] In the existing intelligent building high-efficiency machine room intelligent control system, by integrating advanced monitoring, control and management technologies, the efficient operation of equipment in the machine room is realized. The system first uses sensors and Internet of Things technology to monitor environmental parameters such as temperature, humidity and equipment load in real time. This data is analyzed by a centralized management platform to identify energy consumption patterns and equipment status. Based on the analysis results, the intelligent control system can automatically adjust the operation mode of air conditioning, lighting and other equipment to meet actual needs, thereby avoiding unnecessary energy consumption. In addition, the system uses load management technology to optimize equipment operation and ensure optimal energy efficiency under different load conditions. At the same time, heat recovery technology is applied to recover waste heat generated by equipment for other heating or heating needs, further improving energy utilization efficiency. However, in the intelligent building high-efficiency machine room intelligent control process, the dynamic changes of the machine room environment are not fully considered, and the feedback control mechanism often relies on simple threshold judgments, resulting in a control reaction lag. This control reaction lag causes the machine room to be unable to respond in a timely manner when the load and environment change, resulting in insufficient coordination of feedback control in the intelligent building machine room intelligent control, causing the control response deviation to exceed the limit when the intelligent building machine room is intelligently controlled, thereby reducing the dynamic adaptability of the intelligent building machine room intelligent control. Therefore, how to improve the dynamic adaptability of the intelligent building machine room intelligent control under the influence of the control response deviation exceeding the limit when the intelligent building machine room is intelligently controlled is a problem faced by the industry. SUMMARY

[0004] The application provides a high-efficiency machine room intelligent control system suitable for intelligent buildings, which can improve the dynamic adaptability of the intelligent building machine room intelligent control under the influence of the control response deviation exceeding the limit when the intelligent building machine room is intelligently controlled.

[0005] The application provides a high-efficiency machine room intelligent control system suitable for intelligent buildings, which can improve the dynamic adaptability of the intelligent building machine room intelligent control under the influence of the control response deviation exceeding the limit when the intelligent building machine room is intelligently controlled. The acquisition module is used to monitor the running state of the intelligent building machine room and collect environmental state information of the intelligent building machine room. a processing module configured to decompose the environment state information to obtain a steady-state confidence vector of the intelligent building machine room in operation, and determine a temperature correction coefficient for the intelligent building machine room in operation temperature intelligent control; an adjusting module configured to obtain temperature control quantities of the intelligent building machine room special airflow channel and the machine room environment airflow channel, construct a temperature feature recognition model of the intelligent building machine room in operation according to the temperature control quantities, and adjust a thermal response deviation in the temperature feature recognition model of the intelligent building machine room in operation through the temperature correction coefficient; a correction module configured to determine a system load characteristic of the intelligent building machine room in operation, determine an energy consumption fluctuation quantity of the intelligent building machine room in operation according to the system load characteristic, and correct an adaptive compensation value in an energy consumption adjustment of an energy consumption model of the intelligent building machine room cooling side through the energy consumption fluctuation quantity; a feedback control module configured to perform feedback control on the working state of the intelligent building machine room according to the thermal response deviation in the adjusted temperature feature recognition model of the intelligent building machine room in operation and the adaptive compensation value in the corrected energy consumption adjustment of the energy consumption model of the intelligent building machine room cooling side.

[0006] In this embodiment, the environment state information of the intelligent building machine room is obtained by reading a database.

[0007] In this embodiment, the decomposition of the environment state information to obtain the steady-state confidence vector of the intelligent building machine room in operation specifically includes: weighting the environment state information to obtain an environment weight vector of the intelligent building machine room in operation; mapping the environment weight vector to a steady-state space of the intelligent building machine room in operation to obtain a steady-state running sample set; determining the steady-state confidence vector of the intelligent building machine room in operation according to the steady-state running sample set.

[0008] In this embodiment, the intelligent building machine room special airflow channel refers to an airflow channel specially designed to provide cooling air for the equipment in the machine room.

[0009] In this embodiment, the machine room environment airflow channel refers to an airflow channel formed naturally or artificially in the machine room, mainly used for air flow and ventilation.

[0010] In this embodiment, the determination of the system load characteristic of the intelligent building machine room in operation specifically includes: determining a regulated parameter of the load adjustment system of the intelligent building machine room in operation; obtaining a predicted target value of the energy consumption of the intelligent building machine room in operation; determining the system load characteristic of the intelligent building machine room in operation according to the regulated parameter and the predicted target value.

[0011] In the embodiment, the energy consumption fluctuation of the intelligent building machine room during operation is determined according to the system load characteristics, and specifically includes: extracting an output heat balance parameter corresponding to the energy consumption change of the intelligent building machine room during operation from the system load characteristics; determining an energy consumption control strategy of the intelligent building machine room during operation; determining the energy consumption fluctuation of the intelligent building machine room during operation according to the output heat balance parameter and the energy consumption control strategy.

[0012] In the embodiment, the adaptive compensation value of the energy consumption adjustment in the cooling side energy consumption model of the intelligent building machine room is corrected by the energy consumption fluctuation, and specifically includes: outputting the adaptive compensation value of the energy consumption adjustment in the cooling side energy consumption model of the intelligent building machine room; determining adjustment target information of the energy consumption adjustment of the intelligent building machine room; coordinating and correcting the adaptive compensation value according to the adjustment target information.

[0013] In the embodiment, the adaptive compensation value refers to a value used to correct the difference between the model prediction and the actual energy consumption during the energy consumption adjustment.

[0014] In the embodiment, the energy consumption fluctuation refers to the difference between the actual energy consumption and the predicted energy consumption.

[0015] The technical scheme provided by the embodiments disclosed in the present application has the following beneficial effects: The running state of the intelligent building machine room is monitored by the acquisition module, and the environmental state information of the intelligent building machine room is collected. The environmental state information is decomposed by the processing module to obtain a steady-state confidence vector of the intelligent building machine room during operation, and a temperature correction coefficient for intelligent control of the running temperature of the intelligent building machine room is determined according to the steady-state confidence vector. The temperature control amount of the special airflow channel of the intelligent building machine room and the machine room environment airflow channel is obtained by the adjusting module, and a temperature feature recognition model during operation of the intelligent building machine room is constructed according to the temperature control amount, and the thermal response deviation in the temperature feature recognition model during operation of the intelligent building machine room is adjusted by the temperature correction coefficient. The system load characteristics of the intelligent building machine room during operation are determined by the correction module, the energy consumption fluctuation of the intelligent building machine room during operation is determined according to the system load characteristics, and the adaptive compensation value of the energy consumption adjustment in the cooling side energy consumption model of the intelligent building machine room is corrected by the energy consumption fluctuation. The working state of the intelligent building machine room is feedback controlled according to the thermal response deviation in the adjusted temperature feature recognition model during operation of the intelligent building machine room and the adaptive compensation value of the energy consumption adjustment in the corrected cooling side energy consumption model of the intelligent building machine room by the feedback control module.

[0016] It can be seen that in the present application, the intelligent control of the intelligent building machine room can be realized under the influence of the deviation of the control response exceeding the limit, wherein the running state and environmental information of the machine room are monitored in real time, key data (such as temperature, humidity, air flow, etc.) are collected through sensor technology, the overall perception of the machine room environment is realized, the data-driven method enables the system to identify abnormal conditions in time and reduce potential failure risks, thereby improving the running stability and safety of the equipment; by decomposing the environmental state information into a steady-state confidence vector, using mathematical modeling and data analysis technology, the system can quantitatively evaluate the stability and reliability of the machine room operation, which provides a basis for temperature control, so that the cooling system can be dynamically adjusted according to real-time data to ensure that the equipment operates within the optimal temperature range, reduces energy consumption and failure rate; by establishing a temperature feature recognition model and combining a temperature correction coefficient, the system can accurately identify and adjust the thermal response deviation, this intelligent adjustment mechanism not only improves the cooling efficiency, but also optimizes energy use, avoids excessive cooling or insufficient cooling, and improves the economy and environmental protection of energy; by analyzing the load characteristics of the system, the system can predict the fluctuation of the machine room energy consumption, and use energy management algorithms for dynamic adjustment, which realizes the precise correction of the adaptive compensation value in the cooling side energy consumption model, thereby optimizing energy distribution and reducing overall energy consumption and improving energy efficiency ratio when the load changes; the feedback control mechanism enables the system to automatically adjust the machine room working state according to real-time data and adjusted model results, and the closed-loop control system continuously optimizes the temperature and energy consumption of the machine room through intelligent algorithms, so that the machine room maintains the best operating state under different loads and environmental conditions, ensuring efficient use of resources and safety of equipment.

[0017] In summary, the technical scheme adopted by the present application can improve the dynamic adaptability of intelligent control of the intelligent building machine room under the influence of the deviation of the control response exceeding the limit when the intelligent building machine room is intelligently controlled. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only the embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0019] Figure 1 is a module structure diagram of the efficient machine room intelligent control system suitable for intelligent buildings provided by the present application; Figure 2 is a flowchart for determining the temperature correction coefficient according to the present application; Figure 3is a flow diagram for adjusting thermal response deviation provided according to the present application. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0021] The embodiments of the present application provide a high-efficiency machine room intelligent control system suitable for intelligent buildings. The core of the system is to monitor the running state of the intelligent building machine room through a collection module, and collect the environmental state information of the intelligent building machine room; a processing module is used to decompose the environmental state information to obtain a steady-state confidence vector when the intelligent building machine room is running, and determine a temperature correction coefficient when the running temperature of the intelligent building machine room is intelligently controlled according to the steady-state confidence vector; a regulating module is used to obtain the temperature control amount of the special airflow channel of the intelligent building machine room and the machine room environment airflow channel, construct a temperature feature recognition model when the intelligent building machine room is running according to the temperature control amount, and adjust the thermal response deviation in the temperature feature recognition model when the intelligent building machine room is running through the temperature correction coefficient; a correction module is used to determine the system load characteristics when the intelligent building machine room is running, determine the energy consumption fluctuation amount when the intelligent building machine room is running according to the system load characteristics, and correct the adaptive compensation value when the energy consumption adjustment in the cooling side energy consumption model of the intelligent building machine room through the energy consumption fluctuation amount; a feedback control module is used to perform feedback control on the working state of the machine room of the intelligent building according to the thermal response deviation in the temperature feature recognition model when the intelligent building machine room is running after regulation and the adaptive compensation value when the energy consumption adjustment in the cooling side energy consumption model of the intelligent building machine room after correction. The above scheme is used to improve the dynamic adaptability of the intelligent control of the intelligent building machine room under the influence of the deviation of the control response when the intelligent control is performed on the intelligent building machine room.

[0022] In order to better understand the above technical solutions, the above technical solutions will be described in detail below in combination with the drawings in the specification and specific embodiments. Referring to Figure 1 As shown in the figure, the figure is a module structure diagram of a high-efficiency machine room intelligent control system suitable for intelligent buildings according to the embodiments of the present application. The intelligent control system includes a collection module 100, a processing module 200, a regulating module 300, a correction module 400, and a feedback control module 500, which are described as follows. The collection module 100 is used to monitor the running state of the intelligent building machine room, and collect the environmental state information of the intelligent building machine room.

[0023] In a specific implementation, a plurality of sensors, including temperature sensors, humidity sensors, and air flow sensors, are installed in the machine room, which should be evenly distributed in different areas of the machine room, especially in the positions of equipment-intensive and air flow channels, to ensure comprehensive monitoring.

[0024] In addition, in a specific implementation, first, the information collected by each sensor can be transmitted to the central control system using a data collector or gateway, which can be achieved through wired (such as RS-485, Ethernet) or wireless (such as Zigbee, Wi-Fi) methods, then the collected data is preprocessed, and the preprocessed data is stored in the database as the environmental state information of the intelligent building machine room. A time series database (such as InfluxDB) can be used, and then the environmental state information of the intelligent building machine room can be obtained by reading the database, which is not described here.

[0025] It should be noted that the environmental state information in the present application refers to various physical and chemical parameter data collected in a specific environment (such as an intelligent building machine room), which directly affects the operating efficiency and safety of the equipment, and specifically includes temperature, humidity, air flow speed, air pressure, noise level, etc., which can reflect the actual environmental conditions in the machine room.

[0026] The processing module 200 is configured to decompose the environmental state information to obtain a steady-state confidence vector of the intelligent building machine room during operation, and determine a temperature correction coefficient of the intelligent building machine room during intelligent control of the operating temperature according to the steady-state confidence vector.

[0027] In the present embodiment, the decomposition of the environmental state information to obtain the steady-state confidence vector of the intelligent building machine room during operation can be achieved by the following steps: The environmental state information is weighted and allocated to obtain an environmental weight vector of the intelligent building machine room during operation; The environmental weight vector is mapped to the steady-state space of the intelligent building machine room during operation to obtain a steady-state running sample set; The steady-state confidence vector of the intelligent building machine room during operation is determined according to the steady-state running sample set.

[0028] In a specific implementation, first, the environmental parameters affecting the operation of the machine room, such as temperature, humidity, air flow speed and air pressure, are identified, and the importance of each parameter is scored using an expert scoring method. The score range can be 1 to 5 (1 being the lowest and 5 being the highest). Then, combined with historical data, the actual influence of each parameter is determined through regression analysis or correlation analysis. For example, temperature fluctuations may have a high correlation with equipment failure, so the weight is large. All weights are normalized to ensure that the sum of the weights is 1. The normalized weight is used as the environmental weight vector for the intelligent building machine room operation. Then, using the environmental weight vector, the environmental state information is mapped to a steady state space. This space can be constructed using multi-dimensional data analysis methods such as principal component analysis or t-SNE. The environmental state information at each time point is then encoded as part of the sample set, which is composed of environmental states at multiple time points, forming a high-dimensional data matrix. The algorithm is then used to map this data matrix to a low-dimensional steady state space, highlighting the relationship between environmental variables. For example, each point in a two-dimensional space represents the environmental state at a time point, and its coordinates are obtained after weight adjustment, i.e., the steady state operation sample set is obtained. Finally, using the steady state operation sample set, statistical analysis is performed to calculate the mean and variance of each sample in the steady state space, reflecting the concentration and volatility of the environmental state. Combined with the environmental weight, the steady state confidence vector is calculated. For example, using the weighted average method, the weight of each sample is combined with its corresponding environmental state to obtain the steady state confidence, where the steady state confidence vector = [weight1*state1, weight2*state2, weight3*state3]. In other embodiments, the steady state confidence vector is not limited to this method and is not described in detail in this embodiment.

[0029] It should be noted that in this application, the environmental weight vector refers to the quantification of the influence of each environmental parameter (such as temperature, humidity, air flow speed, etc.) on the operation of the intelligent building machine room. The steady state operation sample set refers to a collection of environmental data samples reflecting the operation state of the intelligent building machine room collected within a certain time period. The steady state confidence vector refers to the amount of information obtained by analyzing the operation state of the machine room under certain environmental conditions, reflecting the reliability and confidence level of the system in a stable state.

[0030] Preferably, in this embodiment, the temperature correction coefficient for intelligent control of the operating temperature of the intelligent building machine room is determined according to the steady state confidence vector, which is used as a reference Figure 2 The figure is a flowchart for determining the temperature correction coefficient in some embodiments of the present application. The temperature correction coefficient in this embodiment can be achieved using the following steps: In step S21, the prediction parameter for intelligent control of the operating temperature of the intelligent building machine room is set. In step S22, the control constraint quantity when the operation temperature of the intelligent building machine room is intelligently controlled according to the steady-state confidence vector is determined; In step S23, the temperature correction reference value when the operation temperature of the intelligent building machine room is intelligently controlled is obtained; In step S24, the temperature correction coefficient when the operation temperature of the intelligent building machine room is intelligently controlled is determined according to the prediction parameter, the control constraint quantity, and the temperature correction reference value.

[0031] In specific implementation, first, the target temperature to be controlled is set according to the historical operation data of the equipment in the machine room, for example, a target range (such as 22°C to 24°C) can be determined by analyzing the temperature data in the past few weeks, and a central value (such as 23°C) is selected as the prediction parameter; then, the control constraint quantity is determined by analyzing the influence of each environmental factor on the operation temperature according to the steady-state confidence vector, including setting the maximum and minimum limits of the temperature to ensure that the temperature is within a safe range, for example, if the steady-state confidence vector indicates that the temperature has the most significant influence on the equipment, the upper limit of the temperature at a certain confidence level can be set to 25°C, and the lower limit to 20°C, that is, the control constraint quantity is obtained; then, the reference value of the temperature correction is obtained by analyzing the historical operation data and real-time monitoring information, which can be calculated comprehensively according to the cooling capacity of the equipment, the environmental temperature change, and the equipment load, for example, the cooling system efficiency of the equipment can be used as a reference to obtain a correction reference value, such as -1°C, indicating that additional cooling is required to maintain the target temperature; finally, the final temperature correction coefficient can be calculated by weighting or linear regression, for example, temperature correction coefficient = prediction parameter * (control constraint quantity / temperature correction reference value), which is not described in detail in the present application.

[0032] It should be noted that in the present application, the prediction parameter represents the target temperature value or range set in intelligent control; the control constraint quantity refers to the upper and lower limits of temperature variation in the temperature control process to ensure that the equipment operates in a safe and effective environment; the temperature correction reference value represents the reference value for adjusting the operation temperature in the temperature control process, reflecting the required temperature adjustment degree under the current environmental conditions; the temperature correction coefficient represents the value required to adjust the actual temperature in order to achieve the preset target temperature in the intelligent control system, which reflects the degree of correction of the deviation of the target temperature according to the real-time environmental state, equipment load, and operating conditions. By applying the temperature correction coefficient, the system can effectively adjust the cooling or heating output to ensure that the equipment in the machine room operates in the best working temperature range.

[0033] The adjusting module 300 is configured to obtain a temperature control quantity of the special airflow channel and the airflow channel of the machine room environment of the intelligent building machine room, construct a temperature feature recognition model of the intelligent building machine room in operation according to the temperature control quantity, and adjust a thermal response deviation in the temperature feature recognition model of the intelligent building machine room in operation through the temperature correction coefficient.

[0034] In a specific implementation, the temperature control quantity of the special airflow channel and the airflow channel of the machine room environment of the intelligent building machine room can be obtained in the following manner. First, temperature sensors are installed at appropriate positions in the special airflow channel and the airflow channel of the machine room environment. The sensors are placed at the inlet and outlet of the airflow to obtain comprehensive temperature data. For example, one sensor can be arranged at each of different heights and positions of an air handling unit (AHU) and a cooling channel of the machine room to capture temperature changes at different levels. Then, data of the sensors are read regularly by using a data acquisition system, and temperature information is transmitted to a central control system in real time. The sensors need to have high precision and fast response capability to ensure accurate capture of temperature changes. The data acquisition frequency can be set to once per minute. The collected temperature data are preprocessed by the central control system to eliminate noise and outliers. The data can be smoothed by using a moving average or weighted average method. Finally, the temperature control quantity of the special airflow channel and the airflow channel of the machine room environment is calculated according to the processed temperature data. For example, if the target temperature is 22°C and the current temperature of the special airflow channel is 24°C, the temperature control quantity can be set to -2°C, indicating that the temperature needs to be reduced. This embodiment is not described in detail.

[0035] It should be noted that, in this application, the temperature control quantity refers to a value that needs to be adjusted to the current environmental temperature in the intelligent control system to achieve the target temperature. It reflects the difference between the actual temperature and the set target temperature, and is used to guide the operation of cooling or heating equipment. The temperature control quantity is used to ensure that the machine room or other controlled environment is maintained within an optimal temperature range to improve the operating efficiency and safety of the equipment.

[0036] In addition, in this application, the special airflow channel of the intelligent building machine room refers to an airflow channel specially designed to provide cooling air for the equipment in the machine room. These channels are usually connected to air conditioning systems or cooling equipment to ensure that cold air flows effectively to heat sources (such as server racks) to maintain the normal working temperature of the equipment. The design of the special airflow channel aims to optimize airflow, reduce the loss of cold air, and improve cooling efficiency. The airflow channel of the machine room environment refers to an airflow channel formed naturally or artificially in the machine room, mainly used for air flow and ventilation to help evenly distribute temperature in the machine room, prevent dead angles and heat accumulation, and maintain the comfort and stability of the overall environment. The environmental airflow channel may involve windows, doors, vents, and other structures, aiming to improve air quality and adjust humidity.

[0037] In a specific implementation, the temperature feature recognition model of the intelligent building machine room during operation can be constructed according to the temperature control amount in the following manner: first, collect historical data related to the temperature of the machine room, including the temperature control amount, the ambient temperature, the equipment load, the cooling system output, and the like, and then clean the collected data to remove outliers and missing data to ensure the integrity of the data; then, through correlation analysis and feature importance evaluation, select features that have a significant impact on temperature changes, for example, a random forest or LASSO regression analysis can be used to determine the relationship between input features (such as external ambient temperature and equipment load) and temperature changes; finally, select a suitable model algorithm, such as linear regression, support vector machine (SVM), neural network, and the like, according to the characteristics and requirements of the data, and then use a training set (such as 70% of the historical data) to train the model, adjust the model parameters by minimizing the prediction error, for example, using a linear regression model, temperature = β0 + β1*ambient temperature + β2*equipment load + ···, where β0, β1, and β2 are weight parameters in the linear regression model, which can be obtained through expert experience or experimental simulation, cross-validation can be used during the training process to ensure the generalization ability of the model, and then a validation set (such as 20% of the historical data) is used to evaluate the performance of the model, calculate error indicators such as root mean square error (RMSE) or mean absolute error (MAE), and adjust the model parameters or select different model algorithms according to the validation results, i.e., obtain the temperature feature recognition model, which will not be described again in this application. In other embodiments, other methods can also be used to construct the temperature feature recognition model.

[0038] It should be noted that in this application, the temperature feature recognition model refers to a mathematical model established in the intelligent control system by analyzing and processing temperature-related data in the machine room, which is used to predict and identify the characteristics and influencing factors of the temperature change in the machine room. The model integrates environmental temperature, equipment load, cooling system output and other parameters, aiming to provide accurate prediction of temperature change trends to optimize temperature control strategies and improve the energy efficiency and stability of the machine room. Through real-time application, the model can help the decision system to achieve accurate temperature regulation and ensure that the equipment operates in the best working conditions.

[0039] Preferably, in this embodiment, the thermal response deviation in the temperature feature recognition model of the intelligent building machine room during operation is adjusted by the temperature correction coefficient, which is Figure 3 The figure is a flowchart of adjusting the thermal response deviation in some embodiments of the present application. The adjustment of the thermal response deviation in this embodiment can be implemented in the following steps: In step S31, the total heat balance of the machine room environment is output from the temperature feature recognition model; In step S32, the thermal response deviation is output from the temperature feature recognition model; In step S33, a regulation feedback value when the intelligent building machine room operation time temperature feature recognition model is adjusted is determined. In step S34, the thermal response deviation in the intelligent building machine room operation time temperature feature recognition model is adjusted according to the total heat balance, the temperature correction coefficient and the regulation feedback value.

[0040] In a specific implementation, first, the total heat balance of the computer room is calculated according to the temperature feature recognition model, including the sum of all heat inputs and heat outputs, the heat inputs can include device heat dissipation, external environmental heat (such as direct sunlight) and heat brought by personnel, and the heat outputs include cold quantity dissipated through the air conditioning system, ventilation and other cooling devices, wherein the total heat balance = total input heat - total output heat; then, the difference between the current actual temperature and the model predicted temperature, i.e. the thermal response deviation, is obtained from the temperature feature recognition model, wherein the thermal response deviation = current temperature - predicted temperature; then, the current state of the system is evaluated and the regulation feedback value is determined according to the output thermal response deviation, the feedback value can be set based on the size of the thermal response deviation, for example, when the deviation is large, the feedback value is set to high, indicating that more adjustment is needed, when the deviation is within an acceptable range, the feedback value can be set to low; finally, the new thermal response deviation can be calculated by the following formula, i.e. new thermal response deviation = original thermal response deviation - (temperature correction coefficient x regulation feedback value), which is not described herein.

[0041] It should be noted that in this application, the total heat balance refers to the total amount reflecting the relationship between all heat inputs and outputs in the computer room, representing the thermal state of the computer room; the thermal response deviation refers to the difference between the current actual temperature and the model predicted temperature, reflecting the temperature control effect of the system; the regulation feedback value is a parameter for guiding the adjustment degree of the temperature control system; the thermal response deviation adjustment is a process of adjusting the thermal response deviation in real time based on the total heat balance, the temperature correction coefficient and the regulation feedback value.

[0042] The correction module 400 is configured to determine the system load characteristics of the intelligent building machine room in operation, determine the energy consumption fluctuation of the intelligent building machine room in operation according to the system load characteristics, and correct the adaptive compensation value of the energy consumption adjustment in the intelligent building machine room cooling side energy consumption model through the energy consumption fluctuation.

[0043] In this embodiment, the system load characteristics of the intelligent building machine room in operation can be determined by the following steps: Determine the regulated parameter of the load regulation system of the intelligent building machine room in operation; Obtain the predicted target value of the energy consumption of the intelligent building machine room in operation; Determine the system load characteristics of the intelligent building machine room in operation according to the regulated parameter and the predicted target value.

[0044] In a specific implementation, first, the key parameters to be monitored and adjusted in the load regulation system are set as the parameters to be regulated in the load regulation system of the intelligent building machine room during operation, including the equipment operating state, such as server load, operating time, etc.; environmental conditions, such as temperature, humidity, etc., which affect equipment performance; power supply, such as voltage, frequency, etc., which affect the energy efficiency of the equipment; then, according to historical data and operation model, the energy consumption target value of the intelligent building machine room in a specific time period is predicted, which can be achieved by using statistical analysis, machine learning algorithm or historical trend analysis to generate an energy consumption prediction model, for example, if the historical data shows that the energy consumption under similar load conditions is 500 kWh, it will be used as the target value; finally, the relationship between the actual energy consumption of the system under the current parameters to be regulated and the predicted target value is calculated to determine the response characteristics of the system, such as the trend of energy consumption change when the load increases or decreases, which can be displayed using charts, models or data analysis tools to show the load characteristics of the system. For example, by plotting the relationship curve between load and energy consumption, the load characteristics of the system during the operation of the building machine room are determined, which will not be described in detail.

[0045] It should be noted that in the present application, the parameters to be regulated represent the key variables that need to be monitored and adjusted in the load regulation system, which affect the energy efficiency and operating state of the system; the energy consumption prediction target value is the expected energy consumption level calculated based on historical data and operation model, which is used as the benchmark for load regulation; the system load characteristics are the characteristics describing the relationship between energy consumption and load of the intelligent building machine room under different conditions, which are used to guide load regulation and optimization.

[0046] In the present embodiment, the energy consumption fluctuation of the intelligent building machine room during operation can be achieved according to the system load characteristics by the following steps: Extracting the output heat balance parameter corresponding to the energy consumption change of the intelligent building machine room during operation from the system load characteristics; Determining the energy consumption control strategy of the intelligent building machine room during operation; According to the output heat balance parameter and the energy consumption control strategy, the energy consumption fluctuation of the intelligent building machine room during operation is determined.

[0047] In a specific implementation, first, the output heat balance parameter related to energy consumption changes is obtained from the system load characteristics, including the input heat, the heat generated by the equipment in the machine room, including servers, network equipment, etc.; the cooling capacity, the cooling capacity provided by the air conditioning or cooling equipment; the environmental heat influence, the influence of the external environment on the temperature in the machine room, such as the heat input caused by weather changes, and then these parameters are integrated to generate the output heat balance parameter through the heat balance equation; then, according to the actual operation of the machine room and the heat balance parameter, the corresponding energy consumption control strategy is formulated, including dynamic adjustment, automatic adjustment of the operation state of the cooling system according to the real-time load change, such as changing the air speed, temperature setting, etc.; peak period management, limiting the operation of some equipment during the peak period of power demand, or using energy-saving mode; predictive control, using a prediction model to adjust the equipment operation in advance to adapt to the expected load change; for example, the output of the cooling equipment can be increased under high load conditions to ensure that the temperature remains within a safe range; finally, the fluctuation value between the actual energy consumption and the expected energy consumption is calculated by comparing the historical data and the energy consumption predicted by the model, that is, the energy consumption fluctuation is equal to the absolute value of the difference between the actual energy consumption and the predicted energy consumption, wherein the actual energy consumption is the real-time monitoring data, and the predicted energy consumption is the target value set in advance according to the control strategy, which can be collected in real time through the monitoring system to ensure that the calculation of the energy consumption fluctuation reflects the current state of the machine room, which is not described in detail in this application.

[0048] It should be noted that in this application, the output heat balance parameter represents a parameter describing the relationship between the heat generated by the equipment in the machine room and the cooling system capacity, which is used to analyze energy consumption changes; the energy consumption control strategy refers to the adjustment scheme formulated for the operation of the machine room, aiming to optimize energy consumption and equipment performance; the energy consumption fluctuation refers to the difference between the actual energy consumption and the predicted energy consumption, reflecting the stability of the energy consumption of the machine room and the control effect.

[0049] In this embodiment, the adaptive compensation value of the energy consumption adjustment of the intelligent building machine room cooling side energy consumption model can be realized by the following steps: Output the adaptive compensation value of the energy consumption adjustment of the intelligent building machine room cooling side energy consumption model; Determine the adjustment target information of the energy consumption adjustment of the intelligent building machine room; Coordinate and correct the adaptive compensation value through the adjustment target information.

[0050] In a specific implementation, first, the adaptive compensation value at the time of energy consumption adjustment is extracted from the intelligent building machine room cooling side energy consumption model, which is used to compensate for the deviation between the model prediction and the actual energy consumption. The model is based on historical operation data and real-time monitoring data, and the adaptive compensation value under the current condition is calculated through heat balance analysis, that is, adaptive compensation value = actual energy consumption - predicted energy consumption. Usually, algorithms or software tools such as linear regression, neural network, etc. are used to improve the prediction accuracy of the model; then, according to the actual operation situation and management requirements of the machine room, the target information of energy consumption adjustment is set, including the target energy consumption level, the upper or lower limit of energy consumption that needs to be achieved; cooling demand, cooling requirement under certain load condition; time window: energy consumption target to be achieved within certain time period; for example, the cooling system energy consumption during peak period should not exceed a certain value to avoid excessive electricity consumption; finally, according to the adjustment target information, the output adaptive compensation value is coordinated and corrected, the compensation value is compared with the target information, and it is judged whether the current compensation value meets the set adjustment target. If the compensation value deviates from the target, corresponding adjustment is made, for example, new compensation value = old compensation value ± adjustment coefficient, wherein the adjustment coefficient can be dynamically set according to the actual deviation, and then iterative calculation is carried out to ensure that the final compensation value meets the energy consumption target, which is not described in detail in this application.

[0051] It should be noted that in this application, the adaptive compensation value represents the value used to correct the difference between the model prediction and the actual energy consumption in the energy consumption adjustment process, ensuring that the model adapts to the current operating conditions; the adjustment target information represents the specific target data used to guide the energy consumption adjustment, including energy consumption level, cooling demand and time limit, etc.; the coordination and correction is a dynamic adjustment process of the adaptive compensation value based on the adjustment target information, to ensure the realization of the energy consumption control target.

[0052] The feedback control module 500 is configured to perform feedback control on the working state of the machine room of the intelligent building according to the thermal response deviation in the adjusted intelligent building machine room temperature feature recognition model and the adaptive compensation value at the time of energy consumption adjustment in the corrected intelligent building machine room cooling side energy consumption model.

[0053] In practice, feedback control of the intelligent building's computer room operating status, based on the thermal response deviation in the adjusted intelligent building computer room operating temperature characteristic identification model and the adaptive compensation value for energy consumption adjustment in the corrected intelligent building computer room cooling-side energy consumption model, can be achieved in the following way: First, monitor the computer room's temperature and energy consumption data in real time to ensure that the collected values ​​are up-to-date. Based on this, extract the thermal response deviation from the temperature characteristic identification model to reflect the difference between the current temperature and the desired temperature. Simultaneously, obtain the adaptive compensation value from the cooling-side energy consumption model to identify the necessity of energy consumption adjustment. Next, based on the extracted data, set the feedback control target. For example, if the thermal response deviation indicates that the temperature is too high, the control target can be set to reduce the temperature to a safe range; if the energy consumption adaptive compensation value indicates that the energy consumption is higher than the target, the control target can be set to reduce energy consumption. Then, adjust the cooling system, such as increasing the fan speed or reducing the airflow. Adjusting temperature settings directly addresses thermal response deviations. Furthermore, by regulating equipment operating conditions, such as reducing load or shutting down non-critical equipment during off-peak hours, overall energy consumption is optimized. During implementation, the control system continuously feeds back current temperature and energy consumption to the model, monitoring and analyzing thermal response deviations and compensation values. The system can set thresholds; when deviations exceed the set range, control measures are automatically triggered. Through real-time data and feedback, the system can iterate and optimize control strategies to achieve optimal energy efficiency and temperature control. Machine learning algorithms improve model prediction accuracy and make feedback control more intelligent. By combining the adjustment results of temperature feature identification models and cooling-side energy consumption models, intelligent building computer rooms can achieve effective feedback control, ensuring optimal operation under dynamic loads and environmental changes, improving energy efficiency, and guaranteeing safe equipment operation. Further details are omitted here.

[0054] It can be seen that in the present application, the intelligent control of the intelligent building machine room can be realized under the influence of the deviation of the control response exceeding the limit, wherein the running state and environmental information of the machine room are monitored in real time, key data (such as temperature, humidity, air flow, etc.) are collected through sensor technology, and comprehensive perception of the machine room environment is realized. The data-driven method enables the system to identify abnormal conditions in a timely manner, reduces potential failure risks, and thus improves the running stability and safety of the equipment. By decomposing the environmental state information into a steady-state confidence vector and using mathematical modeling and data analysis techniques, the system can quantitatively evaluate the stability and reliability of the machine room operation. This evaluation provides a basis for temperature control, enabling the cooling system to dynamically adjust based on real-time data to ensure that the equipment operates within the optimal temperature range, reducing energy consumption and failure rates. By establishing a temperature feature recognition model and combining a temperature correction coefficient, the system can accurately identify and adjust thermal response deviations. This intelligent adjustment mechanism not only improves cooling efficiency but also optimizes energy use, avoiding excessive cooling or insufficient cooling, and improving the economic and environmental performance of energy. By analyzing the load characteristics of the system, the system can predict fluctuations in machine room energy consumption and use energy management algorithms for dynamic adjustment. This process achieves precise correction of the adaptive compensation value in the cooling side energy consumption model, thereby optimizing energy distribution and reducing overall energy consumption and improving energy efficiency when the load changes. The feedback control mechanism enables the system to automatically adjust the machine room operating state based on real-time data and adjusted model results. This closed-loop control system continuously optimizes the temperature and energy consumption of the machine room through intelligent algorithms, enabling the machine room to maintain optimal operating conditions under different loads and environmental conditions, ensuring efficient use of resources and equipment safety.

[0055] In summary, the technical solution adopted by the present application can improve the dynamic adaptability of intelligent control of the intelligent building machine room under the influence of the deviation of the control response exceeding the limit when the intelligent building machine room is intelligently controlled.

[0056] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of the flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks.

[0057] Those skilled in the art can understand that all or part of the steps of various methods in the above embodiments can be completed by instructing the relevant hardware by means of a program, and the program can be stored in a computer readable storage medium, including Read-Only Memory (ROM), Random Access Memory (RAM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), One-time Programmable Read-Only Memory (OTPROM), Electrically-Erasable Programmable Read-Only Memory (EEPROM), Compact Disc Read-Only Memory (CD-ROM) or other optical disk storage, magnetic disk storage, magnetic tape storage, or any other medium that can be used to carry or store data in a computer readable manner.

[0058] It should also be noted that the terms "comprising", "containing", or any other variant thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements, but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or apparatus that includes the element.

Claims

1. A high-efficiency machine room intelligent control system suitable for intelligent buildings, characterized in that, The intelligent control system comprises: The acquisition module is configured to monitor the operation state of the intelligent building machine room and collect environment state information of the intelligent building machine room. The processing module is configured to decompose the environment state information to obtain a steady-state confidence vector of the intelligent building machine room in operation, and determine a temperature correction coefficient of the intelligent building machine room in operation for intelligent control. The adjusting module is configured to obtain a temperature control amount of a special airflow channel of the intelligent building machine room and an airflow channel of the machine room environment, construct a temperature feature recognition model of the intelligent building machine room in operation according to the temperature control amount, and adjust a thermal response deviation in the temperature feature recognition model of the intelligent building machine room in operation through the temperature correction coefficient. The correction module is configured to determine a system load characteristic of the intelligent building machine room in operation, determine an energy consumption fluctuation of the intelligent building machine room in operation according to the system load characteristic, and correct an adaptive compensation value in energy consumption adjustment of a cooling side energy consumption model of the intelligent building machine room through the energy consumption fluctuation. The feedback control module is configured to perform feedback control on the working state of the machine room of the intelligent building according to the thermal response deviation in the temperature feature recognition model of the intelligent building machine room in operation after adjustment and the adaptive compensation value in energy consumption adjustment of the cooling side energy consumption model of the intelligent building machine room after correction.

2. The high-efficiency machine room intelligent control system suitable for intelligent buildings according to claim 1, wherein, The environment state information of the intelligent building machine room is obtained by reading a database.

3. The high-efficient machine room intelligent control system suitable for intelligent building of claim 1, wherein, The decomposition of the environment state information to obtain the steady-state confidence vector of the intelligent building machine room in operation specifically comprises: The environment state information is subjected to weight distribution to obtain an environment weight vector of the intelligent building machine room in operation. The environment weight vector is mapped to a steady-state space of the intelligent building machine room in operation to obtain a steady-state running sample set. The steady-state confidence vector of the intelligent building machine room in operation is determined according to the steady-state running sample set.

4. The high efficiency machine room intelligent control system for intelligent building of claim 1, wherein, The special airflow channel of the intelligent building machine room refers to an airflow channel specially designed to provide cooling air for equipment in the machine room.

5. The high efficient machine room intelligent control system for intelligent building of claim 1, wherein, The airflow channel of the machine room environment refers to an airflow channel formed naturally or artificially in the machine room, mainly used for air flow and ventilation.

6. The high efficient machine room intelligent control system for intelligent building of claim 1, wherein, The determination of the system load characteristic of the intelligent building machine room in operation specifically comprises: The being-adjusted parameter of the load adjusting system of the intelligent building machine room in operation is determined. A predicted target value of energy consumption of the intelligent building machine room in operation is obtained. The system load characteristic of the intelligent building machine room in operation is determined according to the being-adjusted parameter and the predicted target value.

7. The high efficient machine room intelligent control system for intelligent building of claim 1, wherein, The determination of the energy consumption fluctuation of the intelligent building machine room in operation according to the system load characteristic specifically comprises: An output heat balance parameter corresponding to energy consumption change of the intelligent building machine room in operation is extracted from the system load characteristic. An energy consumption control strategy of the intelligent building machine room in operation is determined. The energy consumption fluctuation of the intelligent building machine room in operation is determined according to the output heat balance parameter and the energy consumption control strategy.

8. The high efficiency machine room intelligent control system for intelligent building of claim 1, wherein, The correction of the adaptive compensation value in energy consumption adjustment of the cooling side energy consumption model of the intelligent building machine room through the energy consumption fluctuation specifically comprises: The adaptive compensation value in energy consumption adjustment is output through the cooling side energy consumption model of the intelligent building machine room. An adjustment target information of the intelligent building machine room in energy consumption adjustment is determined. The adaptive compensation value is coordinated and corrected through the adjustment target information.

9. The high efficient machine room intelligent control system for intelligent building of claim 1, wherein, The adaptive compensation value refers to a value used to correct the difference between the model prediction and the actual energy consumption in the energy consumption adjustment process.

10. The high efficiency machine room intelligent control system for intelligent building of claim 1, wherein, The energy consumption fluctuation amount refers to the difference between the actual energy consumption and the predicted energy consumption.

Images