Dynamic adjustment and load balancing of 6G network resources for the instantaneous peak demand of concerts

With the rapid advancement of 6G networks, managing network resources efficiently in high-demand environments such as live concerts has become increasingly important. Concerts, characterized by large crowds and high data traffic due to real-time multimedia streaming, pose significant challenges to traditional cellular infrastructure. This research addresses the dynamic load balancing and resource adjustment required to optimize network performance in such environments. This research proposes a Northern Goshawk Mutated Dynamic Recurrent Neural Network (NG-DynamicRNN) algorithm designed specifically for 6G networks to adapt to the fluctuating peak demands during concerts. The NG-DynamicRNN algorithm performs real-time adjustments to network resources by balancing load across network cells based on factors such as proximity, traffic patterns, and available resources. The algorithm ensures seamless multimedia streaming by efficiently redistributing traffic and preventing congestion during peak demand. Real-time data is collected from user devices, capturing traffic, congestion, and mobility information, and then the data is preprocessed using data cleaning and normalization techniques. Experimental results show that the NG-DynamicRNN algorithm significantly enhances network stability, reduces congestion, and improves key performance metrics, including throughput, connection reliability, and handover success rates, ensuring optimal performance even during the most demanding concert scenarios.