发明名称 Scalable architecture
摘要 Exemplary embodiments may employ techniques for dynamically dispatching requests to resources operating in a distributed computing environment, such as a computing cloud, according to one or more policies. Embodiments may further dynamically adjust resources in the computing environment using predictive models that use current loads as an input. Embodiments may still further maintain a state for a processing environment independent of the type or configuration of a device used to access the environment on behalf of a user.
申请公布号 US8918511(B2) 申请公布日期 2014.12.23
申请号 US201213485836 申请日期 2012.05.31
申请人 The MathWorks, Inc. 发明人 Gulley Edward Whittington;Hicklin Joseph F.;Gonthier James N.;Langley John Richard;Conti Joseph
分类号 G06F15/173;G06F9/50;H04L12/70;H04L12/861;H04L12/64 主分类号 G06F15/173
代理机构 Harrity & Harrity, LLP 代理人 Harrity & Harrity, LLP
主权项 1. A non-transitory computer-readable media storing instructions, the instructions comprising: one or more instructions, executable by one or more processors to cause the one or more processors to: determine a size of a processing buffer associated with a plurality of distributed computing resources available to a distributed computing environment, the distributed computing environment including a technical computing environment,the size of the processing buffer representing a determined percentage amount of excess processing resources, of the plurality of distributed computing resources,the size of the processing buffer being determined using processing capability information that is provided, at a first time, by a predictive model based on first historical information,the size of the processing buffer being set for a particular amount of time, andthe excess processing resources providing additional distributed processing capabilities to the distributed computing environment when the excess processing resources are being used;measure a processing load for the distributed computing environment;receive additional information associated with the processing load, the additional information being based on the predictive model using, at a second time, second historical information to generate estimate information associated with processing one or more future processing loads by the processing buffer, the second time occurring after the first time;input the measured processing load and the additional information to produce a result;evaluate the result to determine whether the determined percentage amount of excess processing resources represented by the size of the processing buffer is adequate, the size of the processing buffer being inadequate when one of: the determined percentage amount of excess processing resources represented by the size of the processing buffer is less than a threshold amount of excess processing resources, orthe determined percentage amount of excess processing resources represented by the size of the processing buffer is greater than the threshold amount of excess processing resources; andmodify the size of the processing buffer when the determined percentage amount of excess processing resources represented by the processing buffer is inadequate, the one or more instructions to modify the size of the processing buffer including one of: one or more instructions to cause additional distributed processing resources to be available to the distributed computing environment, orone or more instructions to cause one or more of the plurality of the distributed computing resources to be unavailable to the distributing computing environment.
地址 Natick MA US