Скачать с ютуб AI4Green CELTIC Excellence Award winning project 2024 in the category green networking в хорошем качестве

AI4Green CELTIC Excellence Award winning project 2024 in the category green networking

AI4Green focused around the need to build comprehensive, sophisticated and energy-efficient algorithms and solutions at both radio access and core networks, but also on data centers and storage while keeping in mind the emergence of new architectures and the development of smart grids. The project met with the challenging goals to save 30-40 % of energy and even had progress beyond these goals when it comes to AI assisted energy savings and fault detection. The results range from research driven results to real products and standardization activities. High energy savings are often achieved when techniques as advanced sleep modes in combination with AI are used. AI4GREEN analysed an extensive amount of data coming from different resources such as 1) environmental awareness (radar measurements, wireless signal propagation), 2) Mobile operator network (deployment, traffic and performance), 3) Mobile users (crowd sourced data and mobile device services usage data). Real measurements supported by operators live networks. To be highlighted is the testing in the most crowded area in Istanbul, where 14% energy savings in live networks by AI assisted sector and carrier shut down has been shown. 10% extra energy savings is achieved with the proposed approach compared to existing model-based approach when it comes to sector shut down. Normally when the traffic load is high during day time, energy saving features are not activated, especially during special events with large crowds gathering to avoid risk of performance degradation. Via mobility prediction, modelling and analysis of temporal and geo-spatial crowd movements, energy saving can be selectively enabled in more than 50% of the cells during 5 hours right after a football game in the city centre. New architectures and communication technologies such as Cell-free massive MIMO on top of virtualized cloud RAN has been studied with intelligent access point clustering and switching off. AI is used to adaptively configure 5G base stations with large antenna elements together with advanced sleep modes bringing in energy savings in the range above 30%. This high percentage comes from the deep sleep capability of the modern technologies in combination with usage of AI. Novel fault detection solutions have been developed avoiding extra drive tests thanks to the data analytics and implementation of AI algorithms. The project resulted in new and improved products impacting the telco business in saving energy and advancing with the latest AI technologies. During the project several field trials have been performed Estimations shown from operators’ side showed that 15% energy savings can be achieved using AI empowered networks, still depending on what kind of network is used. The solutions provided by AI4GREEN can not only reduce the costs for OPEX but also cell to emission can be improved.