All News | Boards | Chips | Devices | Software | Archive | About | Contact | Subscribe
Follow LinuxGizmos:
Twitter Facebook Pinterest RSS feed
*   get email updates   *

Intel contributes open source NEV and Titanium code to “Akraino” edge computing project

Mar 27, 2018 — by Eric Brown 1,664 views

The Linux Foundation announced new support for its “Akraino Edge Stack” project for creating open source cloud services for edge computing, including Intel’s promise to open source parts of its Wind River Titanium Cloud and Network Edge Virtualization SDK.

On Feb. 20, the Linux Foundation announced an Akraino Edge Stack open source project built around code contributions from AT&T for carrier-scale edge computing applications. Today, the LF followed up by announcing new support for the initiative, including the contribution by Intel of major components of its Wind River Titanium Cloud portfolio and Intel Network Edge Virtualization Software Development Kit (Intel NEV SDK).

Intel and 12 other mostly Chinese organizations have joined the AT&T founded Akraino effort. The new members include Altiostar, China Electronics Standardization Institute (CESI), China Mobile, China Telecom, China Unicom, Docker, Huawei, iFlyTek, New H3C Group, Tencent, ZTE, and 99Cloud.

Wind River Titanium Cloud architecture
(click image to enlarge)

Akraino Edge Stack automates services from edge to core, providing an open source software stack for low-latency, carrier-grade edge computing networking technology. The technology supports edge computing applications “running in virtual machines and containers to support reliability and performance requirements,” says the Linux Foundation.


Akraino complements LF networking projects like OpenStack and ONAP (Open Network Automation Platform), says the LF. Launched in Feb. 2017 from the merger of the earlier ECOMP and OPEN-O projects, ONAP is developing a framework for real-time, policy-driven software automation of virtual network functions. The Akraino stack sits above the middleware provided by the LF’s EdgeX Foundry project, which is more specifically focused on standardizing edge services for industrial IoT.

Wind River Titanium Cloud is based on open source components that have been “extended and hardened to address critical infrastructure requirements, such as the high availability, fault management, and performance management needed for continuous 24/7 operation,” says the LF. Titanium Cloud also supplies the “low latency, high performance, scalability, and security needed for edge and IoT workloads.” The Titanium components include patches to existing open source projects, such as OpenStack, QEMU, and Ceph.

Diagram showing the porting of applications to Intel NEV SDK
(click image to enlarge)

The Intel NEV SDK contribution includes a suite of reference libraries and APIs to enable edge-computing solutions for different network deployment scenarios, including small cells, macro cells, wireline, aggregation sites, and central offices. The SDK is prevalidated for working with Wind River Titanium Cloud.

Intel Edge Cloud SDK kit (ADI’s RCC-DFF Development Kit) and block diagram
(click images to enlarge)

Two Intel NEV SDK development kits are available: an Intel Xeon 1U server blade kit with integrated Wind River Titanium Server components including carrier-grade Linux, as well as a Intel Edge Cloud SDK kit for edge device development. The latter is built on a Nano-ITX-based RCC-DFF Development Kit from ADI Engineering that runs Wind River Linux on a quad-core Atom C2508 “Rangely” SoC, a member of Intel’s Atom C3000 line. The Intel Edge Cloud SDK computer integrates an mSATA SSD, dual GbE ports, and a PCIe slot for adding 4G radios, and is designed for small cell base stations, pico cells, and IoT gateways.

The Akraino announcement was made today at the start of the Linux Foundation’s Open Networking Summit in Los Angeles. The LF also announced an LF Deep Learning Foundation for encouraging open source innovation in artificial intelligence, machine learning, and deep learning. There’s also a related Acumos AI Project, billed as a federated platform for managing and sharing models for AI and ML.

Further information

The Akraino Edge Stack is looking for new members. More information may be found at the Linux Foundation’s Akraino Edge Stack website.

(advertise here)

Print Friendly, PDF & Email

Please comment here...