Fuzzy-Assisted Mobile Edge Orchestrator and SARSA Learning for Flexible Offloading in Heterogeneous IoT Environment

Abstract

In the era of heterogeneous 5G networks, Internet of Things (IoT) devices have significantly altered our daily life by providing innovative applications and services. However, these devices process large amounts of data traffic and their application requires an extremely fast response time and a massive amount of computational resources, leading to a high failure rate for task offloading and considerable latency due to congestion. To improve the quality of services (QoS) and performance due to the dynamic flow of requests from devices, numerous task offloading strategies in the area of multi-access edge computing (MEC) have been proposed in previous studies. Nevertheless, the neighboring edge servers, where computational resources are in excess, have not been considered, leading to unbalanced loads among edge servers in the same network tier. Therefore, in this paper, we propose a collaboration algorithm between a fuzzy-logic-based mobile edge orchestrator (MEO) and state-action-reward-state-action (SARSA) reinforcement learning, which we call the Fu-SARSA algorithm. We aim to minimize the failure rate and service time of tasks and decide on the optimal resource allocation for offloading, such as a local edge server, cloud server, or the best neighboring edge server in the MEC network. Four typical application types, healthcare, AR, infotainment, and compute-intensive applications, were used for the simulation. The performance results demonstrate that our proposed Fu-SARSA framework outperformed other algorithms in terms of service time and the task failure rate, especially when the system was overloaded.

A comprehensive review on internet of things task offloading in multi-access edge computing

“…The goal of resource allocation is addressed in approximately 10 % of the reviewed literature [ 99 , 103 , 105 , 111 , 116 , 121 ]. In addition, 48 % of the research work focuses on both task allocation and resource allocation issues [ 76 , 80 , 83 , 87 , 89 , 141 , 142 , 144 , 146 , 92 , 95 , 101 , 102 , 107 , [112] , [113] , [114] , [115] , [117] , [118] , [119] , [120] , [122] , [123] , [124] , [126] , [127] , [128] , [129] , [132] , [133] , [134] , [135] , [136] , 148 , 149 ]. The Distribution and overlay of IoT task offloading problems addressed in MEC are shown in Fig.…”

“…Another important goal of optimizing the IoT computing task offloading mechanism is to reduce energy consumption, thereby extending the life cycle of battery-powered devices. Energy consumption indicators are expressed in many studies as Device energy consumption, Total energy consumption, and Average energy efficiency, etc [ 140 , 143 , [116] , [117] , [118] , 125 , 136 ].…”

“…Device-to-edge (D2E) task offloading in a Multi-Access Edge Computing (MEC) network involves offloading a task from a user's device to an edge server or cloudlet located at the network's edge. This approach allows tasks to be processed closer to the source of data, reducing latency and improving the overall performance of applications [ 73 , 74 , 76 , 77 , 79 , 80 , 83 , 84 , [86] , [87] , [88] , [89] , [144] , [145] , [146] , [147] , 91 , 94 , 97 , 100 , [102] , [103] , [104] , 106 , 107 ], [ 113 , 114 , [116] , [117] , [118] , 120 , 123 , [126] , [127] , [128] , 130 , 132 , 135 , 137 , 148 , 160 , 161 , 167 ].…”

“…In computational offloading within a MEC network, multiple servers as task offloading destinations refer to the scenario where a task from a user's device is offloaded and executed on more than one edge server or cloudlet. This approach involves parallel execution of the task, with different servers sharing the computational load [ 74 , 77 , 81 , [85] , [86] , [87] , [138] , [139] , [140] , [141] , [142] , 144 , [90] , [91] , [92] , [147] , [94] , [95] , [96] , [97] , [98] , [99] , 101 , 102 , 105 , [107] , [108] , [109] ], [ 111 , 112 , 114 , 115 , [117] , [118] , [119] , [121] , [122] , [123] , [124] , [125] , [126] , [127] , [128] , [129] , [131] , [132] , [133] , [134] , 136 , 160 , 161 , 167 , 169 ].…”

“…In Ref. [ 118 ], the author also optimizes task offloading decisions based on deep learning technology. However, this research focuses more on supporting task offloading cost optimization in blockchain application scenarios.…”