A graphical deep learning technique-based VNF dependencies for multi resource requirements prediction in virtualized environments

With recent developments in cloud computing, massive unplanned traffic loads are submitted to cloud platforms. High traffic load variations lead to uncertainty in resource utilization. Therefore, efficient data-driven mechanisms for automatic resource management become crucial. These mechanisms enable complex and distributed systems to anticipate and efficiently react to workload fluctuations. They rely on accurate resource utilization prediction techniques to satisfy the resource needs, in order to fulfill the service level objective for cloud applications and infrastructures. In this paper, we propose a deep learning model to predict the resource consumption (e.g., CPU, memory) in network function virtualization infrastructures. We model an augmented graphical neural network (GNN) that exploit neighbouring relationships between virtual network functions (VNF) composing various service function chains (SFC), and use an augmented feature vector allowing to capture the consumption evolution of a VNF. The model enables to predict the resource needs of VNFs by identifying the multidimensional dependencies according to the graph structure of an SFC. The proposed GNN model has been compared with MLP, LSTM, hybrid LSTM and CNN models to evaluate its accuracy and efficiency. Real word datasets have been used to evaluate the proposed model using five performance metrics. The performance analysis reveals that our graph-features based GNN model outperforms the other models for SFCs with high traffic load variation.