We have developed a new framework using time-series analysis for dynamically assigning mobile network traffic prediction models in previously unseen wireless environments. Our framework selectively employs learned behaviors, outperforming any single model with over a 50% improvement relative to current studies. More importantly, it surpasses traditional approaches without needing prior knowledge of a cell. While this paper focuses on network traffic prediction using our adaptive forecasting framework, this framework can also be applied to other machine learning applications in uncertain environments.
The framework begins with unsupervised clustering of time-series data to identify unique trends and seasonal patterns. Subsequently, we apply supervised learning for traffic volume prediction within each cluster. This specialization towards specific traffic behaviors occurs without penalties from spatial and temporal variations. Finally, the framework adaptively assigns trained models to new, previously unseen cells. By analyzing real-time measurements of a cell, our framework intelligently selects the most suitable cluster for that cell at any given time, with cluster assignment dynamically adjusting to spatio-temporal fluctuations.
@inproceedings{Downey2023,author={Downey, Alexander and Tuna, Evren and Soysal, Alkan},booktitle={arXiv:2311.18824},title={An Adaptive Framework for Generalizing Network Traffic Prediction towards Uncertain Environments},year={2023},month=nov,}
C-24
Adversarial Attacks and Defenses for Wireless Signal Classifiers using CDI-aware GANs
We introduce a Channel Distribution Information (CDI)-aware Generative Adversarial Network (GAN), designed to address the unique challenges of adversarial attacks in wireless communication systems. The generator in this CDI-aware GAN maps random input noise to the feature space, generating perturbations intended to deceive a target modulation classifier. Its discriminators play a dual role: one enforces that the perturbations follow a Gaussian distribution, making them indistinguishable from Gaussian noise, while the other ensures these perturbations account for realistic channel effects and resemble no-channel perturbations.
Our proposed CDI-aware GAN can be used as an attacker and a defender. In attack scenarios, the CDI-aware GAN demonstrates its prowess by generating robust adversarial perturbations that effectively deceive the target classifier, outperforming known methods. Furthermore, CDI-aware GAN as a defender significantly improves the target classifier's resilience against adversarial attacks.
@inproceedings{Sinha2023b,author={Sinha, Sujata and Soysal, Alkan},booktitle={arXiv:2311.18820},title={Adversarial Attacks and Defenses for Wireless Signal Classifiers using CDI-aware GANs},year={2023},month=nov,}
C-23
Channel Aware Adversarial Attacks are Not Robust
Sujata Sinha, and Alkan Soysal
In IEEE Military Communications Conference (MILCOM) Workshops, Nov 2023
Adversarial Machine Learning (AML) has shown significant success when applied to deep learning models across various domains. This paper delves into channel-aware adversarial attacks on DNN-based modulation classification models within wireless environments. Our investigation centers on the robustness of these attacks concerning channel distribution and path-loss parameters. We examine two scenarios: one where the attacker has instantaneous channel knowledge and the other where the attacker is informed by statistical channel data. In both cases, we study channels under conditions of Rayleigh fading alone, Rayleigh fading combined with shadowing, and Rayleigh fading with both shadowing and path loss. Our findings reveal that the success of an AML attack is largely dictated by the distance between the attacker and the legitimate receiver. Without precise distance estimation, adversarial attacks are likely to fail.
@inproceedings{Sinha2023,author={Sinha, Sujata and Soysal, Alkan},booktitle={IEEE Military Communications Conference (MILCOM) Workshops},title={Channel Aware Adversarial Attacks are Not Robust},year={2023},month=nov,}
C-22
Multivariate and Multi-step Traffic Prediction for NextG Networks with SLA Violation Constraints
Evren Tuna, and Alkan Soysal
In International Balkan Conference on Communications and Networking (BalkanCom), Jun 2023
This paper focuses on predicting downlink (DL) traffic volume in mobile networks while minimizing overprovisioning and meeting a given service-level agreement (SLA) violation rate. We present a multivariate, multi-step, and SLA-driven approach that incorporates 20 different radio access network (RAN) features, a custom feature set based on peak traffic hours, and handover-based clustering to leverage the spatiotemporal effects. In addition, we propose a custom loss function that ensures the SLA violation rate constraint is satisfied while minimizing overprovisioning. We also perform multi-step prediction up to 24 steps ahead and evaluate performance under both single-step and multi-step prediction conditions. Our study makes several contributions, including the analysis of RAN features, the custom feature set design, a custom loss function, and a parametric method to satisfy SLA constraints.
@inproceedings{Tuna2023,author={Tuna, Evren and Soysal, Alkan},booktitle={International Balkan Conference on Communications and Networking (BalkanCom)},title={Multivariate and Multi-step Traffic Prediction for NextG Networks with SLA Violation Constraints},year={2023},month=jun,doi={10.1109/BalkanCom58402.2023.10167893},}
2022
C-21
Multivariate Spatio-temporal Cellular Traffic Prediction with Handover Based Clustering
Evren Tuna, and Alkan Soysal
In Conference on Information Sciences and Systems (CISS), Mar 2022
We consider an RNN-based traffic volume prediction, which is a critical problem for network slice management and resource allocation in slicing-enabled next generation cellular networks. We propose to use a novel cost function that takes SLA violations into account. Our approach is multivariate and spatio-temporal in three aspects. First, we consider the effects of several other RAN features in a cell besides the traffic volume. Second, we introduce feature vectors based on peak hours of the day and days of the week. Third, we introduce feature vectors based on incoming handover statistics from the neighboring cells. Our results show about 60\% improvement over MAE-based univariate LSTM models and about 20\% improvement over SLA-based univariate models.
@inproceedings{Tuna2022,author={Tuna, Evren and Soysal, Alkan},booktitle={Conference on Information Sciences and Systems (CISS)},title={Multivariate Spatio-temporal Cellular Traffic Prediction with Handover Based Clustering},year={2022},month=mar,doi={10.1109/CISS53076.2022.9751165},}
2019
C-20
Age of Information Scaling in Large Networks with Hierarchical Cooperation
Baturalp Buyukates, Alkan Soysal, and Sennur. Ulukus
In IEEE Global Communications Conference (Globecom), Dec 2019
@inproceedings{Buyukates19d,author={Buyukates, Baturalp and Soysal, Alkan and Ulukus, Sennur.},title={Age of Information Scaling in Large Networks with Hierarchical Cooperation},year={2019},month=dec,booktitle={IEEE Global Communications Conference (Globecom)},}
C-19
Age of Information in Multicast Networks with Multiple Update Streams
@inproceedings{Buyukates19c,author={Buyukates, Baturalp and Soysal, Alkan and Ulukus, Sennur},title={Age of Information in Multicast Networks with Multiple Update Streams},year={2019},month=nov,booktitle={Asilomar Conference on Signals, Systems and Computers},}
@inproceedings{Soysal18,author={Soysal, Alkan and Ulukus, Sennur},booktitle={Asilomar Conference on Signals, Systems and Computers},title={Age of Information in G/G/1/1 Systems},year={2019},month=nov,}
@inproceedings{Buyukates19a,author={Buyukates, Baturalp and Soysal, Alkan and Ulukus, Sennur},booktitle={IEEE International Conference on Communications (ICC)},title={Age of Information Scaling in Large Networks},year={2019},month=may,}
@inproceedings{Buyukates18,author={Buyukates, Baturalp and Soysal, Alkan and Ulukus, Sennur},booktitle={Asilomar Conference on Signals, Systems and Computers},title={Age of Information in Two-Hop Multicast Networks},year={2018},month=nov,}
2017
C-15
Energy Efficiency Optimization for Non-Overlay Planning of Heterogeneous Cellular Networks
Mahmut Demirtas, and Alkan Soysal
In International conference on Wireless Communications & Mobile Computing (IWCMC), Jun 2017
@inproceedings{Demirtas2017b,author={Demirtas, Mahmut and Soysal, Alkan},booktitle={International conference on Wireless Communications & Mobile Computing (IWCMC)},title={Energy Efficiency Optimization for Non-Overlay Planning of Heterogeneous Cellular Networks},year={2017},month=jun,note={ISSN: 2376-6506},pages={1251--1255},doi={10.1109/IWCMC.2017.7986464},}
2015
C-14
Energy and Spectral Efficient Microcell Deployment in Heterogeneous Cellular Networks
Mahmut Demirtas, and Alkan Soysal
In IEEE Vehicular Technology Conference (VTC), May 2015
@inproceedings{Demirtas2015,author={Demirtas, Mahmut and Soysal, Alkan},booktitle={IEEE Vehicular Technology Conference (VTC)},title={Energy and Spectral Efficient Microcell Deployment in Heterogeneous Cellular Networks},year={2015},month=may,note={ISSN: 1550-2252},pages={1--5},doi={10.1109/VTCSpring.2015.7145803},}
2014
C-13
Optimality of Beamforming in Fading MIMO with Noisy Channel Estimation
Alkan Soysal
In IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), Sep 2014
@inproceedings{Soysal2014,author={Soysal, Alkan},booktitle={IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)},title={Optimality of Beamforming in Fading MIMO with Noisy Channel Estimation},year={2014},month=sep,note={ISSN: 2166-9589},pages={423--427},doi={10.1109/PIMRC.2014.7136202},}
2013
C-12
Short Paper: Performance Analysis of MIMO-based Decode-and-Forward Relaying VANETs
Bengi Aygün, Alkan Soysal, and Alexander M. Wyglinski
In IEEE Vehicular Networking Conference (VNC), Dec 2013
@inproceedings{Aygun2014,author={Aygün, Bengi and Soysal, Alkan and Wyglinski, Alexander M.},booktitle={IEEE Vehicular Networking Conference (VNC)},year={2013},month=dec,note={ISSN: 2157-9865},pages={222--225},doi={10.1109/VNC.2013.6737618},}
C-11
Fading MIMO Relay Channels with Channel Estimation Error
Bengi Aygün, and Alkan Soysal
In IEEE International Conference on Communications (ICC), Jun 2013
@inproceedings{Aygun2013b,author={Aygün, Bengi and Soysal, Alkan},booktitle={IEEE International Conference on Communications (ICC)},title={Fading MIMO Relay Channels with Channel Estimation Error},year={2013},month=jun,note={ISSN: 1938-1883},pages={5522--5526},doi={10.1109/ICC.2013.6655470},}
2012
C-10
Fading MIMO Relay Channels with Covariance Feedback
Bengi Aygun, and Alkan Soysal
In IEEE Wireless Communications and Networking Conference (WCNC), Apr 2012
@inproceedings{Aygun2012,author={Aygun, Bengi and Soysal, Alkan},booktitle={IEEE Wireless Communications and Networking Conference (WCNC)},title={Fading MIMO Relay Channels with Covariance Feedback},year={2012},month=apr,note={ISSN: 1558-2612},pages={70--74},doi={10.1109/WCNC.2012.6214463},}
2011
C-9
A Method for Optimizing Matrix Valued Functions and its Applications to Capacity of MIMO Systems
@inproceedings{Soysal2011,author={Soysal, Alkan},booktitle={Telecommunications Forum (TELFOR)},title={A Method for Optimizing Matrix Valued Functions and its Applications to Capacity of MIMO Systems},year={2011},month=nov,pages={285--288},doi={10.1109/TELFOR.2011.6143546},}
C-8
Achieving the Lower Bound of Fading MIMO Relay Channels with Covariance Feedback at the Transmitters
Bengi Aygün, and Alkan Soysal
In International conference on Wireless Communications & Mobile Computing (IWCMC), Jul 2011
@inproceedings{Aygun2011,author={Aygün, Bengi and Soysal, Alkan},booktitle={International conference on Wireless Communications & Mobile Computing (IWCMC)},title={Achieving the Lower Bound of Fading MIMO Relay Channels with Covariance Feedback at the Transmitters},year={2011},month=jul,note={ISSN: 2376-6506},pages={900--905},doi={10.1109/IWCMC.2011.5982666},}
2010
C-7
Tightness of Capacity Bounds in Correlated MIMO Systems with Channel Estimation Error
Alkan Soysal
In IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), Sep 2010
@inproceedings{Soysal2010c,author={Soysal, Alkan},booktitle={IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)},title={Tightness of Capacity Bounds in Correlated MIMO Systems with Channel Estimation Error},year={2010},month=sep,note={ISSN: 2166-9589},pages={667--671},doi={10.1109/PIMRC.2010.5671679},}
2008
C-6
MIMO Multiple Access Channels with Noisy Channel Estimation and Partial CSI Feedback
@inproceedings{Soysal2008b,author={Soysal, Alkan and Ulukus, Sennur and Clancy, Charles},booktitle={IEEE International Conference on Communications (ICC)},title={Channel Estimation and Adaptive M-QAM in Cognitive Radio Links},year={2008},month=may,note={ISSN: 1938-1883},pages={4043--4047},doi={10.1109/ICC.2008.759},}
C-4
Optimizing the Rate of a Correlated MIMO Link Jointly over Channel Estimation and Data Transmission Parameters
@inproceedings{Soysal2008c,author={Soysal, Alkan and Ulukus, Sennur},booktitle={Conference on Information Sciences and Systems (CISS)},title={Optimizing the Rate of a Correlated MIMO Link Jointly over Channel Estimation and Data Transmission Parameters},year={2008},month=mar,pages={74--79},doi={10.1109/CISS.2008.4558498},}
2006
C-3
Optimum Power Allocation in Fading MIMO Multiple Access Channels with Partial CSI at the Transmitters
@inproceedings{Soysal2006,author={Soysal, Alkan and Ulukus, Sennur},booktitle={Asilomar Conference on Signals, Systems and Computers},title={Optimum Power Allocation in Fading MIMO Multiple Access Channels with Partial CSI at the Transmitters},year={2006},month=oct,note={ISSN: 1058-6393},pages={1526--1530},doi={10.1109/ACSSC.2006.355013},}
2005
C-2
Asymptotic Optimality of Beamforming in Multi-User MIMO-MAC with No or Partial CSI at the Transmitters
@inproceedings{Soysal2005,author={Soysal, Alkan and Ulukus, Sennur},booktitle={IEEE Vehicular Technology Conference (VTC)},title={Asymptotic Optimality of Beamforming in Multi-User MIMO-MAC with No or Partial CSI at the Transmitters},year={2005},month=may,note={ISSN: 1550-2252},pages={1619--1623 Vol. 3},volume={3},doi={10.1109/VETECS.2005.1543594},}
C-1
Transmit Directions and Optimality of Beamforming in MIMO-MAC with Partial CSI at the Transmitters
@inproceedings{Soysal2005b,author={Soysal, Alkan and Ulukus, Sennur},booktitle={Conference on Information Sciences and Systems (CISS)},title={Transmit Directions and Optimality of Beamforming in MIMO-MAC with Partial CSI at the Transmitters},year={2005},month=mar,}