The Effect of Data Marshalling on Computation Offloading Decisions

TL;DR

This paper investigates how data marshalling techniques, especially JSON, influence computation offloading decisions by analyzing their computational costs through experiments, revealing that JSON can significantly impact offloading choices.

Contribution

It provides an empirical analysis of data marshalling's impact on offloading decisions, highlighting the computational costs of JSON versus raw data transfer.

Findings

JSON incurs higher computational costs than raw data transfer

Marshalling techniques significantly influence offloading decisions

Experimental results demonstrate conditions where marshalling impacts performance

Abstract

We conducted an extensive set of experiments with an offloading testbed to understand the impact that data marshalling techniques have on computation offloading decisions. We find that the popular JSON format to marshall data between client and server comes at a significant computational expense compared to a minimalistic raw data transfer. The computational time is significant in that it affects computation offloading decisions in a variety of conditions. We outline some of these conditions.