The goal of our recent Build Your Live Streaming Cloud symposium was to help live video engineers learn how to build and house their own transcoding infrastructure while minimizing power consumption and carbon footprint. Accordingly, we invited Barbara Lange from the Greening of Streaming to speak at the symposium. This article relates the key points of her talk, particularly describing the short-term goals of the Low Energy Sustainable Streaming (LESS) Accord.
By way of background, Barbara is a Volunteer Secretariat for the Greening of Streaming and the principal and CEO of Kibo121, a consultancy dedicated to guiding the media tech sector towards sustainability. Barbara described the Greening of Streaming as a member organization formed roughly two years ago. Its primary focus is on the end-to-end energy efficiency of the technical supply chain that supports streaming services.
The organization has an international membership and is dedicated to addressing the energy implications of the streaming sector. Their mission is to provide the global internet streaming industry with a platform to enhance engineering practices and promote collaboration throughout the supply chain. One core belief is that as streaming increases in scope, understanding the true energy costs, backed by real-world data, is paramount. Barbara mentioned that the organization’s monthly membership meetings are now open to the public, with the next meeting scheduled for October 11 at 11:00 Eastern.
Barbara then described the organization’s structure, highlighting its nine current working groups, which focus on diverse pursuits like defining terminology, organizing industry outreach, and identifying best practices. One notable initiative was the measurement of energy consumption during an English Premier soccer match. The organization also explores power consumption in audio streaming, compression/decompression, and the standardization of energy data.
A newly formed group is dedicated to understanding the energy costs associated with end-user devices. Barbara emphasized the importance of collaboration with academic and other industry groups to avoid duplication of effort and to ensure consistent and effective communication across the industry.
With this as background, Barbara focused on the LESS Accord. She began by addressing a common misconception, which is that contrary to some media reports, there’s almost no direct correlation between internet traffic, measured in gigabytes, and energy consumption, measured in kilowatt-hours. This realization emerged from discussions within Working Group Six, which is responsible for examining compression-related issues. This group initiated the LESS Accord.
The LESS Accord’s mission statement is to define best practices for employing compression technologies in streaming video workflows. The goal is to optimize energy efficiency while ensuring a consistently high-quality viewing experience for users. These guidelines target energy reduction throughout the entire streaming process, from the initial encoding for distribution to the decoding and display on consumer devices for all video delivery services.
As Barbara reported, over the past six months, the group has actively engaged with industry professionals, engineers, and experts. They’ve sought insights and suggestions on how to enhance energy efficiency across all workflow and system stages. The essence of the Accord is to foster a collaborative environment where various, sometimes contrasting, initiatives from recent years can be harmonized.
The ultimate goal is to refine testing objectives and pinpoint organizations that can form project groups. Barbara detailed the first of four projects designated in the LESS Accord’s mission statement.
PROJECT ONE: INTELLIGENT DISTRIBUTION MODEL SHIFTING
Project one involves is determining the most energy-efficient distribution model at any given time and enabling content delivery networks (CDNs) to seamlessly transition between these models. The three distribution models to be considered are:
- Unicast: The dominant model in today’s internet streaming.
- Peer-to-peer: Typically used for video on demand distribution.
- Net layer multicast: Often deployed for IPTV.
While each model has traditionally served a specific purpose, the group believes that all three could be viable options in various contexts. The hypothesis is that if these models can be provisioned almost spontaneously, there should be an underlying heuristic that facilitates the shift from one model to another. If energy efficiency is the primary concern, this shift could allow the CDN to meet that objective.
The main goal of this project is to design a workflow that incorporates energy measurements for the involved systems. The aim is to discern when an operator should transition from one model to another, with energy consumption of the entire system being the primary driver, without compromising the end user’s experience.
PROJECT TWO: THE "GOOD ENOUGH" CONCEPT
Barbara then described the second project, which involves potential energy savings through codec choices and optimization. The central question is whether energy can be conserved by allowing consumers to opt for a streaming experience that prioritizes energy efficiency.
The concept suggests introducing a “green button” on streaming media player devices or applications. By pressing this button, users would choose an experience optimized for energy conservation. Drawing a parallel, Barbara mentioned that many televisions come equipped with an “ECO” mode, which many users tend to disable or overlook. Project two will explore whether consumers might be more inclined to select the energy-efficient option if the energy consumption differences between modes were better communicated.
Taking the idea further, this project will explore consumer behavior if the devices defaulted to this ECO or green mode, and users had the choice to upgrade to a “gold mode” for a potentially enhanced quality. Or, if the default setting prioritized energy efficiency, would this lead to a more energy-conserving streaming system?
The project aims to explore these questions, especially considering that many users currently avoid ECO modes, possibly due to perceived concerns about service quality. As you’ve read, this project seeks to understand user behavior and preferences in the context of energy-efficient streaming.
PROJECT THREE: ENERGY MEASUREMENT THROUGHOUT WORKFLOWS
Barbara then described the third project, which she acknowledged as particularly intricate. The central challenge is to measure energy consumption at every stage of the streaming workflow. This initiative originated from Working Group Four, which has been exploring methods to monitor and probe systems to determine the energy costs associated with each step of the process.
The overarching question is: how much energy is required to deliver a stream to the consumer? While answering this question would be invaluable for economic, marketing, and feedback purposes, it’s a complex endeavor.
The proposed approach involves tracking energy consumption from start to finish in the streaming process. When a video file is created on a computer and encoding begins, an energy reading in kilowatt-hours could be taken. This process would be repeated at each subsequent production, delivery, and playback stage. The idea is to tag the video file with “energy breadcrumbs” or metadata that gets updated as the file progresses through the workflow. By the end, these breadcrumbs would provide a comprehensive view of the energy costs associated with the entire streaming process.
Barbara emphasized the ambitious nature of this project, noting that while it’s uncertain if they can fully realize this vision, they are committed to exploring it. She believes that this project, if successful, could have the most significant impact in terms of understanding energy consumption in the streaming sector.
PROJECT FOUR: TRANSITIONING WORKFLOWS FOR ENERGY EFFICIENCY
Barbara introduced the fourth project, which will explore how to adapt various technologies to transition existing workflows to hardware environments that are more energy-efficient. Some initial areas of exploration include:
- Optimization between different silicon environments: Examining how different hardware platforms can be more energy-efficient.
- Immersion cooling: Comparing traditional air cooling systems with alternative cooling methods in streaming environments. This includes processes like encoding, packaging, caching, and even playback in consumer electronics.
- Deploying tasks to renewable energy infrastructures: Specifically, relocating non-time-sensitive encoding tasks to infrastructures powered by surplus renewable energy. An exciting development in this area is the interest shown by the Scottish Enterprise which aims to test the relocation of non-critical transcoding workloads to a wind-powered facility in Scotland.
Barbara emphasized that all these projects were established during a Greening of Streaming event in June, and are currently in progress. She invited interested parties to join these projects and announced an upcoming member meeting that was held on September 13. Next one – October 11th.
Additionally, at IBC in September, the Greening of Streaming plans to present these projects to a broader audience, kick off the work in the fourth quarter, and continue into the next year. By the NAB event in April 2024, the organization hopes to discuss the projects in-depth and share test results.