Jungyeon Baek

The growing demands of the Internet of Things (IoT) require a platform that supports real-time interactions and high availability of services to devices. In this context, the fog computing paradigm has emerged as an attractive solution for processing the data of IoT applications. Owing to the unpredictable traffic demands and resource heterogeneity in the fog environment, a smart workload distribution is essential to achieve high resource utilization and computing efficiency. To this end, this paper considers a joint link and server load balancing problem with multiple cooperative access points, (APs), in a combined edge-fog-cloud environment. The joint optimization problem is formulated as a stochastic game, and an actor-critic reinforcement learning framework, called FLoadNet, is proposed to optimize the joint policy of the multi-agents. FLoadNet consists of a centralized critic network, with parameter sharing and distributed individual actor networks in all the APs. Due to the learning dynamics and partially observable environment, we propose an extended critic network model, where cooperative APs learn to communicate among themselves while evaluating the value function. Unlike previous studies, the proposed critic network is designed to train both value and message functions, which is shown to significantly reduce the computational cost. The main goal of this work is to advance the development of efficient edge learning and the application of distributed learning algorithms specifically to fog network load balancing. The experimental results show that FLoadNet outperforms baseline load balancing methods.

The fifth-generation wireless technology (5G) has been developed with an aim to provide ubiquitous and scalable connectivity for Internet-of-Things (IoT) nodes. Likewise, the cloud radio access network (C-RAN) architecture can be exploited to enable efficient network access to IoT nodes. Nevertheless, the 5G C-RAN architecture is based on large data centers geographically located far apart, which introduces an inevitable overhead. Therefore, to supply real-time data services near by the data terminals, fog computing emerges as a promising solution. However, constrained physical fog resources and delay-sensitive services hinder the application of new virtualization technologies in the baseband unit (BBU) task allocation management of the fog network. To tackle these challenges, a task allocation framework for hierarchical software-defined fog virtual radio access networks (v-RANs) is proposed in this article. Precisely, we apply an enhanced ant colony optimization (ACO) in combination with a max-min algorithm to efficiently determine the optimal path for BBU task allocation management, while minimizing the transmission time for parallel task execution scheduling. Experimental results demonstrate that the queue delay in our approach is 98.38% and 98.82% lower than the round-robin (RR) algorithm and least connection technique (LCT), respectively.

As wireless services and applications become more sophisticated and require faster and higher capacity networks, there is a need for an efficient management of the execution of increasingly complex tasks based on the requirements of each application. In this regard, fog computing enables the integration of virtualized servers into networks and brings cloud services closer to end devices. In contrast to the cloud server, the computing capacity of fog nodes is limited and thus a single fog node might not be capable of computing-intensive tasks. In this context, task offloading can be particularly useful at the fog nodes by selecting the suitable nodes and proper resource management while guaranteeing the Quality-of-Service (QoS) requirements of the users. This article studies the design of a joint task offloading and resource allocation control for heterogeneous service tasks in multifog nodes systems. This problem is formulated as a partially observable stochastic game, in which each fog node cooperates to maximize the aggregated local rewards while the nodes only have access to local observations. To deal with partial observability, we apply a deep recurrent $Q$ -network (DRQN) approach to approximate the optimal value functions. The solution is then compared to a deep $Q$ -network (DQN) and deep convolutional $Q$ -network (DCQN) approach to evaluate the performance of different neural networks. Moreover, to guarantee the convergence and accuracy of the neural network, an adjusted exploration–exploitation method is adopted. Provided numerical results show that the proposed algorithm can achieve a higher average success rate and lower average overflow than baseline methods.