ESMO: Joint Frame Scheduling and Model Caching for Edge Video Analytics

Abstract

With the advancements in Machine Learning (ML) and edge computing, increasing efforts have been devoted to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">edge video analytics</i> . However, most of the existing works fail to consider the cooperation of edge nodes for ML model caching and video frame scheduling, thus less efficient in practical scenarios with diverse requirements. In this paper, we propose a novel approach named ESMO (joint fram <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">E</b> <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> cheduling and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MO</b> del caching) to jointly optimize Frame Scheduling and Model Caching (FSMC), aiming at enhancing the performance of edge video analytics. In detail, we decompose the FSMC as three sub-problems, where the first two sub-problems (i.e., user's transmit power and edge computing resources allocation problems) are proven to be quasi-convex and strictly convex, respectively; while the third main sub-problem (i.e., trade-off among the VA accuracy, service delay and energy consumption) is NP-hard. Therefore, an efficient Two-layers Genetic Algorithm based algorithm (i.e., TGA-FSMC) is designed to find the close-to-optimal frame scheduling and the model caching decisions in an iterative manner. Finally, we deploy a target recognition prototype to comprehensively evaluate the practical performance in diverse edge nodes and CNN models. Extensive experiments demonstrate the empirical superiority of the ESMO over alternatives on real-world edge video analytics platforms, and it achieves 37.5% <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sim$</tex-math></inline-formula> 87.2% performance improvement.