Prediction method of operational performance based on historical data modeling in grid

Abstract

The invention relates to a prediction method of operational performance based on a historical data modeling in grid, belonging to an operation completing time modeling and prediction method in high-performance grid. The prediction method is characterized by comprising the steps of establishing a historical operational information bank based on a CGDP grid software and a CGSV grid software in grid nodes, wherein the historical operational information bank contains N historical operational information, relating to four aspects of resource allocation, resources loading, operation request and operation actual performance; and simultaneously establishing a set comprising one or more candidate regressive functions, wherein when predicting, the N+1th operation submitted by a user is acquired according to a regressive model of the Nth operation, and the regressive model of the Nth operation is acquired by selecting a candidate regressive model with the smallest difference value from differences of predicted value results of operation actual performance of the Nth operation and the actual performance of the candidate regressive models of the N-1th operation. According to a simulation experiment, the invention can solve the problem of surging operation time and operation expense caused by excessive resource load.

Description

technical field [0001] The invention relates to a modeling method for job completion time in a high-performance grid, and belongs to the field of distributed technology and systems. Background technique [0002] In modern scientific research, the field for people to solve problems is constantly expanding, and the problems they encounter are becoming more and more complex, and the scale is getting larger and larger. Unable to meet demand. With the rapid development of computer and network technology, many organizations and scientific research units have supercomputers with strong computing power, but these machines often do not fully function because they only serve their own units in isolation, and are idle most of the time . Therefore, it has become a necessary requirement to break the geographical restrictions and use various resources widely distributed on the network in coordination. [0003] The proposal and development of grid technology is just to meet the above-me...

AI Technical Summary

Problems solved by technology

And this is often difficult to achieve for most software

[0016] 3) It cannot adapt to both computation-intensive and communication-intensive job types, and can only be modeled separately for computation-intensive and communication-intensive jobs

However, other studies have demonstrated that the NWS prediction error for actual file transfer bandwidth is quite large

[0018] 5) Evaluate in the simulated environment, set the resource load to a fixed state, and do not reflect the dynamic change of resource load

Images