Wireless radio access network rf cell power determination
AssigneeAT&T Intellectual Property I, L.P.
InventorsTanvi Alam, Syed Anwar Aftab, Anandarup Sarkar
Life of this patent
Estimating the term…
Abstract
Aspects of the subject disclosure may include, for example, a device that trains a RF Power Large Language Model (RFP-LLM) using historical RF power data, cell site geography, RF use case constraints, vendor product capabilities, FCC power restrictions, and O-RAN standards. An interactive Generative AI-driven chatbot queries the RFP-LLM for RF power configuration plans for one or more cell sites. A simulation engine evaluates these plans, and the system modifies network configurations to implement the plans, and continuously improves the RFP-LLM with simulation results and feedback. Other embodiments are disclosed.
Claims20
A device, comprising:
- a processing system including a processor;
- and
- a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:
- training an RF Power Large Language Model (RFP-LLM) using historical RF cell power configurations, vendor hardware and software specifications, FCC requirements, and O-RAN standards;
- providing an interactive Generative AI-driven chatbot configured to query the RFP-LLM to determine RF power settings for cell sites;
- generating, by the RFP-LLM, RF power configuration plans for the cell sites;
- simulating, by a simulation engine, the RF power configuration plans to evaluate an effectiveness in meeting competing RF use case needs and conforming to Federal Communications Commission (FCC) requirements;
- and
- reconfiguring at least one RF cell power component based on the RF power configuration plans.
A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processing system including a processor, facilitate performance of operations, the operations comprising:
- training an RF Power Large Language Model (RFP-LLM) using vendor hardware and software specifications, FCC requirements, and O-RAN standards;
- providing an interactive Generative AI-driven chatbot configured to query the RFP-LLM to determine RF component selections for cell sites;
- generating, by the RFP-LLM, RF power configuration plans for the cell sites;
- simulating, by a simulation engine, the RF power configuration plans to evaluate an effectiveness in meeting competing RF use case needs and conforming to Federal Communications Commission (FCC) requirements;
- and
- modifying at least one RF cell power component based on the RF power configuration plans.
A method, comprising:
- training, by a processing system including a processor, an RF Power Large Language Model (RFP-LLM) using historical RF cell power configurations, vendor hardware and software specifications, FCC requirements, and O-RAN standards;
- providing, by the processing system, an interactive Generative AI-driven chatbot configured to query the RFP-LLM to determine RF power settings for cell sites;
- generating, by the processing system using the RFP-LLM, RF power configuration plans for the cell sites;
- training the RFP-LLM, by the processing system, using simulation results from a simulation of the RF power configuration plans;
- and
- reconfiguring at least one RF cell power component based on the RF power configuration plans.
Dependencies are inferred from the claim text.