Nicola Piovesan, PhD


Nicola Piovesan

Nicola Piovesan is a Senior Researcher at Huawei Technologies, in Paris, France.

He earned his PhD degree in Network Engineering at the Universitat Politècnica de Catalunya (UPC), Barcelona, Spain, in 2020, and he received the BSc degree in Information Engineering and the MSc in Telecommunication Engineering from the University of Padova, Italy, in 2013 and 2016, respectively.

From 2016 to 2019, he was an Assistant Researcher at the Mobile Networks Department of the Centre Tecnològic de Telecomunicacions de Catalunya (CTTC). In 2016, he has been awarded with a European Commission’s Marie Skłodowska-Curie fellowship to work as early-stage researcher in the EU H2020 MSCA SCAVENGE (Sustainable Cellular Networks Harvesting Ambient Energy) project.

In 2019, he was at Nokia Bell Labs as a visiting researcher in the Small Cells Research Department.

His current research interests include energy efficiency in mobile networks, optimization, and machine learning in wireless communication systems.

Recent Publications

Telecom Language Models: Must They Be Large?
Nicola Piovesan, Antonio De Domenico, Fadhel Ayed

The increasing interest in Large Language Models (LLMs) within the telecommunications sector underscores their potential to revolutionize operational efficiency. However, the deployment of these sophisticated models is often hampered by their substantial size and computational demands, raising concerns about their viability in resource-constrained environments. Addressing this challenge, recent advancements have seen the emergence of small language models that surprisingly exhibit performance comparable to their larger counterparts in many tasks, such as coding and common-sense reasoning. Phi-2, a compact yet powerful model, exemplifies this new wave of efficient small language models. This paper conducts a comprehensive evaluation of Phi-2's intrinsic understanding of the telecommunications domain. Recognizing the scale-related limitations, we enhance Phi-2's capabilities through a Retrieval-Augmented Generation approach, meticulously integrating an extensive knowledge base specifically curated with telecom standard specifications. The enhanced Phi-2 model demonstrates a profound improvement in accuracy, answering questions about telecom standards with a precision that closely rivals the more resource-intensive GPT-3.5. The paper further explores the refined capabilities of Phi-2 in addressing problem-solving scenarios within the telecom sector, highlighting its potentials and limitations.

Linguistic Intelligence in Large Language Models for Telecommunications
Tasnim Ahmed, Nicola Piovesan, Antonio De Domenico, Salimur Choudhury

Large Language Models (LLMs) have emerged as a significant advancement in the field of Natural Language Processing (NLP), demonstrating remarkable capabilities in language generation and other language-centric tasks. Despite their evaluation across a multitude of analytical and reasoning tasks in various scientific domains, a comprehensive exploration of their knowledge and understanding within the realm of natural language tasks in the telecommunications domain is still needed. This study, therefore, seeks to evaluate the knowledge and understanding capabilities of LLMs within this domain. To achieve this, we conduct an exhaustive zero-shot evaluation of four prominent LLMs—Llama-2, Falcon, Mistral, and Zephyr. These models require fewer resources than ChatGPT, making them suitable for resource-constrained environments. Their performance is compared with state-of-the-art, fine-tuned models. To the best of our knowledge, this is the first work to extensively evaluate and compare the understanding of LLMs across multiple language-centric tasks in this domain. Our evaluation reveals that zero-shot LLMs can achieve performance levels comparable to the current state-of-the-art fine-tuned models. This indicates that pretraining on extensive text corpora equips LLMs with a degree of specialization, even within the telecommunications domain. We also observe that no single LLM consistently outperforms others, and the performance of different LLMs can fluctuate. Although their performance lags behind fine-tuned models, our findings underscore the potential of LLMs as a valuable resource for understanding various aspects of this field that lack large annotated data.


Selected Talks

Card image cap
Data-driven modelling and optimization of green future mobile networks
EuCNC and 6G Summit

June 6, 2023

Card image cap
AI/ML for 5G-Energy Consumption Modelling
ITU AI for Good

July 11, 2023

Card image cap
A Journey Towards Energy Efficiency
Universitat Politècnica de València

September 14, 2023


Recent Patents

Method for shutting down a cell of one or more cells of a base station for wireless communication
N. Piovesan, A. De Domenico, N. Zhao, L. Madier
Filed patent

Devices and methods for real-time ML framework supporting network optimization
A. De Domenico, F. Ayed, N. Piovesan, N. Zhao, M. Spini, A. Maatouk
Filed patent



Awards & Honors
2021 · Huawei · GTS President Award - Technology Innovation and Breakthrough Award
2020 · Huawei · Future Star Award
2016 · European Union · Marie Skłodowska-Curie fellowship
2015 · WorldSensing · Winner of the Smart City Big Data Contest

Using AI to make 5G more sustainable

Services to the research community

Reviewer of IEEE Transactions on Wireless Communications, IEEE Communications Magazine, IEEE Transactions on Green Communications and Networking, IEEE Internet of Things Journal, Wiley Transactions on Emerging Telecommunications Technologies, Elsevier Computer Networks, Elsevier Computer Communications, among others.

Technical Program Commitee Member of IEEE International Conference on Communications conference (ICC 2023, ICC 2024), IEEE Wireless Communications and Networking Conference (WCNC 2022), European Conference on Networks and Communications (EuCNC 2019, EuCNC 2020) and IEEE Vehicular Technology Conference (VTC-Fall 2019).

Co-chair of the Workshop on The Impact of Large Language Models on 6G Networks, in conjunction with IEEE ICC 2024, Denver, USA, June 2024.