AI in the Wales Rainforest
- AI in the Wales Rainforest: Server Configuration
This article details the server infrastructure supporting the "AI in the Wales Rainforest" project. This project utilizes machine learning to analyze biodiversity data collected from remote sensors deployed within the Welsh rainforests. This document is intended for those responsible for maintaining and expanding the server infrastructure, as well as newcomers to the project seeking a high-level understanding of the system.
Project Overview
The "AI in the Wales Rainforest" project involves collecting data from a network of acoustic sensors, camera traps, and environmental monitors. This data is then processed using machine learning models to identify species, monitor population trends, and assess the health of the rainforest ecosystem. The server infrastructure is crucial for data ingestion, model training, and real-time analysis. We rely heavily on Data Storage and Network Infrastructure.
Server Hardware Specifications
The core of the server infrastructure consists of three primary server types: Ingestion Servers, Processing Servers, and Database Servers. Each type is configured with specific hardware to optimize performance for its respective tasks.
| Server Type | CPU | RAM | Storage | Network Interface |
|---|---|---|---|---|
| Ingestion Servers | Intel Xeon Silver 4310 (12 cores) | 64 GB DDR4 ECC | 4 TB NVMe SSD (RAID 1) | 10 Gbps Ethernet |
| Processing Servers | AMD EPYC 7763 (64 cores) | 256 GB DDR4 ECC | 8 TB NVMe SSD (RAID 0) + 32 TB HDD (RAID 6) | 25 Gbps Ethernet + GPU Network (Infiniband) |
| Database Servers | Intel Xeon Gold 6338 (32 cores) | 128 GB DDR4 ECC | 16 TB SAS HDD (RAID 10) | 10 Gbps Ethernet |
The servers are housed in a secure, climate-controlled data center with redundant power and cooling systems. Regular System Backups are performed to ensure data integrity and availability. The network topology is a star configuration connected to the main University Network.
Software Stack
The software stack is designed for scalability, reliability, and ease of maintenance. We use a Linux-based operating system with a focus on open-source solutions.
| Component | Software | Version |
|---|---|---|
| Operating System | Ubuntu Server | 22.04 LTS |
| Database Management System | PostgreSQL | 14.7 |
| Machine Learning Framework | TensorFlow | 2.12 |
| Data Ingestion Pipeline | Apache Kafka | 3.3.1 |
| Containerization | Docker | 20.10 |
| Orchestration | Kubernetes | 1.26 |
All code is managed using Git Version Control and hosted on a private GitLab instance. Continuous Integration/Continuous Deployment (CI/CD) pipelines automate the build, testing, and deployment of software updates. We also utilize Monitoring Tools like Prometheus and Grafana for real-time system monitoring.
Data Flow and Processing
Data from the rainforest sensors is ingested by the Ingestion Servers via Apache Kafka. The Kafka cluster provides a scalable and fault-tolerant messaging system. The data is then processed by the Processing Servers, which run machine learning models trained to identify species and analyze environmental data. The Processing Servers utilize GPUs for accelerated model training and inference. Processed data is then stored in the PostgreSQL database.
| Stage | Description | Key Technologies |
|---|---|---|
| Data Ingestion | Receiving data from sensors and buffering it for processing. | Apache Kafka, MQTT |
| Data Preprocessing | Cleaning, transforming, and preparing the data for model training and inference. | Python, Pandas, NumPy |
| Model Training | Training machine learning models using historical data. | TensorFlow, PyTorch, Scikit-learn |
| Model Inference | Using trained models to make predictions on new data. | TensorFlow Serving, Triton Inference Server |
| Data Storage | Storing processed data and model outputs. | PostgreSQL, TimescaleDB |
The entire pipeline is orchestrated using Kubernetes, which manages the deployment, scaling, and fault tolerance of the various components. Security Protocols are implemented at each stage to protect the data and system. We also have a dedicated Incident Response Plan in place.
Future Expansion
Planned expansions include increasing the number of sensors deployed in the rainforest, adding new data streams (e.g., LiDAR data), and developing more sophisticated machine learning models. This will require scaling the server infrastructure to handle the increased data volume and processing demands. We are also investigating the use of Cloud Computing resources to supplement our on-premise infrastructure.
Server Maintenance is crucial for long-term stability.
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.* ⚠️