Heat dissipation control method and system for domestic switch and switch

Abstract

The invention relates to a heat dissipation control method and system for a domestic switch and the switch, and relates to the field of switch heat dissipation management and control, and the method comprises the steps: carrying out the data transmission calculation prediction in the future, obtaining a predicted data transmission parameter, carrying out the temperature change prediction and environment noise prediction through combining a real-time temperature and a real-time heat dissipation control parameter, and carrying out the heat dissipation control. Obtaining predicted temperature and predicted environment noise, and calculating a configuration noise coefficient in combination with accumulated switch noise; and optimizing and adjusting the real-time heat dissipation control parameter according to the predicted temperature and the noise coefficient to obtain an optimal heat dissipation control parameter for heat dissipation control. The technical problem that a traditional method often depends on a preset heat dissipation control strategy, and heat dissipation control parameters cannot be accurately adjusted according to actual load and environment changes can be solved; the accuracy and rationality of heat dissipation control parameter setting can be improved, dual optimization of temperature control and noise control is achieved, the heat dissipation efficiency is effectively improved, and meanwhile noise pollution is reduced.

Description

Technical Field

[0001] The present invention relates to the field of heat dissipation control of switches, and in particular to a heat dissipation control method, system and switch for domestic switches. Background Art

[0002] As an important device in modern communication networks, the stability and efficiency of switches directly affect the quality of network operation. With the increasing number of network applications, the volatility of switch loads and the complexity of environmental changes are becoming increasingly prominent. Therefore, heat dissipation control of switches has become a key factor in ensuring their efficient and stable operation.

[0003] Traditional switch heat dissipation control methods usually rely on preset heat dissipation control strategies, that is, adjusting the heat dissipation system according to fixed temperature thresholds or set fan speeds. They cannot be dynamically adjusted according to actual load and environmental changes, resulting in excessive or insufficient heat dissipation. Summary of the invention

[0004] The present invention aims to solve the technical problem that the heat dissipation control method of traditional switches often relies on preset heat dissipation control strategies and cannot accurately adjust the heat dissipation control parameters according to actual load and environmental changes, and provides a heat dissipation control method, system and switch for domestic switches to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: In a first aspect, the present invention provides a heat dissipation control method for a domestic switch, comprising: monitoring and obtaining the current real-time temperature, real-time heat dissipation control parameters and accumulated switch noise of the switch; obtaining the data transmission record of the switch within a preset time range in the past, performing calculation and prediction of future data transmission, obtaining predicted data transmission parameters, and performing temperature change prediction and environmental noise prediction in combination with the real-time temperature and real-time heat dissipation control parameters, obtaining predicted temperature and predicted environmental noise, and calculating and configuring a noise coefficient in combination with the accumulated switch noise; optimizing and adjusting the real-time heat dissipation control parameters according to the predicted temperature and noise coefficient, obtaining optimal heat dissipation control parameters, and performing heat dissipation control, wherein the optimization step size is configured according to the change amplitude of the predicted temperature and the real-time temperature.

[0006] Preferably, the heat dissipation control method for a domestically produced switch also includes: monitoring and obtaining the real-time temperature of the switch through a temperature sensor configured on the switch; obtaining the current real-time heat dissipation control parameters of the switch, wherein the heat dissipation control parameters include the fan speed; monitoring and obtaining the switch noise within a preset time interval in the past through a noise sensor configured on the switch, and calculating the average to obtain the cumulative switch noise.

[0007] Preferably, the heat dissipation control method for a domestic switch also includes: obtaining a data throughput sequence of the switch within a preset time range in the past; pre-training a data transmission predictor for predicting future data transmission parameters; inputting the data throughput sequence into the data transmission predictor, and predicting the data throughput at a preset time in the future as a predicted data transmission parameter.

[0008] Preferably, the heat dissipation control method for a domestically produced switch also includes: collecting a set of sample data throughput sequences based on switch operation data in historical time, and collecting the data throughput of the switch at future moments after different sample data throughput sequences to obtain a set of sample predicted data throughputs; using the sample data throughput sequence set and the sample predicted data throughput set, training a data transmission predictor based on machine learning, and performing testing until convergence.

[0009] Preferably, the heat dissipation control method for a domestic switch also includes: obtaining the current real-time data throughput of the switch; collecting a sample real-time data throughput set, a sample real-time temperature set, a sample real-time heat dissipation control parameter set, and a sample future data throughput set, and collecting the switch temperature at future times under different sample real-time data throughputs, sample real-time temperatures, sample real-time heat dissipation control parameters, and sample future data throughputs to obtain a sample predicted temperature set; using the sample real-time data throughput set, sample real-time temperature set, sample real-time heat dissipation control parameter set, sample future data throughput set, and sample predicted temperature set to train a temperature change predictor; inputting the real-time temperature, real-time data throughput, real-time heat dissipation control parameter, and predicted throughput into the temperature change predictor, and predicting the output to obtain the predicted temperature; performing environmental noise prediction based on the predicted data transmission parameters to obtain predicted environmental noise.

[0010] Preferably, the heat dissipation control method for domestic switches also includes: collecting a set of sample predicted data transmission parameters based on noise monitoring data in the environment, and collecting the average environmental noise in the environment under different sample predicted data transmission parameters to obtain a sample environmental noise set; constructing a mapping relationship between the sample predicted data transmission parameter set and the sample environmental noise set to obtain an environmental noise prediction table; inputting the predicted data transmission parameters into the environmental noise prediction table, mapping and classifying to obtain the predicted environmental noise.

[0011] Preferably, the heat dissipation control method for a domestic switch further includes: obtaining the historical average noise in the environment; and calculating the configuration noise coefficient according to the accumulated switch noise, the historical average noise and the predicted environmental noise, as shown in the following formula: ; in, is the noise coefficient, is the historical average noise, is the cumulative switch noise, To predict the environmental noise.

[0012] Preferably, the heat dissipation control method for a domestic switch further includes: calculating the temperature deviation amplitude between the predicted temperature and the real-time temperature as an optimization step; using the optimization step to adjust the real-time heat dissipation control parameter to obtain a first heat dissipation control parameter; inputting the first heat dissipation control parameter into the temperature change predictor in combination with the real-time temperature, the real-time data throughput, and the predicted throughput, and predicting the output to obtain a first control temperature; obtaining the first switch noise under the first heat dissipation control parameter, and calculating the heat dissipation control fitness according to the first control temperature and the noise coefficient, as shown in the following formula: ; in, To control the adaptability of heat dissipation, is the first control temperature, is the standard temperature, is the noise coefficient, is a small real number, For the first switch noise, is standard noise; continue to use the optimization step size to optimize and adjust the first heat dissipation control parameter until convergence, output the optimal heat dissipation control parameter with the maximum heat dissipation control fitness, and perform heat dissipation control.

[0013] In a second aspect, the present invention provides a heat dissipation control system for a domestic switch, including: a status data monitoring and acquisition module, used to monitor and obtain the current real-time temperature, real-time heat dissipation control parameters and accumulated switch noise of the switch; a status change data prediction module, used to obtain the data transmission record of the switch within a preset time range in the past, perform calculation prediction of future data transmission, obtain predicted data transmission parameters, and perform temperature change prediction and environmental noise prediction in combination with the real-time temperature and real-time heat dissipation control parameters, obtain predicted temperature and predicted environmental noise, and calculate the configured noise coefficient in combination with the accumulated switch noise; a heat dissipation control parameter optimization module, used to optimize and adjust the real-time heat dissipation control parameters according to the predicted temperature and noise coefficient, obtain optimal heat dissipation control parameters, and perform heat dissipation control, wherein the optimization step size is configured according to the change amplitude of the predicted temperature and the real-time temperature.

[0014] In a third aspect, the present invention further provides a switch, and when the domestic switch is in operation, heat dissipation can be regulated by a heat dissipation control method for a domestic switch as described in any one of the first aspects.

[0015] The beneficial effects of the present invention are as follows: the current real-time temperature, real-time heat dissipation control parameters and accumulated switch noise of the switch are obtained through monitoring; then the data transmission record of the switch within a preset time range in the past is obtained, and future data transmission calculation prediction is performed to obtain predicted data transmission parameters; then temperature change prediction and environmental noise prediction are performed based on the predicted data transmission parameters, real-time temperature and real-time heat dissipation control parameters to obtain predicted temperature and predicted environmental noise, and the configuration noise coefficient is calculated in combination with the accumulated switch noise; finally, the real-time heat dissipation control parameters are optimized and adjusted based on the predicted temperature and noise coefficient to obtain the optimal heat dissipation control parameters and perform heat dissipation control; the above method can improve the accuracy and rationality of the heat dissipation control parameter setting, realize the dual optimization of temperature control and noise control, avoid excessive heat dissipation or insufficient heat dissipation, thereby effectively improving the heat dissipation efficiency, while reducing noise pollution, and ensuring efficient and stable operation of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic flow chart of a heat dissipation control method for a domestic switch provided by the present invention; Figure 2 A schematic structural diagram of a heat dissipation control system for a domestic switch provided by the present invention.

[0017] In the accompanying drawings, the components represented by the reference numerals are described as follows: A state data monitoring and acquisition module 10 , a state change data prediction module 20 , and a heat dissipation control parameter optimization module 30 . DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0019] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0020] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0021] Embodiment 1, as Figure 1 As shown, an embodiment of the present invention provides a heat dissipation control method for a domestic switch, which specifically includes the following steps: P10: Monitor and obtain the current real-time temperature, real-time heat dissipation control parameters and accumulated switch noise of the switch.

[0022] Further, step P10 of the present invention further includes: P11: Monitor and obtain the real-time temperature of the switch through the temperature sensor configured on the switch; P12: Obtain the current real-time heat dissipation control parameters of the switch, where the heat dissipation control parameters include the fan speed; P13: Monitor and obtain the switch noise within the past preset time interval through the noise sensor configured on the switch, and calculate the average to obtain the cumulative switch noise.

[0023] Specifically, the technical solution provided by the present invention is applicable to scenarios such as office computer rooms and factory computer rooms. In these environments, in addition to paying attention to the temperature control of the equipment, the noise problem is also a key factor. Especially in the office environment, noise may affect the work efficiency and comfort of employees. Therefore, by monitoring the temperature and noise and adjusting the heat dissipation control parameters (such as fan speed) in real time, it is possible to reduce noise pollution while ensuring efficient heat dissipation of the equipment, thereby improving the comfort of the overall working environment.

[0024] First, the operating temperature of the switch is monitored in real time by configuring a temperature sensor on the switch. The temperature sensor can regularly collect the current operating temperature data of the device and transmit it to the control system in real time. By obtaining the real-time temperature, the temperature change of the device can be accurately grasped and overheating can be detected in time. The current real-time heat dissipation control parameters of the switch are obtained, where the heat dissipation control parameters include the fan speed. The fan speed is a key factor affecting the heat dissipation performance of the switch. By monitoring the fan speed, the working intensity of the current heat dissipation system can be understood. For example, if the fan speed is low, insufficient heat dissipation may result.

[0025] By configuring a noise sensor on the switch, the switch noise within a preset time interval (such as 10 minutes) in the past is monitored and obtained. The preset time interval can be set according to the actual scenario. The noise sensor will continuously record the noise data around the switch and obtain the cumulative switch noise by calculating the average noise within the past time period (such as 10 minutes).

[0026] P20: Obtain the data transmission records of the switch within a preset time range in the past, perform calculation predictions on future data transmission, obtain predicted data transmission parameters, and perform temperature change predictions and environmental noise predictions in combination with real-time temperature and real-time heat dissipation control parameters to obtain predicted temperature and predicted environmental noise, and calculate the configuration noise coefficient in combination with the accumulated switch noise.

[0027] Further, step P20 of the present invention further includes: P21: Get the data throughput sequence of the switch within the preset time range in the past.

[0028] Specifically, the data throughput sequence of the switch within a preset time range (such as 10 minutes) in the past is obtained. For example, the data throughput record of the switch within the preset time range in the past is obtained through the network interface or monitoring system of the switch. The data throughput is usually expressed in bytes per second (bps). Collecting this data can help analyze the load of the switch in different time periods. Among them, network data transmission in offices or factories has certain regularity. For example, the data throughput may be larger during the peak working hours in the morning and evening, while it is relatively stable at noon or at night. Through historical data analysis, the changing pattern of data transmission can be identified.

[0029] P22: Pre-trained data transmission predictor for predicting future data transmission parameters.

[0030] Further, step P22 of the present invention further includes: P221: Based on the switch operation data in the historical time, a set of sample data throughput sequences is collected, and the data throughput of the switch at future moments after different sample data throughput sequences is collected to obtain a set of sample predicted data throughputs; P222: Using the sample data throughput sequence set and the sample predicted data throughput set, a data transmission predictor is trained according to machine learning, and the test is performed until convergence.

[0031] Specifically, based on the switch operation data in the historical time (such as the last month), the data throughput sequences in different time intervals are collected. The data throughput is usually expressed in bytes or bit rates per second. By collecting the throughput data in a certain period of time in the past (such as the past few hours or days), a series of sample data throughput sequence sets are formed; then the data throughput of the switch at future moments (such as 10 minutes later) after collecting different sample data throughput sequences is set as the sample predicted data throughput, and the sample predicted data throughput set is obtained, where the sample data throughput sequence and the sample predicted data throughput correspond one to one. Among them, the data throughput of the switch within a certain time range has certain rules, such as the amount of data exchanged and transmitted in the office every day is relatively similar. Therefore, the data throughput at future moments can be predicted based on the past data throughput sequence as a parameter for predicting data transmission.

[0032] Then, a data transmission predictor is constructed based on the BP neural network. The data transmission predictor is used to predict the data throughput of the switch at a future moment according to the historical data throughput sequence. By inputting the historical data sequence, the predictor can give the data throughput value for a period of time in the future (for example, 10 minutes later); the data transmission predictor includes an input layer, multiple hidden layers and an output layer, wherein the input data of the input layer is the data throughput sequence, the hidden layer is used for feature conversion and pattern learning, and the output data of the output layer is the predicted data throughput; then, the sample data throughput sequence set and the sample predicted data throughput set are used as training data, and the training data is divided into a training set, a validation set and a test set according to a predetermined ratio, for example, the training set accounts for 70% and is used to train the model and adjust the network weight and bias; the validation set accounts for 20% and is used to adjust the hyperparameters of the model to avoid overfitting; The test set accounts for 10% and is used to evaluate the final performance of the model. The data transmission predictor is further supervised, trained, verified and tested using the sample data throughput sequence as input data and the sample predicted data throughput as supervision data. During the training process, the sample data throughput sequence is used as input data and the sample predicted data throughput is used as supervision data. The neural network will try to predict the future data throughput by learning the relationship between the input data and the target output. In each iteration, the data transmission predictor will calculate the error between the predicted value and the actual target (i.e., the sample predicted data throughput) and use the back propagation algorithm to adjust the network parameters (weights and biases) to optimize the prediction effect. The mean square error (MSE) is used as the loss function to measure the difference between the predicted value and the actual predicted data throughput. The goal is to minimize the loss function so that the model can accurately predict the future data throughput. During the verification process, the error difference between the training set and the verification set is monitored. If the model has a small error on the training set but a large error on the verification set, there may be overfitting, which needs to be optimized by regularization or adjusting the network structure. After the training is completed and verified, the final model is evaluated using the test set. The data in the test set has not been seen before and is used to evaluate the model's generalization ability on unknown data. At this time, the model no longer adjusts parameters, but makes predictions based on the weights obtained from training. The prediction accuracy of the model is evaluated by calculating the error of the model on the test set. If the prediction accuracy meets the expected indicators, the training converges and a trained data transmission predictor is obtained.

[0033] By building a data transmission predictor based on machine learning, the data throughput at future moments can be accurately predicted, providing a scientific basis for subsequent heat dissipation control.

[0034] P23: Input the data throughput sequence into the data transmission predictor to predict the data throughput at a future preset time as a predicted data transmission parameter.

[0035] Specifically, the data throughput sequence is then input into a trained data transmission predictor, which calculates and predicts the data throughput at a preset future moment (such as 10 minutes later), and uses the predicted data throughput as a predicted data transmission parameter. The predicted data throughput is an estimate of the future switch load, which can provide strong data support for the heat dissipation control system, thereby achieving more accurate temperature control and noise control.

[0036] Further, step P20 of the present invention further includes: P24: Obtain the current real-time data throughput of the switch; P25: Collect a sample real-time data throughput set, a sample real-time temperature set, a sample real-time heat dissipation control parameter set, and a sample future data throughput set, and collect the switch temperature at future times under different sample real-time data throughputs, sample real-time temperatures, sample real-time heat dissipation control parameters, and sample future data throughputs to obtain a sample predicted temperature set; P26: Use the sample real-time data throughput set, sample real-time temperature set, sample real-time heat dissipation control parameter set, sample future data throughput set, and sample predicted temperature set to train a temperature change predictor; P27: Input the real-time temperature, real-time data throughput, real-time heat dissipation control parameter, and predicted throughput into the temperature change predictor, and obtain the predicted temperature through prediction output.

[0037] Specifically, a sample real-time data throughput set, a sample real-time temperature set, a sample real-time heat dissipation control parameter set, and a sample future data throughput set are collected, wherein the sample real-time data throughput reflects the real-time data transmission volume (throughput) of the switch at different time points, and these data usually come from the switch's monitoring system, indicating the change in the switch load; the sample real-time temperature reflects the actual working temperature of the switch at different time points, and the temperature data is obtained through the temperature sensor on the switch; the sample real-time heat dissipation control parameter refers to the real-time fan speed of the switch at different time points, and these parameters are collected through the switch's heat dissipation system; the sample future data throughput refers to the data throughput prediction value at a certain time in the future (such as 10 minutes later). Further, the switch temperature at a future time (such as 10 minutes later) under different sample real-time data throughputs, sample real-time temperatures, sample real-time heat dissipation control parameters, and sample future data throughputs is collected as the sample predicted temperature to obtain a sample predicted temperature set.

[0038] Then, a temperature change predictor is constructed based on the BP neural network. The temperature change predictor is a BP neural network model that can be iteratively optimized in machine learning, including an input layer, multiple hidden layers and an output layer. The input data of the input layer are real-time temperature, real-time data throughput, real-time heat dissipation control parameters and predicted throughput, and the output data of the output layer is the predicted temperature. Then, the sample real-time data throughput, sample real-time temperature, sample real-time heat dissipation control parameter, and sample future data throughput are used as input data, and the sample predicted temperature is used as supervision data. The sample real-time data throughput set, sample real-time temperature set, sample real-time heat dissipation control parameter set, sample future data throughput set, and sample predicted temperature set are used as training data to perform supervised training on the temperature change predictor. First, the input data is passed into the input layer, and the weights and activation functions of each hidden layer are calculated to finally obtain the output of the network, that is, the predicted temperature; then, the sample predicted temperature set (that is, the target data) is used to compare with the predicted temperature output by the network to calculate the prediction error. The commonly used error calculation method is the mean square error; then, the gradient of each weight and bias is calculated through the back propagation algorithm, and the network parameters are updated through the gradient descent method. The goal is to minimize the loss function and minimize the prediction error of the network; iterative training is repeated, and the weights and biases in the network are gradually adjusted through forward propagation and back propagation, so that the network can predict the temperature at future moments according to the input data (real-time throughput, temperature, heat dissipation control parameters, and predicted throughput). After multiple rounds of training, the training is stopped until the loss function converges, and the trained temperature change predictor is obtained.

[0039] Then, the current real-time data throughput of the switch is obtained, that is, the current data throughput of the switch is collected in real time through the monitoring system configured on the switch. The data throughput reflects the load situation of the switch and is usually obtained through a network traffic statistics module. The data unit is usually bps (bits per second). The real-time data throughput directly affects the heat dissipation demand of the switch. The larger the throughput, the heavier the load of the switch, and the more heat will be generated. Then, the real-time temperature, real-time data throughput, real-time heat dissipation control parameters and predicted throughput are input into the temperature change predictor, and the predicted output obtains the predicted temperature. The predicted temperature reflects the estimated temperature of the switch at a future time under given load, heat dissipation configuration and environmental conditions.

[0040] P28: Perform environmental noise prediction based on the predicted data transmission parameters to obtain predicted environmental noise.

[0041] Further, step P28 of the present invention further includes: P281: Based on the noise monitoring data in the environment, collect a set of sample prediction data transmission parameters, and collect the average environmental noise in the environment under different sample prediction data transmission parameters to obtain a sample environmental noise set; P282: Construct a mapping relationship between the sample prediction data transmission parameter set and the sample environmental noise set to obtain an environmental noise prediction table; P283: Input the predicted data transmission parameters into the environmental noise prediction table, and obtain the predicted environmental noise by mapping and classification.

[0042] Specifically, based on the noise monitoring data in the environment, the predicted data transmission parameters at different time points are collected to obtain a set of sample predicted data transmission parameters; then the average environmental noise in the environment under different sample predicted data transmission parameters is collected. The average environmental noise is calculated based on historical noise monitoring results, reflecting the noise level in the environment. The data unit is decibel (dB), where different data transmission parameters will lead to different degrees of environmental noise, especially in high-load scenarios such as offices or factories. The average environmental noise is set as the sample environmental noise to obtain a set of sample environmental noise.

[0043] Environmental noise refers to the noise in an office or factory, and switch noise refers to the noise monitored in the area near the switch. The larger the data transmission parameter, the busier the production activities in the office or factory, and the greater the noise in the environment. Based on this, the predicted environmental noise in the environment at the future moment is predicted according to the predicted data transmission parameter.

[0044] The decision tree is a commonly used classification and regression model that classifies or predicts input data through a series of conditional judgments. Then, a mapping relationship between sample prediction data transmission parameters and sample environmental noise is established. Based on the principle of decision tree, the sample prediction data transmission parameters are used as child nodes, the corresponding sample environmental noise is used as the leaf node of the child node, and the sample prediction data transmission parameter set and the sample environmental noise set are used as training data to construct an environmental noise prediction table. The training process is as follows: first, by calculating the feature importance of each prediction data transmission parameter, the parameter that can most effectively distinguish environmental noise is selected as the split node of the decision tree; then, according to the selected split feature, the training data set is divided, and each divided subset corresponds to a specific prediction data transmission parameter value; then, for each leaf node, the corresponding environmental noise value is assigned. These noise values ​​come from the sample environmental noise set, and the mean or weighted average can be used to represent the environmental noise value of the leaf node.

[0045] Finally, the predicted data transmission parameters are input into the environmental noise prediction table for matching, and the predicted data transmission parameters are matched with the corresponding environmental noise by looking up the corresponding entries in the table, and the predicted environmental noise is obtained by mapping and classification.

[0046] Further, step P20 of the present invention further includes: P29: Obtain the historical average noise in the environment; P210: Calculate the configuration noise coefficient according to the accumulated switch noise, the historical average noise and the predicted environmental noise, as shown in the following formula: ; in, is the noise coefficient, is the historical average noise, is the cumulative switch noise, To predict the environmental noise.

[0047] Specifically, first, obtain the historical average noise in the environment, that is, the average environmental noise in the past period of time (such as the last month). Then, according to the accumulated switch noise, the historical average noise and the predicted environmental noise, calculate the configuration noise coefficient, which is the ratio of the historical average noise to the sum of the accumulated switch noise and the predicted environmental noise. The noise coefficient is used to configure the degree of attention to noise control in the subsequent optimization of heat dissipation control parameters. Among them, the greater the accumulated switch noise, the greater the predicted environmental noise, indicating that the noise that the personnel in the office or factory have recently received and the noise in the future environment are greater, and the stronger the personnel's acceptance of noise in the future, the smaller the noise coefficient, and when optimizing the heat dissipation control parameters in the future, the less attention is paid to noise control, and more attention is paid to temperature control; when the noise coefficient is large, it indicates that the noise tolerance in the environment is low, and stronger noise control is required during optimization, that is, more consideration should be given to noise control when adjusting the heat dissipation control parameters; when the noise coefficient is small, it indicates that the noise tolerance in the environment is high, and more emphasis can be placed on temperature control during optimization, reducing the adjustment of noise control.

[0048] Among them, when the predicted data transmission parameters are larger, the busier the production activities are, and the greater the predicted environmental noise is, it is more important to ensure the stable operation of the switch, pay more attention to the temperature in its heat dissipation control, and pay less attention to the noise control in the heat dissipation control, the smaller the noise coefficient.

[0049] P30: According to the predicted temperature and noise coefficient, the real-time heat dissipation control parameters are optimized and adjusted to obtain the optimal heat dissipation control parameters and perform heat dissipation control, wherein the optimization step size is configured according to the variation range between the predicted temperature and the real-time temperature.

[0050] Further, step P30 of the present invention further includes: P31: Calculate the temperature deviation amplitude between the predicted temperature and the real-time temperature as the optimization step length; P32: Use the optimization step length to adjust the real-time heat dissipation control parameter to obtain the first heat dissipation control parameter; P33: Combine the first heat dissipation control parameter with the real-time temperature, real-time data throughput, and predicted throughput and input it into the temperature change predictor, and predict the output to obtain the first control temperature; P34: Obtain the first switch noise under the first heat dissipation control parameter, and calculate the heat dissipation control fitness according to the first control temperature and noise coefficient, as shown in the following formula: ; in, To control the adaptability of heat dissipation, is the first control temperature, is the standard temperature, is the noise coefficient, is a small real number, avoiding the denominator being 0, For the first switch noise, is standard noise; P35: continue to use the optimization step size to optimize and adjust the first heat dissipation control parameter until convergence, output the optimal heat dissipation control parameter with the maximum heat dissipation control fitness, and perform heat dissipation control.

[0051] Specifically, first, the temperature deviation amplitude between the predicted temperature and the real-time temperature is calculated, and the temperature deviation amplitude is the ratio of the temperature difference between the predicted temperature and the real-time temperature to the real-time temperature, and the temperature deviation amplitude is used as the optimization step size, wherein, if the temperature deviation is small, it indicates that the current temperature is close to the target value, and the heat dissipation control can be fine-tuned to ensure that the switch operates at the optimal temperature; if the temperature deviation is large, it indicates that the current temperature and the target temperature are far apart, and a larger adjustment is required, and the fan speed is increased to quickly reduce the temperature. Then, the real-time heat dissipation control parameter is adjusted using the optimization step size, such as multiplying the real-time heat dissipation control parameter by 1 plus the sum of the optimization step size to obtain a first heat dissipation control parameter. Then, the first heat dissipation control parameter is combined with the real-time temperature, real-time data throughput, and predicted throughput and input into the temperature change predictor for temperature prediction, and the first control temperature is output.

[0052] Further obtain the first switch noise under the first heat dissipation control parameter, that is, the noise generated by the switch under the use of the first heat dissipation control parameter, which can be obtained by historical data query; then construct a heat dissipation control fitness evaluation function, and use the heat dissipation control fitness evaluation function to calculate the first heat dissipation control fitness according to the first switch noise, the first control temperature and the noise coefficient, wherein the heat dissipation control fitness is an indicator used to measure the current heat dissipation control effect, comprehensively considering the two factors of temperature control and noise control, and the larger the value, the better the adaptability.

[0053] Then continue to use the optimization step size to optimize and adjust the first heat dissipation control parameter to obtain the second heat dissipation control parameter, and calculate the second heat dissipation fitness of the second heat dissipation control parameter; continue to iteratively adjust the heat dissipation control parameter and calculate the control fitness until a predetermined number of iterations is reached, then the optimization converges, and multiple heat dissipation control parameters and corresponding multiple heat dissipation control fitnesses are obtained, and the heat dissipation control parameter corresponding to the maximum heat dissipation control fitness is selected as the optimal heat dissipation control parameter; finally, heat dissipation control is performed according to the optimal heat dissipation control parameter.

[0054] By calculating and optimizing the heat dissipation control adaptability, the heat dissipation control parameters can be dynamically adjusted under the premise of considering the two factors of temperature and noise, and finally the optimal heat dissipation control settings are obtained. The recent switch noise and future environmental noise are introduced to calculate the noise coefficient, and the heat dissipation control optimization is performed considering the user's sensitivity to noise. This method can not only effectively improve the heat dissipation efficiency of the switch, but also reduce noise pollution, ensure the efficient and stable operation of the equipment, and at the same time ensure that the noise in the environment will not affect the staff or equipment.

[0055] The heat dissipation control method for a domestic switch provided by an embodiment of the present invention has at least the following technical effects: The current real-time temperature, real-time heat dissipation control parameters and accumulated switch noise of the switch are obtained through monitoring; then the data transmission record of the switch within the preset time range in the past is obtained, and future data transmission calculation prediction is performed to obtain the predicted data transmission parameters; then the temperature change prediction and environmental noise prediction are performed according to the predicted data transmission parameters, real-time temperature and real-time heat dissipation control parameters to obtain the predicted temperature and predicted environmental noise, and the configuration noise coefficient is calculated in combination with the accumulated switch noise; finally, the real-time heat dissipation control parameters are optimized and adjusted according to the predicted temperature and noise coefficient to obtain the optimal heat dissipation control parameters and perform heat dissipation control; the above method can improve the accuracy and rationality of the heat dissipation control parameter setting, realize the dual optimization of temperature control and noise control, avoid excessive heat dissipation or insufficient heat dissipation, thereby effectively improving the heat dissipation efficiency, while reducing noise pollution, and ensuring efficient and stable operation of the equipment.

[0056] Embodiment 2, as Figure 2As shown, based on the same inventive concept as the heat dissipation control method for a domestic switch provided in Example 1, an embodiment of the present invention further provides a heat dissipation control system for a domestic switch, including: a state data monitoring and acquisition module 10, used to monitor and obtain the current real-time temperature, real-time heat dissipation control parameters and accumulated switch noise of the switch; a state change data prediction module 20, used to obtain the data transmission record of the switch within a preset time range in the past, perform calculation prediction of future data transmission, obtain predicted data transmission parameters, and perform temperature change prediction and environmental noise prediction in combination with the real-time temperature and real-time heat dissipation control parameters to obtain predicted temperature and predicted environmental noise, and calculate the configuration noise coefficient in combination with the accumulated switch noise; a heat dissipation control parameter optimization module 30, used to optimize and adjust the real-time heat dissipation control parameters according to the predicted temperature and noise coefficient, obtain optimal heat dissipation control parameters, and perform heat dissipation control, wherein the optimization step size is configured according to the change amplitude of the predicted temperature and the real-time temperature.

[0057] Furthermore, the heat dissipation control system for a domestically produced switch is also used to: monitor and obtain the real-time temperature of the switch through a temperature sensor configured on the switch; obtain the current real-time heat dissipation control parameters of the switch, wherein the heat dissipation control parameters include the fan speed; monitor and obtain the switch noise within a preset time interval in the past through a noise sensor configured on the switch, and calculate the average to obtain the cumulative switch noise.

[0058] Furthermore, the heat dissipation control system for a domestically produced switch is also used to: obtain a data throughput sequence of the switch within a preset time range in the past; pre-train a data transmission predictor for predicting future data transmission parameters; input the data throughput sequence into the data transmission predictor, and predict the data throughput at a preset time in the future as a predicted data transmission parameter.

[0059] Furthermore, the heat dissipation control system for domestic switches is also used to: collect a set of sample data throughput sequences based on switch operation data in historical time, and collect the data throughput of the switch at future moments after different sample data throughput sequences to obtain a set of sample predicted data throughputs; use the sample data throughput sequence set and the sample predicted data throughput set to train a data transmission predictor based on machine learning, and perform testing until convergence.

[0060] Furthermore, the heat dissipation control system for a domestic switch is also used to: obtain the current real-time data throughput of the switch; collect a sample real-time data throughput set, a sample real-time temperature set, a sample real-time heat dissipation control parameter set, and a sample future data throughput set, and collect the switch temperature at future times under different sample real-time data throughputs, sample real-time temperatures, sample real-time heat dissipation control parameters, and sample future data throughputs to obtain a sample predicted temperature set; use the sample real-time data throughput set, sample real-time temperature set, sample real-time heat dissipation control parameter set, sample future data throughput set, and sample predicted temperature set to train a temperature change predictor; input the real-time temperature, real-time data throughput, real-time heat dissipation control parameter, and predicted throughput into the temperature change predictor, and predict the output to obtain the predicted temperature; perform environmental noise prediction based on the predicted data transmission parameters to obtain predicted environmental noise.

[0061] Furthermore, the heat dissipation control system for domestic switches is also used to: collect a set of sample predicted data transmission parameters based on noise monitoring data in the environment, and collect the average environmental noise in the environment under different sample predicted data transmission parameters to obtain a sample environmental noise set; construct a mapping relationship between the sample predicted data transmission parameter set and the sample environmental noise set to obtain an environmental noise prediction table; input the predicted data transmission parameters into the environmental noise prediction table, and obtain the predicted environmental noise by mapping and classification.

[0062] Furthermore, the heat dissipation control system for a domestic switch is also used to: obtain the historical average noise in the environment; and calculate the configuration noise coefficient according to the accumulated switch noise, the historical average noise and the predicted environmental noise, as shown in the following formula: ; in, is the noise coefficient, is the historical average noise, is the cumulative switch noise, To predict the environmental noise.

[0063] Furthermore, the heat dissipation control system for a domestic switch is also used to: calculate the temperature deviation amplitude between the predicted temperature and the real-time temperature as an optimization step; use the optimization step to adjust the real-time heat dissipation control parameter to obtain a first heat dissipation control parameter; input the first heat dissipation control parameter into the temperature change predictor in combination with the real-time temperature, the real-time data throughput, and the predicted throughput, and predict the output to obtain a first control temperature; obtain the first switch noise under the first heat dissipation control parameter, and calculate the heat dissipation control fitness according to the first control temperature and the noise coefficient, as shown in the following formula: ; in, To control the adaptability of heat dissipation, is the first control temperature, is the standard temperature, is the noise coefficient, is a small real number, For the first switch noise, is standard noise; continue to use the optimization step size to optimize and adjust the first heat dissipation control parameter until convergence, output the optimal heat dissipation control parameter with the maximum heat dissipation control fitness, and perform heat dissipation control.

[0064] Embodiment 3, based on the same inventive concept of a heat dissipation control method for a domestic switch provided in Embodiment 1, an embodiment of the present invention further provides a switch, and when the switch is working, heat dissipation can be regulated by a heat dissipation control method for a domestic switch described in any one of Embodiment 1.

[0065] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0066] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. A heat dissipation control method for a domestic switch, characterized in that the method include: Monitor and obtain the current real-time temperature, real-time heat dissipation control parameters and accumulated switch noise of the switch; Obtain the data transmission records of the switch within a preset time range in the past, perform calculation and prediction of future data transmission, obtain predicted data transmission parameters, and perform temperature change prediction and environmental noise prediction in combination with real-time temperature and real-time heat dissipation control parameters to obtain predicted temperature and predicted environmental noise, and calculate the configuration noise coefficient in combination with the accumulated switch noise; According to the predicted temperature and noise coefficient, the real-time heat dissipation control parameters are optimized and adjusted to obtain the optimal heat dissipation control parameters and perform heat dissipation control, wherein the optimization step size is configured according to the variation range between the predicted temperature and the real-time temperature.

2. The heat dissipation control method for a domestic switch according to claim 1, characterized in that: Monitor and obtain the current real-time temperature, real-time cooling control parameters, and accumulated switch noise of the switch, including: Monitor and obtain the real-time temperature of the switch through the temperature sensor configured on the switch; Obtain the current real-time heat dissipation control parameters of the switch, where the heat dissipation control parameters include fan speed; By configuring a noise sensor on the switch, the switch noise within a preset time interval in the past is monitored and the average is calculated to obtain the cumulative switch noise.

3. The heat dissipation control method for a domestic switch according to claim 1, characterized in that: Obtaining data transmission records of the switch within a preset time range in the past and making future data transmission predictions, including: Obtain the data throughput sequence of the switch within a preset time range in the past; Pre-training a data transmission predictor for predicting future data transmission parameters; The data throughput sequence is input into the data transmission predictor to predict the data throughput at a future preset time as a predicted data transmission parameter.

4. The heat dissipation control method for a domestic switch according to claim 3, characterized in that: Pre-training a data transmission predictor for predicting future data transmission parameters, including: According to the switch operation data in the historical time, a set of sample data throughput sequences is collected, and the data throughput of the switch at the future time after different sample data throughput sequences is collected to obtain a set of sample predicted data throughput; The sample data throughput sequence set and the sample predicted data throughput set are used to train a data transmission predictor based on machine learning, and the training is performed until convergence.

5. The heat dissipation control method for a domestic switch according to claim 1, characterized in that: Perform temperature change prediction and environmental noise prediction to obtain predicted temperature and predicted environmental noise, including: Get the current real-time data throughput of the switch; Collect a sample real-time data throughput set, a sample real-time temperature set, a sample real-time heat dissipation control parameter set, and a sample future data throughput set, and collect the switch temperature at a future time under different sample real-time data throughputs, sample real-time temperatures, sample real-time heat dissipation control parameters, and sample future data throughputs to obtain a sample predicted temperature set; Using the sample real-time data throughput set, the sample real-time temperature set, the sample real-time heat dissipation control parameter set, the sample future data throughput set and the sample predicted temperature set, to train a temperature change predictor; Input the real-time temperature, real-time data throughput, real-time heat dissipation control parameter and predicted throughput into a temperature change predictor, and output the prediction to obtain a predicted temperature; According to the predicted data transmission parameters, environmental noise prediction is performed to obtain predicted environmental noise.

6. The heat dissipation control method for a domestic switch according to claim 5, characterized in that: According to the predicted data transmission parameters, environmental noise prediction is performed to obtain predicted environmental noise, including: According to the noise monitoring data in the environment, a sample prediction data transmission parameter set is collected, and the average environmental noise in the environment under different sample prediction data transmission parameters is collected to obtain a sample environmental noise set; Constructing a mapping relationship between the sample prediction data transmission parameter set and the sample environmental noise set to obtain an environmental noise prediction table; The predicted data transmission parameters are input into the environmental noise prediction table, and the predicted environmental noise is obtained by mapping the classification.

7. The heat dissipation control method for a domestic switch according to claim 1, characterized in that: Calculate the configured noise figure, including: Get the historical average noise in the environment; According to the accumulated switch noise, historical average noise and predicted environmental noise, the configuration noise coefficient is calculated as follows: ； in, is the noise coefficient, is the historical average noise, is the cumulative switch noise, To predict the environmental noise.

8. The heat dissipation control method for a domestic switch according to claim 5, characterized in that: According to the predicted temperature and noise coefficient, the real-time heat dissipation control parameters are optimized and adjusted to obtain the optimal heat dissipation control parameters and perform heat dissipation control, including: Calculating the temperature deviation between the predicted temperature and the real-time temperature as an optimization step; Using the optimization step length, adjusting the real-time heat dissipation control parameter to obtain a first heat dissipation control parameter; The first heat dissipation control parameter is combined with the real-time temperature, the real-time data throughput, and the predicted throughput and input into the temperature change predictor, and the prediction output is used to obtain a first control temperature; The noise of the first switch under the first heat dissipation control parameter is obtained, and the heat dissipation control adaptability is calculated according to the first control temperature and the noise coefficient, as shown in the following formula: ； in, To control the adaptability of heat dissipation, is the first control temperature, is the standard temperature, is the noise coefficient, is a small real number, For the first switch noise, is the standard noise; Continue to use the optimization step size to optimize and adjust the first heat dissipation control parameter until convergence, output the optimal heat dissipation control parameter with the maximum heat dissipation control fitness, and perform heat dissipation control.

9. A heat dissipation control system for a domestic switch, characterized in that: The steps for implementing the heat dissipation control method for a domestic switch as described in any one of claims 1 to 8 include: The status data monitoring and acquisition module is used to monitor and obtain the current real-time temperature, real-time heat dissipation control parameters and accumulated switch noise of the switch; A state change data prediction module is used to obtain the data transmission records of the switch within a preset time range in the past, perform calculation predictions on future data transmission, obtain predicted data transmission parameters, and perform temperature change prediction and environmental noise prediction in combination with real-time temperature and real-time heat dissipation control parameters, obtain predicted temperature and predicted environmental noise, and calculate the configuration noise coefficient in combination with the accumulated switch noise; The heat dissipation control parameter optimization module is used to optimize and adjust the real-time heat dissipation control parameters according to the predicted temperature and noise coefficient, obtain the optimal heat dissipation control parameters, and perform heat dissipation control, wherein the optimization step size is configured according to the change range of the predicted temperature and the real-time temperature.

10. A switch, characterized in that: When the switch is working, heat dissipation can be regulated by a heat dissipation control method for a domestic switch as described in any one of claims 1 to 8.

Images