57 results about "Two-level scheduling" patented technology

The invention provides a minor-cycle real-time generation schedule, which comprises the following steps of: S1, determining units participating in real-time generation schedule computing by two stages of dispatching centers; S2, judging whether the difference between a load predicted value Ps used by an intraday generation schedule in the next schedule time and an ultra-short-term load predicted value Ps' used by the intraday generation schedule in the next schedule time is equal to 0 or not, if the difference is equal to 0, executing the step S7, and if the difference is not equal to 0, executing the step S3; S3, respectively working out load deviation values deltaPs,A and deltaPs,B which need to be respectively borne by the units which respectively correspond to the two stages of dispatching centers in the next time; S4, performing statistics adjustable capacity sums deltaPC,A and deltaPC,B of the units which respectively correspond to the two stages of dispatching centers; S5, working out load deviation values deltaPLF,A and deltaPLF,B respectively and finally distributed by the two stages of dispatching centers; S6, working out the adjustment power of every unit of the two stages of dispatching centers; and S7, executing the step S1 after the real-time generation schedule of each unit is obtained. Only the predicted values in the next schedule time are used every time, so that the output of each unit more approaches to the requirement of an actual load.

One embodiment of the present invention sets forth a technique for scheduling thread execution in a multi-threaded processing environment. A two-level scheduler maintains a small set of active threads called strands to hide function unit pipeline latency and local memory access latency. The strands are a sub-set of a larger set of pending threads that is also maintained by the two-leveler scheduler. Pending threads are promoted to strands and strands are demoted to pending threads based on latency characteristics. The two-level scheduler selects strands for execution based on strand state. The longer latency of the pending threads is hidden by selecting strands for execution. When the latency for a pending thread is expired, the pending thread may be promoted to a strand and begin (or resume) execution. When a strand encounters a latency event, the strand may be demoted to a pending thread while the latency is incurred.