An intelligent AI computing power system working state control system

Abstract

The application discloses an intelligent AI computing power system working state control system, relates to the technical field of AI computing power system management, and comprises a data acquisition module, a computing power analysis module, a device prediction module and a device planning module.The data acquisition module is used for collecting data of the previous year operation of the intelligent AI computing power system and classifying the collected data.The technical key points are as follows: the data of the previous year operation of the intelligent AI computing power system is analyzed and processed, and then prediction is carried out, the total computing power Zsl required by the intelligent AI computing power system operation at a future time point of the current year is predicted, and then the number of required devices is analyzed and judged according to the total computing power Zsl, which can help relevant personnel to understand the number of required devices at different time points in the future, can reasonably allocate devices, and can avoid the cases that too many devices are idle or too few standby devices are provided, so that the overall use effect is good, and the application has a good use prospect.

Description

Technical Field

[0001] This invention relates to the field of AI computing power system management technology, specifically to an intelligent AI computing power system working status control system. Background Technology

[0002] Artificial intelligence is an important driving force for the new round of technological revolution and industrial transformation. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

[0003] Artificial intelligence (AI) is an important component of the discipline of intelligence. It attempts to understand the nature of intelligence and to produce a new kind of intelligent machine that can react in a way similar to human intelligence. AI is a very broad science, including robotics, speech recognition, image recognition, natural language processing, expert systems, machine learning, computer vision, and more.

[0004] With the rapid development of artificial intelligence (AI) technology, AI applications are increasingly penetrating various fields, leading to a rapid increase in the demand for high-performance computing resources.

[0005] The existing patent, CN109788008B, entitled "An Application Server Invocation Method and System Based on Nginx," describes a method that includes: using a pre-written shell script to detect the running parameters of application server A; when the running parameters are greater than or equal to a preset threshold, obtaining the running parameters of other application servers in the system, comparing them to determine the most idle application server B, and confirming that the running parameters of application server B are greater than those of application server A; sending a start command to application server B to cause the shell script on application server B to start a pre-deployed application of the same type on application server B; and modifying the Nginx configuration of application server A through the shell script, using Nginx's asynchronous non-blocking event handling mechanism to switch a preset percentage of access traffic from application server A to application server B. This invention can start an idle server to handle some of the access traffic when the performance of the application server degrades, achieving the goal of rational resource utilization.

[0006] However, based on the above content and the existing technology, the central idea of ​​the solution described in the above patent is mainly to determine the operating status of the device, and then determine whether the existing device can support the computing power required for software use based on the operating status of the device.

[0007] However, the above solutions have significant drawbacks in practical use. They are mainly suitable for simple scenarios with minimal data fluctuations. However, most industries experience peak and off-peak seasons, and the amount of data to be processed at different times is very large, with a wide variety of data types. Using the above methods often results in insufficient equipment for software operation or too much equipment being reserved, leading to low overall economic efficiency and failing to meet user requirements. Therefore, we have developed an intelligent AI computing power system working status control system. Summary of the Invention

[0008] (a) Technical problems to be solved

[0009] To address the shortcomings of existing technologies, this invention provides a working status control system for an intelligent AI computing power system. It analyzes and processes data from the previous year's operation of the intelligent AI computing power system, then makes predictions to determine the total computing power Zsl required for the system's operation at future points in the current year. Based on the total computing power Zsl, it analyzes and determines the required number of devices. This helps relevant personnel understand the number of devices needed at different points in the future, enabling reasonable allocation of devices and avoiding situations where too much equipment is idle or insufficient spare equipment. The overall effect is good, and it has promising application prospects.

[0010] (II) Technical Solution

[0011] To achieve the above objectives, the present invention provides the following technical solution:

[0012] A working status control system for an intelligent AI computing power system includes a data acquisition module, a computing power analysis module, an equipment prediction module, and an equipment planning module.

[0013] Data acquisition module: Used to collect data from the previous year's operation of the intelligent AI computing power system and to classify the collected data;

[0014] Computing power analysis module: used to process and analyze the classified data, and calculate the total computing power Zsl required for the intelligent AI computing power system to run at a future time point;

[0015] Equipment prediction module: acquires historical operating data of equipment, analyzes the state value Ztz of equipment at different time points, and calculates the computing power Slx that the equipment can provide at different times based on the state value Ztz;

[0016] Equipment planning module: Obtain the total computing power Zsl required for the operation of the intelligent AI computing power system at a future time point and the computing power Slx that the equipment can provide at different times, analyze the list of equipment required at the future time point, and generate an adjustment plan based on the analysis results.

[0017] This invention discloses a working status control system for an intelligent AI computing power system. It analyzes and processes data from the previous year's operation of the intelligent AI computing power system, then predicts the total computing power Zsl required for the system's operation at future points in the current year. Based on the total computing power Zsl, it analyzes and determines the required number of devices. This helps relevant personnel understand the number of devices needed at different points in the future, enabling reasonable allocation of devices and avoiding situations where too much equipment is idle or too few spares. The overall effect is good, and it has promising application prospects.

[0018] This invention discloses an intelligent AI computing power system working status control system. It acquires historical operating data of the equipment and analyzes the equipment status. It can directly analyze the status value Ztz of the equipment at different time points, and further analyze it to determine the computing power that the equipment can provide at different time points. It analyzes the impact of equipment wear and tear on computing power, which can effectively avoid the situation where the equipment wear and tear causes insufficient computing power to be provided, resulting in the equipment running at high power for a long time and a short service life. Moreover, after calculation, the subsequent allocation of equipment tasks is more reasonable, the use effect is better, and it has good application prospects.

[0019] Preferably, the data collected by the data acquisition module includes the number of model parameters of the intelligent AI computing power system, the time set for model operation, and the amount of data that the system needs to process. The collected data is classified according to the time sequence.

[0020] The preferred formula for calculating the total computing power Zsl required for the operation of the intelligent AI computing system at a future point in time is as follows:

[0021]

[0022] In the formula, The number of model parameters, This represents the ratio of the number of model parameters to the computational complexity of the model. The amount of data the system needs to process. This represents the annual growth rate of the data.

[0023] Preferably, the steps for acquiring historical operating data of the equipment and analyzing the equipment's status values ​​at different points in time are as follows:

[0024] S1 acquires the device's initial operating data, current operating data, and operating time.

[0025] S2 calculates the equipment's wear value and determines the wear stage of the equipment based on the wear value.

[0026] S3 calculates the state value Ztz of the equipment at different time points based on the wear stage of the equipment.

[0027] Preferably, the initial working data and current working data of the device in step S1 represent the maximum computing power of the device being tested.

[0028] Preferably, the formula for calculating the equipment loss value in step S2 is as follows:

[0029]

[0030] In the formula, This represents equipment wear and tear. This represents the initial maximum computing power of the device. This represents the maximum computing power currently available for the device.

[0031] Preferably, the wear stage of the device in step S2 includes a stable stage and a rapid wear stage. The interval corresponding to the stable stage is (0, D), and the interval corresponding to the rapid wear stage is (D, 100). The value range of D is (30, 40).

[0032] When calculated When the device is in a stable phase, the formula for calculating the state value Ztz of the device at different time points is as follows:

[0033]

[0034] In the formula, For the operating time of the equipment, For a point in time, The current time;

[0035] When calculated If the device is in a rapid wear and tear phase, mark it and replace it with a new one.

[0036] Preferably, the formula for calculating the computing power Slx that the device can provide at different times based on the state value Ztz is as follows:

[0037]

[0038] In the formula, This is the ratio of the computing power when the device is initially operating normally to the device's initial maximum computing power.

[0039] Preferably, the steps for analyzing the list of equipment needed at future points in time are as follows:

[0040] Obtain the total computing power Zsl required for the intelligent AI computing power system to operate at the closest possible future time and the computing power Slx that the device can provide at different times;

[0041] Calculate the total computing power of devices currently in operation. Then determine the total computing power. The size of the total computing power Zsl required for the operation of the intelligent AI computing system;

[0042]

[0043] In the formula, This represents the number of devices currently in operation. Let be the computing power of the i-th device that is currently in operation;

[0044] like Increase the number of devices and recalculate the total computing power until... It also retrieves the names of the added devices and aggregates the names of the added devices and the names of the devices currently in operation to generate a device list;

[0045] like Reduce the number of devices with the lowest computing power and recalculate the total computing power until... At this point, obtain the devices that have been reduced n-1 times, remove the names of the reduced devices from the devices that are currently in operation, and generate a list of devices.

[0046] Preferably, when generating the adjustment plan from the analysis results, the equipment list at all time points is obtained, and then the equipment added or removed from the equipment list is marked.

[0047] (III) Beneficial Effects

[0048] This invention provides a working status control system for an intelligent AI computing power system, which has the following beneficial effects:

[0049] 1. This invention describes a working status control system for an intelligent AI computing power system. It analyzes and processes the data from the previous year's operation of the intelligent AI computing power system, and then makes predictions to determine the total computing power Zsl required for the operation of the intelligent AI computing power system at future time points in the current year. Based on the total computing power Zsl, it analyzes and determines the number of devices needed. This helps relevant personnel understand the number of devices needed at different future time points, enabling reasonable allocation of devices and avoiding situations where there is too much idle equipment or insufficient spare equipment. The overall effect is good and it has good application prospects.

[0050] 2. This invention describes a working status control system for an intelligent AI computing power system. It acquires historical operating data of the equipment and analyzes the equipment's status. It can directly analyze the equipment's status value Ztz at different time points and further analyze it to determine the computing power that the equipment can provide at different time points. It analyzes the impact of equipment wear and tear on computing power, which can effectively avoid insufficient computing power provided by the equipment due to wear and tear, resulting in the equipment running at high power for a long time and a short service life. Moreover, after calculation, the subsequent allocation of equipment tasks is more reasonable, the use effect is good, and it has good application prospects. Attached Figure Description

[0051] Figure 1 This is a flowchart of the working status control system of an intelligent AI computing power system according to the present invention. Detailed Implementation

[0052] 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, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0053] Research Reasons

[0054] The core idea of ​​existing intelligent AI computing power system working status control system solutions is to determine the operating status of the equipment, and then determine whether the existing equipment operating status can support the computing power required for software use.

[0055] However, this solution has significant drawbacks in practical use. It is mainly suitable for simple scenarios with minimal data fluctuations. However, most industries experience peak and off-peak seasons, and the amount of data to be processed at different times is very large, with many different types of data. If the above method is not prepared, it is easy to have insufficient reserved equipment to run the software or too much reserved equipment, resulting in low overall economic efficiency.

[0056] Moreover, the tasks of existing equipment are distributed evenly, but the equipment has different service life and different wear and tear from daily operation, so the computing power it can provide varies. In order to avoid the equipment being damaged by high power operation due to excessive task allocation, this method usually allocates a small number of tasks to the equipment, resulting in waste of the equipment.

[0057] Research Plan

[0058] A working status control system for an intelligent AI computing power system, such as Figure 1As shown, it includes a data acquisition module, a computing power analysis module, an equipment prediction module, and an equipment planning module:

[0059] To better allocate equipment, it is necessary to understand the computing power required for the intelligent AI computing system to operate. To understand the computing power required for the intelligent AI computing system to operate, it is necessary to collect historical data and analyze it. This process is based on the data acquisition module.

[0060] The data acquisition module is used to collect data from the previous year's operation of the intelligent AI computing power system and to classify the collected data.

[0061] The data acquisition module collects data including the number of model parameters of the intelligent AI computing power system, the time set for model operation, and the amount of data that the system needs to process. The collected data is classified according to the time sequence.

[0062] The above data can be obtained directly from the enterprise database.

[0063] After obtaining the required data, further analysis and calculation are needed to obtain the desired data. This further analysis and calculation is based on the computing power analysis module.

[0064] Computing power analysis module: used to process and analyze the classified data, and calculate the total computing power Zsl required for the intelligent AI computing power system to run at a future time point;

[0065] The formula for calculating the total computing power Zsl required for the operation of the intelligent AI computing system at a future time is as follows:

[0066]

[0067] In the formula, The number of model parameters, This represents the ratio of the number of model parameters to the computational complexity of the model. The amount of data the system needs to process. This represents the annual growth rate of the data.

[0068] The annual growth rate of data is provided by the enterprise's plan. Special activities adopt special solutions. This patent only applies to the calculation of the total computing power Zsl during daily use.

[0069] This invention discloses an intelligent AI computing power system working status control system. It acquires historical operating data of the equipment and analyzes the equipment status. It can directly analyze the status value Ztz of the equipment at different time points, and further analyze it to determine the computing power that the equipment can provide at different time points. It analyzes the impact of equipment wear and tear on computing power, which can effectively avoid the situation where the equipment wear and tear causes insufficient computing power to be provided, resulting in the equipment running at high power for a long time and a short service life. Moreover, after calculation, the subsequent allocation of equipment tasks is more reasonable, the use effect is better, and it has good application prospects.

[0070] After calculating the total computing power Zsl, it is necessary to allocate the total computing power Zsl. In order to allocate it better, it is necessary to understand the working status of the equipment, and understanding the working status of the equipment is based on the equipment prediction module.

[0071] The equipment prediction module acquires the historical operating data of the equipment, analyzes the state value Ztz of the equipment at different time points, and calculates the computing power Slx that the equipment can provide at different times based on the state value Ztz.

[0072] The steps to obtain historical operating data of the equipment and analyze the equipment's status values ​​at different points in time are as follows:

[0073] S1 acquires the device's initial operating data, current operating data, and operating time.

[0074] The initial and current operating data of the equipment represent the maximum computing power of the tested equipment.

[0075] S2 calculates the equipment's wear value and determines the wear stage of the equipment based on the wear value.

[0076] The formula for calculating equipment loss is as follows:

[0077]

[0078] In the formula, This represents equipment wear and tear. This represents the initial maximum computing power of the device. This represents the maximum computing power currently available for the device.

[0079] The wear and tear stage of the equipment includes a stable stage and a rapid wear and tear stage. The interval corresponding to the stable stage is (0, D), and the interval corresponding to the rapid wear and tear stage is (D, 100). The value range of D is (30, 40).

[0080] S3 calculates the state value Ztz of the equipment at different time points based on the wear stage of the equipment.

[0081] When calculated When the device is in a stable phase, the formula for calculating the state value Ztz of the device at different time points is as follows:

[0082]

[0083] In the formula, For the operating time of the equipment, For a point in time, The current time;

[0084] When calculated During the rapid attrition phase, mark and replace with new equipment. This is because the computing power provided during this phase is low, and the equipment is prone to failure; therefore, it needs to be replaced with new equipment during this phase. Alternatively, it can be replaced when the state value Ztz is located at (0, ...). (The equipment.)

[0085] The formula for calculating the computing power Slx that the device can provide at different times based on the state value Ztz is as follows:

[0086]

[0087] In the formula, This is the ratio of the computing power when the device is initially operating normally to the device's initial maximum computing power.

[0088] Equipment planning module: Obtain the total computing power Zsl required for the operation of the intelligent AI computing power system at a future time point and the computing power Slx that the equipment can provide at different times, analyze the list of equipment required at the future time point, and generate an adjustment plan from the analysis results.

[0089] The steps to analyze the list of equipment needed at a future point in time are as follows:

[0090] Obtain the total computing power Zsl required for the intelligent AI computing power system to operate at the closest possible future time and the computing power Slx that the device can provide at different times;

[0091] Calculate the total computing power of devices currently in operation. Then determine the total computing power. The size of the total computing power Zsl required for the operation of the intelligent AI computing system;

[0092]

[0093] In the formula, This represents the number of devices currently in operation. Let i be the computing power of the i-th device that is currently in operation;

[0094] like Increase the number of devices and recalculate the total computing power until... It also retrieves the names of the added devices and aggregates the names of the added devices and the names of the devices currently in operation to generate a device list;

[0095] like Reduce the number of devices with the lowest computing power and recalculate the total computing power until... At this point, obtain the devices that have been reduced n-1 times, remove the names of the reduced devices from the devices that are currently in operation, and generate a list of devices.

[0096] When generating the adjustment plan from the analysis results, the equipment list at all time points is obtained, and then the equipment added or removed from the equipment list is marked.

[0097] This invention discloses a working status control system for an intelligent AI computing power system. It analyzes and processes data from the previous year's operation of the intelligent AI computing power system, then predicts the total computing power Zsl required for the system's operation at future points in the current year. Based on the total computing power Zsl, it analyzes and determines the required number of devices. This helps relevant personnel understand the number of devices needed at different points in the future, enabling reasonable allocation of devices and avoiding situations where too much equipment is idle or too few spares. The overall effect is good, and it has promising application prospects.

[0098] The above formula is a formula derived from software simulation using a large amount of collected data to obtain the most recent real-world situation. The preset parameters in the formula can be set by those skilled in the art according to the actual situation.

[0099] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0100] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0101] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A working status control system for an intelligent AI computing power system, characterized in that, include: Data acquisition module: Used to collect data from the previous year's operation of the intelligent AI computing power system and to classify the collected data; The data acquisition module collects data including the number of model parameters of the intelligent AI computing power system, the time set for model operation, and the amount of data that the system needs to process. The collected data is classified according to the time sequence. Computing power analysis module: used to process and analyze the classified data, and calculate the total computing power Zsl required for the intelligent AI computing power system to run at a future time point; Equipment prediction module: acquires historical operating data of equipment, analyzes the state value Ztz of equipment at different time points, and calculates the computing power Slx that the equipment can provide at different times based on the state value Ztz; The steps to obtain historical operating data of the equipment and analyze the equipment's status values ​​at different points in time are as follows: S1. Obtain the initial working data of the equipment, the current working data, and the working time of the equipment; The initial and current operating data of the device in step S1 represent the maximum computing power of the device under test. S2. Calculate the equipment's wear value and determine the wear stage of the equipment based on the wear value. The formula for calculating the equipment loss value in step S2 is as follows: ； In the formula, This represents equipment wear and tear. This represents the initial maximum computing power of the device. This represents the maximum computing power currently available for the device. The wear stage of the equipment in step S2 includes a stable stage and a rapid wear stage. The interval corresponding to the stable stage is (0, D), and the interval corresponding to the rapid wear stage is (D, 100). The value range of D is (30, 40). When calculated When the device is in a stable phase, the formula for calculating the state value Ztz of the device at different time points is as follows: ； In the formula, For the operating time of the equipment, For a point in time, The current time; When calculated If the equipment is in a rapid wear and tear phase, mark it and replace it with a new one. S3. Calculate the state value Ztz of the equipment at different time points based on the wear stage of the equipment; Equipment planning module: Obtain the total computing power Zsl required for the operation of the intelligent AI computing power system at a future time point and the computing power Slx that the equipment can provide at different times, analyze the list of equipment required at the future time point, and generate an adjustment plan from the analysis results; The steps to analyze the list of equipment needed at a future point in time are as follows: Obtain the total computing power Zsl required for the intelligent AI computing power system to operate at the closest possible future time and the computing power Slx that the device can provide at different times; Calculate the total computing power of devices currently in operation. Then determine the total computing power. The size of the total computing power Zsl required for the operation of the intelligent AI computing system; ； In the formula, This represents the number of devices currently in operation. Let be the computing power of the i-th device that is currently in operation; like Increase the number of devices and recalculate the total computing power until... It also retrieves the names of the added devices and aggregates the names of the added devices and the names of the devices currently in operation to generate a device list; like Reduce the number of devices with the lowest computing power and recalculate the total computing power until... At this point, obtain the devices that have been reduced n-1 times, remove the names of the reduced devices from the devices that are currently in operation, and generate a list of devices.

2. The intelligent AI computing power system working status control system according to claim 1, characterized in that: The formula for calculating the total computing power Zsl required for the operation of the intelligent AI computing system at a future time is as follows: ； In the formula, The number of model parameters, This represents the ratio of the number of model parameters to the computational complexity of the model. The amount of data the system needs to process. This represents the annual growth rate of the data.

3. The intelligent AI computing power system working status control system according to claim 2, characterized in that: When generating the adjustment plan from the analysis results, the equipment list at all time points is obtained, and then the equipment added or removed from the equipment list is marked.

Images