Edge Computing

IoT, Distributed Systems & Edge AI

2024 Active

Master distributed computing at the network edge. Learn to build IoT sensor networks, deploy machine learning models on edge devices, and architect systems that process data locally for real-time response with minimal latency.

01

ReadingsAvailable

Curated academic and industry resources on edge computing fundamentals, IoT architecture, distributed systems, and real-world deployments.

Edge Computing Fundamentals

Core concepts, architectural patterns, and strategic understanding of when to use edge computing versus cloud-only approaches.

IoT & Sensor Networks

Connecting physical devices with distributed sensors, communication protocols (MQTT, LoRaWAN), and network architectures.

Distributed Systems

System-level thinking: orchestration, synchronization, fault tolerance, CAP theorem, and edge-cloud data consistency.

Edge AI & Machine Learning

Running ML models on edge devices: TinyML, model optimization, quantization, YOLO deployment, and federated learning.

Real-World Deployments

Case studies from smart cities, retail, healthcare, autonomous vehicles, and 5G MEC implementations.

02

FlashcardsAvailable

Interactive learning system with 60 flashcards covering edge concepts, IoT fundamentals, distributed architecture, and edge AI.

Edge Computing Concepts (12 cards)

Edge computing, fog computing, cloudlet, MEC, latency reduction, bandwidth optimization, and offline operation.

IoT Fundamentals (12 cards)

Sensors, actuators, MQTT, CoAP, LoRaWAN, NB-IoT, digital twins, OTA updates, and IoT gateways.

Distributed Architecture (12 cards)

CAP theorem, eventual consistency, replication, load balancing, failover, and edge-cloud synchronization.

Edge AI & ML (12 cards)

Model quantization, pruning, TinyML, federated learning, Edge TPU, and hybrid inference patterns.

Applications (12 cards)

Smart cities, Industry 4.0, autonomous vehicles, retail analytics, healthcare monitoring, and CDNs.

03

Field KitAvailable

Hardware, platforms, and tools for building edge computing systems—from Raspberry Pi to NVIDIA Jetson to Edge Impulse.

Edge Hardware

Raspberry Pi, NVIDIA Jetson, Google Coral, Arduino/ESP32—complete comparison with prices, ML performance, and use cases.

ML Platforms

Edge Impulse (highly recommended), TensorFlow Lite, Roboflow, NVIDIA TAO—end-to-end edge ML workflows.

Vision Models

YOLO v5-v10, MobileNet, EfficientNet, MediaPipe, and 2023-2024 models (FastViT, RT-DETR) optimized for edge.

IoT Platforms

AWS IoT Greengrass, Azure IoT Edge, Google Cloud IoT, Balena fleet management, and Node-RED visual programming.

04

ActivitiesAvailable

Hands-on IoT projects, architecture exercises, team scenarios, and production system case studies.

IoT Projects

Build multi-node sensor networks, deploy edge AI object detection, create edge-to-cloud pipelines, and train TinyML models.

Architecture Exercises

Cloud vs edge decision frameworks, network topology design, and cost analysis for edge deployments.

Team Scenarios

Smart building IoT design sprints, industrial edge implementation planning, and deployment logistics workshops.

Case Studies

Analyze AWS Greengrass, Tesla FSD Computer, Google Nest, and Siemens MindSphere production deployments.

Menu