Energy-Efficient Computation Offloading in Delay-Constrained Massive MIMO Enabled Edge Network Using Data Partitioning

Abstract

We study a wireless edge-computing system which allows multiple users to simultaneously offload computation-intensive tasks to multiple massive-MIMO access points, each with a collocated multiaccess edge computing (MEC) server. Massive-MIMO enables simultaneous uplink transmissions from all users, significantly shortening the data offloading time compared to sequential protocols, and makes the three phases of data offloading, computing, and downloading have comparable durations. Based on this three-phase structure, we formulate a novel problem to minimize a weighted sum of the energy consumption at both the users and the MEC server under a round-trip latency constraint, using a combination of data partitioning, transmit power control and CPU frequency scaling at both the user and server ends. We design a novel nested primal-dual algorithm using two different methods to solve this problem efficiently. Optimized solutions show that for larger requests, more data is offloaded to the MECs to reduce local computation time in order to meet the latency constraint, despite higher energy cost of wireless transmissions. Massive-MIMO channel estimation errors under pilot contamination also causes more data to be offloaded to the MECs. Compared to binary offloading, partial offloading with data partitioning is superior and leads to significant reduction in the overall energy consumption.

Task offloading and resource allocation in an uncertain network

“…(1) 基于最大排队等待时间的静态卸载算法 MWT SO (maximum waiting time based static offloading algorithm) [7] : 用户在基于 MEC 服务器最大排队时间的静态网络中 1) , 对本地 CPU 频率、传输功 率、MEC 服务器的 CPU 频率和卸载决策进行优化;…”

Energy Optimization in Massive MIMO UAV-Aided MEC-Enabled Vehicular Networks

“…Also, the optimization of energy consumption and maximum delay, under perfect and imperfect CSI estimation, was studied for MIMO [46] and massive MIMO [47] systems. Moreover, single-cell [48] and multi-cell [49] MEC networks that enable the simultaneous offloading of multiple APs were previously presented. The benefits of combining massive MIMO and millimeter wave (mmWave) frequencies in wireless local area networks (WLANs) with MEC were underlined in [50], whereas a cell-free system consisting of multiple single/multi-antenna APs with MEC servers and a central cloud server was described in [51].…”

On-Request Wireless Charging and Partial Computation Offloading In Multi-Access Edge Computing Systems

“…µ is the proportionality parameter between the amounts of requested and computed data and is not restricted to the range [0,1], rather it adds an application-centric flexibility to our system model in terms of the data size in downlink. For instance, µ < 1 for face recognition applications or µ 1 for video-rendering applications [32] [33] [24]. The AP simultaneously transmits computed results for all users, and the total energy and time overhead for results downloading are then given as…”

“…Such a system model has versatile applicability to different use-cases. Examples include (i) AR/VR applications in human-machine interfaces used in smart factories, where complex processing tasks may be offloaded to the edge network, which not only enables easy access to different context information available in the network but also prevents head-mounted AR/VR gear from becoming too warm and uncomfortable to wear [22], (ii) gaming or training service data between two 5G connected devices [23], (iii) real-time map rendering for autonomous vehicular applications [24], and (iv) professional low-latency periodic audio transport services for Audio-Video (AV) production applications, music festivals etc. [25].…”