An Efficient Model to Predict Network Packets in TVDC Using Machine Learning

Internet-based computing allows the sharing of on-demand resources. This computing technique includes data processing and storage to globally separated machines, known as Cloud Computing. Confidentiality and integrity of data on the cloud are vital. The key constraints include effective access control, accessibility, and transmission of files, in a dynamic cloud environment, seeking a Trusted Virtual Data Center (TVDC). So, to overcome challenges such as data security and integrity due to exponentially growing data size, this research paper aims to develop a prediction model using the machine learning approach, which identifies the type of incoming packet on the TVDC. Alternatively, in other words, this system predicts whether the incoming packets on the server in the cloud environment are malicious or not, using the machine learning approach. This research explored artificial intelligence verticals in building systems with learned data structures for efficient data access. This research describes the implementation of machine learning algorithms for an efficient model's prediction of the type of incoming packet on the server. It has achieved 88% accuracy using the Gradient Boosted Tree classifier. Also, in this study, the author compares the results of two algorithms, Decision Tree and Gradient Boosted Tree, and finally selects the most optimal for this prediction.