What is edge computing?

This proximity to data at its source can deliver strong business benefits, including faster insights, improved response times and better bandwidth availability.

The explosive growth and increasing computing power of IoT devices, from smartphones to autonomous vehicles, has resulted in massive volumes of data. These data volumes continue to grow alongside the proliferation of connected devices and systems that power real-time data analytics and artificial intelligence (AI) workloads.

Sending all device-generated data to a centralized data center or to the cloud creates bandwidth and latency issues. Edge computing solves this issue by processing and analyzing data at the origin point, enabling faster and more comprehensive data analysis, such as through mobile edge computing on 5G networks. This move creates the opportunity for greater insights, quicker response times and better customer experiences.

Today, edge computing plays a vital role in hybrid cloud strategies. As enterprises evolve hybrid cloud environments into distributed hybrid infrastructures, edge computing has become essential to running complex workloads locally.

Moreover, the integration of edge and AI computing to perform machine learning (ML) tasks directly on connected edge devices is driving major growth. A Fortune Business Insights study values the edge AI market at USD 35.81 billion in 2025, projecting it to reach USD 385.89 billion by 2034 at a compound annual growth rate (CAGR) of 29.9%.¹

In contrast to cloud computing, which relies on remote access to computing resources like compute, storage and networking over the internet, edge computing processes data locally where devices gather it. While distinctly different, edge computing extends the functions of the cloud model to edge locations. Both share underlying technologies, such as virtualization, containers and microservices, all of which play an important role in edge deployments.

The edge computing model relies on several foundational components:

• Edge devices
• Edge gateways
• Network infrastructure
• Software and analytics
• Edge servers, clusters and virtual servers
• Cloud or centralized data center

Edge devices are hardware that collects, processes and acts on data at the source. This broad category includes computing hardware located at the network boundary and as IoT edge devices, which are physical components connected to a network generating data through one or more sensors. IoT edge devices range from industrial edge applications (for example, smart cities, industrial robots) to consumer devices (for example, smartphones, home security controls).

A Statista study projects the number of IoT devices worldwide will more than double from 19.8 billion in 2025 to 40.6 billion by 2034.²

A computer gateway is a computing node, such as a router, server or software-defined wide area network (SD-WAN) device that acts as a secure intermediary between edge devices and the cloud or central data center.

This component manages data traffic and communication between the two environments.

This connectivity layer links components like controllers, ethernet adapters, gateways and other resources through an edge network, from edge to cloud to on-premises. This link enables data to flow between distributed locations and central systems.  

Often combined with 5G, edge network infrastructure supports high bandwidth and low latency.

Edge computing infrastructure includes software platforms, analytics tools and management systems that process, analyze and orchestrate workloads across edge environments.

Leading cloud computing service providers (for example, IBM, Red Hat, Microsoft, Google) offer edge computing solutions designed to integrate across hybrid cloud environments and support AI workloads.

Computing resources, such as edge servers, edge clusters and virtual servers (typically VMware), deployed at the edge handle local processing and storage demands for workloads that require low-latency response.

This central environment, where larger workloads, storage and deeper analytics reside, works with edge locations as part of a broader distributed hybrid infrastructure.

This infrastructure includes private cloud and public cloud settings, depending on an organization’s infrastructure strategy.

Edge computing helps organizations gain faster access to their data and act on it before it ever reaches a central data center. The following are some of the major benefits:

• Improved performance: By reducing latency and increasing speed, edge computing delivers better performance and greater reliability with less downtime.
• Optimized decision-making: Data analytics that take place at the edge of the network means faster access to insights. Today, organizations can apply AI/ML analytics and complex algorithms to enhance real-time decision-making and optimize customer experiences, such as in personalized retail.
• Stronger security and compliance: When data stays local, organizations have more control over how it is protected. This localization lowers exposure to security risks and makes it easier to meet compliance requirements and data sovereignty obligations throughout distinct regions.
• Enhanced scalability: Software-based solutions support network automation at the edge, enabling organizations to manage and scale deployments as needed, including high-traffic events like flash sales.
• Increased operational efficiency: When edge devices handle data processing locally, organizations lessen the amount of data sent to central locations like the cloud and get more out of existing resources.
• Reduced costs: Processing data onsite and sending only what is necessary to the central servers on-premises or in the cloud reduces network bandwidth usage and overall infrastructure costs.

Edge computing offers clear advantages, but it is not without complexity. Large organizations can have thousands of edge devices (for example, sensors for predictive maintenance on a floor), which increases the difficulty of deployments, provisioning and monitoring.

Edge devices also have limited compute and storage resources, which can constrain what workloads they handle. In addition, reliable connectivity across distributed locations can present issues, particularly for organizations operating in remote locations where network access can be unreliable.

Organizations can address these challenges with software and management platforms from edge service providers that automate provisioning, monitor security and manage workloads across environments. By combining edge computing with 5G, organizations can keep systems running even when traditional internet connections are unreliable or unavailable.

As edge infrastructure matures, organizations are increasingly combining it with machine learning to process and act on data directly on connected edge devices.

This approach, known as edge AI, reduces dependence on centralized cloud infrastructure and helps streamline operations across complex industries (for example, supply chain management, manufacturing). Unlike cloud-based approaches, edge AI devices can also function offline, making them suitable for applications that cannot rely on a continuous internet connection.

Edge computing supports a range of industries and applications. From healthcare to financial services, organizations deploy edge computing use cases that include:

• Healthcare
• Transportation
• Telecommunications
• Financial services
• Entertainment