Ashwin Amanna

Survey of cognitive radio architectures

Cognitive Radio and Cognitive Networking are emerging fields of research that has the potential for transformative changes to the current status quo. Cognitive systems utilize environmental observations such as spectrum or network conditions to change operational configurations in order to optimize performance at individual node or over end-to-end goals. This paper surveys some of these origin cognitive frameworks and correlates these frameworks to cognitive radio implementations of today. Several definitive implementations and cognitive radio architectures are reviewed and compared. This paper also identifies area of need and suggests directions forward for novel research in this area through interdisciplinary collaboration with the cognitive sciences, integrating prediction and proactive operation into cognitive radio/network architectures and identifying less researched artificial intelligence algorithms that show promise towards cognitive radio architecture.

Green Communications: A Call for Power Efficient Wireless Systems

Telecommunication usage has skyrocketed in recent years and will continue to grow as developing world reaches to wireless as the communication medium of choice. The telecommunications world is only now addressing the significant environmental impact it is creating as well as the incredible cost on power usage. This realization has led to a push towards Green Communications that strives for improving energy efficiency as well as energy independence of telecommunications. A survey of existing metrics for energy efficiency is discussed with specific adaptations for a communication centric viewpoint. This paper reviews recent energy efficient advances made at specific point within the communications cycle such as components, network operation and topology, and incorporating renewable and alternative energy into base stations. We further survey several holistic approaches that illustrate the dependencies between layers of the communications stack and operation/deployment. These approaches include cross layer design, cognitive radio, and wireless distributed computing.

Railway Cognitive Radio

Wireless communication plays a vital role in the success of railroad operations. This article describes an effort toward 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, spectrally efficient, and less costly to deploy and maintain. Cognitive radios (CRs) 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 because of realizing some functionality in software as opposed to a purely hardware platform. By using situational awareness from the radio in the form of observable parameters, often known as meters, a cognitive engine (CE) uses software-based decision-making and learning algorithms to determine whether a change in the radio parameters, commonly referred to as knobs, is required based on sets of predefined goals.

Metacognition: Enhancing the performance of a cognitive radio

The application of techniques from artificial intelligence, human decision-making processes, optimization, and learning methodologies have led to significant development in the field of cognitive radios. A cognitive radio improves on a traditional radio by incorporating situational awareness, learning, and decision-making to meet the application goals and adapt to the current operating environment. The field of cognitive radios is a very active, multi-disciplinary research area with significant benefits in many application areas. In this paper, we propose a “metacognitive engine”, where a master process or controller that monitors and adapts the cognition process, generally called the “cognitive engine”. The metacognitive engine utilizes situational awareness and scenario classification and drives the cognitive process. By incorporating radio-level or system-level goals/missions and selecting the most suitable performance metric based on the mission and current state of the cognitive process, the metacognitive controller can adapt/modify the cognitive process to better utilize past experiences and achieve the best performance in the given operating environment. A case study where we apply the metacognitive radio to improve wireless communication systems used for signaling and train control in railroads is also presented.

Hybrid Experiential-Heuristic Cognitive Radio Engine Architecture and Implementation

The concept of cognitive radio (CR) focuses on devices that can sense their environment, adapt configuration parameters, and learn from past behaviors. Architectures tend towards simplified decision-making algorithms inspired by human cognition. Initial works defined cognitive engines (CEs) founded on heuristics, such as genetic algorithms (GAs), and case-based reasoning (CBR) experiential learning algorithms. This hybrid architecture enables both long-term learning, faster decisions based on past experience, and capability to still adapt to new environments. This paper details an autonomous implementation of a hybrid CBR-GA CE architecture on a universal serial radio peripheral (USRP) software-defined radio focused on link adaptation. Details include overall process flow, case base structure/retrieval method, estimation approach within the GA, and hardware-software lessons learned. Unique solutions to realizing the concept include mechanisms for combining vector distance and past fitness into an aggregate quantification of similarity. Over-the-air performance under several interference conditions is measured using signal-to-noise ratio, packet error rate, spectral efficiency, and throughput as observable metrics. Results indicate that the CE is successfully able to autonomously change transmit power, modulation/coding, and packet size to maintain the link while a non-cognitive approach loses connectivity. Solutions to existing shortcomings are proposed for improving case-base searching and performance estimation methods.

Experimental testbed for investigating IEEE 802.11 handoff in vehicular environment

Wireless networks based on the IEEE 802.11 standard have become very prevalent recently. Most of these networks support only nomadic mobility of wireless devices. However, in case of vehicle-to-infrastructure communications the mobile devices in the vehicles need to have the ability to quickly switch their association to a new access point (AP) when they move out of range of their initial access point to ensure seamless connectivity. The handoff latency in vehicular environments can be improved if the mobile device has prior knowledge about the channels that access points in its vicinity are using. This paper describes a testbed for testing vehicle-to-infrastructure communications and gives experimental results showing improvement in handoff latency with prior knowledge of channels to scan.

ACTIVE RFID FOR ENHANCED RAILWAY OPERATIONS

RFID tags have been used by railways for many years, RFID has proven its worth in inventory management, yet this technology is underutilized for enhancing railway operations and health monitoring due to limitations of passive RFID technology. Active RFID provides enhanced capabilities with potential to improve railway operations. Active technology differs from passive RFID by incorporating an onboard power source enabling longer ranges, changeable data fields, and the ability to transmit independently of the reader. This paper compares the advantages and disadvantages of active compared to passive RFID in terms of power requirements, transmission range, and dynamic data. A survey of existing products and vendors is presented. The existing active RFID standards are reviewed and elements of the data tag protocols are detailed as well as protocols for mitigating collisions of data packets. Finally, specific railway applications utilizing active RFID are discussed.

Cognitive radio engine parametric optimization utilizing Taguchi analysis

Cognitive radio (CR) engines often contain multiple system parameters that require careful tuning to obtain favorable overall performance. This aspect is a crucial element in the design cycle yet is often addressed with ad hoc methods. Efficient methodologies are required in order to make the best use of limited manpower, resources, and time. Statistical methods for approaching parameter tuning exist that provide formalized processes to avoid inefficient ad hoc methods. These methods also apply toward overall system performance testing. This article explores the use of the Taguchi method and orthogonal testing arrays as a tool for identifying favorable genetic algorithm (GA) parameter settings utilized within a hybrid case base reasoning/genetic algorithm CR engine realized in simulation. This method utilizes a small number of test cases compared to traditional design of experiments that rely on full factorial combinations of system parameters. Background on the Taguchi method, its drawbacks and limitations, past efforts in GA parameter tuning, and the use of GA within CR are overviewed. Multiple CR metrics are aggregated into a single figure-of-merit for quantification of performance. Desirability functions are utilized as a tool for identifying ideal settings from multiple responses. Kiviat graphs visualize overall CR performance. The Taguchi method analysis yields a predicted best combination of GA parameters from nine test cases. A confirmation experiment utilizing the predicted best settings is compared against the predicted mean, and desirability. Results show that the predicted performance falls within 1.5% of the confirmation experiment based on 9 test cases as opposed to the 81 test cases required for a full factorial design of experiments analysis.

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.Copyright

Cognitive Engine Architecture for Railway Communications

This paper discusses a railway specific cognitive radio that builds upon software defined radio (SDR) platforms to adapt the radio based situational awareness. Cognitive Radio incorporates artificial intelligence based algorithms with reconfigurable software-defined radios that enable automatic adjustments of the radio to improve performance and overcome obstacles the radio may confront in the field (i.e. environmental/man-made interference, occupying the same channel as a user with higher priority, etc.). This paper describes the Railway Cognitive Radio (Rail-CR) architecture and illustrates preliminary results in simulation. The proposed cognitive engine architecture consists of a case-based reasoned (CBR) and a Genetic Algorithm (GA) optimization routine. This paper discusses the overall cognitive architecture, the relationship between the CBR and the GA based on weighted objective functions, and metrics for assessing performance. Methods for case representation, quantifying similarity between cases histories, and techniques for managing case growth rate are presented as well as a proposed test bed SDR platform.Copyright