Optimized Hierarchical Tree Deep Convolutional Neural Network of a Tree-Based Workload Prediction Scheme for Enhancing Power Efficiency in Cloud Computing

Workload prediction is essential in cloud data centers (CDCs) for establishing scalability and resource elasticity. However, the workload accuracy center could be better due to noise, redundancy, low performance prediction. This paper designs a hierarchical tree-based deep convolutional neural network (T-CNN) model with sheep flock optimization (SFO) enhance CDCs’ power efficiency The kernel method used preprocess historical information from CDCs. Additionally, T-CNN weight parameters are optimized using SFO. suggested TCNN-SFO technology has successfully reduced excessive consumption while correctly forecasting incoming demand. Further, proposed assessed two benchmark datasets: Saskatchewan HTTP traces NASA. developed executed Java tool. Therefore, associated existing methods, technique achieved higher of 20.75%, 19.06%, 29.09%, 23.8%, 20.5%, as well lower energy 20.84%, 18.03%, 28.64%, 30.72%, 33.74% when validating dataset. It also 32.95%, 12.05%, 32.65%, 26.54%.