Browsing by Author "Helva, Alperen"

Now showing 1 - 3 of 3

MOSAL: A Subspace-Based Forecasting Algorithm for Throughput Maximization in IoT Networks
(Institute of Electrical and Electronics Engineers Inc., 2022) Mert Nakıp; Alperen Helva; Cüneyt Güzeliş; Volkan Rodoplu; Guzelis, Cneyt; Rodoplu, Volkan; Helva, Alperen; Nakip, Mert
Predictive solution techniques have been developed recently to solve the massive access problem of the Internet of Things (IoT). These techniques forecast the traffic generation patterns of individual IoT devices in the coverage area of an IoT gateway and schedule the Medium Access Control (MAC)-layer resources at the gateway in advance based on these forecasts. Although predictive solutions have achieved high network performance a key problem is that their performance depends highly on the performance of forecasters. In this article to minimize the effects of forecasting errors on the performance of predictive networks we develop a subspace-based forecasting algorithm called 'Motion On a Subspace under Adaptive Learning rate (MOSAL).' First our algorithm trains a forecaster by minimizing the performance loss of an IoT network based on the emulation of an Application-Specific Error Function (ASEF) by an Artificial Neural Network (ANN). Second the algorithm moves close to a subspace of the forecasting errors while aiming to maximize network throughput. Our results show that MOSAL achieves a throughput performance that surpasses the performance of commonly used standard gradient descent training algorithms at a reasonable execution time. These results open the way to the deployment of predictive solutions at IoT gateways in practice in the near future. © 2023 Elsevier B.V. All rights reserved.
Nesnelerin interneti için altuzay tabanlı uygulamaya özgü hata metriği öykünmesi ile bütünleşik tahminleme-çizelgeleme
(2021) Helva, Alperen; Rodoplu, Volkan; Güzeliş, Cüneyt
The massive access problem refers to the challenge posed in uplink wireless communication from a massive number of Internet of Things (IoT) devices to an IoT gateway, base station or access point. In this thesis, first, we present an Application-Specific Error Function (ASEF), which measures the impact of the forecasting error on network performance for Joint Forecasting-Scheduling (JFS). Second, we propose a Neural Network (NN)-based emulation of ASEF on a subspace of forecasting errors, which we call ``Emulation of ASEF'' (E-ASEF), and develop a novel algorithm, ``Motion On a Subspace under Adaptive Learning rate'' (MOSAL), which moves on this subspace of forecasting errors while minimizing the application-specific error metric at the output of MAC-layer scheduling. Our results show that MOSAL improves the performance of the JFS system while achieving a low execution time. This work paves the way to achieving high network performance at an IoT Gateway that has a massive number of IoT devices in its coverage area.
Citation - Scopus: 6
Subspace-Based Emulation of the Relationship between Forecasting Error and Network Performance in Joint Forecasting-Scheduling for the Internet of Things
(Institute of Electrical and Electronics Engineers Inc., 2021) Mert Nakıp; Alperen Helva; Cüneyt Güzeliş; Volkan Rodoplu; Guzelis, Cuneyt; Rodoplu, Volkan; Helva, Alperen; Nakip, Mert
We develop a novel methodology that discovers the relationship between the forecasting error and the performance of the application that utilizes the forecasts. In our methodology an Artificial Neural Network (ANN) learns this relationship while the forecasting error is kept inside a subspace of the entire space of forecasting errors during training. We apply our methodology to the case of Joint Forecasting-Scheduling (JFS) for the Internet of Things (IoT). Our results hold potential to improve the performance of JFS in next-generation networks and can be applied to a much wider range of problems beyond IoT. © 2021 Elsevier B.V. All rights reserved.