Charles Clancy

Applications of Machine Learning to Cognitive Radio Networks

Cognitive radio offers the promise of intelligent radios that can learn from and adapt to their environment. To date, most cognitive radio research has focused on policy-based radios that are hard-coded with a list of rules on how the radio should behave in certain scenarios. Some work has been done on radios with learning engines tailored for very specific applications. This article describes a concrete model for a generic cognitive radio to utilize a learning engine. The goal is to incorporate the results of the learning engine into a predicate calculus-based reasoning engine so that radios can remember lessons learned in the past and act quickly in the future. We also investigate the differences between reasoning and learning, and the fundamentals of when a particular application requires learning, and when simple reasoning is sufficient. The basic architecture is consistent with cognitive engines seen in AI research. The focus of this article is not to propose new machine learning algorithms, but rather to formalize their application to cognitive radio and develop a framework from within which they can be useful. We describe how our generic cognitive engine can tackle problems such as capacity maximization and dynamic spectrum access.

A utility proportional fairness approach for resource allocation in 4G-LTE

In this paper, we introduce an approach for resource allocation of elastic and inelastic adaptive real-time traffic in fourth generation long term evolution (4G-LTE) system. In our model, we use logarithmic and sigmoidal-like utility functions to represent the users applications running on different user equipments (UE)s. We present a resource allocation optimization problem with utility proportional fairness policy, where the fairness among users is in utility percentage (i.e user satisfaction with the service) of the corresponding applications. Our objective is to allocate the resources to the users with priority given to the adaptive real-time application users. In addition, a minimum resource allocation for users with elastic and inelastic traffic should be guaranteed. Our goal is that every user subscribing for the mobile service should have a minimum quality-of-service (QoS) with a priority criterion. We prove that our resource allocation optimization problem is convex and therefore the optimal solution is tractable. We present a distributed algorithm to allocate evolved NodeB (eNodeB) resources optimally with a priority criterion. Finally, we present simulation results for the performance of our rate allocation algorithm.

Utility Proportional Fairness Resource Allocation with Carrier Aggregation in 4G-LTE

In this paper, we consider a resource allocation optimization problem with carrier aggregation in fourth generation long term evolution (4G-LTE). In our proposed model, each user equipment (UE) is assigned a utility function that represents the application type running on the UE. Our objective is to allocate the resources from two carriers to each user based on its application that is represented by the utility function assigned to that user. We consider two groups of users, one with elastic traffic and the other with inelastic traffic. Each user is guaranteed a minimum resource allocation. In addition, a priority resource allocation is given to the UEs running adaptive real time applications. We prove that the optimal rate allocated to each UE by the single carrier resource allocation optimization problem is equivalent to the aggregated optimal rates allocated to the same user by the primary and secondary carriers when their total resources is equivalent to the single carrier resources. Our goal is to guarantee a minimum quality of service (QoS) that varies based on the user application type. We present a carrier aggregation rate allocation algorithm to allocate two carriers resources optimally among users. Finally we present simulation results with the carrier aggregation rate allocation algorithm.

A robust optimal rate allocation algorithm and pricing policy for hybrid traffic in 4G-LTE

In this paper, we consider resource allocation optimization problem in the fourth generation long-term evolution (4G-LTE) with elastic and inelastic real-time traffic. Mobile users are running either delay-tolerant or real-time applications. The users applications are approximated by logarithmic or sigmoidal-like utility functions. Our objective is to allocate resources according to the utility proportional fairness policy. Prior utility proportional fairness resource allocation algorithms fail to converge for high-traffic situations. We present a robust algorithm that solves the drawbacks in prior algorithms for the utility proportional fairness policy. Our robust optimal algorithm allocates the optimal rates for both high-traffic and low-traffic situations. It prevents fluctuation in the resource allocation process. In addition, we show that our algorithm provides traffic-dependent pricing for network providers. This pricing could be used to flatten the network traffic and decrease the cost per bandwidth for the users. Finally, numerical results are presented on the performance of the proposed algorithm.

Spectrum sharing between public safety and commercial users in 4G-LTE

In this paper, we consider resource allocation optimization problem in fourth generation long term evolution (4G-LTE) for public safety and commercial users running elastic or inelastic traffic. Each mobile user can run delay-tolerant or real-time applications. In our proposed model, each user equipment (UE) is assigned a utility function that represents the application type running on the UE. Our objective is to allocate the resources from a single evolved node B (eNodeB) to each user based on the user application that is represented by the utility function assigned to that user. We consider two groups of users, one represents public safety users with elastic or inelastic traffic and the other represents commercial users with elastic or inelastic traffic. The public safety group is given priority over the commercial group and within each group the inelastic traffic is prioritized over the elastic traffic. Our goal is to guarantee a minimum quality of service (QoS) that varies based on the user type, the user application type and the application target rate. A rate allocation algorithm is presented to allocate the eNodeB resources optimally among public safety and commercial users. Finally, the simulation results are presented on the performance of the proposed rate allocation algorithm.

A Utility Proportional Fairness Resource Allocation in Spectrally Radar-Coexistent Cellular Networks

Spectrum sharing is an elegant solution to addressing the scarcity of the bandwidth for wireless communications systems. This research studies the feasibility of sharing the spectrum between sectorized cellular systems and stationary radars interfering with certain sectors of the communications infrastructure. It also explores allocating optimal resources to mobile devices in order to provide with the quality of service for all running applications whilst growing the communications network spectrally coexistent with the radar systems. The rate allocation problem is formulated as two convex optimizations, where the radar-interfering sector assignments are extracted from the portion of the spectrum non-overlapping with the radar operating frequency. Such a double-stage resource allocation procedure inherits the fairness into the rate allocation scheme by first assigning the spectrally radar-overlapping resources.

Applying graphics processor acceleration in a software defined radio prototyping environment

With higher bandwidth requirements and more complex protocols, software defined radio (SDR) has ever growing computational demands. SDR applications have different levels of parallelism that can be exploited on multicore platforms, but design and programming difficulties have inhibited the adoption of specialized multicore platforms like graphics processors (GPUs). In this work we propose a new design flow that augments a popular existing SDR development environment (GNU Radio), with a dataflow foundation and a stand-alone GPU accelerated library. The approach gives an SDR developer the ability to prototype a GPU accelerated application and explore its design space fast and effectively. We demonstrate this design flow on a standard SDR benchmark and show that deciding how to utilize a GPU can be non-trivial for even relatively simple applications.

Radar inband and out-of-band interference into LTE macro and small cell uplinks in the 3.5 GHz band

National Telecommunications and Information Administration (NTIA) has proposed vast exclusions zones between radar and Worldwide Interoperability for Microwave Access (WiMAX) systems which are also being considered as geographic separations between radars and 3.5 GHz Long Term Evolution (LTE) systems without investigating the changes induced by the distinct nature of the LTE systems as opposed to WiMAX. This paper performs a detailed system-level analysis of the interference effects from shipborne radar systems into LTE macro cells and outdoor small cells. Even though the results reveal impacts of radar interference on LTE systems performance, they provide clear indications of conspicuously narrower exclusion zones for LTE vis-à-vis those proposed for WiMAX and pave the way toward deploying 3.5 GHz LTE within the exclusion zones.

A utility proportional fairness radio resource block allocation in cellular networks

This paper presents a radio resource block allocation optimization problem for cellular communications systems with users running delay-tolerant and real-time applications, generating elastic and inelastic traffic on the network and being modelled as logarithmic and sigmoidal utilities respectively. The optimization is cast under a utility proportional fairness framework aiming at maximizing the cellular systems utility whilst allocating users the resource blocks with an eye on application quality of service requirements and on the procedural temporal and computational efficiency. Ultimately, the sensitivity of the proposed modus operandi to the resource variations is investigated.

A hidden Markov model detection of malicious Android applications at runtime

A hidden Markov model approach is leveraged to detect potentially malicious Android applications at runtime based on analyzing the Intents passing through the binder. Real world applications are emulated, their Intents are parsed, and, after appropriate discretization of the Intent action fields, they train the hidden Markov models for recognizing anomalous and benign Android application behaviors. The inferred stochastic processes can probabilistically estimate whether an application is performing a malicious or benign action as it is running on the device. Such a decision is realized through a maximum likelihood estimation. The results show that the method is capable of detecting malicious Android applications as they run on the platform.