Green Energy and Traffic Forecasting using AI/ML Challenge Launch

  • * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

  • Date
    6 August 2024
    Timeframe
    14:00 - 15:00
    Duration
    60 minutes
    Share this session

    With the goal of achieving net-zero emissions by 2050, the Information and Communication Technology (ICT) industry is intensifying its focus on reducing environmental impact. Optimizing energy usage in mobile networks has become crucial. Mobile networks utilize a mix of energy sources—including traditional electricity grids, solar panels, and diesel generators—each with its own cost and carbon emissions implications, and varying availability. To address the challenges of rising energy costs and promote a greener telecom industry, accurate forecasting of daily solar energy generation and the development of effective energy management strategies are essential. This challenge encourages participants to apply machine learning to predict solar energy production and devise strategies for optimal energy use, advancing more sustainable and cost-efficient energy practices within mobile networks. 

    The second problem statement introduces a novel challenge within the domain of spatio-temporal forecasting. Specifically, it focuses on predicting traffic throughput volumes at the beam level within communication networks. Participants are encouraged to apply cutting-edge machine-learning techniques to develop and implement models for accurate traffic volume forecasting. Precise traffic volume prediction is crucial for optimizing network traffic flow and resource allocation. Successful models have the potential to significantly impact traffic management, resulting in substantial societal benefits such as energy efficiency, reduced network congestion, enhanced user experience, and improved environmental sustainability.