The advent of today’s technologically advanced internet has also created many types of network attacks. One of the toughest things on internet security right now is about denial-of-service attacks. Also, distributed denial-of-service attacks represent a more dangerous scenario, since their impacts can be devastating. This attack, among many others, will cripple the processing power of a target often without any warning. DDoS attacks could threaten the availability and security of networks. One of the best ways to identify these attacks is using machine learning (ML) algorithms trained based on network traffic patterns. A study-based research work is performed that discuss the role of different types ML algorithms to identify DDoS attack which includes Multi-layer Perceptron, Decision Tree, Support Vector Machine, Logistic Regression, and K-Nearest Neighbors. The study focuses on MLP, one type of Deep Neural Network because it is capable of learning complex nonlinear associations in data. The paper compares the performance of these algorithms in identifying DDoS attack using a well-established benchmark dataset. Various parameters such as accuracy, F1-score, recall, and precision are calculated to determine each technique's effectiveness. The analysis sheds light on the strengths and weaknesses of different algorithms in relation to DDoS identification.