Internet of Things (IoT) becomes an emerging network technology that expedites billions of devices to be connected via the Internet to provide real-time intelligent application services. The benefits of Software-Defined Networking (SDN) can be used to fulfill IoT requirements. Quality of Service provisioning is an on-going demand in software-defined IoT (SD-IoT), particularly for large scale environments. In this paper, we address this issue by proposing a seamless model of AI-aided Traffic Differentiated QoS Routing and Dynamic Offloading in distributed fragmentation optimized SDN-IoT. Firstly, we propose a Multi-Criterion based Deep Packet Inspection method for classifying the network traffic, which is held in Edge Routers (access points). Secondly, we construct a Partially Connected Network Topology using the ISOMAP algorithm for an effective rule placement and routing. We propose a Traffic Differentiated QoS Routing for forwarding data packets via the most suitable switches. We select the optimum route by Deep Alternative Neural Network (DANN). Based on the relationships among switches, the path is selected and flow rules are deployed. The poor QoS is often caused by load imbalance in controllers and switches. To overwhelm this issue, we propose a Dynamic Offloading scheme in SD-IoT. We offload the data packets from the overloaded controller to the underloaded controller using Hassanat Distance-based K-nearest neighbors (HDK-NN) algorithm. Similarly, we propose a Ranking-based Entropy function (R-Ef) to allow dynamic offloading among switches. Simulation is performed using the NS3.26 simulator and the results proved that our proposed AI-aided SD-IoT model provides superior QoS performance compared to previous approaches.

Contemporary dynamic market conditions are characterized by high levels of competition. Businesses are forced to make continuous changes in order to maintain a high level of customer’s satisfaction. Contact centers are part of the global economy and a key channel for communication with customers. Access to the contact centers is realized through several channels (telephone, e-mail, fax, web forms, etc.), but the primary method is still a phone call. Most call centers use Interactive Voice Response (IVR) to route users with a particular problem for directing the user to an agent with appropriate capabilities (Skill-based routing – SBR). This type of contact center operation can have a negative impact on the quality considering customer’s experience, due to the complexity and length of the process, which often results in directing calls to the inadequate agent and describing the problem multiple times to reach the right agent. This paper aims at applying machine learning methods based on prior experience with matching customers and agents in order to reduce time and target agents with adequate problem-solving abilities.

Routing process should encompass finding the best route through the network according to different criteria, with respect to the principle of load balancing, dynamic adaptation to current network conditions, special treatment of traffic based on QoS levels, as well as minimum energy consumption through energy-aware routing. The emergence of the IoT paradigm, 5G networks, increased number of real-time and mobile applications, as well as the increasingly complex requirements in terms of QoS, have put a grave task ahead of the researchers and the industry. Adaptive and efficient management of current network and traffic, and basis for making the networks resistant and ready for the inevitable changes in the foreseeable future, must be ensured. The idea of software-defined networks has offered a new architecture that seeks to overcome the disadvantages of classical network architectures. This approach has enabled direct programmability of the network, faster and simpler introduction of innovations, greater granularity of routing criteria, implementation of consistent and comprehensive policies, real-time response to changes, etc. This paper is a state-of-the-art overview of SDN traffic routing benefits in different network environments, as well as open issues and challenges to be addressed in future research.

An enormous amount of data in real space and better means of collecting, storing, analyzing and modeling are available through to the use of modern ICT solutions. Geographic Information Systems (GIS) are developed to make their basic operations a matrix for a thorough knowledge of the real world. With the development of modern information and communication technologies, these systems have become the means of an integrated, multidisciplinary approach to research, regardless of the space size and the dynamics of phenomena in it. Using the power of GIS systems, it is possible to improve and facilitate operations in all segments of traffic engineering, from planning to traffic management by performing spatial analyzes with appropriate visualization. Real benefits of using GIS are reflected in possibility of integrating spatial data with other types of information, such as various measurements in traffic and traffic statistics, into a single application for complex analysis. GIS enables the detection of patterns that would otherwise be difficult or impossible to notice, and provides additional assistance in essential understanding of complex real systems such as the transport system itself.