While cloud computing is still a hot topic the headlines, venture capitalists in the technology field have already turned their attention toward something new. Peter Levine, a partner at Andreessen Horowitz, believes the next big topic is called “edge computing“.
Edge computing is defined as “a method of optimizing cloud computing systems by performing data processing at the edge of the network, near the source of the data”. According to researchers, the word “edge” is defined as “any computing and network resources along the path between data sources and cloud data centers.” For example, a smart phone is the edge between human body and cloud data center. Edge computing is driven by the Internet of Things (IoT). Cisco estimated that the IoT applications will generate 507.5 zettabytes (1 zettabytes equal to 1 trillion gigabytes) per year by 2019 . How to transfer, compute and store these data is a big challenge for the current cloud computing system.
Take self-driving car as an example. Each self-driving car has hundreds of on-vehicle sensors and will generate 40TB of data for every 8 hours of driving . The analysis and computing of this data must be done in real-time with ultra-low latency to ensure the safety of passengers and the public. If vehicles need to send data to the cloud computing center and wait to receive the decision, catastrophe could already occur due to the delay in the transmittance process. Moreover, cloud computing centers do not need to process, compute and store all the data collected via the vehicle sensors. Some of the data has short-term value and is solely needed for a specific movement. Edge computing is designed to solve these problems.
Adding a computing unit right next to the data source will help to reduce the latency, improve the speed of reaction and satisfy the need for real-time decision making in the IoT environment. This concept is not something new. The computer industry has been shifting back and forth between centralized to distributed in the past decades, from mainframe (centralized), to client server (distributed) to mobile-cloud (centralized) . From this trend, the concept of edge computing (distributed) is naturally the next wave in the computing industry.
Edge computing is more than a pure concept. Companies are funding research projects focusing on developing this technology. In 2016, Huawei, China Academy of Information and Communications Technology, Shenyang Institute of Automation of the Chinese Academy of Sciences Intel Corporation, ARM Holdings, and iSoftStone Information Technology formed the Edge Computing Consortium in Beijing, China with the focus to “promotes open cooperation in the OT and ICT fields, nurtures the industry’s best application practices, and advances sound and sustainable development of the edge computing industry.” Additionally, the faster speeds and lower latency expected with 5G technologywill be essential elements to enable edge computing.
Since each edge computing unit needs to handle compute, storage, and networking functions, the booming of edge computing will increase the demand for microprocessors, memory chips, and other network components in the coming years. Giving the volume of just IoT devices, the demand is going to be tremendous.
As a mission to help our customers prepare for the next trend in the high technology industry and promptly respond to their requirements, Advanced MP Technology keeps a watchful eye on the newest trends and technological developments, and adjusts our approach and strategy to prepare for the up and coming challenges in the supply chain of electronic components.