Event driven grant allocation

摘要

Systems and methods are described for event-driven predictive scheduling of a return link of a communications system. Embodiments detect an event (e.g., a packet) on a forward link that may indicate future usage of the return link. The event is then associated with an event model that characterizes the event, and the event model is further associated with a predictive model. Scheduling of the return link is implemented and/or adjusted according to the predictive model. For example, return link allocations are adjusted by one or more amounts (e.g., one or more grants are allocated or bandwidth is adjusted by a certain amount) and at one or more designated timing offsets according to the predictive model. According to various embodiments, the predictive model is generated by tracking feedback from the return link and/or by scanning packets on the forward link.

主权项

1. A method for event-driven predictive scheduling of a return link in a communication system comprising:
detecting, at a provider side of the communications system, an event predictor corresponding to a download packet associated with an HTTP object destined for a user terminal over a forward link of the communications system, the event predictor indicating a future event to occur in association with receipt of the download packet at the user terminal; selecting a prediction model according to the detected event predictor from a plurality of prediction models maintained at the provider side of the communications system, wherein each prediction model of the plurality of prediction models estimates a size or timing of a future communications event associated with the HTTP object; generating a resource allocation according to the selected prediction model at the provider side of the communications system, the resource allocation indicating a magnitude by which to adjust resources of the return link of the communications system associated with the user terminal, and the resource allocation indicating a timing offset at which to adjust the resources by the magnitude, the timing offset corresponding to an amount of time after occurrence of the event; scheduling the resources of the return link of the communications system associated with the user terminal at least according to the resource allocation; and communicating data corresponding to the data packet and data corresponding to the resource allocation to the user terminal over the forward link of the communications system; wherein selecting the prediction model according to the detected event predictor comprises: scanning the download packet to extract metadata, the metadata indicating at least one HTTP object likely to be requested subsequent to receiving the download packet at the user terminal; and selecting the prediction model at least according to the metadata.