AI in the Yellow River
AI in the Yellow River: Server Configuration Documentation
Welcome to the documentation detailing the server configuration for the "AI in the Yellow River" project. This document is designed for newcomers to our MediaWiki site and provides a detailed overview of the hardware and software components powering this initiative. This project focuses on utilizing artificial intelligence to monitor and predict flooding events within the Yellow River basin. Understanding the server infrastructure is crucial for contributing effectively.
Project Overview
The "AI in the Yellow River" project utilizes a distributed server architecture to process massive datasets from various sources, including hydrological sensors, weather stations, and satellite imagery. The primary goal is real-time analysis and accurate flood prediction. Data ingestion, model training, and prediction services are all handled by the server cluster. This necessitates a robust and scalable infrastructure. See also Data Acquisition Process for information on data sources.
Hardware Specifications
Our server cluster consists of three primary node types: Master Nodes, Worker Nodes, and Storage Nodes. Each node type is specialized to perform certain functions. Details are provided below. Refer to Network Topology for a diagram of the network connections.
Master Nodes
Master Nodes manage the cluster, schedule tasks, and monitor the health of other nodes. They are also responsible for initial data distribution. We currently have two Master Nodes for redundancy.
| Specification | Value |
|---|---|
| CPU | Dual Intel Xeon Gold 6248R (24 cores/48 threads per CPU) |
| RAM | 256 GB DDR4 ECC Registered |
| Storage (OS) | 1 TB NVMe SSD |
| Network Interface | Dual 100 Gbps Ethernet |
| Operating System | CentOS Linux 7 |
Worker Nodes
Worker Nodes perform the computationally intensive tasks of model training and prediction. These nodes are equipped with powerful GPUs. We have eight Worker Nodes currently deployed. For detailed information on the AI models used, see AI Model Descriptions.
| Specification | Value |
|---|---|
| CPU | Dual Intel Xeon Silver 4210 (10 cores/20 threads per CPU) |
| RAM | 128 GB DDR4 ECC Registered |
| GPU | 4 x NVIDIA A100 (80GB VRAM each) |
| Storage (Data) | 4 TB NVMe SSD |
| Network Interface | Dual 100 Gbps Ethernet |
| Operating System | Ubuntu Server 20.04 |
Storage Nodes
Storage Nodes provide persistent storage for the massive datasets used by the project. They are optimized for high throughput and data integrity. We have four Storage Nodes in operation. See Data Backup Strategy for details on data protection.
| Specification | Value |
|---|---|
| CPU | Intel Xeon E-2224 (6 cores/12 threads) |
| RAM | 64 GB DDR4 ECC Registered |
| Storage | 16 x 16 TB Enterprise SAS HDD (RAID 6) |
| Network Interface | Dual 25 Gbps Ethernet |
| Operating System | FreeBSD 13 |
Software Stack
The software stack is carefully chosen to support the AI workloads and ensure efficient data processing. See Software Dependencies for a complete list of required packages.
- Operating Systems: CentOS 7, Ubuntu Server 20.04, FreeBSD 13 (as detailed above).
- Containerization: Docker and Kubernetes are used for application deployment and orchestration. See Kubernetes Configuration.
- Programming Languages: Python 3.8 is the primary language for AI model development and deployment.
- AI Frameworks: TensorFlow and PyTorch are used for building and training AI models.
- Data Storage: Ceph is used as the distributed file system for storing large datasets.
- Message Queue: RabbitMQ is used for asynchronous communication between services. See Message Queue Architecture.
- Monitoring: Prometheus and Grafana are used for system monitoring and visualization. See Monitoring Dashboard Configuration.
- Database: PostgreSQL is used for storing metadata and historical data. Refer to Database Schema Documentation.
Network Configuration
The server cluster is connected via a high-speed InfiniBand network. This provides low latency and high bandwidth for communication between nodes. The network is segmented into different VLANs for security purposes. See Firewall Rules for detailed firewall configurations.
- Network Topology: A full mesh topology is implemented for optimal redundancy and performance.
- IP Addressing: Static IP addresses are assigned to each node.
- DNS: BIND is used for internal DNS resolution.
- Firewall: iptables is used to enforce network security policies.
Security Considerations
Security is paramount for the "AI in the Yellow River" project. We employ a multi-layered security approach to protect against unauthorized access and data breaches. See Security Audit Reports for details on recent security assessments.
- Access Control: Role-Based Access Control (RBAC) is implemented to restrict access to sensitive data and resources.
- Encryption: Data is encrypted both in transit and at rest.
- Intrusion Detection: Snort is used for intrusion detection and prevention.
- Regular Security Audits: Regular security audits are conducted to identify and address vulnerabilities.
Main Page Contributing to the Project Troubleshooting Guide Contact Information Data Processing Pipeline Model Training Procedures Deployment Instructions API Documentation Alerting System Configuration System Logs Analysis Performance Tuning Disaster Recovery Plan Change Management Process Version Control System
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 configuration
Need Assistance?
- Telegram: @powervps Servers at a discounted price
⚠️ *Note: All benchmark scores are approximate and may vary based on configuration. Server availability subject to stock.* ⚠️