JRC2010-36201 RAIL-CR: COGNITIVE RADIO FOR ENHANCED RAILWAY COMMUNICATION

Robust, reliable, and interoperable wireless communications play a vital role in the success of railroad operations. This paper describes an effort towards developing a railroad-specific “cognitive radio ” (Rail-CR) that can meet the needs of future wireless communication systems for railways by making positive train control (PTC) communication more interoperable, robust, reliable, and spectrally efficient, and less costly to deploy and maintain. Cognitive radios are a cutting edge research area that combines artificial intelligence (AI) with Software Defined Radios (SDRs) with the goal of improving upon existing radio performance. SDRs are radios in which capabilities are flexible due to realizing some functionality in software as opposed to a purely hardware platform. By utilizing situational awareness from the radio in the form of observable parameters, often known as „meters‟, a cognitive engine (CE) utilizes software-based decision-making algorithms to determine if a change in the radio parameters, commonly referred to as „knobs‟, is required based on sets of predefined goals. Additionally, learning algorithms dovetail with the decision making to enable the system to track and utilize past decisions and observations. 1