AI-Powered ISP Network Security Dashboard: Real-Time Monitoring and Intelligent Analysis System

This project is an AI-powered ISP network security dashboard built with Node.js and Express, integrating Supabase data storage and Google Gemini API analysis capabilities. It provides network performance testing (latency, bandwidth), anomaly detection, multi-dimensional health scoring, and intelligent recommendation functions to help ISPs proactively optimize service quality and address the pain point of traditional monitoring tools lacking intelligent analysis.

In the digital age, ISPs face users' high demands for network latency, bandwidth, and stability. Traditional monitoring tools can only display basic data and lack intelligent analysis and predictive insights. This project aims to integrate AI with network security analysis, track network patterns in real time, automatically detect anomalies, and provide actionable recommendations for operation and maintenance personnel, serving as an intelligent assistant for ISPs.

Adopting a frontend-backend separation architecture: The backend builds RESTful APIs based on Node.js + Express to handle business logic; Supabase (PostgreSQL) is used for data storage to support real-time synchronization; the frontend reserves docking interfaces (under development). The technology stack includes Node.js, Express, Supabase, Google Gemini API, etc.

Core function modules: 1. Network latency testing (Ping test + historical data tracking); 2. Bandwidth speed testing (bidirectional speed test + multiple test size options); 3. Multi-dimensional network health scoring (overall, gaming, streaming, etc. scenarios); 4. AI intelligent summary (Google Gemini API as main solution + rule engine as backup solution).

Data analysis and anomaly detection: Provides overview statistics, time-series data analysis (supports time range filtering), automated anomaly detection (learns normal patterns and marks deviations), and detailed test analysis (decomposition of single test results), facilitating preventive maintenance and troubleshooting.

Technical implementation highlights: Modular code organization (layered Config/Controllers/Models, etc.); security measures (Helmet middleware, CORS configuration, compression, logging); automatic document generation (Swagger UI); externalized environment configuration (.env file).

Application scenarios: 1. ISP network operation and maintenance (real-time monitoring, architecture optimization); 2. Enterprise network management (private deployment to monitor office networks); 3. Network quality research (data export supports big data analysis).

This project upgrades traditional monitoring to an intelligent platform, proactively identifying problems and providing insights. Future expansion directions: Integrate more AI prediction models, support more test types, enrich visualization, and introduce alert mechanisms.