Search

This paper presents the first, novel, dynamic, resilient, and consistent Blockchain COngestion ContrOL (BCOOL) system for vehicular networks that fills the gap of trustworthy Blockchain congestion prediction systems. BCOOL relies on the heterogeneity of Machine Learning, Software-Defined Networks and Network Function Virtualization that is customized in three hybrid cloud/edge-based On/Offchain smart contract modules and ruled by an efficient and reliable communication protocol. BCOOL’s first novel module aims at managing message and vehicle trustworthiness using a novel, dynamic and hybrid Blockchain Fogbased Distributed Trust Contract Strategy (FDTCS). The second novel module accurately and proactively predicts the occurrence of congestion, ahead of time, using a novel Hybrid On/Off-Chain Multiple Linear Regression Software-defined Contract Strategy (HOMLRCS). This module presents a virtualization facility layer to the third novel K-means/Random Forest-based On/Off-Chain Dynamic Service Function Chaining Contract Strategy (KRF-ODSFCS) that dynamically, securely and proactively predicts VNF placements and their chaining order in the context of SFCs w.r.t users’ dynamic QoS priority demands. BCOOL exhibits a linear complexity and a strong resilience to failures. Simulation results show that BCOOL outperforms the next best comparable strategies by 80% and 100% reliability and efficiency gains in challenging data congestion environments. This yields to fast, reliable and accurate congestion prediction decisions, ahead of time, and optimizes transaction validation processing time. Globally, the Byzantine resilience, complexity and attack mitigation strategies along with simulation results prove that BCOOL securely predicts the congestion and provides real-time monitoring, fast and accurate SFC deployment decisions while lowering both capital and operational expenditures (CAPEX/OPEX) costs.

Network congestion-related studies consist mainly of two parts: congestion detection and congestion control. Several researchers have proposed different mechanisms to control congestion and used channel loads or other factors to detect congestion. However, the number of studies concerning congestion detection and going beyond into congestion prediction is low. On this basis, we decide to propose a method for congestion prediction using supervised machine learning. In this paper, we propose a Naive Bayesian network congestion warning classification method for Heterogeneous Vehicular Networks (HetVNETs) using simulated data that can be locally applied in a fog device in a HetVNET. In addition, we propose a centralized and dynamic cloud-fog-based architecture for HetVNET. The Naive Bayesian network congestion warning classification method can be applied in this architecture. Support Vector Machine (SVM), K Nearest Neighbor (KNN) and Random Forest classifiers, which are popular methods in classification problems, are considered to generate congestion warning prediction models. Numerical results show that the proposed Naive Bayesian classifier is more reliable and stable and can accurately predict the data flow warning state in HetVNET. Moreover, based on the obtained simulation results, applying the proposed congestion classification approach can improve the network’s performance in terms of the packet loss ratio, average delay and average throughput, especially in the dense vehicular environments of HetVNET.