The blended-wing-body underwater glider (BWBUG) is a new type of underwater vehicle that has been applied in natural resource exploration with great success. Compared with conventional torpedo shapes, BWBUG's shape has a higher lift-to-drag ratio (LDR), so its shape design has become a research focus of ocean engineering in recent years. It is noteworthy that the traditional design process assumes no prior knowledge and starts from scratch. However, since problems rarely exist in isolation, solving the shape problem of a traditional glider may provide useful information, but the disparity in design space impedes information transmission. This paper presents a heterogeneous transfer optimization method for glider shape, which consists of four parts: simulation, image processing, manifold learning, and the evolution algorithm. The simulation's goal is to create pressure and velocity clouds. Manifold learning will use the information from cloud maps to create a low-dimensional feature space. The information mapped in low-dimensional space will be used to assist evolutionary algorithms in searching for optimal solutions. The proposed method was tested for the shape optimization problem of a BWBUG, and the results show that knowledge learned from different but related problem domains is potentially beneficial to the new design.

Virtual reality (VR) over wireless has emerged as an important application in future mobile networks. However, it is difficult for the existing mobile networks to meet the requirements of massive data transmissions and ultra-low latency for wireless VR. Multi-access edge computing (MEC) network, providing caching and computing capacities at network edge, emerges as a promising method to support wireless VR. However, mobile VR users' quality of experience (QoE) may be degraded by frequent handoffs. In this paper, we propose a proactive caching, computing and communication (3C) resource allocation method to provide smooth VR videos to handoff users. Specifically, the expected 3-dimensional (3D) video or 2D video for rendering is cached at a target base station (BS) ahead of time, and the size and quality of the video file are decided according to the 3C resources at the BS. Then, we model the the proactive 3C resource allocation as a Markov decision process and an effective allocation policy is obtained by a model-free algorithm based on deep reinforcement learning. Numerical results show that the proposed method can provide VR users with high QoE when they are moving between BSs.