Workload prediction for network-based computing
AssigneeEmpire Technology Development LLC
InventorsZhen Shen, Xuefeng Song
Life of this patent
Estimating the term…
Abstract
Technologies are generally described for systems and methods effective to efficiently schedule a workload in a cloud computing system. In one example, calendar data is collected from respective sets of devices associated with respective sets of subscribers and a workload to be performed at a specific time or range of time is predicted based in part on an analysis of calendar data. Moreover, timing data associated with a set of predicted requests is determined based on the analysis and at least a portion of cloud computing resources that service the set of predicted requests are dynamically scheduled based on timing data.
Claims35
A method, comprising:
- receiving, by a system comprising a processor, calendar data from respective first sets of devices associated with respective first sets of subscribers;
- determining a workload to be performed at a specific time or range of time based in part on an analysis of the calendar data;
- and
- based on the workload, allocating a first set of servers to respond to a first set of requests received from the first sets of devices and a second set of servers to respond to a second set of requests received from respective second sets of devices associated with respective second sets of subscribers that do not share the calendar data, wherein the first set of servers have a response time for responding to requests that is slower than the second set of servers.
A system, comprising:
- a memory;
- and
- at least one processor, communicatively coupled to the memory, that facilitates execution of one or more computer-executable components, comprising:
- a data collection component configured to receive calendar data from a first set of devices associated with a first subscriber;
- and
- a resource management component configured to schedule, based in part on the calendar data, a first portion of a set of servers to facilitate provision of service for a first request from a first device of the first set of devices and schedule a second portion of the set or servers to facilitate provision of service for a second request from a second device of a second set of devices associated with a second subscriber that does not share the calendar data, wherein the second portion of the set of servers are instructed to respond at a faster rate than the first portion of the set of servers.
A computer-readable storage medium having stored thereon computer-executable instructions that, in response to execution, cause a computing system comprising a processor to perform operations, comprising:
- analyzing calendar data received from respective first sets of devices associated with respective first sets of subscribers;
- based on the analyzing, determining timing data associated with a set of predicted requests received from the respective first sets of devices;
- and
- scheduling, based on the timing data, a first portion of a set of servers that process the set of predicted requests and a second portion of the set of servers that process a set of unpredicted requests received from respective second sets of devices associated with respective second sets of subscribers that do not share the calendar data, wherein the second portion of the set of servers are instructed to respond to requests faster than the first portion of the set of servers.
A communication device, comprising:
- a memory;
- and
- at least one processor, communicatively coupled to the memory, that facilitates execution of at least one computer-executable component to at least:
- facilitate a transmission of calendar data to a network device of a communication network, wherein the calendar data is utilized to allocate a first subset of a set of servers within the communication network to process a request from the communication device and allocate a second subset of the set of servers to process a different request from a different communication device that does not share the calendar data;
- and
- direct the request to the communication network, subsequent to transmission of the calendar data, wherein the first subset of the set of servers respond to the request at a slower rate than the second subset of the set of servers respond to the different request.
A method, comprising:
- receiving, by a system comprising a processor, a first request from a first device that has shared calendar data prior to the receiving and a second request from a second device that has not shared calendar data prior to the receiving;
- and
- determining a first subset of a set of network servers to process the first request and determining a second subset of the set of network servers to process the second request, wherein the first subset of the set of network servers are instructed to respond at a slower rate than the second subset of the set of servers.
Dependencies are inferred from the claim text.