SDN-Enabled Adaptive and Reliable Communication in IoT-Fog Environment Using Machine Learning and Multiobjective Optimization

Abstract

The Internet of Things (IoT) has inspired the development of emerging new applications. Backed by the resourceful fog computing, the IoT devices are capable to meet the demands of tasks, even the most computationally-intensive ones. However, many existing IoT applications are unable to perform well, while communicating with the fog server due to different QoS requirements. Constantly changing traffic demands of applications is another challenge to consider. The demand for real-time applications includes communicating over a path that is less prone to delay. Moreover, applications that offload computationally-intensive tasks to the fog server need a reliable path that has lower probability of link failure. This results in a trade-off among continuously changing objectives, i.e., minimizing the end-to-end delay and maximizing the reliability of paths between IoT devices and the fog server. To tackle this problem, we propose a novel approach that considers an SDNenabled multi-hop scenario for the IoT-Fog environment. We evaluated the reliability level of links by employing the real-life network statistics recorded for a period of over 5 months. We use a multi-objective optimization (MOO) algorithm to search the Pareto-optimal paths by considering the two conflicting objectives. Our experimental evaluation considers two different applications -a real-time application (App-1) using UDP sockets and a task offloading application (App-2) using TCP sockets. Our results show that: (i) using MOO, the trade-off between the two objectives can be optimized, and (ii) the SDN controller was able to make adaptive decision on-the-fly to choose the best path from the Pareto-optimal set. The App-1, communicating over the selected path finished its execution in 13% less time than communicating over the shortest path. The App-2 had 41% less packet loss using the selected path compared to using the shortest path.

Impact of Artificial Intelligence-enabled Software-defined Networks in Infrastructure and Operations: Trends and Challenges

“…SDN offers network simplification, reduced costs, productivity in bandwidth, and seamless cloudbased on-ramps with substantial application performance, particularly for critical applications, with no privacy or protection. The works discussed in [15] and [16] are evidence of how artificial intelligence fusion with SDN has improved the results in terms of performance. 1) Combining SDN with 5G: 5G networks spread across vertical and regional areas over the next decade are increasing.…”

“…Varying the monitoring period from 3, 5, 10 seconds, various metrics were compared with static, dynamic, and artificial intelligence-enabled routing to prove that the network can learn from past experiences. Machine learning is www.ijacsa.thesai.org a stream of artificial intelligence, where it is also used to optimize multiple objectives and improve QoS in [16]. Also, this shows that artificial intelligence increases reliable links in the process of communication in terms of TCP and UDP.…”

Resource Management in SDN-Based Cloud and SDN-Based Fog Computing: Taxonomy Study

“…The machine learning approach is utilized in [48], specifically the K-Nearest Neighbor (KNN) algorithm, together with multi-objective optimization-specifically, Non-dominated Sorting Genetic Algorithm (NSGA-II)-to meet the QoS constraint based on application type, either maximizing the path reliability or minimizing the delay. The system consists of three parts that are network architecture that consists of SDN switches, fog nodes, IoT devices and links associated with QoS parameters, i.e., bandwidth and transmission delay.…”

Open Innovation Mode of Green Innovation System for Manufacturing Industry

“…ey often do not worry too much about market risk or market value. It is easier to develop a breakthrough technology with high market value and high technology content than the enterprises [19].…”