Cooperative Computation and Cache Scheduling for UAV-Enabled MEC Networks

Abstract

Since the flight of Unmanned Aerial Vehicle (UAV) greatly consumes the limited on-board energy and affects the ability to afford computation services, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">it is urgent and challenging to minimize UAV’s endurance time while satisfying varieties of constraints from the UAVs and users, such as energy budgets, cache capacities, computation resources, and latency requirements.</i> In this paper, the UAVs are endowed with the capability to temporarily buffer some offloaded tasks and process them later, then adopt cooperative computation and cache scheduling to minimize their total endurance time. Following this, the formulated problem is a mix-integer nonlinear programming problem, which can be further transformed into three more tractable subproblems: 1) <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathbf {P_{O}}$ </tex-math></inline-formula> , offloading decision and scheduling strategy for computing & caching; 2) <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathbf {P_{H}}$ </tex-math></inline-formula> , hovering trajectory design; and 3) <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathbf {P_{C}}$ </tex-math></inline-formula> , computation resource allocation, and then iteratively tackled in a sequence. Due to the high complexity of solving <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathbf {P_{O}}$ </tex-math></inline-formula> , the low-complexity algorithm based on the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means clustering and Penalty Method is proposed to reduce complexity and facilitate the processing procedure, which can save about 91.04%–189.36% running time and ONLY sacrifice 8.05%–22.08% of the total endurance time. Simulation results show that cooperative computation and cache scheduling has a great effect on saving endurance time.

Topics & Concepts