unplush image
How Artificial Intelligence reduces the carbon footprint for telcos
Did you know 78% of telcos are counting on AI energy solutions to cut energy use? From the originally produced energy in power plants only 90% “arrives” at the network, so there is already a loss of 10% during energy transmission. From this remaining energy about 80% is consumed by radio access, the rest by transport, core and OSS. 30% of that network energy (35% of the original energy) is consumed by auxiliary passive components such as air conditioning and power systems so only 70% (65% of the original energy) is consumed by the network element itself.
Site solutions for energy are extremely important. Power hungry fans and power supplies consume another 20%, only the rest arrives at the chipsets as such and can be used for transmitting traffic. From that remaining energy, only 30% is really used in a productive revenue-generating way since on average most resources are running idle. Therefore, AI based solutions performing dynamic shutdowns of unused resources are key. In effect, 85% of the original energy “disappears” and is not used productively.
Dynamic shutdowns of unused active and passive elements in low-traffic situations
AI models and machine learning predict network traffic and adjust shutdown times dynamically to extend savings windows compared to static schedules, avoiding any degradation of network performance. Supervised learning permanently adjusts predictions based on the latest load and network performance feedback. The AI solution enables differentiated energy saving plans for different areas such as rural or urban. The result is a coherent energy control that dynamically adapts energy consumption to traffic levels while maintaining a premium user experience. We have seen that AI-based solutions achieve two to five times more savings than non-AI systems that perform temporary shutdowns based on fixed schedules.
Automated remote control of the antenna angle
Dynamically adjusts the azimuth and elevation angle of antennas to reduce energy consumption further at given capacity and coverage requirements. Due to full automation, there is no need for personnel to go to the station to adjust the antenna.
Hardware power saving control
Hardware can continue to use power even when it’s not in use unless it’s physically shut off. Hard power saving control makes sure equipment that isn’t needed is fully shut down, which can further increase energy savings by up to 50%. With the accurate predictions of the AI engine, the unplugged equipment is powered up right in time when it is again needed.
AI powered energy management across active radio and passive equipment
Telco AI analytics benchmarks energy trends and spots anomalies in the performance of historically “invisible” passive equipment such as batteries or air conditioners that could be draining energy and need to be reconfigured or replaced. Drawing from sources including radio networks, connected devices, weather data, asset databases, energy bills and alarms, AI uses advanced analytics to identify patterns and trends and provide benchmarks. This data feeds into a dashboard that displays anomalies such as faulty equipment, leakage or theft.
AI powered cooling
Intelligent Fresh Air Ventilators exchanging hot and cold air inside and outside the computing room and intelligent air conditioning can massively reduce the operating time of cooling systems throughout the day. This can lead to a 70% reduction in cooling costs which are the major energy cost driver of radio sites.
AI savings simulation
AI models can simulate the results of proposed changes to calculate the impact on network energy efficiency and CO2 emissions in advance. The system can make recommendations to correct, upgrade or modernize, and offers advanced simulation capabilities, so you can see how much energy you’ll save by implementing proposed changes.
How to make AI energy management for networks happen
Because of its software nature, AI-based energy efficiency solutions can be deployed in just a few weeks without major upfront investment — especially thanks to outcome-based Software-as-a-Service (SaaS) business models, which enable you to pay only for the energy savings outcomes you actually achieve. Implementing the AI system over a public cloud can make it even faster by easing the processing and analysis of the large volume and velocity of network data.
Real-world experience shows that AI-driven automation can be implemented in a matter of weeks, making it the most immediate opportunity for large cost savings. We have seen power savings in real networks from 7% to 30%. AI based multi-vendor software can save to apply to not just the equipment of a single RAN vendor but the whole network.
As a total-site software-based telco energy solution, an AI system can be set up quickly to minimize all kinds of energy waste.
5G network may be wasting energy. AI can change that in a flash
For any CSPs out there who have been waiting for the right solution to come along and help them meet their sustainability goals with energy savings.
No comments:
Post a Comment