Resource allocation method and server

Abstract

The invention discloses a resource allocation method and a server. The method comprises the following steps: the server predicts a resource demand value of a terminal in a future period of time according to the historical information of the terminal, wherein the historical information comprises one or more of a resource demand value predicted by the server for the terminal in a historical time period, a resource allocation value allocated by the server for the terminal in the historical time period, request information sent to the server by the terminal in the historical time period and an actual resource occupation value of the terminal in the historical time period; the server determines a resource allocation value of the terminal in a future period of time according to the resource demand value predicted for the terminal in the future period of time and the current residual total resource of the server, and the resource allocated for the terminal in the future period of time is usedfor the server to process a request from the terminal in the future period of time. By implementing the method and the device, resources can be reasonably allocated, concurrent capability of the server is improved, and media focus interruption is prevented.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to a resource allocation method and a server. Background technique [0002] In virtual set-top boxes and similar scenarios that provide remote dynamic media services (such as electronic program guide (EPG) browsing of smart TVs, etc.), the user sends an operation command to the remote server, and the remote server performs the user's operation. Response, complete media content processing, and then push to the client to present media information. [0003] The ability to handle massive user media requests (high concurrency) is the core competitiveness of the remote server. Improving concurrency while ensuring user experience is the core appeal of remote dynamic media services. [0004] Limited resources and massive concurrent users are a pair of trade offs. The problem of concurrent optimization is actually a problem of reasonable allocation of limited resources. The server do...

AI Technical Summary

Problems solved by technology

[0004] Limited resources and massive concurrent users are a pair of trade offs. The problem of concurrent optimization is actually a problem of reasonable allocation of limited resources. The server does not have a mechanism for estimating the resource requirements of each user, so the resource occupation for processing user requests cannot be fully realized. Effective management, in the case of high concurrency, surges are prone to occur, the total system resources may be limited, and the resource needs of all users cannot be met, and uncontrolled resource allocation may easily lead to interruption of media focus

Images