Attack-Aware IoT Network Traffic Routing Leveraging Ensemble Learning

Network Intrusion Detection Systems (NIDSs) are indispensable defensive tools against various cyberattacks. Lightweight, multipurpose, and anomaly-based detection NIDSs employ several methods to build profiles for normal and malicious behaviors. In this paper, we design, implement, and evaluate the performance of machine-learning-based NIDS in IoT networks. Specifically, we study six supervised learning methods that belong to three different classes: (1) ensemble methods, (2) neural network methods, and (3) kernel methods. To evaluate the developed NIDSs, we use the distilled-Kitsune-2018 and NSL-KDD datasets, both consisting of a contemporary real-world IoT network traffic subjected to different network attacks. Standard performance evaluation metrics from the machine-learning literature are used to evaluate the identification accuracy, error rates, and inference speed. Our empirical analysis indicates that ensemble methods provide better accuracy and lower error rates compared with neural network and kernel methods. On the other hand, neural network methods provide the highest inference speed which proves their suitability for high-bandwidth networks. We also provide a comparison with state-of-the-art solutions and show that our best results are better than any prior art by 1~20%.

Optimal Taxes in Atomic Congestion Games

How can we design mechanisms to promote efficient use of shared resources? Here, we answer this question in relation to the well-studied class of atomic congestion games, used to model a variety of problems, including traffic routing. Within this context, a methodology for designing tolling mechanisms that minimize the system inefficiency (price of anarchy) exploiting solely local information is so far missing in spite of the scientific interest. In this article, we resolve this problem through a tractable linear programming formulation that applies to and beyond polynomial congestion games. When specializing our approach to the polynomial case, we obtain tight values for the optimal price of anarchy and corresponding tolls, uncovering an unexpected link with load balancing games. We also derive optimal tolling mechanisms that are constant with the congestion level, generalizing the results of Caragiannis et al. [8] to polynomial congestion games and beyond. Finally, we apply our techniques to compute the efficiency of the marginal cost mechanism. Surprisingly, optimal tolling mechanism using only local information perform closely to existing mechanism that utilize global information, e.g., Bilò and Vinci [6], while the marginal cost mechanism, known to be optimal in the continuous-flow model, has lower efficiency than that encountered levying no toll. All results are tight for pure Nash equilibria and extend to coarse correlated equilibria.

Interference-free Walks in Time: Temporally Disjoint Paths

We investigate the computational complexity of finding temporally disjoint paths or walks in temporal graphs. There, the edge set changes over discrete time steps and a temporal path (resp. walk) uses edges that appear at monotonically increasing time steps. Two paths (or walks) are temporally disjoint if they never use the same vertex at the same time; otherwise, they interfere. This reflects applications in robotics, traffic routing, or finding safe pathways in dynamically changing networks. On the one extreme, we show that on general graphs the problem is computationally hard. The "walk version" is W[1]-hard when parameterized by the number of routes. However, it is polynomial-time solvable for any constant number of walks. The "path version" remains NP-hard even if we want to find only two temporally disjoint paths. On the other extreme, restricting the input temporal graph to have a path as underlying graph, quite counterintuitively, we find NP-hardness in general but also identify natural tractable cases.

Adaptive Traffic Routing Practice for Load Balance and Congestion Control in AdHoc Network in Cloud-MANET

Cloud services can dramatically improve the computing proficiency of mobile devices. Mobile operators can count on the cloud to carry out thorough computing operations such as research, data mining and multimedia handling. Load balancing and network congestion are the difficult ad hoc network tasks due to its un-predictable dynamic behavior and random topology alteration of such systems. The most important reason of data loss in wireless grids is flexibility, network congestion and channel errors. The majority of the accessible directing schemes deal with the energy efficiency, congestion and balancing overload load outstandingly. Proficient routing protocol is proposed in this manuscript which will adaptively control the network congestion and achieve load balancing in Mobile Ad Hoc Networks (MANET). The proposed technique discovers multiple alternate paths between two nodes. The cost and stability of the link and traffic load is calculated depending on the available power of the participated nodes. If the traffic load on a specific link escalates beyond the threshold value, the traffic will be distributed to other alternate links. It is clear with the simulation outcomes that the projected approach enhances the network lifespan by integrating load balancing and congestion control with energy efficient algorithm. Thereby, it reduces the packet dropping probability and node to node delay in the network and improves the system lifetime.

A STUDY OF ROUTING METHODS IN URBAN WIRELESS MESH NETWORKS BASED ON REINFORCEMENT LEARNING

Приведены результаты исследования методов маршрутизации на основе обучения с подкреплением с помощью имитационной модели. Рассмотрена задача маршрутизации сетевого трафика для фрагмента ячеистой сети городского масштаба, управляемой на основе технологий искусственного интеллекта. Представлена модель системы массового обслуживания для изучения процесса маршрутизации, а также обучения выбора маршрута. Имитационная модель фрагмента ячеистой сети разработана в пакете Anylogic и обучается на основе платформы Microsoft Bonsai. The results of the study of network traffic routing methods based on reinforcement learning using a simulation model are presented. The problem of network traffic routing for a fragment of a city-scale mesh network, controlled on the basis of artificial intelligence technologies, is considered. The article presents a queueing model for studying the routing process, as well as learning how to choose a route. The mesh network fragment simulation model was developed in the Anylogic package and is trained on the basis of the Microsoft Bonsai platform.

FAIR: User-friendly delivery of climate and weather data

<p>Climate and weather data play an important role for <span>e.g.</span><span> identifying actions against climate change and optimizing industries. However, a correct understanding and handling of such data is often difficult for users without a meteorological background. Moreover, specialized software solutions and an infrastructure capable of handling large amounts of data are needed to process and analyze these data.</span><span> </span></p><p><span>The research project FAIR addresses this issue by simplifying the exchange of information and data between the German Meteorological Service (DWD) and stakeholders from industry and public. To fulfill this purpose, microservices for processing, caching, visualizing, and analyzing meteorological data in an efficient way are being developed. Processing comprises, for example, the selection of specific information from model data or the conversion of the result into formats commonly used by the user. The compilation of microservices makes it possible to support different types of applications and at the same time to make data from third parties available to the DWD. To demonstrate the utility of these microservices, three test scenarios are considered: 1) wind farm planning, 2) integration of meteorological data for individual traffic routing, and 3) planning of social events such as festivals.</span><span> </span></p><p><span>In this article, we present the general idea and the current state of the project. The focus is on the challenges that have been identified for the three test scenarios and our technical approaches to address them. </span><span>Herein we present the developed architecture, the data flow, the FAIR portal and the handling of metadata.</span></p>