Foto
LASSE
Active Projects
GImpSI - Management of Salinity Impacts on Insulation

The GImpSI project - Management of Salinity Impacts on Insulation, is developed in partnership with the INESC P&D Brasil network, and aims to design a system that allows monitoring and managing the effects of salinity deposited on the insulation of high voltage substations. This allows, among other benefits, the developed system to indicate the ideal times for equipment washing, which reduces the risk of failures caused by the accumulation of salinity. In this context, the LASSE team collaborates with the development of software and hardware for signal acquisition, wireless communication and other platforms for monitoring and managing IoT devices.

Digital Twins and Artificial Intelligence for 6G Networks

The project addresses the evolution of cellular networks, currently in the fifth generation (5G), and anticipates the next generation (6G) planned for 2030. 5G networks have three main use cases: enhanced mobile broadband (eMBB), ultra-reliable low-latency communications (URLLC), and massive machine-type communications (mMTC). These use cases introduce new management challenges due to the different requirements for latency, data rate, and packet loss. To meet these requirements, technologies such as millimeter-wave transmission and network slicing have been incorporated. However, these advances increase the complexity of network management. To address these...

Signal Processing and Synchronization Algorithms for X-hauling in 6G

Deepen investigations into synchronization and signal processing techniques for x-hauling, and initiate investigations into non-terrestrial networks (NTN), focusing on issues related to fronthauls (FH) of satellites with considerable latency.

Digital Connectivity in Remote Locations (CELCOM)

The project's main objective is to explore software and hardware-based solutions to enable internet access for extractive communities that do not benefit from information and communication technologies (ICTs). Therefore, CELCOM seeks to implement second-generation (2G) mobile networks, centered on Global System for Mobile Communications (GSM), or fourth-generation (4G) networks, centered on Long Term Evolution (LTE), using Wi-Fi radios and technologies standardized by 3GPP. There is also interest in exploring open-source software solutions such as the Telecom Infra Project (TIP) and Open Wireless Router (OpenWRT) as network management resources and developing a graphical interface that facilitates the handling of these technologies.

Universal: Artificial Intelligence for Next-Generation Network Resource Optimization in Strategic Scenarios

With the advancement of mobile communications, Post-5G networks (B5G/6G) will become more complex, resulting in significant challenges for new use case scenarios. Agribusiness, critical mission, and digital twins are strategic examples for Brazil of the use of B5G/6G and are investigated in this project. The complexity generated by the enormous number of parameters and optimizations to be made in the protocol stack to ensure good end-to-end performance brings difficulties to the implementation and management of these networks. The use of artificial intelligence and machine learning (AI/ML) in trend prediction and pattern extraction from the collection of environmental measurements and performance indicators plays a prominent role in...

Smart 5G Core And MUltiRAn Integration (Samurai)

5G networks will meet the diverse requirements of new services and applications, such as IoT, virtual/augmented reality, autonomous cars, and precision agriculture. To handle this diversity, multiple operating modes, provided by different wireless access technologies, have been defined. Additionally, 5G networks are being developed under an intense softwarization process, characterized by the use of cloud, virtualization, and programmability. This process is significant in access networks and even more notable in the 5G core. Faced with many challenges, there are several open questions, such as the integration of non-3GPP IoT access network technologies into a 5G core. The SAMURAI project proposes to research, deploy, and extend 5G...

LFC: Online Semi-Supervised Learning for Predicting Critical Changes in Software

The LFC project - Learning From Commits - fits into the broad area of Just-in-time Software Defect Prediction (JIT-SDP), which seeks to use advanced algorithms to detect software changes (e.g., git commits) with the potential to introduce defects. The main challenge of JIT-SDP is dealing with data sent in streams, sparsely labeled with an unknown probability distribution and subject to concept drift...

ORANOR: An Intelligent OpenRAN Orchestrator of High Availability, Low Power Consumption Service Function Chains

The ORANOR project aims to address the deployment challenges of the OpenRAN 5G architecture, which, despite its many advantages, also exposes network components to malicious attacks and requires careful orchestration to ensure the continuity and reliability of services in the face of the probability of failures. The main proposal of the project is to use optimization and machine learning techniques for efficient resource orchestration, minimizing the risk of failures and energy consumption, as well as identifying and mitigating vulnerabilities related to possible cyber attacks. Such solutions will be encoded in the form of xApps and rApps for OpenRAN architecture....

Finished Projects
End-to-End Automation of 6G Networks via Artificial Intelligence, Digital Twins, and Standardized Interfaces

Unlike 4G networks, 5G mobile networks were designed to serve three categories of devices, identified as 5G use cases: eMBB (Enhanced mobile broadband), URLLC (ultra-reliable low latency communications), and mMTC (massive machine type communications). Thus, there are different types of devices that networks are being designed to serve, with different requirements in terms of rate and latency, in addition to the possibility of a much larger number of devices to be served. Current systems are in a transition process, from a network typically designed to deliver content, without considering the characteristics of each...

Intelligent and Distributed Algorithms for the Physical Layer of 6G Systems

The activities proposed in the project seek to solve two open topics in the case of 5G and 6G networks considering different types of architectures and scenarios: fronthaul networks with massive MIMO and synchronization. In the first topic, algorithms and estimation techniques are researched for the massive MIMO fronthaul scenario, where the use of transport networks without support for the IEEE 1588 protocol is assumed. Another topic of interest is in the cell-free context, where the impact of synchronization failures on network performance is studied...

Synchronization and Compression Techniques for 5G Signals and Multiple Antenna Techniques

The project is characterized as research because new techniques for fifth-generation (5G) cellular networks will be sought. These techniques can be developed or adapted from pre-existing ones, within three lines of investigation. These lines of investigation are emerging topics and addressed in several IEEE scientific articles. The first line concerns compression techniques for transporting signals in the network segment called fronthaul in 5G networks. Compression techniques for 5G operating with multiple antenna transmission techniques and within the O-RAN context will be investigated. The second line of investigation seeks to develop synchronization techniques via packet networks using the IEEE 1588 protocol in networks without support for this protocol...

Connected Artificial Intelligence for 5G Networks with Computer Vision Applications

Communication technologies are very important. Currently, they influence not only the daily lives of people, who notice mainly when the system is down and the service is unavailable, but also the sovereignty of countries. It is crucial that Brazil has know-how in telecommunications. UFPA offers a Telecommunications Engineering course. The present project is part of a collaboration of more than a decade between UFPA and the company Ericsson. This collaboration has already received a national award due to the positive results it brought to UFPA, and the current project is an opportunity for professors and students to conduct research on fifth-generation (5G) technologies. In addition to the technological issue, there is also the social importance...

Integrated System for Continuous Assessment of Grounding System Safety in Energized Substations Subject to Lightning Strikes

In this project, prototypes of a data acquisition equipment, based on a microcontroller, were developed in order to diagnose the degradation conditions of grounding grids in energized substations. The developed system is portable with embedded hardware and software. It captures voltage and current data present in a grounding system, at industrial frequency. A wireless sensor network was built, and the information captured by the data acquisition systems is transmitted to a remote entity using IEEE802.15.4/ZigBee technologies. The entire system allows for continuous and remote assessment of the grounding system...

5G Connectivity in Coordinated Applications with Machine Intelligence

The project encompasses research activities on 5G technologies involving machine intelligence, exemplified through experimentation environments using drones. New applications have been responsible for a large part of the increase in network traffic, which in the last 4 years has increased to about 140 exabytes. This increase in traffic, combined with the increased complexity of the network and the search for automatic solutions, motivates this project. It is based on the investigation of machine learning techniques to achieve a good cost-efficiency ratio in 5G network scenarios. The project has three main areas of scope: machine learning, 5G networks, and drone applications. More specifically, this...

End-to-End Automation of 6G Networks via Artificial Intelligence

The project aims to develop innovative solutions for the autonomous management of B5G/6G mobile networks through the incorporation of machine learning and, in general, artificial intelligence (ML/AI) in radio access networks (RAN) and transport networks. Its specific objectives are 1) To investigate AI as a tool for network optimization with respect to PHY and transport network, with emphasis on the former; 2) To establish AI methodologies that are compatible with the efforts of standardization bodies, such as 3GPP (3rd Generation Partnership Project), O-RAN (KAZEMIFARD, 2021), ETSI (European Telecommunications Standards Institute), through groups that develop Experiential Networked Intelligence (ENI)...

Synchronization and Compression Techniques for 5G Signals and Multiple Antenna Techniques

The project is characterized as research because new techniques for fifth-generation (5G) cellular networks will be sought. These techniques can be developed or adapted from pre-existing ones, within three lines of investigation. These lines of investigation are emerging topics and addressed in several IEEE scientific articles. The first line concerns compression techniques for transporting signals in the network segment called fronthaul in 5G networks. Compression techniques for 5G operating with multiple antenna transmission techniques and within the O-RAN context will be investigated. The second line of investigation seeks to develop synchronization techniques via...

Connected Artificial Intelligence for 5G Networks with Computer Vision Applications

Communication technologies are very important. Currently, they influence not only the daily lives of people, who notice mainly when the system is down and the service is unavailable, but also the sovereignty of countries. It is crucial that Brazil has know-how in telecommunications. UFPA offers a Telecommunications Engineering course. The present project is part of a collaboration of more than a decade between UFPA and the company Ericsson. This collaboration has already received a national award due to the positive results it brought to UFPA, and the current project is an opportunity for professors and students to conduct research on fifth-generation (5G) technologies. In addition to the technological issue, there is also the social importance...

5G Connectivity in Coordinated Applications with Machine Intelligence

The project encompasses research activities on 5G technologies involving machine intelligence, exemplified through experimentation environments using drones. New applications have been responsible for a large part of the increase in network traffic, which in the last 4 years has increased to about 140 exabytes. This increase in traffic, combined with the increased complexity of the network and the search for automatic solutions, motivates this project. It is based on the investigation of machine learning techniques to achieve a good cost-efficiency ratio in 5G network scenarios. The project has three main areas of scope: machine learning, 5G networks, and drone applications. More specifically, this...