Core Technologies of Edge Intelligence for the IoT

As we know, the IoT has enormous potential. But its evolution has been affected by product development challenges, such as rapidly changing requirements, and a variety of hardware/software technologies and applications. Customers encounter the following pain points in developing an IoT product:

• How to support heterogeneous sensors and actuators via the internet?
• How to integrate heterogeneous wire/wireless connectivity protocols (e.g., Modbus, LoRa, Sigfox, Wi-Fi, Bluetooth, etc.)?
• How can I easily port original software to different hardware (e.g., MCU, x86/ARM CPU, GPU, etc.) and OSs (e.g., Microsoft Windows, Linux Distributions, mbed OS, Android, etc. )?
• How can I easily connect to various cloud services? (e.g., WISE-PaaS, Microsoft Azure, ARM mbed Cloud, IBM Bluemix, etc.)?
• How can I maintain data ownership and its implications for security and privacy?
• How can I quickly develop a robust IoT application?
• How to deploy, upgrade, and maintain lots of devices and services?
• How do I transform big data into valuable business information?

Developing an IoT product usually requires solving problems with sensors, connectivity, security, the cloud, storage, device maintenance, edge/cloud analytics, system integration, device hardware, application development, and so on. One of the first challenges that many companies face is how to migrate to an IoT application while balancing design time, time-to-market, and risk.

IoT data can be large in terms of volume and the applications typically have real-time requirements. Transmitting massive amounts of raw data over a network puts a load on network resources. In some cases, it is much more efficient to process data near its source and send only the valuable fraction over the network to a cloud center. Edge computing is a distributed information technology (IT) architecture in which client data is processed at the periphery of the network, as close to the originating source as possible. Time-sensitive data in edge computing may be processed at the point of origin by an intelligent device or sent to an intermediary server located in close geographical proximity to the client. Data that is less time sensitive is sent to the cloud for historical analysis, big data analytics, and long-term storage.

Advantech EIS adopts edge computing architecture for its IoT solution. EIS enables local IoT networks to perform edge intelligence to maximise energy efficiency, reduce privacy threats, promote easy implementation and modularisation, and minimise latencies.