Who should attend
The target course participants are software professionals interested in architecting and building intelligent edge computing systems.
It is applicable for professionals engaged in the following areas.
- Software Architects
- Senior Software Engineers
About the course
What do the rise of 5G, Industry 4.0 Smart Manufacturing, Smart Nation, Self-driving cars have in common? They all rely on the distributed IoT paradigm known as “Edge Computing”.
Edge Computing promises reduced latency and improved privacy by processing data using artificial intelligence and machine learning near where the action is happening – as close as possible to the sensors and IoT “things” layers. Unlike the centralised processing on cloud servers, Edge Computing is more appliable to time-sensitive, mission-critical applications, and supports locality and redundancy by distributing the processing across nearby nodes.
According to Telenavio, the development of 5G telecommunication networks and connected automation infrastructure in many industry, healthcare and transport domains will have a significant impact on the market value of the Edge and Fog Computing within the next few years. In addition, deep learning algorithms have been squeezed into smaller and smaller devices with the development of TinyML, Tensorflow Lite for Microcontrollers, etc.
The combination of both factors – higher bandwidth communications and better ability to do intelligent processing on embedded devices – will bring about a rise in Edge Computing applications. This is also why Amazon and Microsoft are heavily investing in Edge Computing infrastructure and micro data centers, such as Azure IoT Edge, AWS IoT, AWS Wavelength.
This is 4-day programme is intended for anyone who wishes to gain specialised knowledge in the exciting cutting-edge world of Edge Computing systems. This course will benefit those working in medical, manufacturing, defense, transport, and any domains that can utilise automation with sensor data.
Participants will gain in-depth knowledge as well as practical skills through projects and assessment that reinforce their learning and engage their newly acquired knowledge. Hands-on workshops are conducted in Python using Docker and Tensorflow on Raspberry Pi.
- Design Edge compute systems to provide multi-level intelligence for IoT, transducers and other devices, using the OpenFog Reference Architecture.
- Build data collection, analytics, and decision-making capabilities into these Edge compute systems, using the IOTA distributed ledger.
- Integrate machine learning and analytics into Edge Computing to perform decision-making, self-healing, and self-learning, using Tensorflow on Raspberry Pi.
What Will Be Covered
The outline teaching agenda is as follows:
Day 1: Design and Orchestration for Multi-Layer Edge Computing
- Methodologies and key principles in designing integrated Edge Computing sensor networks
- Capabilities of Edge Computing nodes, sensors, transducers and related technologies
- Fog architecture and cloud-based IoT orchestration patterns/practices for Edge Computing systems
- Platforms and technologies for configuring and orchestrating Edge Computing topologies
- Industrial use case / hands-on exercise to design a layered Edge Computing system
Day 2: Data Collection, Analytics, and Decision-making in Edge Computing
- Industry tools and technologies for data collection, transmission, and analytics for IoT
- Range of statistical and machine learning modeling techniques, such as linear and logistic regression
- Features, pros and cons of the statistical approaches, algorithms and tools
- Industrial use case / hands-on exercise applying data collection and analysis techniques to a real-world Edge Computing system
Day 3: Self-monitoring and Self-healing in Edge Computing
- Quality of Service monitoring, fault management, and self-healing for IoT
- Advanced mathematical modelling techniques such as convolutional or recurrent neural networks.
- Industrial use case / hands-on exercise to design a self-monitoring and healing Edge Computing system
Day 4: Self-learning and Adaptation for Edge Computing
- Self-learning models such as reinforcement learning and online learning algorithms
- Selection and optimization of advanced models for self-learning Edge computing applications
- Industrial use case / hands-on exercise on designing a self-learning Edge Computing system
Lisa is with the Software Engineering and Design Practice, StackUp program for National University of Singapore, Institute of Systems Science (NUS-ISS). Lisa has multiple years of extensive experience in software product research and development at Microsoft Corporation (USA). Her background in...
Because of COVID-19, many providers are cancelling or postponing in-person programs or providing online participation options.
We are happy to help you find a suitable online alternative.