Meta-Analytical Comparison Of Energy Consumed By Two Sorting Algorithms Gcinizwe Dlamini a , Firas Jolha a , Zamira Kholmatova a , Giancarlo Succi a,* a Innopolis University, Universitetskaya ul. 1, Innopolis, 420500, Russia Abstract Mobile devices performance and uptime heavily depend on energy consumed at the hardware and software level. Hence implementation of efficient algorithms has become a crucial aspect for increasing the performance of such systems and battery life for mobile devices. Sorting algorithms are implicitly the building block of many program implementation. Over the past years, researchers have spent more time optimizing hardware components to reduce their energy consumption. However, it has not been so clear which sorting algorithm is more energy efficient. In this study, we conduct a meta-analytical comparison of the energy consumed by the two most common sorting algorithms namely quick sort and merge sort. Our study mainly focused on energy consumption for mobile devices and embedded systems. For our meta-analysis and literature review, we took into consideration studies published not more than 20 years ago. The meta-analytical results show that there is no significant difference between both algorithms in terms of energy efficiency. Keywords: sorting algorithms, energy consumption, quick sort, merge sort, embedded systems, mobile computing, energy efficiency, mobile devices 1. Introduction Sorting algorithms are fundamental to almost ev- ery information system software including mobile de- vices, embedded systems, intelligent Systems, internet of things (IoT), and many more. Selecting an energy- efficient sorting algorithm is crucial in helping to reduce loss in terms of money, time, and wastage of resources. For devices (i.e mobile and embedded devices) powered by batteries, the up-time heavily depends on the energy consumed by the software. As software complexity in- creases from year to year, the hardware engineering re- search community has been dedicating more time in op- timizing the energy efficiency of hardware components [1]. As every information system is made up of hard- ware and software, the research community has not been only focusing on hardware optimization but also on software. There has been ongoing research over the last few years to minimize energy consumption by the * Corresponding Author Email addresses: g.dlamini@innopolis.university (Gcinizwe Dlamini), f.jolha@innopolis.university (Firas Jolha), z.kholmatova@innopolis.university (Zamira Kholmatova), g.succi@innopolis.ru (Giancarlo Succi) use of advanced programming techniques and energy- efficient algorithms to increase the service time of dif- ferent battery-powered devices [2]. The effort made by the software engineering community has resulted in formulation of research fields such as Green software, green hardware and Green information technology (IT) [3]. Energy consumption and efficiency are part of the cornerstone of green software engineering [3]. Until recently, greater progress in minimizing energy con- sumption is related to hardware optimization. How- ever to reach optimal energy consumption in any com- puter system, hardware optimization efforts must be complemented by software optimization efforts. Hard- ware and software work efficiently with this interaction [4]. Noticing the effort put by computer hardware re- searchers, software researchers conducted studies mea- suring the energy consumption of different methods and algorithms varying experimental environment [5]. The increase of conducted primary studies has raised the challenge of making conclusion from an ever growing number of primary studies having at times varying ex- perimental setups and conclusions. The reasons for dif- ferences in empirical research have begun to be actively studied in the last 2-3 years [6, 7]. One simple solution to the problem of variation could be conducting a pri- Preprint submitted to Information Sciences May 19, 2022