Papers by Andrea Panebianco
2025 IEEE International Conference on Communications Workshops (ICC Workshops), Sep 22, 2025
Performance optimization of UnderWater (UW) acoustic communications is particularly challenging d... more Performance optimization of UnderWater (UW) acoustic communications is particularly challenging due to the short coherence time, long propagation delay, and extremely scenario-specific features of the UW channel. These issues clearly call for the implementation of adaptive communication techniques. One effective way to achieve this goal is to rely on Machine Learning (ML), which can easily identify the optimal UW communication parameters to optimize various performance metrics, such as network throughput and energy consumption. However, popular approaches, such as stateful Reinforcement Learning (RL) and Deep Reinforcement Learning (DRL), usually require considerable storage, computing, and energy resources, and may not fit in resource-constrained UW devices. For this reason, in this paper we propose POSEIDON, a framework for transmission power and modulation scheme adaptation based on Multi-Armed Bandit (MAB), a lightweight, stateless alternative to stateful RL and DRL. We evaluate POSEIDON on DESERT, a powerful framework for realistic simulations of UW networks, and compare its performance against two DRL baselines. The results show that, in spite of the lightweight nature of POSEIDON, our framework is able to outperform the DRL baselines by achieving an improvement of up to 72.49% in the network throughput, and up to 77.16% in energy consumption. Moreover, POSEIDON generally exhibits a significantly more stable performance, with fewer oscillations despite the high variability of the UW channel conditions.
2025 IEEE Wireless Communications and Networking Conference (WCNC), May 9, 2025
UnderWater (UW) communication channels pose unique challenges due to their limited bandwidth, sig... more UnderWater (UW) communication channels pose unique challenges due to their limited bandwidth, significant temporal variability, and long transmission delays. Addressing these challenges calls for the implementation of robust protocols capable of dynamically adjusting transmission parameters in response to channel conditions. In such a perspective, the development of intelligent algorithms capable of quickly adapting to current channel conditions based on measurements is of crucial importance. Indeed, this allows to adapt the signal transmission characteristics to the channel conditions, and to accordingly ensure optimal performance. In this perspective, this paper introduces a Multi-Player Multi-Armed Bandit (MP-MAB) framework for smart modulation adaptation in UnderWater Acoustic (UWA) Networks. Our solution is specifically tailored to run on resource-constrained UW nodes, thanks to the simplicity and low-complexity of MAB. Our framework can leverage realtime throughput statistics to dynamically select the optimal modulation technique for multi-hop signal transmission in UW scenarios. Notably, this happens in a fully-distributed way on a per-node basis, as each UW node runs a local MAB agent to autonomously select the best modulation to use according to its own channel conditions. Using the DESERT UW simulator, we evaluate the performance of our proposed framework and compare it with alternative state-of-the-art learning approaches. Results demonstrate the higher efficiency and responsiveness of our algorithm compared to the alternatives, despite its simplicity and fully-decentralized nature.
GLOBECOM 2024 - 2024 IEEE Global Communications Conference, Mar 11, 2025
Long Range (LoRa) technology, with its low-power and long-range communication capabilities, has e... more Long Range (LoRa) technology, with its low-power and long-range communication capabilities, has emerged as a popular choice for Internet of Things (IoT) applications. In spite of its long communication range, single-hop LoRa networks may be extremely inefficient in high path-loss scenarios, such as urban, indoor and underground environments. One solution to this issue is to instead resort to multi-hop LoRa networks. However, the routing of the generated packets towards the LoRa network gateway poses several challenges, such as balancing the network energy consumption, minimizing the number of hops, and selecting high-quality paths towards the gateway. One way to solve this issue is to implement distributed smart algorithms that can efficiently address all this aspects in a reliable and fullyscalable way. In this regard, this paper introduces MAGELLAN, a novel routing algorithm for multi-hop LoRa networks based on Multi-Armed Bandit (MAB) learning. MAGELLAN aims to achieve efficient packet delivery while minimizing the number of hops and fairly distributing the energy consumption across the network. We have conducted an extensive numerical evaluation by using the LoRaEnergySim simulator, and compared MAGELLAN against various routing approaches, including LMHP, a state-ofthe-art routing algorithm. The results show that MAGELLAN achieves a superior performance in terms of energy-fairness and Packet Delivery Ratio (PDR), therefore improving the network lifetime and performance. More in detail, MAGELLAN achieves a reduction of up to 10% in the energy consumption as compared to a the random approach, and of to 14% in the PDR as compared to LMHP approach.
IEEE Open Journal of the Communications Society, 2025
UnderWater (UW) Acoustic networks face unique challenges due to limited bandwidth, high latency, ... more UnderWater (UW) Acoustic networks face unique challenges due to limited bandwidth, high latency, and dynamic channel conditions, necessitating adaptive communication protocols to optimize performance under strict energy constraints. Modulation schemes play a crucial role in determining the efficiency and reliability of these networks; dynamically adjusting modulation depending on channel conditions can significantly enhance network performance. While Machine Learning algorithms offer valuable solutions for real-time adaptation, many existing methods are based on deep learning, which often demands computational resources beyond the capabilities of typical UW devices. In contrast, Multi-Armed Bandit (MAB) algorithms offer a simpler yet effective solution, well-suited for environments with limited computational resources. In this paper, we present AMUSE, a scalable and efficient framework designed to leverage the MAB approach for dynamic modulation selection, while enabling the optimization of various key performance metrics. Specifically, to illustrate the high level of flexibility of AMUSE in addressing multi-objective optimization, we here focus on the trade-off of Packet Error Rate (PER) and energy consumption across changing conditions, so as to make both reliability and energy efficiency the basis of the modulation adaptation decision-making process. Through extensive simulation in the DESERT simulator, we evaluate AMUSE performance against other state-of-the-art algorithms based on Deep Reinforcement Learning (DRL). Despite its simple design, AMUSE proves to be more efficient and responsive than the baselines, making it a powerful solution for improving UW communication performance. The results show that, in spite of the lightweight nature of AMUSE, our framework is able to outperform the DRL baselines by achieving an improvement of up to 23.64% in the network PER, and up to 80.65% in energy saving.
Computer Networks, 2024
Underwater communications suffer from numerous challenges typically associated with relevant sign... more Underwater communications suffer from numerous challenges typically associated with relevant signal attenuation, long propagation delay, limited available bandwidth, and high error rates that severely affect underwater transmission performance. Therefore, it is crucial to apply adaptive or predictive techniques to ensure the best possible performance and guarantee reliability in underwater communication, especially in rapidly changing environments. Using adaptive (i.e., reactive) or predictive (i.e., proactive) methods, it is possible to avoid data retransmission, improve the lifetime of underwater nodes, reduce maintenance frequency and the necessary equipment replacement and recharge, and consequently optimize performance in general. In this regard, many works in the literature propose various adaptive or predictive techniques for UnderWater Acoustic (UWA) networks, which we critically classify and discuss in this qualitative survey.
ICC 2024 - IEEE International Conference on Communications, Aug 20, 2024
Underwater (UW) communication channels experience limited bandwidth, high time variability and mu... more Underwater (UW) communication channels experience limited bandwidth, high time variability and much longer delays as compared to traditional terrestrial channels. This makes communication in UW scenarios particularly challenging. One way to cope with this issue is to employ reliable smart protocols that can dynamically adjust transmission parameters based on channel conditions. The effectiveness of these solutions also relies on the design of intelligent algorithms that can forecast channel conditions based on measurements and adapt the transmission characteristics of signals according to the current state of the UW channel, in order to always guarantee the best performance. In this work we propose AMUSE, the first Multi-Armed Bandit-based algorithm for smart modulation adaptation in Underwater Acoustic Networks. Note that AMUSE is specifically designed to suit resource-constrained UW nodes thanks to its simplicity and low-complexity. In particular, AMUSE relies on the current Packet Delivery Ratio (PDR) statistics to select in real time the best modulation technique to use for multihop signal transmission in the aforementioned UW scenarios. By employing the DESERT simulator we compare the performance achieved using AMUSE to those obtained using alternative state-of-the-art learning approaches. The results show that, in spite of its simplicity, our algorithm is more efficient and responsive than the other considered approaches.
2024 IEEE International Conference on Communications Workshops (ICC Workshops), Aug 12, 2024
UnderWater (UW) communications are challenging task due to their environment, which can cause hig... more UnderWater (UW) communications are challenging task due to their environment, which can cause high data corruption and loss. UW communication channels also experience limited bandwidth, high time variability and much longer delays as compared to traditional terrestrial channels. This leads to frequent retransmissions, which consume valuable energy for the network nodes and shorten their lifetime. One way to cope with these issues is to employ reliable smart protocols that can improve packet routing in a UW network to optimize transmission efficiency, minimize latency, save energy, and ensure network robustness. In this paper we propose BOUNCE, a novel routing algorithm for UnderWater Acoustic (UWA) networks based on Multi-Armed Bandit. The main goal of BOUNCE is to efficiently route packets to ensure the highest transmission quality, the least packet latency, all while keeping an eye on a fair-balancing of the network energy consumption. We run an extensive simulation campaign, and tested BOUNCE against two baselines, namely the state-of-the-art RLOR algorithm, and a random approach. The results demonstrated how BOUNCE is able to outperform the other baselines in terms of energy consumption and fairness, packet latency, and Packet Delivery Rate. More in detail, BOUNCE achieves a reduction of up to 9.5% in the energy consumption and of up to 41 % in the network latency, as well as an improvement of up to 27.5 % in the Packet Delivery Ratio.
Computer Networks, 2024
Unlike traditional terrestrial scenarios, communication channels in underwater environments face ... more Unlike traditional terrestrial scenarios, communication channels in underwater environments face severe limitations in bandwidth and experience long propagation delay. In order to address these issues, reliable techniques capable to dynamically adapt transmission parameters to time-varying channel conditions are necessary. Actually, their effectiveness primarily relies on an accurate characterization of the underwater communication channels, which is often obtained through predictive models. In this paper, we compare the performance of different types of SNR-based predictive models (i.e., Markov models, Hidden Markov models) in terms of balance between accuracy and complexity. We also provide a Kalman filter-based prediction of SNR values and compare this prediction with the performance achieved with the Markov models above mentioned. The models we have considered to carry out the comparison analysis have been developed based on real shallow water traces taken over the Tyrrhenian Sea, Italy.
Frontiers in Communications and Networks, 2023
In this paper, we present a machine-learning technique to counteract jamming attacks in underwate... more In this paper, we present a machine-learning technique to counteract jamming attacks in underwater networks. Indeed, this is relevant in security applications where sensor devices are located in critical regions, for example, in the case of national border surveillance or for identifying any unauthorized intrusion. To this aim, a multi-hop routing protocol that relies on the exploitation of a Q-learning methodology is presented with a focus on increasing reliability in data communication and network lifetime. Performance results assess the effectiveness of the proposed solution as compared to other efficient state-of-the-art approaches.
2023 IEEE International Conference on Communications Workshops (ICC Workshops), Oct 23, 2023
As compared to traditional terrestrial links, underwater channels suffer for the limited bandwidt... more As compared to traditional terrestrial links, underwater channels suffer for the limited bandwidth and long propagation delays. To cope with these issues, transmissions should be reliable and the relevant parameters dynamically tunable based on the channel conditions. To this aim, availability of a realistic channel model for the specific physical settings considered is a key element. Accordingly, in this paper we derive an underwater acoustic channel model based on field test measurements carried out in the Tyrrhenian sea. Specifically two models are obtained, one based on a Markov channel modeling with multiple possible states and another based on Kalman filter design. We compare their accuracy in predicting channel status and show that, based on the specific channel setting and application scenario, different channel models can be chosen to identify a trade-off between good prediction accuracy and affordable complexity.
Computer Communications, 2022
In the last years, underwater research has been gaining momentum due to the plethora of emerging ... more In the last years, underwater research has been gaining momentum due to the plethora of emerging application scenarios that are appearing, typically associated to marine wildlife protection, national borders monitoring or underwater historical sites preservation. However, research in this area is still at infancy, and implementation of the Internet of Underwater Things vision is not yet at its adulthood. One of the most critical issues is indeed associated to the need for developing a network of devices which can connect and remotely deliver data to a front-end elaboration center. To this purpose, the need for increasing network lifetime and improving the quality of the monitored parameters, while guaranteeing real time control of the network, calls for the design of tools for remotisation, actuation and control. In this paper we report about the design and development of an integrated acoustic/LoRa system for transmission of multimedia sensor data over the Internet of Underwater Things. We detail the blocks composing the system and show results obtained through field tests that assess the possibility to transmit multimedia data, as well as control data, for real time reconfiguration of the system parameters through properly designed Android or Web applications.
Uploads
Papers by Andrea Panebianco