HARL enables agents to execute cooperative tasks by adopting agent-specific policies. Most of existing HARL methods use individual policy neural networks to ensure monotonic improvement, which leads to substantial computational overhead. The proposed SDE-HARL overcomes this limitation by decomposing each agent's policy neural network into a lightweight local neural network and a global neural network executed at an edge server. Each local neural network generates and sends a compressed latent representation to the edge server, which aggregates the representations and produces agent-specific inferences. As such, SDE-HARL allows to significantly save computing and networking resources while preserving agent-specific behavior. A key feature of SDE-HARL is grouping agents with similar roles via a role-aware mechanism and share partial parameters in their global networks, while an identity-aware mechanism is introduced to promote behavioral diversity among agents within the same group. We prototyped SDE-HARL on an experimental testbed composed of a Jetson Nano and Raspberry PI to measure latency and network resource consumption. We evaluated SDE-HARL's performance on several benchmark datasets, including Google Research Football and StarCraft II. Experimental results show that SDE-HARL reaches up to 90% win rate while reducing latency, energy consumption, and networking overhead respectively by 2x, 2.5x, and 5x compared to existing work.

Hierarchical edge-cloud computing-aided Internet of Things (IoT) networks offer low-latency and cost-efficient services to a growing number of data-intensive IoT devices. However, optimizing service placement, which involves determining the most suitable locations within a network to deploy various services, is critical to balancing workloads dynamically and ensuring efficient resource utilization. In this paper, we jointly optimize service placement, edge/cloud cooperation, task offloading, and bandwidth allocation to enhance processing efficiency and response times. The main objective is to minimize both the overall end-to-end latency and the system cost, including service deployment and operational costs. The formulated problem belongs to the class of non-convex mixed-integer nonlinear programming, where finding a feasible solution is already challenging. Towards a stable system, we first transform the original problem into a more tractable form and then decompose it into sub-problems which are solved at different timescales. Combining tools from relaxation and the successive convex approximation method, we develop iterative algorithms to solve these problems efficiently. With an appropriate penalty parameter, the proposed algorithms guarantee convergence to at least a local optimum. We produce extensive numerical results to demonstrate the superior performance of the proposed algorithms over benchmark schemes as well as emphasize the significance of the joint service placement and resource allocation in enhancing system performance and efficiency.

WiFi sensing-based human pose estimation (HPE) has gained significant attention in the academic community due to its advantages over vision- and sensor-based methods, including nonintrusiveness, convenience, and enhanced privacy protection. However, most existing WiFi-based pose Estimators suffer from poor performance and lack robustness in the presence of random noise. To address these challenges, this article presents a novel HPE architecture comprising two key modules: 1) a Denoiser and 2) an Estimator. The Denoiser is based on an autoencoder structure, while the Estimator is based on a new convolutional neural network (CNN) called SDy-CNN, which is designed to dynamically focus on high-information subcarriers of orthogonal frequency division multiplexing signals. Additionally, Bayesian optimization is employed to fine-tune the architecture’s parameters for optimal performance flexibly. Experiments conducted on a comprehensive dataset, MM-Fi, demonstrate that the proposed architecture significantly outperforms existing state-of-the-art Estimators, achieving up to an 8.38% improvement in HPE accuracy in clean data scenarios and up to a 14% improvement in noisy data scenarios. It has also been proven to gain computational efficiency when being much faster than other methods.