Detection of Distributed Denial-of-Service (DDoS) Attacks in Software-Defined Vehicular Networks (SDVN) Using Flow-Based Analysis and Machine Learning Models
Keywords:
Software-Defined Vehicular Networks, Machine Learning, Distributed Denial of Service, Accuracy.Abstract
This research aims to design an odoo (On Demand Open Object) ERP monitoring platform for real-time monitoring of the water pumping station in rural Tartous (Al-Jakrah). It simulates the sensors used for pressure, flow, temperature, and humidity. A neural network model (LSTM) was used to analyze the sensor simulation data in order to detect and locate leaks.
The monitoring platform simulates the operation of the sensors used and assesses leak risk based on measurement results. The platform allows for the simulation of various leak scenarios (minor, medium, and catastrophic) and pinpoints the leak's location along the main transmission line.
The application demonstrated good performance, with the leak detection model successfully identifying different leak incidents.