A load monitoring method, apparatus and equipment based on multi-level data

Abstract

This invention relates to the field of load monitoring technology, and discloses a load monitoring method, apparatus, and device based on multi-level data. The method includes: acquiring system load data at multiple time granularities at the current moment; calculating the average value and standard deviation of the load data at each time granularity; determining the weight of the load data at each time granularity based on the standard deviation; fusing the average value, standard deviation, and weight of the load data at each time granularity to obtain the comprehensive load data of the industrial data acquisition computer system at the current moment, and continuing to determine the comprehensive load data for the next moment. This invention, through multi-time granularity data acquisition and analysis, can more comprehensively and accurately monitor the system load, reducing misjudgments and omissions. The dynamic adjustment mechanism of the weights improves flexibility, and the comprehensive load data avoids resource waste or insufficiency, improving the overall efficiency and performance of the system.

Description

Technical Field

[0001] This invention relates to the field of load monitoring technology, and specifically to a load monitoring method, apparatus, and equipment based on multi-level data. Background Technology

[0002] An industrial data acquisition computer system is a computer system specifically designed to collect, process, and store data from industrial equipment, sensors, and other automated systems. It is widely used in various industries, including manufacturing, energy, transportation, and logistics. Load fluctuations are common in industrial data acquisition computer systems, and the system's operating efficiency and service quality are directly affected by these load changes. To ensure the system's stability and efficiency under different load conditions, accurate load monitoring is necessary to adjust resource allocation promptly based on load conditions.

[0003] Existing load monitoring methods typically rely on data analysis at a single time granularity, that is, periodically collecting system load data at preset time intervals (such as every minute or every hour). This method is simple and easy to implement, but lacks flexibility. Although it helps to understand the load situation in a specific period, it cannot comprehensively reflect the load change trend of the entire system, resulting in insufficient sensitivity to load changes. Consequently, it cannot respond to resource allocation demands under high load conditions in a timely manner, affecting the overall performance of the system. Summary of the Invention

[0004] In view of this, the present invention provides a load monitoring method, apparatus and equipment based on multi-level data to solve the problem that existing load monitoring methods cannot fully reflect load change trends, and the accuracy and flexibility of load monitoring are low, resulting in the inability to accurately allocate resources.

[0005] In a first aspect, the present invention provides a load monitoring method based on multi-level data, the method comprising:

[0006] At the current moment, acquire load data of the industrial data acquisition computer system at multiple time granularities;

[0007] Calculate the mean and standard deviation of the load data at each time granularity;

[0008] The weights corresponding to the load data at each time granularity are determined based on the standard deviation of the load data at each time granularity.

[0009] The average value, standard deviation, and weight of the load data at each time granularity are fused to obtain the comprehensive load data of the industrial data acquisition computer system at the current moment, and then the comprehensive load data for the next moment is determined.

[0010] This invention provides a load monitoring method based on multi-level data. By acquiring load data at different time granularities, it can comprehensively reflect the system's load status from multiple time dimensions, avoiding the bias and errors caused by a single time granularity, and improving the accuracy of the overall assessment. Then, the average value and standard deviation of the load data at each time granularity are calculated. The average value reflects the average load level at a certain time granularity, while the standard deviation describes the degree of load fluctuation. The weight of each time granularity is determined based on the standard deviation, and the weights are dynamically adjusted according to load fluctuations. Finally, the average value, standard deviation, and weights are fused to obtain comprehensive load data, which not only reflects the average load level but also takes into account fluctuations and their relative importance, providing a more comprehensive and accurate load monitoring result, which helps the system to allocate resources rationally. Through multi-time granularity data acquisition and analysis, the system's load status can be monitored more comprehensively and accurately, reducing misjudgments and omissions. The dynamic adjustment mechanism of weights improves flexibility, and the comprehensive load data avoids resource waste or insufficiency, improving the overall efficiency and performance of the system.

[0011] In one optional implementation, the weights corresponding to the load data at each time granularity are determined based on the standard deviation of the load data at each time granularity, including:

[0012] Obtain the preset fluctuation threshold, the preset basic weight coefficient and the threshold sensitivity coefficient corresponding to each time granularity;

[0013] If the standard deviation of the load data at any time granularity is greater than the preset fluctuation threshold, the preset basic weight coefficient corresponding to the time granularity is increased based on the preset fluctuation threshold, the standard deviation corresponding to the time granularity, and the threshold sensitivity coefficient to obtain the initial weight corresponding to the load data at the time granularity.

[0014] If the standard deviation of the load data at any time granularity is not greater than the preset fluctuation threshold, based on the preset fluctuation threshold, the standard deviation corresponding to the time granularity, and the threshold sensitivity coefficient, the preset basic weight coefficient corresponding to the time granularity is reduced to obtain the initial weight corresponding to the load data at the time granularity.

[0015] With all initial weights corresponding to the load data at all time granularities being positive, the initial weights corresponding to the load data at each time granularity are standardized to obtain the weights corresponding to the load data at each time granularity.

[0016] This invention provides a load monitoring method based on multi-level data. By dynamically adjusting the weights, it can more accurately reflect the load situation at each time granularity, avoid the deviation caused by a single static weight, and introduce a threshold sensitivity coefficient, so that the weights can be flexibly adjusted according to the actual situation to adapt to different load modes and application scenarios, thereby improving the accuracy of load monitoring.

[0017] In one alternative implementation, the method further includes:

[0018] If the initial weight of the load data at any time granularity is negative, the initial weight of the load data at any time granularity will be set to the preset weight value.

[0019] This invention provides a load monitoring method based on multi-level data, which improves the accuracy of load monitoring by preventing negative weights and ensuring that the weights at each time granularity are reasonable.

[0020] In one optional implementation, assuming the initial weights corresponding to the load data at all time granularities are positive, the initial weights corresponding to the load data at each time granularity are standardized to obtain the weights corresponding to the load data at each time granularity, including:

[0021] The sum of the initial weights corresponding to the load data at all time granularities is determined as the weight sum value;

[0022] The ratio of the initial weight to the sum of weights for the load data at each time granularity is used as the new weight for the load data at each time granularity.

[0023] This invention provides a load monitoring method based on multi-level data. By standardizing the weights, the rationality of the weights is ensured, avoiding excessively large or small weights at certain time granularities, thereby improving the accuracy of load monitoring.

[0024] In one optional implementation, the average value, standard deviation, and weight of the load data at each time granularity are fused to obtain the comprehensive load data of the industrial data acquisition computer system at the current moment, including:

[0025] For each time granularity, determine the product of the threshold sensitivity coefficient and the standard deviation corresponding to the time granularity;

[0026] Determine the sum of the product and the average value of the load data at the time granularity;

[0027] The sum is multiplied by the weights of the load data at the time granularity, and the result of the load analysis at the time granularity is taken as the result.

[0028] The sum of the load analysis results corresponding to all time granularities is determined as the comprehensive load data.

[0029] This invention provides a load monitoring method based on multi-level data. By integrating the average value, standard deviation, and weight, it can comprehensively analyze the load situation at multiple time granularities to obtain comprehensive load data that reflects the overall load situation, thereby improving the accuracy of load monitoring.

[0030] In one alternative implementation, at the current moment, the load data of the industrial data acquisition computer system at multiple time granularities is acquired, including:

[0031] Based on the current time, and according to the preset data acquisition cycle, load data of the industrial data acquisition computer system is acquired for multiple time intervals. Each time interval corresponds to a time granularity, and the interval lengths of multiple time intervals increase sequentially.

[0032] This invention provides a load monitoring method based on multi-level data. By acquiring load data at different time granularities, it can provide richer information for monitoring load change trends, avoid the one-sidedness caused by a single time granularity, and improve the accuracy and flexibility of load monitoring.

[0033] In one alternative implementation, the method further includes:

[0034] Based on the comprehensive load data of the industrial data acquisition computer system at the current moment, the system can adjust resource allocation.

[0035] This invention provides a load monitoring method based on multi-level data. By adjusting resource allocation in real time based on comprehensive load data at the current moment, it can quickly respond to sudden high loads and ensure the overall performance of the system.

[0036] Secondly, the present invention provides a load monitoring device based on multi-level data, the device comprising:

[0037] The acquisition module is used to acquire load data of the industrial data acquisition computer system at multiple time granularities at the current moment;

[0038] The calculation module is used to calculate the average and standard deviation of the load data at each time granularity;

[0039] The determination module is used to determine the weight of the load data at each time granularity based on the standard deviation of the load data at each time granularity.

[0040] The fusion module is used to fuse the load data based on the average value, standard deviation, and weight of the load data at each time granularity to obtain the comprehensive load data of the industrial data acquisition computer system at the current moment.

[0041] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the load monitoring method based on multi-level data described in the first aspect or any corresponding embodiment thereof.

[0042] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the load monitoring method based on multi-level data described in the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0043] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0044] Figure 1 This is a flowchart of a load monitoring method based on multi-level data according to an embodiment of the present invention;

[0045] Figure 2 This is a flowchart of another load monitoring method based on multi-level data according to an embodiment of the present invention;

[0046] Figure 3 This is a structural block diagram of a load monitoring device based on multi-level data according to an embodiment of the present invention;

[0047] Figure 4 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of 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, 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.

[0049] Existing load monitoring methods typically rely on data analysis at a single time granularity, which lacks flexibility. While helpful in understanding load conditions during specific periods, they fail to comprehensively reflect the overall load change trend of the system, resulting in insufficient sensitivity to load changes. Consequently, they cannot respond promptly to resource allocation demands under high load conditions, impacting overall system performance. This invention provides a load monitoring method based on multi-level data. Through multi-time granularity data collection and analysis, it can more comprehensively and accurately monitor system load conditions, reducing misjudgments and omissions. The dynamic weight adjustment mechanism improves flexibility, and by integrating load data, it can avoid resource waste or insufficiency, improving the overall efficiency and performance of the system.

[0050] According to an embodiment of the present invention, a load monitoring method based on multi-level data is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0051] This embodiment provides a load monitoring method based on multi-level data, which can be used in terminals such as computers. Figure 1 This is a flowchart of a load monitoring method based on multi-level data according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0052] Step S101: At the current moment, acquire the load data of the industrial data acquisition computer system at multiple time granularities.

[0053] Specifically, the load data includes the system's CPU (Central Processing Unit) usage, memory usage, and network bandwidth usage. Related technologies monitor system load by analyzing data at a single time granularity, such as hourly or daily data. However, this approach cannot handle load fluctuations, leading to inaccurate load analysis and impacting system resource allocation. Therefore, this invention uses the current moment as a benchmark to acquire load data at multiple time granularities. This provides a more comprehensive understanding of load change trends, helps identify load fluctuations, and thus enables more accurate load monitoring.

[0054] Step S102: Calculate the mean and standard deviation of the load data at each time granularity.

[0055] Specifically, by calculating the statistical characteristics of the load data at each time granularity, this embodiment of the invention uses the average value and standard deviation as examples to illustrate, which can help to understand the load level and its fluctuation at each time granularity, and help to understand the load change trend and monitor the load situation more accurately.

[0056] Step S103: Determine the weight of the load data at each time granularity based on the standard deviation of the load data at each time granularity.

[0057] Specifically, since different time granularities and their corresponding standard deviations have different degrees of influence on load fluctuations, the larger the standard deviation, the more severe the load fluctuations. Therefore, a corresponding weight is determined for the load data at each time granularity to improve the accuracy of load monitoring.

[0058] Step S104: Based on the average value, standard deviation and weight of the load data at each time granularity, the comprehensive load data of the industrial data acquisition computer system at the current moment is fused to obtain the comprehensive load data of the next moment.

[0059] Specifically, load data from different time granularities at the current moment are merged to obtain comprehensive load data that reflects the overall load level of the system. Load monitoring continues at the next time moment, enabling continuous load monitoring of the system. This comprehensive load data integrates load data from different time granularities, providing a complete and balanced load assessment. It avoids the biases inherent in single time granularities, allowing the system to accurately allocate resources and ensure system performance.

[0060] This invention provides a load monitoring method based on multi-level data. By acquiring load data at different time granularities, it can comprehensively reflect the system's load status from multiple time dimensions, avoiding the bias and errors caused by a single time granularity, and improving the accuracy of the overall assessment. Then, the average value and standard deviation of the load data at each time granularity are calculated. The average value reflects the average load level at a certain time granularity, while the standard deviation describes the degree of load fluctuation. The weight of each time granularity is determined based on the standard deviation, and the weights are dynamically adjusted according to load fluctuations. Finally, the average value, standard deviation, and weights are fused to obtain comprehensive load data, which not only reflects the average load level but also takes into account fluctuations and their relative importance, providing a more comprehensive and accurate load monitoring result, which helps the system to allocate resources rationally. Through multi-time granularity data acquisition and analysis, the system's load status can be monitored more comprehensively and accurately, reducing misjudgments and omissions. The dynamic adjustment mechanism of weights improves flexibility, and the comprehensive load data avoids resource waste or insufficiency, improving the overall efficiency and performance of the system.

[0061] This embodiment provides a load monitoring method based on multi-level data, which can be used in the aforementioned terminals. Figure 2 This is a flowchart of another load monitoring method based on multi-level data according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0062] Step S201: At the current moment, acquire the load data of the industrial data acquisition computer system at multiple time granularities.

[0063] Specifically, step S201 includes:

[0064] Step S2011: Based on the current time, according to the preset data acquisition cycle, acquire load data of multiple time intervals of the industrial data acquisition computer system. Each time interval corresponds to a time granularity, and the interval length of multiple time intervals increases sequentially.

[0065] Specifically, we will use multiple time intervals of 1 hour, 1 day, 7 days, and 30 days as examples, corresponding to hourly, daily, weekly, and monthly time granularities, respectively. Assuming the current time is 11:24 AM on November 30, 2024, the hourly time interval is 10:24 AM; the daily time interval is from 11:24 AM on November 29 to 11:24 AM on November 30; the weekly time interval is from 11:24 AM on November 24 to 11:24 AM on November 30; and the monthly time interval is from 11:24 AM on November 1 to 11:24 AM on November 30. Assuming the preset data collection cycle for load data is 5 minutes, meaning system load data is collected every five minutes, the collected load data is summarized according to the above four time intervals to obtain the load data for each time granularity.

[0066] Step S202: Calculate the mean and standard deviation of the load data at each time granularity.

[0067] Specifically, assuming the preset data collection period for load data is 5 minutes, that is, the system load data is collected once every 5 minutes, and each time granularity usually includes multiple preset data collection periods. Therefore, for each time granularity, the load situation at each time granularity is represented by calculating the average value and standard deviation of the load data at that time granularity. For the hourly time granularity, the corresponding average value and standard deviation are obtained by the following formula (1); for the daily time granularity, the corresponding average value and standard deviation are obtained by the following formula (2); for the weekly time granularity, the corresponding average value and standard deviation are obtained by the following formula (3); for the monthly time granularity, the corresponding average value and standard deviation are obtained by the following formula (4).

[0068]

[0069] Among them, Avg hour This represents the average load data at the hourly time granularity; N represents the number of preset data collection periods included in the hourly time granularity; Load i σ represents the load data collected during the i-th preset data acquisition cycle; hour This represents the standard deviation of the load data at the hourly time granularity.

[0070]

[0071] Among them, Avg day This represents the average load data at the daily time granularity; Avg hour,j The average load data for the j-th hour can be obtained using equation (1) above; σ day This represents the standard deviation of the load data at the daily time granularity.

[0072]

[0073] Among them, Avg week This represents the average load data at a weekly time granularity; Avg day,k The average load data for day k can be obtained from equation (2) above; σ week This represents the standard deviation of the load data at the weekly time granularity.

[0074]

[0075] Among them, Avg month This represents the average load data at a monthly time granularity; Avg day,m The average load data for day m can be obtained from equation (2) above; σ month This represents the standard deviation of the load data at the monthly time granularity.

[0076] Step S203: Determine the weight of the load data at each time granularity based on the standard deviation of the load data at each time granularity.

[0077] Specifically, step S203 includes:

[0078] Step S2031: Obtain the preset fluctuation threshold, the preset basic weight coefficient and the threshold sensitivity coefficient corresponding to each time granularity.

[0079] Specifically, the preset fluctuation threshold is used to measure whether load fluctuation is normal. If the standard deviation is greater than this value, the load fluctuation is considered strong, and the weight of the load fluctuation needs to be increased based on the preset basic weight coefficient corresponding to the time granularity. If the standard deviation is less than this value, the load fluctuation is considered mild, and the weight of the load fluctuation needs to be decreased based on the preset basic weight coefficient corresponding to the time granularity. The preset basic weight coefficient represents the initial value of the influence of each time granularity on the load fluctuation. The threshold sensitivity coefficient is used to adjust the influence of the standard deviation on the weight. Optionally, all three values ​​are preset values ​​and can be adaptively adjusted according to actual conditions. Different values ​​can be preset for different application scenarios to improve the flexibility of load monitoring.

[0080] Step S2032: If the standard deviation of the load data at any time granularity is greater than the preset fluctuation threshold, based on the preset fluctuation threshold, the standard deviation corresponding to the time granularity, and the threshold sensitivity coefficient, the preset basic weight coefficient corresponding to the time granularity is increased to obtain the initial weight corresponding to the load data at any time granularity.

[0081] Specifically, when the standard deviation of the load data at any time granularity is greater than the preset fluctuation threshold, that is, the load data fluctuates greatly, the weight corresponding to that time granularity is increased to give it a more important position in the comprehensive load assessment. Optionally, the initial weight corresponding to the load data at each time granularity can be obtained by the following formula (5). First, determine the difference between the standard deviation and the preset fluctuation threshold. Then, multiply the difference by the threshold sensitivity coefficient corresponding to the time granularity to obtain the first product. Finally, add the first product to the preset basic weight coefficient corresponding to the time granularity to obtain the initial weight.

[0082] ω time =base time +k time (σ time -σ threshold (5)

[0083] Where, ω time The base represents the initial weight corresponding to the load data at any given time granularity; time This represents the preset basic weight coefficient corresponding to this time granularity; k time This represents the threshold sensitivity coefficient corresponding to this time granularity; σ time σ represents the standard deviation of the load data at this time granularity. threshold This indicates the preset fluctuation threshold.

[0084] Step S2033: If the standard deviation of the load data at any time granularity is not greater than the preset fluctuation threshold, based on the preset fluctuation threshold, the standard deviation corresponding to the time granularity, and the threshold sensitivity coefficient, reduce the preset basic weight coefficient corresponding to the time granularity to obtain the initial weight corresponding to the load data at any time granularity.

[0085] Specifically, when the standard deviation of the load data at any time granularity is not greater than the preset fluctuation threshold, that is, the load data fluctuation is small, the influence of the weight corresponding to that time granularity in the comprehensive load assessment is reduced by decreasing the weight of that time granularity. Optionally, the initial weight corresponding to the load data at each time granularity can be obtained by the following formula (6). First, determine the difference between the preset fluctuation threshold and the standard deviation. Then, multiply the difference by the threshold sensitivity coefficient corresponding to that time granularity to obtain the second product. Finally, subtract the second product from the preset basic weight coefficient corresponding to that time granularity to obtain the initial weight.

[0086] ω time =base time -k time (σ threshold -σ time (6)

[0087] Where, ω time The base represents the initial weight corresponding to the load data at any given time granularity; time This represents the preset basic weight coefficient corresponding to this time granularity; k time This represents the threshold sensitivity coefficient corresponding to this time granularity; σ time σ represents the standard deviation of the load data at this time granularity. threshold This indicates the preset fluctuation threshold.

[0088] Step S2034: If the initial weights of the load data at all time granularities are positive, standardize the initial weights of the load data at each time granularity to obtain the weights of the load data at each time granularity.

[0089] In some optional implementations, step S2034 above includes:

[0090] Step a1: Determine the sum of the initial weights corresponding to the load data at all time granularities as the weight sum.

[0091] Specifically, taking the four time granularities in step S201 above as an example, the sum of the four initial weights is determined by the following formula (7).

[0092] ω total =ω hour +ω day +ω week +ωmonth (7)

[0093] Where, ω total Represents the weights and values; ω hour ω represents the initial weight corresponding to the hourly time granularity; day This represents the initial weight corresponding to the daily time granularity; ω week This represents the initial weight corresponding to the weekly time granularity; ω month This represents the initial weight corresponding to the monthly time granularity.

[0094] Step a2: The ratio of the initial weight to the sum of weights of the load data at each time granularity is used as the weight of the load data at each time granularity.

[0095] Specifically, refer to equation (8) below, where the ratio of each initial weight to the sum is used as the weight corresponding to the load data at each time granularity. By standardizing the initial weights corresponding to the load data at each time granularity, the sum of the weights is made to 1, which facilitates subsequent comprehensive analysis.

[0096]

[0097] Where, Normalizedω time ω represents the standardized weights of the initial weights at any given time granularity. time This represents the initial weight corresponding to this time granularity; ω total This represents the sum of the initial weights corresponding to all time granularities.

[0098] Step S2035: If the initial weight of the load data at any time granularity is negative, set the initial weight of the load data at any time granularity to a preset weight value.

[0099] Specifically, if the initial weight calculated in steps S2033 and / or S2035 is negative, the initial weight is set to 0 or other preset values ​​so that the weight result meets the actual application requirements, ensures that the weights of all time granularities are within a reasonable range, and avoids outliers from interfering with the load monitoring results.

[0100] In some optional implementations, taking the four time intervals assumed in step S201 as an example, four corresponding time granularities are obtained, assuming a preset fluctuation threshold of 150; the standard deviation of the load data at the hourly time granularity is 180, the preset basic weight coefficient is 0.4, and the threshold sensitivity coefficient is 0.05; the standard deviation of the load data at the daily time granularity is 140, the preset basic weight coefficient is 0.3, and the threshold sensitivity coefficient is 0.03; the standard deviation of the load data at the weekly time granularity is 130, the preset basic weight coefficient is 0.2, and the threshold sensitivity coefficient is 0.02; and the standard deviation of the load data at the monthly time granularity is 150, the preset basic weight coefficient is 0.1, and the threshold sensitivity coefficient is 0.01. Using equation (5) or (6) above, we can obtain the initial weights corresponding to the load data at the hourly time granularity as 0.4 + 0.05 × (180 - 150) = 1.9; the initial weights corresponding to the load data at the daily time granularity as 0.3 + 0.03 × (160 - 150) = 0.6; the initial weights corresponding to the load data at the weekly time granularity as 0.2 - 0.02 × (150 - 140) = 0; and the initial weights corresponding to the load data at the monthly time granularity as 0.1 - 0.01 × (150 - 130) = -0.1 = 0 (when the initial weights are negative, they are set to the preset weight value of 0). Thus, the sum of the above four initial weights is 2.5. By standardizing them using equation (8) above, we obtain the weights corresponding to the load data at the hourly time granularity as 0.76; the weights corresponding to the load data at the daily time granularity as 0.24; the weights corresponding to the load data at the weekly time granularity as 0; and the weights corresponding to the load data at the monthly time granularity as 0.

[0101] Step S204: Based on the average value, standard deviation and weight of the load data at each time granularity, the comprehensive load data of the industrial data acquisition computer system at the current moment is fused to obtain the comprehensive load data of the next moment.

[0102] Specifically, step S204 includes:

[0103] Step S2041: For each time granularity, determine the product of the threshold sensitivity coefficient and the standard deviation corresponding to the time granularity.

[0104] Step S2042: Determine the sum of the product and the average value of the load data at the time granularity.

[0105] Step S2043: The sum of the values ​​and the weights of the load data at the time granularity are used as the load analysis result at the time granularity.

[0106] Specifically, based on the standardized weights, averages, standard deviations, and preset threshold sensitivity coefficients of the load data at each time granularity, the load analysis results of the load data obtained at each granularity are obtained through the following formula (9).

[0107] θ time =Normalizedω time ×(Avg time +k time ×σ time (9)

[0108] Where, θ time This represents the load analysis results at any time granularity; Normalizedω time This represents the standardized weights for that time granularity; Avg time This represents the average value of the load data at this time granularity; k time This represents the threshold sensitivity coefficient corresponding to this time granularity; σ time This represents the standard deviation of the load data at this time granularity.

[0109] Step S2044: The sum of the load analysis results corresponding to all time granularities is determined as the comprehensive load data.

[0110] Specifically, taking four time granularities as an example, the load analysis results of the four time granularities are fused using the following formula (10) to obtain comprehensive load data. By considering multiple time granularities for comprehensive analysis, the overall load fluctuation at the current moment can be accurately reflected. Furthermore, weights are introduced during the comprehensive analysis process to highlight the influence of important time granularities and improve the accuracy of load monitoring.

[0111] θ final =θ hour +θ day +θ week +θ month (10)

[0112] Where, θ final Represents the overall load data; θ hour This represents the load analysis results corresponding to the hourly time granularity; θ day This represents the load analysis results corresponding to each day's time granularity; θ week This represents the load analysis results corresponding to the weekly time granularity; θ month This represents the load analysis results corresponding to the monthly time granularity.

[0113] Step S207: Based on the comprehensive load data of the industrial data acquisition computer system at the current moment, the industrial data acquisition computer system adjusts its resource allocation.

[0114] Specifically, comprehensive load data is a dynamic value obtained by integrating load data from multiple time granularities, such as hourly, daily, weekly, and monthly. It reflects the system's load status in real time, allowing the system to adaptively adjust resource allocation based on this comprehensive load data. This enables better adaptation to different load environments, especially accurate resource allocation under high load conditions. If the comprehensive load data is high, the system can automatically increase resources (such as CPU and memory) to cope with the upcoming high load. If the current comprehensive load data is low, the system can reduce unnecessary resource consumption, saving costs. Through continuous monitoring and adjustment, the system can quickly respond to load changes and ensure stable performance.

[0115] This invention provides a load monitoring method based on multi-level data. By acquiring load data at different time granularities, it can comprehensively reflect the system's load status from multiple time dimensions, avoiding the bias and errors caused by a single time granularity, and improving the accuracy of the overall assessment. Then, the average value and standard deviation of the load data at each time granularity are calculated. The average value reflects the average load level at a certain time granularity, while the standard deviation describes the degree of load fluctuation. The weight of each time granularity is determined based on the standard deviation, and the weights are dynamically adjusted according to load fluctuations. Finally, the average value, standard deviation, and weights are fused to obtain comprehensive load data, which not only reflects the average load level but also takes into account fluctuations and their relative importance, providing a more comprehensive and accurate load monitoring result, which helps the system to allocate resources rationally. Through multi-time granularity data acquisition and analysis, the system's load status can be monitored more comprehensively and accurately, reducing misjudgments and omissions. The dynamic adjustment mechanism of weights improves flexibility, and the comprehensive load data avoids resource waste or insufficiency, improving the overall efficiency and performance of the system.

[0116] This embodiment also provides a load monitoring device based on multi-level data, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0117] This embodiment provides a load monitoring device based on multi-level data, such as... Figure 3 As shown, it includes:

[0118] The acquisition module 301 is used to acquire load data of the industrial data acquisition computer system at multiple time granularities at the current moment.

[0119] The calculation module 302 is used to calculate the average value and standard deviation of the load data at each time granularity.

[0120] The determination module 303 is used to determine the weight corresponding to the load data at each time granularity based on the standard deviation of the load data at each time granularity.

[0121] The fusion module 304 is used to fuse the load data based on the average value, standard deviation and weight of the load data at each time granularity to obtain the comprehensive load data of the industrial data acquisition computer system at the current moment, and to continue to determine the comprehensive load data at the next moment.

[0122] In some alternative implementations, the determining module 303 includes:

[0123] The first acquisition unit is used to acquire the preset fluctuation threshold, the preset basic weight coefficient and the threshold sensitivity coefficient corresponding to each time granularity.

[0124] The first adjustment unit is used to increase the preset basic weight coefficient corresponding to the time granularity based on the preset fluctuation threshold, the standard deviation of the time granularity and the threshold sensitivity coefficient when the standard deviation of the load data at any time granularity is greater than the preset fluctuation threshold, so as to obtain the initial weight corresponding to the load data at the time granularity.

[0125] The second adjustment unit is used to reduce the preset basic weight coefficient corresponding to the time granularity based on the preset fluctuation threshold, the standard deviation of the load data at any time granularity and the threshold sensitivity coefficient, so as to obtain the initial weight corresponding to the load data at any time granularity, provided that the standard deviation of the load data at any time granularity is not greater than the preset fluctuation threshold.

[0126] The standardization unit is used to standardize the initial weights of the load data at each time granularity, assuming that the initial weights of the load data at all time granularities are positive, so as to obtain the weights of the load data at each time granularity.

[0127] In some alternative embodiments, the device further includes:

[0128] The third weight determination module is used to set the initial weight corresponding to the load data at any time granularity to a preset weight value when the initial weight corresponding to the load data at any time granularity is negative.

[0129] In some alternative implementations, the standardization unit includes:

[0130] The first weight determination sub-unit is used to determine the sum of the initial weights corresponding to the load data at all time granularities as the weight sum value.

[0131] The second weight determination sub-unit is used to take the ratio of the initial weight to the sum of weights of the load data at each time granularity as the new weight corresponding to the load data at each time granularity.

[0132] In some alternative implementations, the fusion module 304 includes:

[0133] The first determining unit is used to determine the product of the threshold sensitivity coefficient and the standard deviation corresponding to each time granularity.

[0134] The second determining unit is used to determine the sum of the product and the average value of the load data at the time granularity.

[0135] The third determining unit is used to multiply the sum by the weight of the load data at the time granularity as the result of the load analysis at the time granularity.

[0136] The fourth determination unit is used to determine the sum of the load analysis results corresponding to all time granularities as the comprehensive load data.

[0137] In some optional implementations, the acquisition module 301 includes:

[0138] The second acquisition unit is used to acquire load data of the industrial data acquisition computer system for multiple time intervals based on the current time and according to a preset data acquisition cycle. Each time interval corresponds to a time granularity, and the interval lengths of the multiple time intervals increase sequentially.

[0139] In some alternative embodiments, the device further includes:

[0140] The adjustment module is used to adjust the resource allocation of the industrial data acquisition computer system based on the comprehensive load data of the industrial data acquisition computer system at the current moment.

[0141] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0142] In this embodiment, the load monitoring device based on multi-level data is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0143] This invention also provides a computer device having the above-described features. Figure 3 The load monitoring device shown is based on multi-level data.

[0144] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 Take a processor 10 as an example.

[0145] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0146] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0147] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function. The data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, which can be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0148] Memory 20 may include volatile memory, such as random access memory. Memory may also include non-volatile memory, such as flash memory, hard disk, or solid-state drive. Memory 20 may also include combinations of the above types of memory.

[0149] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 4 Taking the example of a connection between China and Israel via a bus.

[0150] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0151] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc. Further, the storage medium may also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0152] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0153] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A load monitoring method based on multi-level data, characterized in that, The method includes: At the current moment, acquire load data of the industrial data acquisition computer system at multiple time granularities; Calculate the mean and standard deviation of the load data at each time granularity; The weights corresponding to the load data at each time granularity are determined based on the standard deviation of the load data at each time granularity. The average value, standard deviation, and weight of the load data at each time granularity are fused to obtain the comprehensive load data of the industrial data acquisition computer system at the current moment, and then the comprehensive load data for the next moment is determined. The step of determining the weight corresponding to the load data at each time granularity based on the standard deviation of the load data at each time granularity includes: Obtain a preset fluctuation threshold, a preset basic weight coefficient corresponding to each time granularity, and a threshold sensitivity coefficient. The threshold sensitivity coefficient is used to adjust the degree of influence of the standard deviation on the weight. If the standard deviation of the load data at any time granularity is greater than the preset fluctuation threshold, based on the preset fluctuation threshold, the standard deviation corresponding to the time granularity, and the threshold sensitivity coefficient, the preset basic weight coefficient corresponding to the time granularity is increased to obtain the initial weight corresponding to the load data at the time granularity. If the standard deviation of the load data at any time granularity is not greater than the preset fluctuation threshold, based on the preset fluctuation threshold, the standard deviation corresponding to the time granularity, and the threshold sensitivity coefficient, the preset basic weight coefficient corresponding to the time granularity is reduced to obtain the initial weight corresponding to the load data at the time granularity. With the initial weights corresponding to the load data at all time granularities being positive, the initial weights corresponding to the load data at each time granularity are standardized to obtain the weights corresponding to the load data at each time granularity. The average value, standard deviation, and weight of the load data at each time granularity are fused to obtain the comprehensive load data of the industrial data acquisition computer system at the current moment, including: For each time granularity, determine the product of the threshold sensitivity coefficient and the standard deviation corresponding to the time granularity; Determine the sum of the product and the average value of the load data at the time granularity; The product of the sum and the weight of the load data at the time granularity is taken as the load analysis result at the time granularity. The sum of the load analysis results corresponding to all time granularities is determined as the comprehensive load data.

2. The method according to claim 1, characterized in that, The method further includes: If the initial weight corresponding to the load data at any time granularity is negative, the initial weight corresponding to the load data at that time granularity is set to a preset weight value.

3. The method according to claim 1, characterized in that, When the initial weights corresponding to the load data at all time granularities are positive, the initial weights corresponding to the load data at each time granularity are standardized to obtain the weights corresponding to the load data at each time granularity, including: The sum of the initial weights corresponding to the load data at all time granularities is determined as the weight sum value; The ratio of the initial weight corresponding to the load data at each time granularity to the sum of the weights is used as the weight corresponding to the load data at each time granularity.

4. The method according to claim 1, characterized in that, The acquisition of load data from the industrial data acquisition computer system at multiple time granularities at the current moment includes: Based on the current time, and according to a preset data acquisition cycle, load data of the industrial data acquisition computer system is acquired for multiple time intervals. Each time interval corresponds to a time granularity, and the interval lengths of the multiple time intervals increase sequentially.

5. The method according to claim 1, characterized in that, The method further includes: Based on the comprehensive load data of the industrial data acquisition computer system at the current moment, the industrial data acquisition computer system adjusts resource allocation.

6. A load monitoring device based on multi-level data, characterized in that, The device includes: The acquisition module is used to acquire load data of the industrial data acquisition computer system at multiple time granularities at the current moment; The calculation module is used to calculate the average and standard deviation of the load data at each time granularity; The determination module is used to determine the weight of the load data at each time granularity based on the standard deviation of the load data at each time granularity. The fusion module is used to fuse the load data based on the average value, standard deviation and weight of the load data at each time granularity to obtain the comprehensive load data of the industrial data acquisition computer system at the current time, and to continue to determine the comprehensive load data at the next time. The determining module includes: The first acquisition unit is used to acquire a preset fluctuation threshold, a preset basic weight coefficient and a threshold sensitivity coefficient corresponding to each time granularity, wherein the threshold sensitivity coefficient is used to adjust the degree of influence of the standard deviation on the weight. The first adjustment unit is used to, when the standard deviation of the load data at any time granularity is greater than the preset fluctuation threshold, increase the preset basic weight coefficient corresponding to the time granularity based on the preset fluctuation threshold, the standard deviation corresponding to the time granularity, and the threshold sensitivity coefficient, to obtain the initial weight corresponding to the load data at the time granularity. The second adjustment unit is used to reduce the preset basic weight coefficient corresponding to the time granularity based on the preset fluctuation threshold, the standard deviation of the load data at any time granularity and the threshold sensitivity coefficient, so as to obtain the initial weight corresponding to the load data at the time granularity, provided that the standard deviation of the load data at any time granularity is not greater than the preset fluctuation threshold. The standardization unit is used to standardize the initial weights of the load data at each time granularity, given that the initial weights of the load data at all time granularities are positive, so as to obtain the weights of the load data at each time granularity. The fusion module includes: The first determining unit is used to determine, for each time granularity, the product of the threshold sensitivity coefficient and the standard deviation corresponding to the time granularity; The second determining unit is used to determine the sum of the product and the average value of the load data at the time granularity; The third determining unit is used to multiply the sum by the weight of the load data at the time granularity as the load analysis result at the time granularity. The fourth determining unit is used to determine the sum of the load analysis results corresponding to all time granularities as the comprehensive load data.

7. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the load monitoring method based on multi-level data as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the load monitoring method based on multi-level data as described in any one of claims 1 to 5.

Images