| Abstract |
The smart applications development worldwide demands for ultra-reliable data communication to assure the richness of data and processing in time. These smart applications create massive amounts of data to be processed in 6G networks with advanced technologies. 6G big data analytics become the demand for next-generation data communication and smart city applications. Traditional data analytics algorithms lag in efficiency while processing big data due to huge volume, data dependency and timely processing. A deep learning model called reinforcement learning is promising for processing big data in smart applications. The proposed study, advanced big data Analytics using Deep learning (ABDAS-DL), gives a pioneering approach that combines Deep Reinforcement learning (DRL) based Deep Q network (DQN) with long-term, short-term memory (LSTM) for harnessing the vast capacity of 6G connectivity within the domain of advanced big data analytics. This study utilises smart transport-based data for taxi route optimisation by analysing climatic and surrounding factors. The look of 6G connectivity guarantees incredible facts of data transmission speeds and tremendously low latency, taking off new horizons for managing large datasets in real time. The performance of the proposed model is measured in terms of processing time, network, reliability and scalability. The proposed model takes 30 s to process the data and fix the taxi route, while another traditional model consumes more than an hour. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. |
