How Verizon is using digital twins to reduce energy costs
Operators are striving to use technology to improve the energy efficiency of their networks as we showcased in our recent report The sustainable telco: engineering networks for net zero. Verizon, for example, has been able to reduce energy costs by over $100 million a year by using network digital twins to build energy consumption models, according to Shankar Arumugavelu, Chief Digital and Information Officer, speaking at DTW 2022.
The creation of network digital twins is part of a long-term investment by Verizon in advanced analytics that will help it optimize network investments based on total cost of ownership, while improving customer experience. Michael Raj, Vice President of Network Enablement (AI & Data), explained how Verizon uses the virtual representation of its physical network to analyze and predict the performance, cost and efficiency of its network sites and equipment.
Creating a digital copy of the real world requires multiple layers of interrelated data and the better the data, the better the twin. Therefore, one of Verizon’s first steps was to standardize data for each of the different layers, including network performance and energy billing. This included standardizing data related to the configuration, make and model of antennae across multiple different sites. For although Verizon already had the data, “vendors A, B and C have different terminologies,” explains Raj. As a result, “Verizon developed common terminologies and a common index… to [be able to] mine this data across common standards”. Other data standardization work included aggregating the billing systems for different utility providers, cleaning up the data and matching it to the sites.
One of the advantages of having standardized data about energy costs, consumption and network performance is it makes it much easier to identify and analyze anomalies.
“We were able to gather the power consumption data for all of the cell sites and see some crazy anomalies,” says Raj. As a result, “we could question why this costs $1,000 versus the same configuration elsewhere, which only costs $500 … and identify specific problems related to those outliers, as well as make recommendations for how to remediate those situations when found in the future.”
Identifying room for improvement
The information also helps Verizon compare how different vendors’ equipment consumes energy in the field as opposed to in a lab and use the results to push for better performance.
“Let's say for 100 GB of capacity, vendor A proves to be more 35% more efficient in practice than vendor B, now we can push vendor B to create a more energy efficient solution,” says Raj.
And because the digital twin provides a standardized environment in which to visualize issues and test potential solutions, it encourages teams to take a more creative approach to improving operations.
“It's allowed us to increase the ideation across our operations team now that they have a single source to look at how the standard differs across networks, lines of business, services and types of technology,” explains Raj.
Having a clear picture of energy consumption across all its sites also helps Verizon make decommissioning decisions and optimize sleep settings at sites that house both 4G and 5G networks.
“When using sleep mode to reduce energy consumption in the middle of the night when there is no traffic, Verizon is able to observe the delta in terms of savings and calculate ROI.”
The data gathered also feeds into sustainability reporting: Verizon can use the network digital twin to quickly identify which locations rely on renewable energy, for example, when calculating its GHG emissions.
In addition, Verizon uses its network digital twin to help forecast energy costs, based on changes to the network, such as the addition of a new cell site or decommissioning, as well as energy price fluctuations, caused, for example, by the war in Ukraine. This gives financial officers a much more detailed energy price forecast against which to budget, which in turn helps them better manage financial markets’ expectations.
“Historically, limited forecasting could lead to short-sighted decisions based on positive performance in one quarter, without an understanding of how adverse conditions in subsequent quarters might impact budgets. In the future, what we'll be able to show is that although we are trending lower [in terms of energy spend], months of hard energy bills are coming,” says Raj. “This more granular forecasting piece is underappreciated, but CFOs will get a lot of peace of mind.’
Analyzing and improving energy efficiency is part of the digital twin’s wider remit of helping Verizon manage its total cost of network ownership while optimizing customer experience, with customer experience as the holy grail of the project.
“The customer’s experience of network performance cannot be compromised,” says Raj. “You don't want to power down a site [to save energy] and create new issues for customers in that area, he explains. "We've been very focused on doing the analysis required to understand which sites may be power-down candidates, identifying which may have low usage or adequate coverage from nearest neighbors. Ultimately, using data to inform decision making in this way will allow us to achieve cost-savings from energy optimization initiatives at scale."
(This article was updated 9 January 2023)