English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The limited energy and computing resources of unmanned aerial vehicles (UAVs)hinder the application of aerial artificial intelligence. The utilization ofsplit inference in UAVs garners significant attention due to its effectivenessin mitigating computing and energy requirements. However, achievingenergy-efficient split inference in UAVs remains complex considering of variouscrucial parameters such as energy level and delay constraints, especiallyinvolving multiple tasks. In this paper, we present a two-timescale approachfor energy minimization in split inference, where discrete and continuousvariables are segregated into two timescales to reduce the size of action spaceand computational complexity. This segregation enables the utilization of tinyreinforcement learning (TRL) for selecting discrete transmission modes forsequential tasks. Moreover, optimization programming (OP) is embedded betweenTRL's output and reward function to optimize the continuous transmit power.Specifically, we replace the optimization of transmit power with that oftransmission time to decrease the computational complexity of OP since wereveal that energy consumption monotonically decreases with increasingtransmission time. The replacement significantly reduces the feasible regionand enables a fast solution according to the closed-form expression for optimaltransmit power. Simulation results show that the proposed algorithm can achievea higher probability of successful task completion with lower energyconsumption.

Energy-Efficient Power Control for Multiple-Task Split Inference in UAVs: A Tiny Learning-Based Approach