Blockchain-enabled online traffic congestion duration prediction in cognitive internet of vehicles

The real-time intelligent perception and prediction of traffic situation can assist connected automated vehicles (CAVs) in route planning and reduce traffic congestion in cognitive internet of vehicles (CIoVs). The traditional centralized offline training and deployment generally fail to adapt to the dynamic traffic environment and incur significant communication overheads. Blockchain technology has attracted great attention in the information storage of vehicular networks for its advantages in decentralization, transparency, traceability, and tamperproof capability. However, due to the bottlenecks such as high computational cost and unable to prevent malicious attacks, current blockchains are incapable actuate on efficient online traffic situational cognition and prediction for CIoVs. Motivated by this, we propose a consortium blockchain-enabled cognitive segments sharing framework for online multi-step congestion duration prediction. We design a cognitive model of traffic situation based on anomaly detection and filtering mechanism to guarantee the accuracy of the cognitive segments before being packaged into the block. Furthermore, to improve the consensus efficiency and resist malicious attacks, we consider a credit evaluation mechanism and proposed a credit-based delegated byzantine fault tolerance (CDBFT) consensus algorithm. Last, we propose an online multi-step prediction algorithm based on long short-term memory (LSTM) to predict future traffic congestion duration. Experiment results based on a real dataset demonstrate that the proposed algorithms achieve shorter consensus delay and higher predictive accuracy than existing algorithms while effectively resisting malicious attacks.