MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641050097 A) filed by Dr Ch. Rama Krishna; Nomula Srinivas; Dr Katapaka Yadaiah; Mennaiah Batta; and Malla Reddy Deemed To Be University, Hyderabad, Telangana, on April 20, for 'reconfigurable fractal metasurface antenna with ai-driven beam steering for multi-band 6g communications.'
Inventor(s) include Dr Ch. Rama Krishna; Nomula Srinivas; Dr Katapaka Yadaiah; Mennaiah Batta; and Dr G Prasanna Kumar.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses a technical framework for a reconfigurable fractal metasurface antenna designed to meet the high-speed and low-latency requirements of multi-band 6G communication networks. Conventional antenna systems often struggle with limited bandwidth and fixed radiation patterns, which lead to significant signal degradation and inefficient spectrum utilization in dynamic urban environments. The invention overcomes these limitations by providing a programmable metasurface infrastructure that utilizes fractal geometry to achieve multi-resonance characteristics across sub-6 GHz and millimeter-wave (mmWave) frequencies. The system architecture utilizes a combination of active switching components and an AI-driven control core to enable real-time, adaptive beam steering. Traditional phased array systems frequently suffer from high power consumption and hardware complexity when attempting to track high-mobility users in 6G scenarios, whereas the proposed model leverages machine learning algorithms to predict optimal beam configurations. This dual-pathway approach ensures that the antenna maintains a high gain and narrow beamwidth across multiple bands, facilitating seamless connectivity for ultra-reliable low-latency communication (URLLC) and massive machine-type communication (mMTC). The invention further incorporates an intelligent neural network module that processes environmental feedback and user mobility data to optimize the phase distribution across the fractal meta-atoms. By utilizing deep reinforcement learning, the framework provides a robust solution for beam alignment without the need for exhaustive codebook searches, thereby reducing the computational overhead of the base station. The result is a proactive wireless interface that significantly enhances spectral efficiency, ensuring that the 6G network can adapt to varying traffic densities and multi-path fading conditions with high precision. Furthermore, the system integrates a decentralized reconfiguration layer that allows the metasurface to switch between different operational modes, such as wide-area broadcasting and point-to-point narrow beaming. This capability ensures that the hardware can support diverse 6G use cases, from augmented reality (AR) streaming to industrial IoT synchronization, through a single aperture. By maintaining a dynamic library of optimized beam patterns, the invention provides an adaptive electromagnetic solution that supports the development of future-proof telecommunications infrastructures and automated network management protocols. Finally, the invention provides a cloud-native scalability interface that allows for the simultaneous coordination of multiple metasurface nodes across a metropolitan area. This architecture enables the network to standardize its beamforming benchmarks, allowing for the minimization of inter-cell interference through synchronized beam coordination. By utilizing automated data ingestion and AI-based pattern synthesis, the invention minimizes the manual effort required for RF planning, ensuring that high-priority communication links are established with zero-compromise reliability and forensic accuracy."
Disclaimer: Curated by HT Syndication.
