The Internet of Things (IoT) is shaping the next generation of cyber-physical systems to improve the future industry for smart cities. It has created novel and essential applications that require specific network performance to enhance the quality of services. Since network performance requirements are application-oriented, it is of paramount importance to provide tailored solutions that seamlessly manage the network resources and orchestrate the network to satisfy user requirements. In this article, we propose ELISE, a Reinforcement Learning (RL) framework to optimize the slotframe size of the Time Slotted Channel Hopping (TSCH) protocol in IIoT networks while considering the user requirements. We primarily address the problem of designing a framework that self-adapts to the optimal slotframe length that best suits the user’s requirements. The framework takes care of all functionalities involved in the correct functioning of the network, while the RL agent instructs the framework with a set of actions to determine the optimal slotframe size each time the user requirements change. We evaluate the performance of ELISE through extensive analysis based on simulations and experimental evaluations on a testbed to demonstrate the efficiency of the proposed approach in adapting network resources at runtime to satisfy user requirements.

Wireless Sensor Networks (WSNs), which are enablers of the Internet of Things (IoT) technology, are typically used en-masse in widely physically distributed applications to monitor the dynamic conditions of the environment. They collect raw sensor data that is processed centralised. With the current traditional techniques of state-of-art WSNs programmed for specific tasks, it is hard to react to any dynamic change in the conditions of the environment beyond the scope of the intended task. To solve this problem, a synergy between Software-Defined Networking (SDN) and WSNs has been proposed. This paper aims to present the current status of Software-Defined Wireless Sensor Network (SDWSN) proposals and introduce the readers to the emerging research topic that combines Machine Learning (ML) and SDWSN concepts, also called ML-SDWSNs. ML-SDWSN grants an intelligent, centralised and resource-aware architecture to achieve improved network performance and solve the challenges currently found in the practical implementation of SDWSNs. This survey provides helpful information and insights to the scientific and industrial communities, and professional organisations interested in SDWSNs, mainly the current state-of-art, ML techniques, and open issues.