3results about How to "Minimize overhead" patented technology

This invention relates to a preemptive scheduling method for heterogeneous multi-core processors based on multi-agent reinforcement learning. It includes: constructing a system model comprising a set of sporadic real-time tasks and a heterogeneous multi-core platform; pre-setting fixed preemption points for tasks; dividing task execution into non-preemptive segments; modeling the scheduling problem as a partially observable Markov decision process; designing state representations that include task dynamic attributes and platform heterogeneity characteristics; wherein the task dynamic attributes are normalized values ​​of relative deadline pressure, execution progress ratio, and relaxation; and the platform heterogeneity characteristics include a weighted sum of core computing power level and global idle computing power; clustering processors according to computing power; assigning independent agents to each cluster; and adopting a fully cooperative mode to share global rewards; employing a centralized training and distributed execution framework; using the discrete soft actor-critic algorithm during training; with each agent's policy network collaboratively optimizing under the guidance of a centralized value function; and during execution, each agent independently deciding on preemption timing based on local observations. This invention achieves cooperative preemptive scheduling among heterogeneous cores through multi-agent reinforcement learning, effectively reducing task overdue rates and system overhead, and improving real-time performance.

A user equipment and a method performed by the user equipment are disclosed. The method includes the following steps: receiving system information for configuring a first K offset as a scheduling offset for correcting the timing of uplink signals for NTN; receiving a control signal for configuring or updating a second K offset based on the first K offset; and transmitting uplink signals based on the first K offset or the second K offset, wherein the uplink signals are transmitted based on the first K offset in association with a random access channel (RACH).

An adaptive link management method and system based on satellite mobile communication employs a PPP-based UDP protocol for initial link negotiation. Network address and other information are exchanged through link establishment request and confirmation signaling interactions. Network segment relationships are determined based on address information: GRE encapsulation with proxy ARP assistance is used for same network segments, while standard GRE encapsulation is used for different network segments. Link endpoint identifiers are negotiated and a bidirectional transmission link is established under the selected encapsulation mode. After link establishment, both parties periodically exchange keep-alive signaling to maintain connectivity. Simultaneously, the status of connected local access devices is monitored, and information is synchronized according to a preset period and / or status changes to dynamically update the transmission path and perform IP address conflict detection and handling. The transmission link is released normally through link release signaling. This scheme improves link adaptability and bandwidth utilization, effectively prevents address conflicts, and thus enhances network reliability.