Edge Computing

Noun · Development

Definitions

  1. Edge Computing is a distributed computing paradigm that processes data closer to where it is generated rather than sending everything to a centralized cloud data center. By placing computation at the network edge (in cell towers, local servers, IoT gateways, or CDN nodes), edge computing reduces latency, decreases bandwidth usage, and enables real-time processing for applications that cannot tolerate the round-trip time to distant cloud servers. Use cases include autonomous vehicles (millisecond reaction times), industrial IoT (factory floor analytics), augmented reality (responsive overlays), content delivery (caching at edge nodes), and 5G network applications. In web development, edge computing manifests as edge functions (Cloudflare Workers, Vercel Edge Functions) that run serverless code at CDN points of presence near users. The model complements rather than replaces cloud computing: heavy processing and storage remain centralized, while time-sensitive and bandwidth-intensive operations happen at the edge.

    In plain English: Running code on servers that are geographically close to users instead of in one far-away data center — making things faster by reducing the distance data has to travel.

  2. Major cloud providers now offer edge computing platforms: AWS Lambda@Edge, Cloudflare Workers, Deno Deploy, and Vercel Edge Functions. These let developers deploy code to hundreds of locations worldwide, bringing computation within milliseconds of any user.

    Example: 'We moved geolocation and A/B test assignment to edge functions. The decision is made in 2ms at the CDN edge instead of 150ms round-tripping to our origin.'

    Source: platform landscape

Etymology

1990s
Akamai pioneers content delivery networks (CDNs), pushing computation to the network edge — the conceptual ancestor of edge computing
2012
The term 'edge computing' gains traction as IoT devices proliferate, requiring low-latency processing closer to data sources
2020s
Cloudflare Workers, Deno Deploy, and Vercel Edge Functions bring edge computing to web developers as a mainstream deployment target

Origin Story

Moving computation to where the data is, instead of the other way around

**Edge computing** refers to processing data near its source (the "edge" of the network) rather than sending everything to a centralized data center. The term emerged from CDN (Content Delivery Network) terminology in the late 1990s, where **edge servers** were nodes placed geographically close to end users to reduce latency.

Akamai, founded in 1998, was a pioneer: their network of edge servers cached content close to users, and by the early 2000s they were describing their infrastructure as "edge computing." The concept gained new urgency with the Internet of Things (IoT): billions of sensors and devices generating data that couldn't all be sent to the cloud for processing due to bandwidth, latency, and privacy constraints.

Modern edge computing ranges from CDN-based serverless functions (Cloudflare Workers, Vercel Edge Functions) to industrial IoT gateways in factories and autonomous vehicle processors. The common thread is the same: some decisions need to be made in milliseconds, and the speed of light imposes a hard limit on how fast data can travel to a distant data center and back.

Coined by: CDN industry / Akamai (popularized)

Context: Late 1990s CDN infrastructure

Fun fact: The speed of light in fiber optic cable is about 200,000 km/s. A round trip from New York to a data center in Oregon takes about 60ms just for the light to travel. For real-time applications like autonomous driving, where decisions must be made in under 10ms, edge computing isn't optional — it's physics.

Related Terms