Edge Computing and it’s Rapid Strides in Healthcare
Existing Computing Landscape
Over the past few decades, rapid developments in Mobile internet and Internet of Things (IoT) applications have had a profound impact on cloud computing architectures.
Accelerated use of cloud-based applications has increased data center traffic, leading to Hyperscale data centers. With further growth in IoT based products in Industrial, Healthcare and Smart city segments, the demand to strengthen the data center capabilities shall increase.
As per Cisco Global Cloud Index, by FY 2021, 94% of workloads and compute instances will be processed by cloud data centers; 6% will be processed by traditional data centers.
The ever-expanding cloud infrastructure is challenged by few key imperatives
· Latency/Determinism — Latency, the time delay due to interaction between cloud and IoT device, is an essential measure to assess the network capabilities. Critical Healthcare applications like Telemedicine and Electronic Health Records (EHRs) have strict Latency requirements.
· Data/Bandwidth — According to Statista, by FY2020, the install base of IoT devices is forecast to grow to almost 31 billion worldwide. With a spurt in the number of IoT devices (15–20 connected medical devices per bed), data generation continues to rise at record rates. Hence, the network bandwidth becomes more limited, overwhelming the cloud and leading to a greater bottleneck of data.
Privacy/Security — Based on IBM, 2018 Cost of Data breach study, Healthcare data breaches cost about $408 per patient record for the industry, three times more than any other sector. With increase in cloud data, the vulnerability to a breach has increased accordingly.
The Advent of Edge Computing
Edge computing basically brings cloud computing down to the EDGE of the network, in the physical world. Edge computing is using computing power at the EDGE (Eg, IoT device) to filter or process data and then send only the required data to the cloud.
Edge computing solves each one of the imperatives highlighted above. The global edge computing market size is projected to reach USD 3.24 billion by FY2025, according to a study conducted by Grand View Research, Inc.,
Key Players and Innovations in Edge Computing
· Google’s Edge TPU, a purpose-built accelerator chip designed to run TensorFlow Lite machine learning models at the edge.
It’s so small that four of the chips can fit onto one penny.
· Cloud IOT Edge is the software to run with the Edge TPU.
Google says, “Your sensors become more than data collectors — they make local, real-time, intelligent decisions”
Qualcomm — The Company intends to “Make Device-AI Ubiquitous” and is approaching the problem from multiple aspects.
· Specialized hardware architecture, such as Hexagon DSP with Qualcomm Hexagon Vector Extensions on Snapdragon 835 offers a 25X improvement in energy efficiency and an 8X improvement in performance.
— Network optimization techniques for on-device applications to take better advantage of memory and space/time complexity
NVIDIA — Jetson TX2 and the JetPack 3.0 AI SDK. Jetson is the world’s leading low-power embedded platform, enabling server-class AI compute performance for edge devices everywhere
Jetson TX2 is ideal for deploying advanced AI to remote field locations with poor or expensive internet connectivity. Jetson TX2 also offers near-real-time responsiveness and minimal latency — key for intelligent machines that need mission-critical autonomy
Edge Computing in Healthcare
According to a study conducted by Grand View Research, Inc.,
· The healthcare & life sciences edge computing segment is estimated to cross USD 326 million by 2025, with highest CAGR between 2017 and 2025
· The growth of the segment can be attributed to provision of storage capabilities and real-time computing by edge computing solutions
Wearables, with the help of edge computing can be considered as reliable tools for long term health monitoring systems. Aging population can leverage these tools to stay healthier and become more proactive with their own healthcare
Patients undergoing cancer treatment can make use of wearables and apps to check on the diagnosis and treatment through the data collected on a daily basis. This will also monitor their appetite, lifestyle, activity level and fatigue level
In real-time telemedicine, apart from video-conferencing peripheral sensing devices can also be attached to the patient in order to offer the ability of remote interactive examinations. Edge computing will potentially bring a great boost to telehealth that can be used in bandwidth-constrained rural and regional areas.
Edge computing will become increasingly important in various applications. This paradigm will be a key part is various applications such as wireless health monitoring, self-driving cars, robotics, drones and virtual reality.
With all the major players such as Qualcomm, Google, NVIDIA, Amazon and Microsoft taking innovation leaps in this technology, edge computing is expected to be ubiquitous in multiple applications.