AI in the Bay of Bengal
AI in the Bay of Bengal: Server Configuration
This document details the server configuration supporting the "AI in the Bay of Bengal" project, a real-time marine environmental monitoring and prediction system utilizing artificial intelligence. This guide is aimed at new contributors to the project and provides a comprehensive overview of the server infrastructure. It covers hardware specifications, software stack, networking, and security considerations.
Project Overview
The "AI in the Bay of Bengal" project aims to leverage data from a network of buoys, satellites, and coastal sensors to predict phenomena like cyclone formation, sea level rise, algal blooms, and changes in marine biodiversity. The system employs machine learning models for forecasting and anomaly detection, requiring significant computational resources and a robust server infrastructure. This documentation outlines that infrastructure. Data is processed using Python and TensorFlow, with results accessible via a web interface built with PHP and JavaScript. The system relies heavily on PostgreSQL for data storage and Redis for caching. All code is version controlled via Git.
Hardware Specifications
The server infrastructure is distributed across two primary locations: a primary data center in Chennai, India, and a secondary disaster recovery site in Singapore. The Chennai site houses the primary processing and storage servers, while the Singapore site provides redundancy and failover capabilities.
The Chennai Data Center consists of the following servers:
| Server Role | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Primary Processing (x4) | 2 x Intel Xeon Gold 6338 (32 cores/64 threads) | 256 GB DDR4 ECC REG | 8 x 4TB NVMe SSD (RAID 0) | 100 Gbps Ethernet |
| Data Storage (x3) | 2 x AMD EPYC 7763 (64 cores/128 threads) | 512 GB DDR4 ECC REG | 24 x 16TB SAS HDD (RAID 6) | 40 Gbps Ethernet |
| Database Server (x2) | 2 x Intel Xeon Silver 4310 (12 cores/24 threads) | 128 GB DDR4 ECC REG | 2 x 1TB NVMe SSD (RAID 1) | 25 Gbps Ethernet |
| Caching Server (x2) | 2 x Intel Xeon E-2388G (8 cores/16 threads) | 64 GB DDR4 ECC REG | 2 x 960GB NVMe SSD (RAID 1) | 10 Gbps Ethernet |
The Singapore Disaster Recovery site mirrors the database and caching servers:
| Server Role | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Database Server (x2) | 2 x Intel Xeon Silver 4310 (12 cores/24 threads) | 128 GB DDR4 ECC REG | 2 x 1TB NVMe SSD (RAID 1) | 25 Gbps Ethernet |
| Caching Server (x2) | 2 x Intel Xeon E-2388G (8 cores/16 threads) | 64 GB DDR4 ECC REG | 2 x 960GB NVMe SSD (RAID 1) | 10 Gbps Ethernet |
Software Stack
The following software components are utilized:
- Operating System: Ubuntu Server 22.04 LTS
- Web Server: Apache 2.4
- Database: PostgreSQL 14 with PostGIS extension
- Caching: Redis 6.2
- Programming Languages: Python 3.9, PHP 8.1, JavaScript (ES6+)
- Machine Learning Framework: TensorFlow 2.9
- Version Control: Git
- Monitoring: Prometheus and Grafana
- Containerization: Docker for development and deployment of microservices.
- Regular security audits and vulnerability scans.
- Intrusion detection and prevention systems (IDS/IPS).
- Strong password policies and multi-factor authentication.
- Data encryption at rest and in transit.
- Regular backups and disaster recovery procedures.
- Access control lists (ACLs) to restrict access to sensitive resources.
- Up-to-date software patches and security updates.
- Implementation of SELinux for enhanced security.
- Implementation of a Kubernetes cluster for improved scalability and orchestration.
- Migration to a cloud-based infrastructure for increased flexibility and cost-effectiveness.
- Integration of additional data sources, such as weather radar data.
- Development of more sophisticated machine learning models.
- Telegram: @powervps Servers at a discounted price
Networking Configuration
The servers are interconnected using a dedicated 100Gbps fiber optic network within the Chennai data center. Connectivity to the internet is provided through multiple Tier-1 providers for redundancy. The Singapore site is connected to the Chennai site via a dedicated encrypted VPN tunnel. A firewall is implemented at the network perimeter to protect against unauthorized access. Internal network segmentation is used to isolate different server roles. DNS is managed using BIND9.
| Component | Configuration Details |
|---|---|
| Primary Network | 10.0.0.0/8 (Chennai), 192.168.1.0/24 (Singapore) |
| Firewall | pfSense 2.5.2 with intrusion detection and prevention systems |
| Load Balancer | HAProxy for distributing traffic to processing servers. |
| VPN | IPsec tunnel between Chennai and Singapore |
Security Considerations
Security is paramount due to the sensitive nature of the data. The following measures are in place:
Future Enhancements
Planned future enhancements include:
Intel-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Core i7-6700K/7700 Server | 64 GB DDR4, NVMe SSD 2 x 512 GB | CPU Benchmark: 8046 |
| Core i7-8700 Server | 64 GB DDR4, NVMe SSD 2x1 TB | CPU Benchmark: 13124 |
| Core i9-9900K Server | 128 GB DDR4, NVMe SSD 2 x 1 TB | CPU Benchmark: 49969 |
| Core i9-13900 Server (64GB) | 64 GB RAM, 2x2 TB NVMe SSD | |
| Core i9-13900 Server (128GB) | 128 GB RAM, 2x2 TB NVMe SSD | |
| Core i5-13500 Server (64GB) | 64 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Server (128GB) | 128 GB RAM, 2x500 GB NVMe SSD | |
| Core i5-13500 Workstation | 64 GB DDR5 RAM, 2 NVMe SSD, NVIDIA RTX 4000 |
AMD-Based Server Configurations
| Configuration | Specifications | Benchmark |
|---|---|---|
| Ryzen 5 3600 Server | 64 GB RAM, 2x480 GB NVMe | CPU Benchmark: 17849 |
| Ryzen 7 7700 Server | 64 GB DDR5 RAM, 2x1 TB NVMe | CPU Benchmark: 35224 |
| Ryzen 9 5950X Server | 128 GB RAM, 2x4 TB NVMe | CPU Benchmark: 46045 |
| Ryzen 9 7950X Server | 128 GB DDR5 ECC, 2x2 TB NVMe | CPU Benchmark: 63561 |
| EPYC 7502P Server (128GB/1TB) | 128 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/2TB) | 128 GB RAM, 2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (128GB/4TB) | 128 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/1TB) | 256 GB RAM, 1 TB NVMe | CPU Benchmark: 48021 |
| EPYC 7502P Server (256GB/4TB) | 256 GB RAM, 2x2 TB NVMe | CPU Benchmark: 48021 |
| EPYC 9454P Server | 256 GB RAM, 2x2 TB NVMe |
Order Your Dedicated Server
Configure and order your ideal server configurationNeed Assistance?
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️