Method and apparatus providing decentralized, goal-orientated adaptive learning in an adaptive orthogonal frequency division multiplex communication system

摘要

Disclosed is an OFDM communications system and a method of operating the OFDM communications system. The system includes an OFDM transmitter for transmitting data over a plurality of OFDM sub-channels, where the OFDM transmitter has a plurality of modulators of different types. The system further includes an OFDM receiver for receiving the data from the plurality of OFDM sub-channels, where the OFDM receiver has a plurality of corresponding demodulators of the different types. The system further includes, in accordance with this invention, an adaptive learning automata that contains a group or team of independent, decentralized automaton operating in accordance with a game theory-based approach. Each of the plurality of automaton are responsible for managing one MCS switching threshold value so as to maximize at least one selected performance criterion. The OFDM transmitter is responsive to the MCS switching thresholds for selecting an appropriate one or ones of said modulators for modulating the data for various ones of the sub-channels.