Computation offloading and resource allocation for low-power IoT edge devices

Abstract

With the proliferation of portable and mobile IoT devices and their increasing processing capability, we witness that the edge of network is moving to the IoT gateways and smart devices. To avoid Big Data issues (e.g. high latency of cloud based IoT), the processing of the captured data is starting from the IoT edge node. However, the available processing capabilities and energy resources are still limited and do not allow to fully process the data on-board. It calls for offloading some portions of computation to the gateway or servers. Due to the limited bandwidth of the IoT gateways, choosing the offloading levels of connected devices and allocating bandwidth to them is a challenging problem. This paper proposes a technique for managing computation offloading in a local IoT network under bandwidth constraints. The existing bandwidth allocation and computation offloading management techniques underutilize the gateway's resources (e.g. bandwidth) due to the fragmentation issue. This issue stems from the discrete coarse-grained choices (i.e. offloading levels) on the IoT end nodes. Our proposed technique addresses this issue, and utilizes the available resources of the gateway effectively. The experimental results show on average 1 hour (up to 1.5 hour) improvement in battery life of edge devices. The utilization of gateway's bandwidth increased by 40%. 1

Survey on Multi-Access Edge Computing for Internet of Things Realization

“…User mobility, network topology, network scalability, and load balancing are some other factors to be considered in order to define fare resource utilization policies on MEC servers. Specifically when IoT gateways share limited bandwidth among multiple IoT devices which can handle video, audio or bio-medical signals, the allocation of bandwidth will become challenging [120]. The low power wireless technologies (e.g., BLE, ZigBee, low power Wi-Fi, and LPWAN standards like LoRA or SigFox) used in IoT networks have limited bandwidth.…”

Internet of Things and data mining: From applications to techniques and systems

“…Data mining applications are implemented in the form of complete data pipeline that converts raw data streams into knowledge patterns. The computational complexities and resource consumption of each data conversion operation vary among different applications, therefore, developing application partitioning and computation offloading strategies in edge computing systems becomes very hard (Orsini, Bade, & Lamersdorf, 2015;Rehman, Sun, Wah, Iqbal, & Jayaraman, 2016;Rehman, Sun, Wah, & Khan, 2016;Samie et al, 2016).…”

Distributed Trade-Based Edge Device Management in Multi-Gateway IoT

“…Edge computing enables analysis of information processing at the source of the data, which sometimes is referred to as in-network (He et al 2015) or on-board processing (Lazarescu 2014). This paradigm not only reduces the huge workload of central computing servers (e.g., clouds) but also decreases the latency of data processing, which includes the latency for sending the required data plus the response time for performing the task on the cloud server (Samie et al 2016b).…”

“…However, to offload the computation, the raw or partially/processed data must be transmitted to the gateway, and this is where the bandwidth constraint comes into play. The total throughput of low-power wireless technologies for IoT is only a few kilobits per second (Samie et al 2016b), which sometimes may even decrease due to the interference.…”