Because of the dynamic nature of network traffic patterns, such as new traffic application arrivals or flash events, it is becoming increasingly difficult for conventional anomaly detection systems to separate various applications based on their traffic patterns. In this study, by leveraging transport layer packet-level and flow-level features, new structures called application fingerprints are generated, which express such features in a compact and efficient manner. Based on the generated fingerprints, we propose a novel traffic classification framework. The proposed system generates profiles of normal applications using a multi-modal probability distribution. The proposed classification framework is then extended to detect distributed denial of service (DDoS) attacks from the collected statistical information at flow level. To demonstrate the feasibility of the proposed system, we evaluate its performance using five realworld traffic datasets. The experiment results show that the proposed method is capable of achieving an accuracy of over 97%, whereas the misclassification rate is only 2.5%.

Mobile data traffic is increasing astronomically. This enormous extent was not only caused by the increasing in the number of mobile devices, but also the growing number of applications running on clouds. Most of these mobile devices have limited resources for computing, they are relying on cloud computing, which is inadequate to realize millisecond-scale latency in the 5G network. To deal with this issue, Mobile Edge Computing (MEC) has been introduced to supplement cloud computing by pushing Computing, Caching, Communication, and Control (4C) to the edges. However, the proposed MEC server at each base station is not enough to deal with 4C, when it operates independently, and without any collaboration with other MEC servers. This results in increasing the delay and making backhaul to continue suffering from huge data exchange between end-users and remote clouds. To address this challenge, we propose collaborative cache allocation and computation offloading, where the MEC servers collaborate for executing computation tasks and data caching. We formulate an optimization problem that aims at maximizing the resource utilization. The simulation results show that our proposal is easy to be implemented in production network.

As the Internet of Things (IoT) landscape rapidly evolves, robust network security measures are imperative. In particular, Intrusion Detection Systems play a very important role in the preservation of an IoT environment from malicious activities. This paper provides a comprehensive performance comparison of various machine learning classifiers, including K-Nearest Neighbors, Gradient Boosting, XGBoost, Support Vector Machines, Random Forests, Decision Trees, and Extremely Randomized Trees, for intrusion detection in IoT networks. Comparative analysis shows that although all models did very well, the ensemble methods—GB, XGBoost, RF, and ERT—constantly performed better than others in F1-Score, recall, accuracy, and precision. Among them, ERT is turned out to be the most effective model for real-time attack detection on IoT devices, with an accuracy of 99.7% besides excellent precision and recall. XGBoost and RF also turn out to have high reliability and accuracy with F1-Scores of 0.95. These findings further underscore that ensemble methods outperform in intrusion detection for IoT networks and, thus, offer important insights to improve security within networks and protect critical IoT-based infrastructures from a variety of threats.

The modern day advancement is increasingly digitizing our lives which has led to a rapid growth of data. Such multidimensional datasets are precious due to the potential of unearthing new knowledge and developing decision-making insights from them. Analyzing this huge amount of data from multiple sources can help organizations to plan for the future and anticipate changing market trends and customer requirements. While the Hadoop framework is a popular platform for processing larger datasets, there are a number of other computing infrastructures, available to use in various application domains. The primary focus of the study is how to classify major big data resource management systems in the context of cloud computing environment. We identify some key features which characterize big data frameworks as well as their associated challenges and issues. We use various evaluation metrics from different aspects to identify usage scenarios of these platforms. The study came up with some interesting findings which are in contradiction with the available literature on the Internet.

Information Centric Networking (ICN) is one of the most promising future Internet architectures to tackle the increasing network traffic by enabling in-network caching to cache popular contents. Although in-network caching reduces the network traffic by providing requested content locally to the users, several challenging issues are still unsolved. For example, identical contents are replicated in all routers along each request’s forwarding path, which incurs faster cache replacement and degrades cache utilization, and temporally cached content’s locations are not easy to track or search in the network. Besides, it is tough to correctly predict future popularity of contents and decide which contents to store. Hence, in this paper, an online caching and cooperative forwarding scheme is proposed to enhance cache utilization and to reduce network delay, as well as reduce the workload on each router. The caching problem is formulated as a Ski-Rental problem, which is a classical method for online decision making, in combination with consistent-hashing to obtain an online coordinated caching solution. The proposed request forwarding scheme is based on consistent-hashing where every router knows the potential location of the cached copy of the requested content and thereby avoiding the unnecessary forwarding. Finally, the proposed request forwarding and caching schemes were validated by a chunk-level simulator. The simulation results show that the proposed scheme outperforms the existing algorithms in terms of content hit rate, server load, the processing load on routers and access delay.

The router’s buffer accommodates transient packets to guarantee that the network’s links do not become idle. However, buffer overflow causes packet loss, which is a signal of congestion. In Content Centric Networking (CCN), the Interest packet, which is used for requesting content, may be dropped due to such congestion. Each Interest packet is assigned a specific lifetime, and when the lifetime expires without obtaining the requested content, the consumer needs to resend the Interest. However, waiting for the expiration of an Interest’s lifetime for retransmission is only appropriate for best effort traffic rather than services that are delay sensitive. In order to provide delay-sensitive applications with better quality of service, we propose a congestion control mechanism for CCN, in which, we prevent congestion before it happens through monitoring buffer size. Upon reaching the buffer threshold, the node notifies its downstream node. On receiving the notification, the downstream node adjusts traffic rate by allocating new incoming Interests to other face(s). However, when the downstream node fails to reduce traffic rate, the same procedure continues until the consumer node reduces sending rate. The simulation results show that the proposed mechanism is capable of significant performance improvements, with higher throughput.