Title: Improving 6TiSCH Network Formation and Transmission using Q-Learning

Summary: The study proposes a unified approach to augment the formation and transmission efficiency within 6TiSCH (IPv6 over IEEE802.15.4e time-slotted channel hopping mode) wireless sensor networks leveraging Q-Learning. Addressing the challenges of congestion, increased network formation time, and elevated energy consumption prevalent in dense networks, the proposal introduces Q-Trickle, an adaptive trickle timer algorithm. Q-Trickle optimizes the transmission or suppression of DIO (DODAG Information x-x-object) control packets based on minimal cell and transmission queue conditions, ensuring fair transmission distribution and mitigating transmission congestion. Additionally, to enhance the Routing Protocol for Low-Power and Lossy Networks (RPL) in 6TiSCH networks, an adaptive parent change algorithm alongside an RPL x-x-objective Function (OF) based on cell usage, collectively termed as ACI-RPL, is proposed. ACI-RPL dynamically adjusts to network conditions, promoting better parent selection in dynamic networks. Together, Q-Trickle and ACI-RPL aim to reduce network congestion, energy consumption, and foster a more efficient and reliable communication infrastructure within 6TiSCH networks, paving the way for substantial advancements in managing and optimizing such networks.