Minimising Delay and Energy in Online Dynamic Fog Systems

Abstract

The increasing use of Internet of Things (IoT) devices generates a greater demand for data transfers and puts increased pressure on networks. Additionally, connectivity to cloud services can be costly and inefficient. Fog computing provides resources in proximity to user devices to overcome these drawbacks. However, optimisation of quality of service (QoS) in IoT applications and the management of fog resources are becoming challenging problems. This paper describes a dynamic online offloading scheme in vehicular traffic applications that require execution of delay-sensitive tasks. This paper proposes a combination of two algorithms: dynamic task scheduling (DTS) and dynamic energy control (DEC) that aim to minimise overall delay, enhance throughput of user tasks and minimise energy consumption at the fog layer while maximising the use of resource-constrained fog nodes. Compared to other schemes, our experimental results show that these algorithms can reduce the delay by up to 80.79% and reduce energy consumption by up to 66.39% in fog nodes. Additionally, this approach enhances task execution throughput by 40.88%.

Dynamically Controlling Offloading Thresholds in Fog Systems

“… We conducted extensive experiments to evaluate the performance of our proposed scheme and compare our proposed algorithm to various benchmarks. This paper extends our previous work [ 1 ] by introducing a dynamic offloading threshold, made use of in an online model for evaluating service delay. …”

“…The multi-objective problem of minimizing delay, maximizing throughput, and minimizing energy consumption is decomposed into two sub-problems [ 1 ]: (i) delay minimization and throughput maximization, and (ii) energy saving.…”

“…The number of IoT devices and their generated tasks are constantly growing, imposing a burden on cloud infrastructure, in particular if processing of these tasks must take place within Quality of Services (QoS) constraints [ 1 , 2 ]. The processing of these tasks in the cloud can trigger systems to suffer high communication latency, security issues, and network congestion [ 3 ].…”

“…Resource management can involve multiple factors, saving energy consumption in the fog environment is one of these factors, and is considered in this work. Integrating computational offloading and resource management is essential to effectively utilize fog resources [ 1 ].…”

“…In online dynamic fog systems, where uncertainties are arising due to multiple factors, with no prior awareness of task arrival rate, the number of connected IoT devices, and computational capacity of fog nodes, addressing computational offloading and resource management is challenging to obtain optimum outcomes [ 1 ]. Computational offloading has mostly been explored in offline fog systems, where all system data are known beforehand, and limited work has been carried out in online dynamic fog systems.…”