Search

Multi-access Edge Cloud (MEC) networks are powerful for providing emerging computation-intensive and latency-sensitive applications with low latency leveraging ubiquitous edge devices. These networks enable complex applications to be split into multiple components/subtasks and deployed among multiple edge servers with limited computation and communication resources. However, multiple subtasks within an application are dependent on each other. They cannot be executed in parallel, resulting in non-trivial resource waste when allocating resources to every subtask throughout the lifetime of the application. This article investigates the multi-component task offloading problem in MEC networks that addresses the dependencies among components and three-dimensional (3D) resource allocation, i.e., computation, communication, and time slots. The problem is NP-hard and challenging to solve due to the complex task dependencies, including triangular dependencies among multiple subtasks and the routing of edges between dependent subtasks. To address the challenge, we first propose a non-destructive task reconfiguration algorithm that transforms a task call graph into multiple sequential layers, breaking out the triangular dependency. Then, we develop a dePendency-awaRe task offloAding algorithm wIth taSk rEconfiguration (PRAISE) algorithm to maximize the total offloading benefit. PRAISE decouples the original problem into task offloading and 3D convex resource optimization. Simulation results show that PRAISE outperforms baselines with higher system benefits and lower resource costs.

Free space optical communication (FSO) has been becoming one of the main directions of future communication network due to its advantages of high transmission rate, small divergence angle, and strong confidentiality. The acquisition, tracking, pointing (ATP) sub-system is an important guarantee for stable communication of FSO system. In the AI-enabled ATP system, data augmentation algorithms are effective to reduce the size of the dataset for spot prediction, and thus to lower the system structural complexity. In this letter, we propose a novel data augmentation algorithm that introduces wavelet transform into the fusing-and-filling generative adversarial network (F2GAN). The wavelet transform is utilized to convert the image information from time domain to frequency domain. The diversity of the generated images obtained from the GAN model is thus enhanced with the richer details. The experimental results show that, compared to the F2GAN algorithm, the proposed algorithm can improve peak signal to noise ratio by 14.5%, structure similarity index measure by 11.8%, and learned perceptual image patch similarity by 21%, respectively.

Cooperative communication has been widely studied as an effective technique for free-space optical (FSO) systems to combat the effects of atmospheric conditions and beam misalignment. Related works on cooperative FSO communication mostly used a fixed splitter to uniformly distribute optical power for broadcast transmission, which tends to cause the insufficient utilization of optical power when the relay links have different channel statuses. In this paper, we focus on the optical power utilization of cooperative FSO communication, which remains less touched in previous works, while it is a decisive factor in system performance. We propose an elastic optical splitter structure to improve the efficiency of optical power by dynamically adjusting its optical output to the changing atmospheric channels. The elastic optical splitter brings a new chance for the relay selection and power allocation, which will become a different issue from that in traditional cooperative FSO systems. Thus, we further propose an adaptive relay selection and power allocation scheme using a deep reinforcement learning algorithm. Results demonstrate that the proposed elastic optical splitter is superior to the fixed optical splitter for cooperative FSO communication in bit error rate (BER) by a performance improvement of 1 to 2 orders of magnitude. Along with the proposed adaptive relay selection and power allocation scheme, the performance is further improved by more than 25% under different channel conditions.