A power management method for a computer wireless local area network module

Abstract

The present application relates to wireless LAN power management technical field, specifically, it is a kind of computer wireless LAN module power management method.It includes the network equipment management software is collected network traffic data and application state data, and utilizes autoregressive moving average model to construct flow prediction model, defines network traffic fuzzy set and application requirement fuzzy set, and establishes fuzzy rule, determines input membership degree, and according to rule trigger intensity calculates output membership degree, utilizes gravity method and converts fuzzy mode membership degree into specific voltage parameter, and regulates and controls power supply.The present application constructs flow prediction model, utilizes clustering analysis method, dynamically adjusts the working mode of wireless LAN module, then utilizes gravity method and converts fuzzy mode membership degree into specific voltage parameter, realizes the fine control of power management to wireless LAN module, reduces power consumption.

Description

Technical Field

[0001] This invention relates to the field of wireless local area network (WLAN) power management technology, and more specifically, to a power management method for a computer WLAN module. Background Technology

[0002] A computer's wireless LAN module is a hardware component that enables a computer to connect to a local area network wirelessly. Its main function is to receive and send wireless signals, allowing the computer to communicate with wireless routers or other wireless access points. The wireless LAN module is a relatively power-intensive component; when it is working, especially during high-intensity data transmission or continuous searching for nearby wireless networks, it consumes a significant amount of power. Effective power management can reduce the power consumption of the wireless LAN module when wireless network usage is not required, thereby extending the device's battery life and optimizing system resources and performance.

[0003] Currently, power management of computer wireless LAN modules is simply achieved through power gating circuits. When the wireless LAN module is idle, the power gating circuit cuts off the power supply to some circuits of the module. When there is a new data transmission demand, the power supply is quickly restored to start the corresponding circuits. This method cannot adjust the working mode of the wireless LAN module according to the amount of data transmission, resulting in energy consumption. In order to enable real-time power management of the wireless LAN module based on network traffic data and application status data, and to specifically adjust the relevant power parameters to improve energy efficiency while ensuring the normal operation of the computer, we propose a power management method for computer wireless LAN modules. Summary of the Invention

[0004] The purpose of this invention is to solve the problem that when a computer's wireless LAN module performs power management, it cannot adjust the working mode of the wireless LAN module according to the amount of data transmission. In order to enable real-time power management of the wireless LAN module based on network traffic data and application status data, and to specifically adjust the relevant power parameters, the working mode of the wireless LAN can be dynamically adjusted to improve energy efficiency.

[0005] To achieve the above objectives, the present invention provides a power management method for a computer wireless local area network module, comprising the following steps:

[0006] S1. Use network device management software to collect network traffic data and application status data, and use an autoregressive moving average model to build a traffic prediction model.

[0007] S2. Define the fuzzy set of network traffic and the fuzzy set of application requirements, and establish fuzzy rules;

[0008] S3. Determine the input membership degree based on the collected network traffic data and application requirement data, and calculate the output membership degree based on the rule trigger strength;

[0009] S4. Use the centroid method to convert the fuzzy mode membership into specific voltage parameters and regulate the power supply.

[0010] As a further improvement to this technical solution, step S1 utilizes an autoregressive moving average model to construct a traffic prediction model, and the method steps are as follows:

[0011] S1.1.1 Data Cleaning and Processing: The historical network traffic data collected from the wireless LAN module is cleaned, and the data is stabilized using the differential method.

[0012] S1.1.2 Determine model parameters: Use the autocorrelation function to determine the autoregressive order p of the model, use the Yule-Walker equation to determine the moving average order q, and use the autocorrelation function plot and the partial autocorrelation function plot to determine the difference order d;

[0013] S1.1.3 Model Fitting: The least squares method is used to estimate the model parameters and to test whether the model residuals satisfy the white noise assumption.

[0014] S1.1.4, Flow Forecasting Stage: Flow forecasting is performed using a well-fitted autoregressive moving average model, the formula of which is:

[0015]

[0016] in, Y is an autoregressive operator, θ(B) is a moving regression operator, B is a lag operator, and Y is a moving regression operator. t For time series data, ε t is white noise, and d is the difference order.

[0017] As a further improvement to this technical solution, step S1.1.2 uses the autocorrelation function to determine the autoregressive order p of the model, and the formula is as follows:

[0018]

[0019] Where, p k Let y be the autoregressive order with a lag of k periods, T be the length of the time series, and y be the autoregressive order with a lag of k periods. t It is a time series. For time series y t The mean of y, where k is the lag period, and y t-k It is a time series from k to t.

[0020] As a further improvement to this technical solution, when fitting the model in S1.1.3, the Shapiro-Wilk test is used to check the normality of the residuals. If the residuals do not conform to a normal distribution, the model parameters are adjusted.

[0021] As a further improvement to this technical solution, the method and steps for establishing fuzzy rules in step S2 are as follows:

[0022] S2.1.1 Clustering Analysis Process: The K-Means clustering algorithm is used to cluster network traffic data and application requirement data;

[0023] S2.1.2 Defining the range of fuzzy sets: Analyze each cluster to determine the network state it represents, and determine the range of fuzzy sets based on the data distribution of cluster centers and members;

[0024] S2.1.3 Establish fuzzy rules: Establish fuzzy rules based on the network state represented by the cluster and the actual power management requirements, and refine the rules by incorporating device state factors.

[0025] As a further improvement to this technical solution, in the S2.1.1 cluster analysis process, the elbow rule is used to determine the appropriate number of clusters, measure the relationship between the density of clusters and the number of clusters, and find the turning point where the cluster change trend changes from a sharp decline to a gradual decline.

[0026] As a further improvement to this technical solution, the method for determining the input membership degree in step S3 is as follows:

[0027] S3.1.1 Determine the parameters of the Gaussian membership function: use the statistical mean of the variables corresponding to the fuzzy set as the center position of the Gaussian membership function, and use the standard deviation of the fuzzy set data to determine the width of the Gaussian membership function;

[0028] S3.1.2 Calculate the trigger strength of the rule: Determine the membership degree of network traffic and application requirements in the corresponding fuzzy set, and select the minimum value of the input membership degree as the trigger strength of the rule;

[0029] S3.1.3 Calculate the output membership degree: When a rule is triggered, determine the membership degree of the output fuzzy set based on the conclusion of the rule.

[0030] As a further improvement to this technical solution, when determining the Gaussian membership function parameters in step S3.1.1, the standard deviation is adjusted by the expected rate of change of membership degree, thereby adjusting the shape of the membership function.

[0031] As a further improvement to this technical solution, when calculating the output membership degree in S3.1.3, if there are multiple rules affecting the membership degree of the output fuzzy set, the maximum value method is used to determine the final output membership degree.

[0032] As a further improvement to this technical solution, the S4 membership degree is converted into specific voltage parameters. This is achieved by calculating the contribution of each fuzzy set to the power supply parameters and obtaining the final voltage according to the voltage conversion formula, which is as follows:

[0033]

[0034] Where V is voltage, V min The minimum value of the lower limit of the voltage range among all modes, ∑ i μ i C is the sum of all membership degrees. i The voltage contribution is represented by n, which is the number of membership degrees.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0036] 1. The power management method of the computer wireless LAN module collects network traffic data and application status data through network device management software, and uses an autoregressive moving average model to build a traffic prediction model to predict the computer's traffic usage. Based on the predicted network traffic and application requirements, the range of the corresponding fuzzy set is dynamically adjusted using cluster analysis, and corresponding fuzzy rules are established. Then, the working mode of the wireless LAN module is dynamically adjusted according to the transmission of traffic data.

[0037] 2. Determine the input membership degree based on the collected network traffic data and application requirement data, calculate the output membership degree according to the rule trigger strength, and then use the centroid method to convert the fuzzy pattern membership degree into specific voltage parameters. Adjust the power supply and regulate the voltage of the wireless LAN module to a specific value through power distribution, so as to realize fine control of power management of the wireless LAN module and reduce power consumption. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the method flow of the present invention;

[0039] Figure 2 This is a schematic diagram of the process flow of step S1 of the present invention;

[0040] Figure 3 This is a schematic diagram of the S2 step of the present invention;

[0041] Figure 4 This is a schematic diagram of the S3 step of the present invention. Detailed Implementation

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Currently, when managing the power of a computer's wireless LAN module, it is not possible to adjust the operating mode of the wireless LAN module according to the amount of data transmitted. In order to enable real-time management of the power of the wireless LAN module based on network traffic data and application status data, and to specifically adjust the relevant power parameters, the operating mode of the wireless LAN can be dynamically adjusted to improve energy efficiency.

[0044] Therefore, this invention proposes to collect network traffic data and application status data through network device management software, construct a traffic prediction model using an autoregressive moving average model, define fuzzy sets of network traffic and application demand, establish fuzzy rules, determine input membership degrees based on the collected network traffic data and application demand data, calculate output membership degrees based on rule trigger strength, and use the centroid method to convert fuzzy mode membership degrees into specific voltage parameters to regulate the power supply, thereby achieving refined control of power management for wireless LAN modules and reducing power consumption.

[0045] Specifically as follows:

[0046] Please see Figure 1 As shown, the present invention provides a power management method for a computer wireless local area network module, comprising the following steps:

[0047] S1. Use network device management software to collect network traffic data and application status data, and use an autoregressive moving average model to build a traffic prediction model.

[0048] S2. Define the fuzzy set of network traffic and the fuzzy set of application requirements, and establish fuzzy rules;

[0049] S3. Determine the input membership degree based on the collected network traffic data and application requirement data, and calculate the output membership degree based on the rule trigger strength;

[0050] S4. Use the centroid method to convert the fuzzy mode membership into specific voltage parameters and regulate the power supply.

[0051] like Figure 2 As shown, S1 uses an autoregressive moving average model to construct a traffic prediction model, and the method steps are as follows:

[0052] S1.1.1 Data Cleaning and Processing: The historical network traffic data collected from the wireless LAN module is cleaned, and the data is stabilized using the differential method.

[0053] S1.1.2 Determine model parameters: Use the autocorrelation function to determine the autoregressive order p of the model, use the Yule-Walker equation to determine the moving average order q, and use the autocorrelation function plot and the partial autocorrelation function plot to determine the difference order d;

[0054] S1.1.3 Model Fitting: The least squares method is used to estimate the model parameters and to test whether the model residuals satisfy the white noise assumption.

[0055] S1.1.4, Flow Forecasting Stage: Flow forecasting is performed using a well-fitted autoregressive moving average model, the formula of which is:

[0056]

[0057] in, Y is an autoregressive operator, θ(B) is a moving regression operator, B is a lag operator, and Y is a moving regression operator. t For time series data, ε t is white noise, and d is the difference order.

[0058] Collect historical network traffic data from the wireless LAN module. This data should be arranged in time series, for example, recording the size of network traffic (data transmission volume, number of data packets, etc.) at fixed time intervals (such as every minute, every 5 minutes, etc.). The time span of the collected data should be long enough to include different network usage scenarios and traffic patterns, such as collecting data from at least the past week or month.

[0059] Data cleaning removes outliers, which may be caused by network failures, temporary high-load applications, or monitoring errors. Outliers can be identified through statistical methods. For example, if the difference between a data point and its neighboring data points exceeds a certain multiple of the standard deviation, the data point is considered an outlier and is handled appropriately (such as replacing it with the average of the neighboring data points).

[0060] To ensure data stationarity, network traffic data may exhibit non-stationary characteristics such as seasonality or trends. A common method is differencing. For example, perform first-order differencing on the original data (i.e., subtract the previous data point from the next data point) and observe whether the differencing data is stationary. If it is still not stationary, continue with second-order differencing or other suitable transformations until the data becomes stationary. Stationary data is more easily processed by autoregressive moving average models.

[0061] To more accurately determine the autoregressive order p, section S1.1.2 uses the autocorrelation function to determine the autoregressive order p of the model, with the following formula:

[0062]

[0063] Where, p k Let y be the autoregressive order with a lag of k periods, T be the length of the time series, and y be the autoregressive order with a lag of k periods. t It is a time series. For time series y t The mean of y, where k is the lag period, and y t-k It is a time series from k to t.

[0064] Suppose we have a simple time series, y = [y1, y2, y3, y4, y5]. First, calculate its mean:

[0065]

[0066] Calculate the autocorrelation coefficient p1 for lag k=1, the numerator is When t=2 Similarly, calculate the scores for each term from t=2 to t=5 and sum them, with the denominator being... Calculate p1 using the autoregression order formula. Repeat the above calculation process for different lag values ​​k to obtain the complete autocorrelation function.

[0067] For a p-order autoregressive model, in, ε is the autoregressive coefficient. t For white noise, according to the Yule-Walker equation, the partial autocorrelation coefficient... The (u-th order partial autocorrelation coefficient) satisfies the following system of equations:

[0068]

[0069] For u = 1, Obtained from the system of equations of order 1 and Similarly, higher-order partial autocorrelation coefficients q can be calculated.

[0070] Once the values ​​of p and q are determined, the selected ARIMA(p,q) model can be used to fit the preprocessed network traffic data. During the fitting process, the least squares method is used to estimate the parameters of the model.

[0071] The goal of the least squares method is to find a set of parameters that minimizes the sum of squared errors between the model's predictions and the actual observations.

[0072] For the linear regression model y = β0 + β1x1 + ... + β n x n +ε, where y is the dependent variable and x i β is the independent variable. i Let be the parameter to be estimated, and ε be the error term. The sum of squared errors is... Where m is the number of samples, y i These are actual observed values. These are the model's predicted values.

[0073] Take the partial derivative with respect to the sum of squared errors:

[0074] Solving the equation yields: The parameters of the model can then be obtained.

[0075] In order to adjust the model parameters, in S1.1.3, when fitting the model, the Shapiro-Wilk test is used to check the normality of the residuals. If the residuals do not conform to the normal distribution, the model parameters are adjusted.

[0076] The Shapiro-Wilk test is a statistical test method that examines whether sample data comes from a normally distributed population. It measures the degree of deviation of the data from a normal distribution by calculating a statistic based on the order and covariance matrix of the sample data. The null hypothesis is that the data follows a normal distribution, and the alternative hypothesis is that the data does not follow a normal distribution.

[0077] If the residual value is greater than the set significance level (usually 0.05), the null hypothesis cannot be rejected, meaning the residuals can be considered to follow a normal distribution. When the value is less than or equal to the significance level, the null hypothesis is rejected, meaning the residuals do not follow a normal distribution. For example, if the residual value is 0.03, it indicates that at the significance level, the residuals do not follow a normal distribution, and further data transformation (such as logarithmic transformation, Box-Cox transformation, etc.) or reconsidering the model specification may be necessary.

[0078] Traffic prediction is performed using a well-fitted ARIMA model. Assuming an ARIMA(p,q) model has been fitted and network traffic data from the past n time points is available, to predict traffic at the next m time points, the past data is first input into the model to obtain its current state. Then, based on the model's equations, the predicted values ​​for the future time points are calculated step by step using the formula:

[0079]

[0080] in Y is an autoregressive operator, θ(B) is a moving regression operator, B is a lag operator, and Y is a moving regression operator. t For time series data, εt The noise is white, and d is the difference order. The predicted values ​​for future time points are obtained using recursive calculations.

[0081] like Figure 3 As shown, S2 establishes fuzzy rules, and the method steps are as follows:

[0082] S2.1.1 Clustering Analysis Process: The K-Means clustering algorithm is used to cluster network traffic data and application requirement data;

[0083] S2.1.2 Defining the range of fuzzy sets: Analyze each cluster to determine the network state it represents, and determine the range of fuzzy sets based on the data distribution of cluster centers and members;

[0084] S2.1.3 Establish fuzzy rules: Establish fuzzy rules based on the network state represented by the cluster and the actual power management requirements, and refine the rules by incorporating device state factors;

[0085] The K-Means clustering algorithm divides the dataset into K clusters, each with a centroid. Normalized network traffic data and related variables are used as input, and the selected clustering algorithm is run. For example, using K-Means to divide the data into 3 clusters, each data point is assigned to a cluster, and the centroid and members of each cluster are obtained. Each cluster is then analyzed to determine the network state it represents. For instance, data points in a cluster might have high data transmission rates, a large number of data packets, and the corresponding device state is screen-on and running high-demand applications; this cluster can be defined as a "high traffic - high demand" fuzzy set.

[0086] The range of the fuzzy set is determined based on the data distribution of cluster centers and members. For the "high traffic-high demand" fuzzy set, taking data transmission rate as an example, the minimum, maximum, and average data transmission rates in the cluster are calculated. If the average is 7MB / s, the minimum is 5MB / s, and the maximum is 10MB / s, this range can be used as the range of the traffic component in the "high traffic-high demand" fuzzy set. A similar method is used to determine the range for other variables (such as application requirements).

[0087] Fuzzy rules are established based on the network state represented by the clusters and the actual power management requirements. For example, for the fuzzy set of "high traffic-high demand", a rule can be established: "If the network state is 'high traffic-high demand', then the wireless LAN module enters active mode".

[0088] In order to more accurately determine the number of clusters, the elbow rule is used in the S2.1.1 cluster analysis process to determine the appropriate number of clusters, measure the relationship between the density of clusters and the number of clusters, and find the turning point where the cluster change trend changes from a sharp decline to a gradual decline.

[0089] The core idea of ​​the elbow rule is to measure the relationship between the density of clusters and the number of clusters. As the number of clusters increases, the data points within each cluster become more compact, and the sum of the distances from each data point to its cluster center (usually measured by the sum of squared errors, SSE) gradually decreases. However, as the number of clusters continues to increase, the rate of decrease in SSE gradually slows down. What we need to find is the turning point where this trend changes from a sharp decrease to a gradual decrease. The number of clusters corresponding to this point is more appropriate, just like the bent position of a person's elbow.

[0090] Choose a range for the number of clusters, usually starting with a small value, such as k=2. For each k value, execute the K-Means clustering algorithm. After each clustering, calculate the sum of squared errors (SSE). Plot a curve with the number of clusters k on the x-axis and the corresponding SSE value on the y-axis. Observe the shape of this curve and find the bend point, i.e., the elbow. At the beginning of the curve, as k increases, the SSE decreases rapidly; after the elbow, the rate of decrease in SSE slows down significantly. The k value corresponding to this elbow is a suitable number of clusters.

[0091] Suppose we have a set of network traffic and device status data for a wireless LAN module. We perform cluster analysis on this data to determine the appropriate number of clusters for the power management mode. When k=2, the calculated SSE is 1000; when k=3, the SSE drops to 600; when k=4, the SSE is 400; when k=5, the SSE is 300; when k=6, the SSE is 250; when k=7, the SSE is 220; and when k=8, the SSE is 200.

[0092] After plotting the curves, it can be observed that the curvature is more pronounced when k=4. From k=4 to k=5, the decrease in SSE is smaller than before. Therefore, according to the elbow rule, a suitable number of clusters might be 4. This means that the data can be divided into 4 clusters to establish fuzzy sets and rules for power management. For example, these 4 clusters might correspond to four different network and device state combinations: high traffic and high demand, high traffic and low demand, low traffic and high demand, and low traffic and low demand, respectively, for subsequent fuzzy inference and power management decisions.

[0093] like Figure 4 As shown, S3 determines the input membership degree, and the method steps are as follows:

[0094] S3.1.1 Determine the parameters of the Gaussian membership function: use the statistical mean of the variables corresponding to the fuzzy set as the center position of the Gaussian membership function, and use the standard deviation of the fuzzy set data to determine the width of the Gaussian membership function;

[0095] S3.1.2 Calculate the trigger strength of the rule: Determine the membership degree of network traffic and application requirements in the corresponding fuzzy set, and select the minimum value of the input membership degree as the trigger strength of the rule;

[0096] S3.1.3 Calculate the output membership degree: When a rule is triggered, determine the membership degree of the output fuzzy set based on the conclusion of the rule;

[0097] Through data collection and analysis, the statistical mean of the variables corresponding to a certain fuzzy set was obtained. This mean can be used as the center position of the Gaussian membership function. For example, for the fuzzy set "high traffic," the average data transmission rate of the network traffic is μ = 5 MB / s. Therefore, the center position of the Gaussian membership function... In this context, μ = 5 MB / s represents the theoretically highest membership level in this fuzzy set.

[0098] The standard deviation of the data is used to determine the width of the function. For example, when calculating the standard deviation δ for "high-traffic" network traffic data, a smaller δ indicates that the data is concentrated around the mean, and the membership function decreases relatively quickly; a larger δ indicates that the data is more dispersed, and the membership function decreases relatively slowly.

[0099] In order to adjust the shape of the membership function, in S3.1.1, when determining the parameters of the Gaussian membership function, the standard deviation is adjusted by the expected rate of change of membership, thereby adjusting the shape of the membership function;

[0100] The rate of change of membership degree describes how quickly the membership degree changes with the variable. In the Gaussian membership function, the rate of change is related to the standard deviation. A smaller standard deviation will cause the membership degree to change rapidly around the mean, while a larger standard deviation will cause the membership degree to change more gradually.

[0101] For example, if we expect the membership degree to decrease from 1 to 0.5 within a range of ±1 MB / s from the mean, we can similarly substitute this into the Gaussian membership function. The δ value can be calculated. Through this calculation, the standard deviation can be adjusted based on the expected rate of change of membership, ensuring the membership function's shape meets requirements. For example, if the obtained δ value is small, it indicates the current membership function is decreasing too rapidly, not meeting the expected rate of change, and needs to be appropriately increased to make the membership change smoother; conversely, if the δ value is large, it needs to be decreased to accelerate the rate of decrease in membership.

[0102] In fuzzy inference, suppose we have a fuzzy rule: "If network traffic is 'high traffic' and application demand is 'high demand,' then the wireless LAN module enters active mode." For each input variable (network traffic and application demand), we first determine their membership degree in their respective fuzzy sets. For example, using the Gaussian membership function, we calculate the membership degree of network traffic for "high traffic" as μ1 = 0.7, and the membership degree of application demand for "high demand" as μ2 = 0.6. The trigger strength of the rule is usually taken as the minimum value of the input membership degree, so the trigger strength of this rule is α = min(μ1, μ2) = 0.6.

[0103] Once a rule is triggered, the membership degree of the output fuzzy set (i.e., the active mode) is determined based on the rule's conclusion. Assuming no other rules previously affected the membership degree of the active mode, the membership degree of the active mode is equal to the rule trigger strength, which is 0.6.

[0104] In order to determine the final output membership degree, when calculating the output membership degree in S3.1.3, if there are multiple rules affecting the membership degree of the output fuzzy set, the maximum value method is used to determine the final output membership degree.

[0105] If multiple rules affect the membership degree of the output fuzzy set—for example, another rule also results in a membership degree of 0.4 for the active mode—these output membership degrees need to be merged. A maximum value method can be used, meaning the final membership degree of the active mode is max(0.6, 0.4). This means that based on the current input and fuzzy rules, the wireless LAN module enters the active mode with a membership degree of 0.6. This membership degree will be used in the subsequent defuzzification process to determine the specific power management parameters.

[0106] To transform membership degrees into specific voltage parameters, specifically S4 membership degrees, the contribution of each fuzzy set to the power supply parameters is calculated, and the final voltage is obtained according to the voltage transformation formula, which is as follows:

[0107]

[0108] Where V is voltage, V min The minimum value of the lower limit of the voltage range among all modes, ∑ i μ i C is the sum of all membership degrees. i The voltage contribution is represented by n, which is the number of membership degrees.

[0109] Through fuzzy reasoning, the membership degree of each sleep mode in the current state is obtained. For example, after calculation, the membership degree of deep sleep mode is μ1 = 0.3, the membership degree of light sleep mode is μ2 = 0.5, and the membership degree of standby mode is μ3 = 0.2, thus determining the minimum value V of the lower voltage limit. min =1.8V, the sum of all membership degrees Substituting the calculated value into the formula yields... The fuzzy sleep mode membership was converted into specific power parameter settings using the center of gravity method. These parameters can be used to configure the power supply of the wireless LAN module to achieve a suitable power management mode.

[0110] In summary, the working principle of this solution is as follows:

[0111] The power management method for this computer wireless LAN module collects network traffic data and application status data through network device management software. It then uses an autoregressive moving average model to construct a traffic prediction model to predict computer traffic usage. Based on the predicted network traffic and application demands, it dynamically adjusts the range of corresponding fuzzy sets using cluster analysis and establishes corresponding fuzzy rules. Furthermore, it dynamically adjusts the working mode of the wireless LAN module based on the transmission of traffic data. It determines the input membership degree based on the collected network traffic data and application demand data, calculates the output membership degree based on the rule trigger strength, and then uses the centroid method to convert the fuzzy mode membership degree into specific voltage parameters for power regulation. Through power allocation, it regulates the voltage of the wireless LAN module to specific values, achieving refined control of the wireless LAN module's power management and reducing energy consumption.

[0112] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A power management method for a computer wireless local area network module, characterized in that: Includes the following steps: S1. Use network device management software to collect network traffic data and application status data, and use an autoregressive moving average model to build a traffic prediction model. S2. Define the fuzzy set of network traffic and the fuzzy set of application requirements, and establish fuzzy rules; S3. Determine the input membership degree based on the collected network traffic data and application requirement data, and calculate the output membership degree based on the rule trigger strength; S4. Use the centroid method to convert the fuzzy mode membership into specific voltage parameters and regulate the power supply. S1 uses an autoregressive moving average model to construct a traffic prediction model, and the method and steps are as follows: S1.1.1 Data Cleaning and Processing: The historical network traffic data collected from the wireless LAN module is cleaned, and the data is stabilized using the differential method. S1.1.2 Determine model parameters: Use the autocorrelation function to determine the autoregressive order p of the model, use the Yule-Walker equation to determine the moving average order q, and use the autocorrelation function plot and the partial autocorrelation function plot to determine the difference order d; S1.1.3 Model Fitting: The least squares method is used to estimate the model parameters and to test whether the model residuals satisfy the white noise assumption. S1.1.4, Flow Forecasting Stage: Flow forecasting is performed using a well-fitted autoregressive moving average model, the formula of which is: in, Y is an autoregressive operator, θ(B) is a moving regression operator, B is a lag operator, and Y is a moving regression operator. t For time series data, ε t The noise is white noise, and d is the difference order. The method for establishing fuzzy rules in step S2 is as follows: S2.1.1 Clustering Analysis Process: The K-Means clustering algorithm is used to cluster network traffic data and application requirement data; S2.1.2 Defining the range of fuzzy sets: Analyze each cluster to determine the network state it represents, and determine the range of fuzzy sets based on the data distribution of cluster centers and members; S2.1.3 Establish fuzzy rules: Establish fuzzy rules based on the network state represented by the cluster and the actual power management requirements, and refine the rules by incorporating device state factors; The S4 membership degree is converted into specific voltage parameters. The final voltage is obtained by calculating the contribution of each fuzzy set to the power supply parameters and applying the voltage conversion formula, which is as follows: Where V is voltage, V min The minimum value of the lower limit of the voltage range among all modes, ∑ i μ i C is the sum of all membership degrees. i The voltage contribution is represented by n, which is the number of membership degrees.

2. The power management method for a computer wireless local area network module according to claim 1, characterized in that: S1.1.2 uses the autocorrelation function to determine the autoregressive order p of the model, and the formula is as follows: Where, p k Let y be the autoregressive order with a lag of k periods, T be the length of the time series, and y be the autoregressive order with a lag of k periods. t It is a time series. For time series y t The mean of y, where k is the lag period, and y t-k It is a time series from k to t.

3. The power management method for a computer wireless local area network module according to claim 1, characterized in that: When fitting the model in S1.1.3, the Shapiro-Wilk test is used to check the normality of the residuals. If the residuals do not conform to a normal distribution, the model parameters are adjusted.

4. The power management method for a computer wireless local area network module according to claim 1, characterized in that: In the S2.1.1 cluster analysis process, the elbow rule is used to determine the appropriate number of clusters, measure the relationship between cluster density and the number of clusters, and find the turning point where the cluster change trend changes from a sharp decline to a gradual decline.

5. The power management method for a computer wireless local area network module according to claim 1, characterized in that: The method for determining the input membership degree in S3 is as follows: S3.1.1 Determine the parameters of the Gaussian membership function: use the statistical mean of the variables corresponding to the fuzzy set as the center position of the Gaussian membership function, and use the standard deviation of the fuzzy set data to determine the width of the Gaussian membership function; S3.1.2 Calculate the trigger strength of the rule: Determine the membership degree of network traffic and application requirements in the corresponding fuzzy set, and select the minimum value of the input membership degree as the trigger strength of the rule; S3.1.3 Calculate the output membership degree: When a rule is triggered, determine the membership degree of the output fuzzy set based on the conclusion of the rule.

6. The power management method for a computer wireless local area network module according to claim 5, characterized in that: When determining the Gaussian membership function parameters in S3.1.1, the standard deviation is adjusted by the expected rate of change of membership degree, thereby adjusting the shape of the membership function.

7. The power management method for a computer wireless local area network module according to claim 5, characterized in that: When calculating the output membership degree in S3.1.3, if multiple rules affect the membership degree of the output fuzzy set, the maximum value method is used to determine the final output membership degree.

Images