Search

Due to the flexibility of drones, it is promising to use them in Search and Rescue (SAR) operations for intelligently searching for lost humans over large areas. However, the limited computing resources of drones pose challenges when deploying deep neural network models. To address this problem, we design a lightweight human recognition model for drones, combining the Ghost Module and the Mobilenetv3 Block. The Ghost Module generates more feature maps with fewer parameters, and the squeeze-and-excitation (SE) attention module in the Mobilenetv3 Block greatly improves recognition accuracy. Furthermore, recognizing that relying solely on the human recognition model offers limited assistance in SAR operations, we propose a collaborative recognition mode between the drone and the rescue command center (RCC). In this collaborative recognition mode, we design an offloading model for deployment on the drone. The offloading model learns from the middle layer perception features of the lightweight recognition model and selectively offloads the vision taken by the drone to the RCC. The recognition results provided by the RCC are used to update the parameters of the offloading model. We introduce a reinforcement learning algorithm, a dual-buffer-based proximal policy optimization algorithm (DBPPO), to train the offloading model with the goal of maximizing accuracy and recall while minimizing the offloading ratio. Specifically, we incorporate an additional data buffer for training the Actor network in the PPO algorithm in a supervised manner, with supervised training interspersed throughout the PPO training process. Eventually, experiments comparing different methods demonstrate the effectiveness of the lightweight recognition model and the collaborative recognition mode in SAR operations.

In this article, we study the joint platoon partition, power control and spectrum allocation for platoon communication in cellular vehicle-to-everything (V2X) networks with uncertain channel parameters. A distributionally robust (DR) optimization problem is formulated to maximize the vehicle-to-infrastructure (V2I) capacity whilst guaranteeing the reliability of intra-platoon communication. For solving the DR problem, a statistical-based approach is developed to learn the distributional ambiguity set from historical uncertain channels. Then, based on it, a data-driven equivalent transformation approach is proposed to transform the probabilistic vehicle-to-vehicle (V2V) reliability requirement into a deterministic semidefinite expression. Considering that the resource allocation is built on the platoon partition result, the formulated problem is decomposed into a resource allocation problem and a platoon partition problem. Then, a low-complexity two-stage wireless resource allocation strategy is proposed for V2X networks, which contains power control and spectrum matching. After that, the platoon partition is transformed into a specific Markov chain design problem. An exploration-consolidation learning algorithm is proposed to obtain the optimal platoon partition according to the designed Markov transition rate. Finally, simulation results verify that the proposed algorithm is superior to other existing schemes.

This paper investigates the joint resource allocation and group formation for platoon in vehicle-to-everything (V2X) networks under vehicular channel uncertainty. To achieve the high spectrum efficiency and overcome the platoon head communication range limitation, an adaptive multicast-based group cooperation communication model is developed for the platoon with dynamic topology. Considering the heterogeneous characteristics of different types of links, i.e., high capacity for vehicle-to-infrastructure (V2I) links and ultra-reliability for vehicle-to-vehicle (V2V) links, we attempt to maximize the V2I capacity whilst satisfying a probability constraint for ultra-reliable V2V-supported intra-platoon communication. To handle the intractable probability constraint, a support vector clustering (SVC) based method is developed to capture the distributional geometry of massive uncertain channel samples as a sphere in high-dimensional feature space with asymmetric structure. Based on it, the probability constraint is transformed into a tractable linear convex set. After that, an exploration-selection-alternating-iterative algorithm is developed to solve the formulated problem with coupled optimization variables. Specifically, in the exploration process, a two-stage algorithm is proposed for the resource allocation problem under fixed group formation decision, which includes power control and spectrum allocation. During the selection process, a performance difference-based decision transition rate is designed to optimize group formation solution. Simulation results demonstrate the proposed data-driven approach can overcome the over-conservatism of the traditional symmetric-geometry-based uncertainty sets, and the multicast-based group cooperation communication model corresponds to a higher performance on V2I capacity than other traditional schemes.

Mobile edge computing provides the opportunity for edge systems to underpin a variety of computation-intensive yet delay-sensitive applications. We acknowledge that the limited computing and storage resource of an individual edge server allows only a subset of services to be placed at a time. This raises the question of service placement, which refers to where to place each type of service. Moreover, which service to place allows which type of tasks to be processed, and thereby affects task scheduling performance, which refers to where/whether to schedule each task and task splitting among edge and cloud. Respect of the interactions between service placement and task scheduling (SPTS), a joint optimized design of SPTS is investigated in this article. Our main contribution is a novel spatial-temporal collaboration of SPTS to minimize the overall cost of edge systems. Spatial collaboration is explored to enable edge servers within specific geographic regions collaboratively serve users' demands, while temporal collaboration is explored to optimize the SPTS in multiple time slots and pursue a long-term performance. We first propose an online and decentralized algorithm for spatial-temporal collaborative of SPTS. We then extend the proposed single-timescale of the proposed algorithm into multiple timescales to have service (re)placed at a larger timescale and hence alleviate service interruption. While proved to preserve the asymptotic optimality, the larger timescale slow down the optimal service placement decision. A learn-and-adapt strategy is further designed to speed up the service placement. Theoretical analysis and simulations are performed to validate the efficiency of the proposed algorithm.