Ramin Safavinejad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ramin Safavinejad has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Lingjia Liu
Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA
9 shared publications - Shashank Jere
Bradley Department of Electrical and Computer Engineering, Wireless@Virginia Tech, Virginia Tech, Blacksburg, VA, USA
4 shared publications - Nima Mohammadi
Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA
3 shared publications - Hao Chen
Samsung Research America, Plano, TX, USA
2 shared publications - Hao-Hsuan Chang
Standards and Mobility Innovation Laboratory, Samsung Research America, Plano, TX, USA
2 shared publications - Jianzhong Zhang
Harbin Engineering University
2 shared publications
Latest Publications
- 10 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications
- Vol. PP (15361284) , 1-7
Mobile Distributed MIMO (MD-MIMO) for NextG: Mobility Meets Cooperation in Distributed Arrays
Distributed multiple-input multiple-output (D-MIMO) is a promising technology to realize the promise of massive MIMO gains by fiber-connecting the distributed antenna arrays, thereby overcoming the form factor limitations of co-located MIMO. In this paper, we introduce the concept of a mobile D-MIMO (MD-MIMO) network, a further extension of the D-MIMO technology where distributed antenna arrays are connected to the base station with a wireless link allowing all radio network nodes to be mobile. This approach significantly improves deployment flexibility and reduces operating costs, enabling the network to adapt to the highly dynamic nature of next-generation (NextG) networks. We discuss use cases, system design, network architecture, and the key enabling technologies for MD-MIMO. Furthermore, we investigate a case study of MD-MIMO for vehicular networks, presenting detailed performance evaluations for both downlink and uplink. The results show that an MD-MIMO network can provide substantial improvements in network throughput and reliability.
- 10 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications
- Vol. PP (15361284) , 1-7
Mobile Distributed MIMO (MD-MIMO) for NextG: Mobility Meets Cooperation in Distributed Arrays
Distributed multiple-input multiple-output (D-MIMO) is a promising technology to realize the promise of massive MIMO gains by fiber-connecting the distributed antenna arrays, thereby overcoming the form factor limitations of co-located MIMO. In this paper, we introduce the concept of a mobile D-MIMO (MD-MIMO) network, a further extension of the D-MIMO technology where distributed antenna arrays are connected to the base station with a wireless link allowing all radio network nodes to be mobile. This approach significantly improves deployment flexibility and reduces operating costs, enabling the network to adapt to the highly dynamic nature of next-generation (NextG) networks. We discuss use cases, system design, network architecture, and the key enabling technologies for MD-MIMO. Furthermore, we investigate a case study of MD-MIMO for vehicular networks, presenting detailed performance evaluations for both downlink and uplink. The results show that an MD-MIMO network can provide substantial improvements in network throughput and reliability.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 5880-5884
Learning to Track: RNN-Based Online Real-Time Beam Tracking in Massive MIMO Systems
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 15, 5880-5884
Learning to Track: RNN-Based Online Real-Time Beam Tracking in Massive MIMO Systems
- 5 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 863-867
Configuring RNN's Recurrent Weights Using Domain Knowledge for LTI Approximation
Recurrent Neural Networks (RNNs) are powerful models for sequential tasks, but their training can be computationally intensive. On the other hand, Echo State Networks (ESNs), a specific RNN architecture, simplify this by configuring a fixed, random reservoir of recurrent weights. Instead of setting random weights as in the ESN case, in this work, we investigate the recurrent weight configuration problem of the fully-fledged RNN for the task of Linear Time-Invariant (LTI) system approximation. Our investigation focuses on a specific RNN architecture with a network of recurrent neurons limited to self-loops and linear activation. We demonstrate that as the recurrent weights of this RNN are trained on large datasets, their distribution converges to a near-identical match of an optimal distribution that can be analytically derived using the available domain knowledge of the LTI system. This insight establishes that domain-informed weight configuration is a highly efficient alternative to data-driven training. Building upon this, we propose a novel deterministic algorithm to set the recurrent weights, which significantly improves approximation accuracy. Numerical results show our domain-informed RNN weight configuration achieves up to a four-order-of-magnitude performance gain over conventional ESNs.
- 5 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 863-867
Configuring RNN's Recurrent Weights Using Domain Knowledge for LTI Approximation
Recurrent Neural Networks (RNNs) are powerful models for sequential tasks, but their training can be computationally intensive. On the other hand, Echo State Networks (ESNs), a specific RNN architecture, simplify this by configuring a fixed, random reservoir of recurrent weights. Instead of setting random weights as in the ESN case, in this work, we investigate the recurrent weight configuration problem of the fully-fledged RNN for the task of Linear Time-Invariant (LTI) system approximation. Our investigation focuses on a specific RNN architecture with a network of recurrent neurons limited to self-loops and linear activation. We demonstrate that as the recurrent weights of this RNN are trained on large datasets, their distribution converges to a near-identical match of an optimal distribution that can be analytically derived using the available domain knowledge of the LTI system. This insight establishes that domain-informed weight configuration is a highly efficient alternative to data-driven training. Building upon this, we propose a novel deterministic algorithm to set the recurrent weights, which significantly improves approximation accuracy. Numerical results show our domain-informed RNN weight configuration achieves up to a four-order-of-magnitude performance gain over conventional ESNs.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (6) , 4517-4531
Dyna-ESN: Efficient Deep Reinforcement Learning for Partially Observable Dynamic Spectrum Access
This paper focuses on advancing reinforcement learning for challenging environments characterized by partial observability and non-stationarity, such as dynamic spectrum access (DSA). In the literature, the Deep Recurrent Q-Network was introduced to capitalize on the inherent temporal correlations present in DSA. Nevertheless, its practicality is still questionable due to sample inefficiency and slow convergence. We introduce Dyna-ESN, leveraging both model-based and model-free methods by employing Reservoir Computing for generative modeling. Specifically, we utilize Echo State Networks (ESNs) to synthesize samples for enhancing the sample efficiency of a model-free Deep Echo State Q-network, enabling effective operation of agent given limited genuine relevant samples obtained through interaction with environment. To mitigate potential adverse effects of synthetic samples, an evaluation algorithm guides the sample selection process, ensuring reliability. A sample augmentation technique is also introduced to allow agents to collect adequate samples despite controlling the sensing rate and duration of secondary transmissions. Our analysis explores trade-offs between data evaluation and sample efficiency, as well as the bias-variance trade-off of the model, identifying optimal design parameters. Evaluating the performance of Dyna-ESN in DSA scenarios demonstrates its performance benefits over existing methods, paving the way for more efficient and effective techniques in complex dynamic environments.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 24 (6) , 4517-4531
Dyna-ESN: Efficient Deep Reinforcement Learning for Partially Observable Dynamic Spectrum Access
This paper focuses on advancing reinforcement learning for challenging environments characterized by partial observability and non-stationarity, such as dynamic spectrum access (DSA). In the literature, the Deep Recurrent Q-Network was introduced to capitalize on the inherent temporal correlations present in DSA. Nevertheless, its practicality is still questionable due to sample inefficiency and slow convergence. We introduce Dyna-ESN, leveraging both model-based and model-free methods by employing Reservoir Computing for generative modeling. Specifically, we utilize Echo State Networks (ESNs) to synthesize samples for enhancing the sample efficiency of a model-free Deep Echo State Q-network, enabling effective operation of agent given limited genuine relevant samples obtained through interaction with environment. To mitigate potential adverse effects of synthetic samples, an evaluation algorithm guides the sample selection process, ensuring reliability. A sample augmentation technique is also introduced to allow agents to collect adequate samples despite controlling the sensing rate and duration of secondary transmissions. Our analysis explores trade-offs between data evaluation and sample efficiency, as well as the bias-variance trade-off of the model, identifying optimal design parameters. Evaluating the performance of Dyna-ESN in DSA scenarios demonstrates its performance benefits over existing methods, paving the way for more efficient and effective techniques in complex dynamic environments.
- 17 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (2) , 890-906
O-RAN-Enabled Intelligent Network Slicing to Meet Service-Level Agreement (SLA)
Network slicing plays a critical role in enabling multiple virtualized and independent network services to be created on top of a common physical network infrastructure. In this paper, we introduce a deep reinforcement learning (DRL)-based radio resource management (RRM) solution for radio access network (RAN) slicing under service-level agreement (SLA) guarantees. The objective of this solution is to minimize the SLA violation. Our method is designed with a two-level scheduling structure that works seamlessly under Open Radio Access Network (O-RAN) architecture. Specifically, at an upper level, a DRL-based inter-slice scheduler is working on a coarse time granularity to allocate resources to network slices. And at a lower level, an existing intra-slice scheduler such as proportional fair (PF) is working on a fine time granularity to allocate slice dedicated resources to slice users. This setting makes our solution O-RAN compliant and ready to be deployed as an ‘xApp’ on the RAN Intelligent Controller (RIC). For performance evaluation and proof of concept purposes, we develop two platforms, one industry-level simulator and one O-RAN compliant testbed; evaluation on both platforms demonstrates our solution’s superior performance over conventional methods.
- 17 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (2) , 890-906
O-RAN-Enabled Intelligent Network Slicing to Meet Service-Level Agreement (SLA)
Network slicing plays a critical role in enabling multiple virtualized and independent network services to be created on top of a common physical network infrastructure. In this paper, we introduce a deep reinforcement learning (DRL)-based radio resource management (RRM) solution for radio access network (RAN) slicing under service-level agreement (SLA) guarantees. The objective of this solution is to minimize the SLA violation. Our method is designed with a two-level scheduling structure that works seamlessly under Open Radio Access Network (O-RAN) architecture. Specifically, at an upper level, a DRL-based inter-slice scheduler is working on a coarse time granularity to allocate resources to network slices. And at a lower level, an existing intra-slice scheduler such as proportional fair (PF) is working on a fine time granularity to allocate slice dedicated resources to slice users. This setting makes our solution O-RAN compliant and ready to be deployed as an ‘xApp’ on the RAN Intelligent Controller (RIC). For performance evaluation and proof of concept purposes, we develop two platforms, one industry-level simulator and one O-RAN compliant testbed; evaluation on both platforms demonstrates our solution’s superior performance over conventional methods.
- 5 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (12) , 18888-18902
Deep Reinforcement Learning for Dynamic Spectrum Access: Convergence Analysis and System Design
In dynamic spectrum access (DSA) networks, secondary users (SUs) need to opportunistically access primary users’ (PUs) radio spectrum without causing significant interference. Since the SU-PU interaction is limited, deep reinforcement learning has been introduced to help SUs conduct spectrum access. Specifically, deep recurrent Q network (DRQN) has been utilized in DSA networks for SUs to aggregate information from recent experiences to make spectrum access decisions. DRQN is notorious for its sample efficiency since it needs a rather large number of training samples to tune its parameters which is a computationally demanding task. Deep echo state network (DEQN) has been introduced for DSA networks to address the sample efficiency issue of DRQN. In this work, we compare the convergence of DRQN and DEQN by comparing the upper bounds we obtain on their covering number, a notion of richness. Furthermore, we introduce a method to determine the right hyper-parameters for DEQN, providing system design guidance for DEQN-based DSA networks. Extensive performance evaluation confirms that DEQN-based DSA strategy is the superior choice with regard to computational power while outperforming DRQN-based ones.
- 5 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Wireless Communications
- Vol. 23 (12) , 18888-18902
Deep Reinforcement Learning for Dynamic Spectrum Access: Convergence Analysis and System Design
In dynamic spectrum access (DSA) networks, secondary users (SUs) need to opportunistically access primary users’ (PUs) radio spectrum without causing significant interference. Since the SU-PU interaction is limited, deep reinforcement learning has been introduced to help SUs conduct spectrum access. Specifically, deep recurrent Q network (DRQN) has been utilized in DSA networks for SUs to aggregate information from recent experiences to make spectrum access decisions. DRQN is notorious for its sample efficiency since it needs a rather large number of training samples to tune its parameters which is a computationally demanding task. Deep echo state network (DEQN) has been introduced for DSA networks to address the sample efficiency issue of DRQN. In this work, we compare the convergence of DRQN and DEQN by comparing the upper bounds we obtain on their covering number, a notion of richness. Furthermore, we introduce a method to determine the right hyper-parameters for DEQN, providing system design guidance for DEQN-based DSA networks. Extensive performance evaluation confirms that DEQN-based DSA strategy is the superior choice with regard to computational power while outperforming DRQN-based ones.
- 21 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 71 (9) , 5169-5181
Theoretical Foundation and Design Guideline for Reservoir Computing-Based MIMO-OFDM Symbol Detection
In this paper, we derive a theoretical upper bound on the generalization error of reservoir computing (RC), a special category of recurrent neural networks (RNNs). The specific RC implementation considered in this paper is the echo state network (ESN), and an upper bound on its generalization error is derived via the empirical Rademacher complexity (ERC) approach. While recent work in deriving risk bounds for RC frameworks makes use of a non-standard ERC measure and a direct application of its definition, our work uses the standard ERC measure and tools allowing fair comparison with conventional RNNs. The derived result shows that the generalization error bound obtained for ESNs is tighter than the existing bound for vanilla RNNs, suggesting easier generalization for ESNs. With the ESN applied to symbol detection in MIMO-OFDM (Multiple Input Multiple Output-Orthogonal Frequency Division Multiplexing) systems, we show how the derived generalization error bound can guide underlying system design. Specifically, the derived bound together with the empirically characterized training loss is utilized to identify the optimum reservoir size in neurons for the ESN-based symbol detector. Finally, we corroborate our theoretical findings with results from simulations that employ 3GPP standards-compliant wireless channels, signifying the practical relevance of our work.
- 21 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 71 (9) , 5169-5181
Theoretical Foundation and Design Guideline for Reservoir Computing-Based MIMO-OFDM Symbol Detection
In this paper, we derive a theoretical upper bound on the generalization error of reservoir computing (RC), a special category of recurrent neural networks (RNNs). The specific RC implementation considered in this paper is the echo state network (ESN), and an upper bound on its generalization error is derived via the empirical Rademacher complexity (ERC) approach. While recent work in deriving risk bounds for RC frameworks makes use of a non-standard ERC measure and a direct application of its definition, our work uses the standard ERC measure and tools allowing fair comparison with conventional RNNs. The derived result shows that the generalization error bound obtained for ESNs is tighter than the existing bound for vanilla RNNs, suggesting easier generalization for ESNs. With the ESN applied to symbol detection in MIMO-OFDM (Multiple Input Multiple Output-Orthogonal Frequency Division Multiplexing) systems, we show how the derived generalization error bound can guide underlying system design. Specifically, the derived bound together with the empirically characterized training loss is utilized to identify the optimum reservoir size in neurons for the ESN-based symbol detector. Finally, we corroborate our theoretical findings with results from simulations that employ 3GPP standards-compliant wireless channels, signifying the practical relevance of our work.
- 6 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 12 (5) , 774-778
Channel Equalization Through Reservoir Computing: A Theoretical Perspective
Deep learning practice, including in wireless communications, often relies on trial and error to optimize neural network (NN) structures and their corresponding hyperparameters. We show that Reservoir Computing, especially the Echo State Network (ESN), is an ideal learning-based equalizer for a general fading channel and for an ESN equalizing a channel with known statistics, theoretically derive its optimum reservoir weights which are randomly initialized in state-of-the-art and lack interpretability. The theoretical results are validated with simulations. In contrast to existing literature, this work analytically adapts the NN structure to the problem being addressed, guaranteeing optimum equalization under known channel statistics.
- 6 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 12 (5) , 774-778
Channel Equalization Through Reservoir Computing: A Theoretical Perspective
Deep learning practice, including in wireless communications, often relies on trial and error to optimize neural network (NN) structures and their corresponding hyperparameters. We show that Reservoir Computing, especially the Echo State Network (ESN), is an ideal learning-based equalizer for a general fading channel and for an ESN equalizing a channel with known statistics, theoretically derive its optimum reservoir weights which are randomly initialized in state-of-the-art and lack interpretability. The theoretical results are validated with simulations. In contrast to existing literature, this work analytically adapts the NN structure to the problem being addressed, guaranteeing optimum equalization under known channel statistics.