The Value Of Edge Computing

Generally speaking, sensors, cameras, microphones, and a series of different IoT and mobile devices collect data from their locations and send them to a centralized data center or cloud.

Data shows that by 2020, there will be more than 50 billion smart devices connected worldwide. These devices will generate data calculated in zettabytes (ZB) each year, which will grow to more than 150 ZB by 2025. Sending this data to the cloud will cause some major problems.

First of all, 150ZB of data will cause capacity problems. Second, it is expensive to transfer large amounts of data from its original location to a centralized data center. It is estimated that only 12% of the data is currently analyzed and processed, while only 3% of the data helps produce meaningful results. The remaining 97% of the data is wasted after being collected and transmitted. Third, storage, transmission, and analysis of data consume huge amounts of energy. Therefore, we need to find an effective way to reduce costs and reduce waste.

Introducing edge computing and storing data locally can reduce transmission costs. At the same time, the use of AI functions can also eliminate data waste. For example, the new low-power edge computing server CPUs currently in use are connected to AI acceleration SoCs in the form of GPUs and ASICs or a series of chips.

In addition to solving capacity, energy, and cost issues, edge computing can also improve network reliability because applications can continue to run during general network outages by clearing certain threat profiles (such as global data center denial of service (DoS attacks), which can improve safety.

Most importantly, edge computing can reduce latency for real-time scenarios (such as virtual reality shopping malls, mobile device video caching), and at the same time create many new application opportunities in environments such as self-driving cars, gaming platforms, or fast-paced manufacturing.