Tackling the hot topic of global power consumption for mobile networks
Northampton, MA –News Direct– Ericsson
Global power consumption for mobile networks is a hot topic. One of the biggest challenges in our industry is the carbon footprint and the costs generated by energy consumption. As long as the energy mix used by the networks is not carbon neutral and partly comes from fossil energy, the operation of mobile networks will contribute to the emission of greenhouse gases into the atmosphere. This means that reduced energy consumption through smarter use of mobile networks can have a decreasing effect on greenhouse gas emissions.
If energy consumption continues to increase, it is highly likely that energy prices will also increase. Either way, network operating costs will be higher and the combination will increase the total cost of ownership. Reducing energy consumption will require the combined efforts of the telecommunications industry. It must be considered from all angles, leaving no stone unturned.
An Inconvenient Truth: For RAN
The first step to solving a problem is to accept that there is one. That’s why our Network Analytics feature supports observability of energy consumption across generations. The main villain in this story is the consumption of the site. Radio Access Network (RAN) sites account for approximately 85% of network consumption, with data centers making up the remaining 15. This could increase in the case of cloud RAN.
Ericsson’s future intelligent automation platform will support rApps such as the future energy saving manager. The energy saving manager can make centralized decisions about which energy saving functions to activate and in which configuration.
Part of Ericsson’s philosophy for intelligent RAN automation is to choose centralized or decentralized control for each specific use case for maximum impact. For better energy efficiency, centralized control enables holistic decision-making based on analysis of data from multiple sites. This analysis can then be used to create the best local configuration to maximize KPIs and performance while reducing overall power consumption.
Going one step further, improved data collection and analysis enables service providers to make active decisions about prioritization. This includes determining if (and to what extent) a negative impact on KPIs can be allowed to further improve energy savings. This may differ depending on where in the network energy savings and KPI targets can be achieved and adjusted.
Think globally, act locally: on the node
Node-level energy saving requires the energy metering function to support the energy analysis function. MIMO standby is an effective feature to maintain user experience while minimizing waste when less capacity is sufficient. The problem was that it previously required manual configuration, which is time-consuming and less efficient. To address the issue, we launched AI-powered MIMO sleep, which automates setup to reduce manual work and improve feature performance (both for KPIs and power savings) at the of the knot. For more information, see the PoC results.
Features like AI-powered MIMO sleep mode allow us to make the most of the current resource utilization paradigm. The next leap in node power savings will come from a paradigm shift. Today, resources are by definition “always on” and turned off or put into low-power mode when the traffic situation permits. In the future, we envision moving to an “always on” paradigm where resources sit idle until needed. With smart predictions, they can be activated when needed. By using AI-powered capabilities, we can make accurate traffic predictions to achieve additional savings while providing users with the same great performance.
The day after tomorrow: prospects
In the future, we see that Reinforcement Learning (RL) approaches will further improve energy savings and network performance. RL is especially useful in the type of dynamic, complex, high-demand environments that make up mobile networks.
RL can be applied in several ways to networks in general and to energy conservation in particular. An example is the two successful trials that Ericsson concluded applying reinforcement learning to remote electrical antenna tilting (RET). At a glance, it doesn’t seem that complicated, but each time you tilt an antenna, it changes the shape of the cell the antenna is in. This in turn affects the user experience of those served by that cell and the cells around it, tilting further from the surrounding antennas has a cascading effect in the network. This makes it all the more impressive that in a single live network, when optimizing for reduced ERP, Ericsson and partner service provider caused a 20% decrease in DL transmit power without affecting performance.
RL also presents more possibilities for large scale and complex orchestration. For example, power savings could be incorporated into traffic control and used to route traffic to the most power-efficient resources in the network. This would allow other resources to hibernate while the traffic control scheme is active.
If we step back and look at the network and its entire lifecycle, it’s easy to see that we not only need to optimize for today and what’s already deployed, but also seriously consider what should be deployed in the future. Considering what to deploy and where is especially important now that much of the world is in the midst of 5G rollout.
It’s quite simple: smarter and more accurate deployment reduces the hardware required and the environmental footprint of the network. The cognitive software suite has several features that support this. Including capacity planning for traffic forecasting, site selection to determine the best location for deployment, and RF design to optimize the models used for network design. The full impact is an optimized network layout that reduces the strain on the wallet and the environment.
Earth Hour, every hour
At Ericsson, we know that business can only thrive in a sustainable environment. But, of course, unlike Earth Hour, mobile networks can’t be allowed to shut down, so we all need to make sure we’re optimizing every hour. We take this challenge seriously and provide solutions across mobile networks and their lifecycles. We believe it benefits us now and future generations.
Contact us if you would like to learn more about how we can help you reduce your mobile network’s carbon footprint and become more energy efficient!
Intelligent RAN Automation
AI: Improving customer experience in a complex 5G world
An Intelligent Platform: Using O-RAN’s SMO as a Catalyst for RAN Openness and Innovation
Ensuring Energy Efficient Networks with Artificial Intelligence
Can AI reduce grid energy costs?
Ericsson launches AI-powered energy infrastructure operations
How to break the energy curve
Discover additional media content and other ESG stories from Ericsson on 3blmedia.com
See source version at newsdirect.com: https://newsdirect.com/news/tackling-the-hot-topic-of-global-energy-consumption-for-mobile-networks-441598197