Industry 4.0 is characterized by digitalized production facilities, where a large volume of sensors collect a vast amount of data that is used to increase the sustainability of the production by e.g. optimizing process parameters, reducing machine downtime and material waste, and the like. However, making intelligent data-driven decisions under timeliness constraints requires the integration of time-sensitive networks with reliable data ingestion and processing infrastructure with plug-in support of Machine Learning (ML) pipelines. However, such integration is difficult due to the lack of frameworks that flexibly integrate and program the networking and computing infrastructures, while allowing ML pipelines to ingest the collected data and make trustworthy decisions in real time. In this paper, we present AIDA - a novel holistic AI-driven network and processing framework for reliable data-driven real-time industrial IoT applications. AIDA manages and configures Time-Sensitive networks (TSN) to enable real-time data ingestion into an observable AI-powered edge/cloud continuum. Pluggable and trustworthy ML components that make timely decisions for various industrial IoT applications and the infrastructure itself are an intrinsic part of AIDA. We introduce the AIDA architecture, demonstrate the building blocks of our framework and illustrate it with two use cases. 

Software-Defined Internet of Vehicles (SD-IoV) is an emerging technology that is being used in modern intelligent transportation systems (ITS). The ultimate goal of SD-IoV is to provide seamless connectivity to the end-users with low latency and high-speed data transfer. However, due to the increase in the density of the connected IoV using an open channel, i.e., the Internet, the foremost challenges of high power consumption and secure data transfer are inevitable in such an environment. An external eavesdropper may intercept the transmitted message to access the legitimate information over the public channel, i.e., the Internet. Most of the solutions reported in the literature to tackle these issues may not be applicable in the SD-IoV environment due to high computation and communication costs. Motivated from this, in this paper, the problems of high power consumption and secure data transfer in SD-IoV are formulated using mixed-integer non-linear programming (MINLP) with associated constraints. To solve the aforementioned problem, we propose a joint power optimization and secrecy ensured scheme known as SecGreen. SecGreen has an efficient energy harvesting algorithm using simultaneous wireless information and power transfer (SWIPT) to maximize the energy efficiency. Moreover, to mitigate various security attacks, a resilient lightweight secrecy association protocol is designed between vehicle and trusted gateway node of SD-IoV so that only trusted vehicles can communicate with each other and with the nearest base stations. The secrecy association protocol uses security primitives such as- physically unclonable function (PUF), one-way hash function, and bitwise exclusive OR (XOR) operations which are suitable for energy-constraint sensors in SD-IoV. The performance of the SecGreen is compared with the existing schemes, Stable & Scalable Link Optimization (SSLO), and Secure & Energy-Efficient Blockchain-enabled (SEEB) respectively. The result shows that when the number of packets across the subchannel increases, the energy consumption increases. Also, the result shows that the proposed scheme attains 22.5% and 20.34% better energy efficiency as compared to SSLO and SEEB schemes, respectively. In addition, the SecGreen scheme achieves 37.48% and 32.15% higher throughput as compared to SSLO and SEEB schemes. The results obtained show the superior performance of the proposed SecGreen scheme in comparison to these existing competitive schemes in the literature.

The need to provide services closer to the end-user proximity leads to the exchange of a large volume of data generated from the smart devices deployed at different geo-distributed sites. The massive amount of data generated from the smart devices need to be transmitted, analyzed, and processed. This requires seamless data exchanges among geo-separated nodes, which results in a considerable burden on the underlying network infrastructure and can degrade the performance of any implemented solution. Therefore, a dynamic, agile, and programmable network management paradigm is required. To handle the challenges mentioned above, software-defined networking (SDN) gained much attention from academia, researchers, and industrial sectors. Shifting the computational load from forwarding devices to a logically centralized controller is a dream of every network operator who wants to have complete control and global visibility of the network. Also, the concept of network functions virtualization (NFV) in SDN controller is required to increase resource utilization efficiency. Thus, in this paper, a comprehensive survey on SDN for various smart applications is presented. This survey covers the infrastructural details of SDN hardware and OpenFlow switches, controllers, simulation tools, programming languages, open issues, and challenges in SDN implementation with advanced technologies such as 5G and microservices. In addition, the challenges on the control plane and data plane are highlighted in detail, such as fault tolerance, routing, scheduling of flows, and energy consumption on OpenFlow switches. Finally, various open issues and challenges future scope of SDN are discussed and analyzed in the proposal.