We consider a resource allocation and offloading decision-making problem in a mobile edge computing (MEC) network. Since the locations of user equipments (UEs) vary over time in practice, we consider a dynamic network, where the UEs could leave or join the network coverage at any location. Since the joint offloading decision that minimizes the network cost also varies with the topology, the expected best offloading decision for the previous topology would not match the new topology. Consequently, the system suffers from recurring cost peaks due to the topology change. Thus, we propose a robust distributed hierarchical online learning approach to enhance the algorithm’s robustness and reduce the cost peaks. Specifically, the UEs learn the utility of each offloading decision via deep Q networks (DQNs) from their interaction with the MEC network. Meanwhile, the computational access points (CAPs) train their deep neural networks (DNNs) online with the real-time data collected from the UEs to predict their corresponding Q-value vectors. Therefore, the UEs and CAPs form a hierarchical collaborative-learning structure. When the topology changes, each UE downloads its Q-value vector as the Q-bias vector and learns its difference from the actual Q-value vector via its DQN. With different agents learning distributedly, both the peak and sum costs are reduced as the joint offloading decision could start from a near-local-optimal point. In simulations, our robust approach successfully reduces the peak cost and sum cost by up to 50% and 30%, respectively. This demonstrates the need for a robust learning algorithm design in a practical dynamic MEC network.

We consider a multi-user multi-server mobile edge computing (MEC) network with time-varying fading channels and formulate an offloading decision and resource allocation problem. To solve this mixed-integer non-convex problem, we propose two hybrid approaches that learn offloading strategy with DQN (opt-DQN) or Q-table (opt-QL) at each user equipment (UE). The communication resources are allocated with an optimization algorithm at each computational access point (CAP). We also propose a pure DQN method that learns both the offloading strategy and resource allocation via Q-learning (QL). We analyze the convergence behavior of the QL-based algorithms from a game-theoretical perspective and demonstrate the performance of the proposed hybrid approaches for different network sizes. The simulation results show that the hybrid approaches reach lower costs than other baseline algorithms and the pure-DQN approach. Moreover, the performance of the pure-DQN approach degrades severely as the network size increases, while opt-DQN still performs the best, followed by opt-QL. These observations demonstrate that the hybrid approach that combines the advantages of both QL and convex optimization is a promising design for a multi-user MEC network, wherein complicated offloading and resource allocation strategies need to be determined in a timely and accurate fashion.

We consider a dynamic mobile edge computing (MEC) network with multiple computational access points (CAPs) that serve user equipment (UEs). We assume that UEs could join or leave the network due to mobility, resulting in the dynamic change in the network topology. To fully exploit the computational resource in the MEC network, the offloading decision, transmission power, and the computational resource should be appropriately allocated, and a robust design that addresses the above issues is necessary. In this work, we propose a robust hierarchical learning approach that applies deep Q networks (DQNs) and deep neural networks (DNNs) at the UEs and CAPs, respectively. Each UE interacts with the network environment and learns the best offloading decision policy in a local scope. Via sharing the local best policy learned by the UEs to the CAPs, the CAPs learn the relation between the UE location and the locally best strategy. The proposed robust approach suppresses the peak in cost caused by the dynamic topology change by up to 160% compared with a non-robust algorithm in the simulation. This demonstrates the necessity and benefit of robust design in a more realistic and dynamic MEC network.

Recently, Mobile-Edge Computing (MEC) has been considered as a powerful supplement to a wireless network by processing computationally intensive tasks for resource-limited mobile devices. However, despite saving computational energy at User Equipment (UE), there is additional transmission energy consumption. As a result, the joint offloading strategy should be carefully selected to save energy and computational time. In this work, we investigated a sum cost minimization problem in a multi-UE multi-computing access point (CAP) system with time-varying channels. Our approach combines the optimization-based resource allocation algorithm with a Q-learning-based strategy selection mechanism. Without the need for communication overhead for CSI and inter- neighborhood cost value exchange, our algorithm shows prominent performance over the benchmark schemes with moderate assumptions.

To explore the possible facilitative role of the Internet in the process of research collaboration, this study endeavored to systematically compare the phenomenon of co‐authorship and the impacts of co‐authorship between pre‐web and post‐web stages in the field of information systems. Three hypotheses were proposed in this study. First, research collaboration increases in the post‐web stage relative to the pre‐web stage. Second, research collaboration is positively related to research impact, operationally defined as the number of citations. Lastly, the positive relationship between research collaboration and research impact is stronger in the post‐web stage than that in the pre‐web stage. Articles published in the field of information systems in both time periods were collected to test the hypotheses. The empirical results strongly support H1 and H2, showing that co‐authorship increases in the post‐web stage, and positively correlates with citations received by information systems articles. The positive effects of interdisciplinary collaborations and collaborations among multiple authors are enhanced in the post‐web stage, but such enhancement is not found for international collaboration. H3 is partially supported.