Contributed by Andrew Burrell, Head of Marketing & Communications, Nokia.
One of the reasons for the world’s glacially slow response to the dangers of climate change is the sheer difficulty of taking effective action. Most people accept that dramatic reductions in greenhouse gas (GHG) emissions are needed, but the high costs and often severe lifestyle changes needed are daunting barriers.
We could cite many examples, but let’s look at just two:
- The aviation industry must reduce carbon emissions, but means people flying less
- Reducing the carbon footprint of buildings is essential, but means substantial spending on new heating and insulating systems.
Fortunately, it’s a different story when it comes to mobile telecom networks. While such networks may account for just over 1% of global electricity consumption, that 1% adds up to a significant volume of GHG emissions. Unsurprisingly, customers, investors, regulators and governments are urging communications service providers (CSPs) to take action.
While CSPs may be keen to reduce their network energy consumption (and thus costs), the challenge is to do it without compromising network performance, customer satisfaction or the bottom line.
Target the radio network
So how can it be done without forcing CSPs into large-scale hardware redeployments, comprehensive network modernization or architecture redesigns? And how can network carbon footprints be reduced without degrading the user experience?
CSPs aiming to cut the largest possible chunk of energy consumption at the fastest possible pace need to focus on the radio access network (RAN). That’s because the RAN accounts for around 80% of all mobile network energy consumption. “Waste” is an issue because only 15% of that energy is used to transmit data. The other 85% goes into secondary systems such as heating and cooling, lighting, uninterruptible and other power supplies, and running idle resources.
Modernizing network infrastructure can help but is hindered by slow upgrade cycles and requires high upfront CAPEX investments. If we want to have an immediate impact, there are two main strategies to reduce network energy use: dynamic network shutdowns and full-site power management.
Dynamically shutting down unused network elements during low-traffic periods can save much energy. Artificial intelligence (AI) maximizes the potential savings by using all sorts of data to precisely predict when to shut down infrastructure and perfectly balance energy savings, network performance and customer experience.
Using AI to control dynamic shutdowns can extend sleep times by several hours compared to statically scheduled shutdowns. AI can further boost energy savings by another 50% by eliminating the need to keep resources on standby ready to serve a sudden uplift in demand.
Managing passive equipment
Yet dynamic shutdowns only account for network elements, not power-hungry auxiliary components such as fans, cooling systems, lighting and power supplies. To ensure maximum energy efficiency, AI-powered energy consumption management must cover both active radio and passive equipment. The key is to benchmark energy trends to spot performance anomalies in historically “invisible” passive equipment that could be draining energy and might need to be reconfigured or replaced. Implementing such AI-based energy management can reduce energy costs by 20-30%.
The best news is that, because it is software, AI-based energy efficiency can be deployed in just a few weeks without major upfront investment. Software as a Service business models can also mean that CSPs pay their vendors only for the outcomes that are actually achieved. Implementing the technology over a public cloud can make it even more convenient by easing the processing and analysis of the large volume and velocity of network data.
Maintaining the customer experience
The question that now arises is how can CSPs guarantee that network performance and customer experience don’t suffer when parts of the network are powered down? How do they ensure resources are powered up again in time for traffic peaks? In other words, how to ensure network performance requirements and energy consumption are precisely aligned?
A problem of such complexity calls for AI-based energy solutions that can predict precisely the right time to power off resources and power them on again. Just-in-time waking is hard to achieve with static or rules-based methods, usually requiring extensive wake-up windows or the use of standby mode to shorten response times.
China Mobile adopts an AI-based solution
This was the situation facing China Mobile which wanted a to cut energy consumption and control costs without compromising the customer experience. The CSP realized it needed a comprehensive energy efficiency plan to reduce emissions and lower costs without affecting the customer experience or compromising network performance.
China Mobile decided to use the Nokia AVA Energy Efficiency solution for:
- Predictive and dynamic management of passive and active components to gain much finer-grained control over energy consumption
- Predictive closed loop actions for faster, automated responses to changing conditions instead of relying on manual interventions that cause delayed responses
- Automated remote antenna control to adjust coverage dynamically according to shifting capacity requirements.
China mobile was able to permanently balance energy savings and performance requirements, allowing key performance indicators (KPIs) to be pre-set, with savings calculated by the AI system.
Contrary to most areas of daily life, energy savings in telecoms do not require massive lifestyle changes and do not have an impact on the services and the experiences customers are used to. That has to be good news for people and the planet.
Andrew is speaking on the ‘Energy efficiency and sustainability by design’ panel discussion at FutureNet World on the 11th of May. Register here.