Stan McClellan

Dr. Stan McClellan

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 November 2015 in Network Protocols and Algorithms
Verified
Journal Article
Open access
PDF file
SMStan McClellan
Stan McClellan
WPWuxu Peng
Wuxu Peng
EGEd Gonzalez
Ed Gonzalez
The Stream Control Transmission Proto- col (SCTP) is a relatively new transport protocol. It has several underlying mechanisms that are similar to the Transmission Control Protocol (TCP), as well as several improvements that are important in certain classes of applications. The timeout scheme of SCTP, however, is almost identical to that used in TCP. With the dynamics of today’s Internet, that timeout scheme may be too passive. This paper presents an al- gorithm which dynamically adjusts the overall context of the retransmission timeout process without chang- ing the fundamental retransmission mechanisms. This approach manages the impact of fast retransmissions and timeouts to significantly improve the throughput of SCTP applications. The algorithm has been im- plemented and tested in real network environments. Experimental results show that the algorithm avoids spurious retransmissions and provides better through- put by intelligently managing RTO boundaries and allowing conventional timeout schemes to participate more actively in the retransmission process.

1 December 2018
Verified
Conference Paper
Closed access
BDBikramjit Dasgupta
Bikramjit Dasgupta
Damian VallesDamian Valles
Damian Valles
SMStan McClellan
Stan McClellan
This paper compares the performance and accuracy of four machine learning algorithms in classifying four characteristic phenomena in wireless signal use: decreases in bandwidth due to signal over-saturation, signal improvement due to a device moving closer to a wireless signal, signal attenuation due to increasing distance, and congestion caused by competition with high intensity cross-traffic on a switch. With large enough data samples, an SVM with a moderately high C parameter yielded the smallest 95% confidence intervals when compared to the other machine learning algorithms. This indicates that machine learning techniques can be used for such applications as congestion-control.

19 July 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SMStan McClellan
Stan McClellan
Damian VallesDamian Valles
Damian Valles
GKGeorge Koutitas
George Koutitas
A feedback-based architecture is presented for the distribution grid which enables the use of Machine Learning (ML) techniques for various applications, including Dynamic Voltage Optimization (DVO) and Demand Response (DR). In this architecture, sensor devices are resident on the distribution grid and therefore have a unique awareness of multiple system parameters. This enables the use of ongoing ML techniques for implementation of critical applications in the Smart Grid. Monitoring devices are placed at the endpoints and monitoring/control devices are placed along the power line on various types of grid-resident systems. Because the devices are grid-resident and interact directly with other devices on the same physical link, applications such as ML-assisted DVO can be targeted with very high confidence.