SYSTEM AND METHOD FOR ADAPTIVE CELL SEARCH BASED ON ARTIFICIAL INTELLIGENCE MODEL OF AN ELECTRONIC DEVICE

Smart overview of the Invention

A method is designed for user equipment (UE) to select a target cell by detecting movement based on location changes and signal power variations of the current serving cell. It involves determining personalized user data from various contextual parameters, predicting the user's destination, and identifying potential target cells along the user's path. The selection process utilizes an artificial intelligence (AI) model that dynamically updates weights for network quality parameters.

Background Context

The technology addresses existing issues in cell reselection, particularly in 5G networks. Current methods rely heavily on fixed weights for parameters like signal quality and block error rate, leading to inefficiencies such as high battery consumption and poor call quality. The conventional approaches do not adapt to user behavior or network conditions, which can result in frequent call drops and suboptimal throughput.

Challenges with Conventional Methods

• Fixed weights for network parameters do not account for personalized user behavior.
• Higher call drops may occur due to inadequate RF link management.
• Battery drainage is exacerbated when weights are not adjusted according to battery strength.
• Network resource usage is often not optimized, leading to inefficiencies.

Dynamic Adaptation through AI

The proposed system employs an AI model that updates weights based on real-time data, including personalized user information and network conditions. This dynamic adjustment allows the UE to make more informed decisions about which cell to connect to, improving overall performance. For instance, during a voice call or when the battery is low, the system can prioritize connections that enhance call quality or conserve battery life.

Conclusion and Future Implications

This innovative approach not only enhances cell selection efficiency but also addresses critical shortcomings of traditional methods. By integrating AI into the cell selection process, users can experience improved connectivity, reduced call drops, and better management of battery resources. Future developments may focus on refining these AI models further to optimize user experience in various network environments.