Victor Hugo Lázaro Lopes

Victor Hugo Lázaro Lopes

Auto-generated profile, based on publicly available information

Victor Hugo Lázaro Lopes

Institute of Informatics, Federal University of Gois, Goinia, Brazil

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 August 2023 in IEEE Transactions on Wireless Communications
Verified
Journal Article
Closed access
CNCleverson Veloso Nahum
Cleverson Veloso Nahum
VLVictor Hugo L. Lopes
Victor Hugo L. Lopes
RDRyan M. Dreifuerst
Ryan M. Dreifuerst
PBPedro Batista
Pedro Batista
ICIlan Correa
Ilan Correa
RHRobert Heath
Robert Heath
Network slicing at the radio access network (RAN) domain, called RAN slicing, requires elasticity, efficient resource sharing, and customization. In this scenario, radio resource scheduling (RRS) is responsible for dealing with scarce and limited frequency spectrum resources available at the RAN domain while fulfilling the slice intents. The wide variety of scenarios supported in 5G and beyond 5G networks makes the RRS problem in RAN slicing scenario a significant challenge. This paper proposes an intent-aware reinforcement learning method to perform the RRS function in a RAN slicing scenario. The slice’s quality of service intents is described in a common intent model in a service-level agreement. The proposed method tries to prevent intent faults by making the management of radio resources available among slices. This method uses slices’ and users’ equipment network metrics in the observation space. The proposed method is evaluated under different network conditions and outperforms different baselines considering the slices’ intents fulfillment.

24 November 2022 in IEEE Access
Verified
Journal Article
Open access
VLVictor Hugo L. Lopes
Victor Hugo L. Lopes
CNCleverson Veloso Nahum
Cleverson Veloso Nahum
RDRyan M. Dreifuerst
Ryan M. Dreifuerst
PBPedro Batista
Pedro Batista
AKAldebaro Klautau
Aldebaro Klautau
RHRobert Heath
Robert Heath
Fifth-generation (5G) cellular communication systems have embraced massive multiple-input-multiple-output (MIMO) in the low- and mid-band frequencies. In a multiband system, the base station can serve different users in each band, while the user equipment can operate only in a single band simultaneously. This paper considers a massive MIMO system where channels are dynamically allocated in different frequency bands. We treat multiband massive MIMO as a scheduling and resource allocation problem and propose deep reinforcement learning (DRL) agents to perform user scheduling. The DRL agents use buffer and channel information to compose their observation space, and the agent’s reward function maximizes the transmitted throughput and minimizes the packet loss rate. We compare the proposed DRL algorithms with traditional baselines, such as maximum throughput and proportional fairness. The results show that the DRL models outperformed baselines obtaining a 20% higher network sum rate and an 84% smaller packet loss rate. Moreover, we compare different DRL algorithms focusing on training time to assess the online implementation of the DRL agents, showing that the best agent needs about 50K training steps to converge.

1 May 2019
Verified
Conference Paper
Closed access
PTPaulo Gabriel Teixeira
Paulo Gabriel Teixeira
VLVictor Hugo Lázaro Lopes
Victor Hugo Lázaro Lopes
RSRodrigo Pereira dos Santos
Rodrigo Pereira dos Santos
MKMohamad Kassab
Mohamad Kassab
VNValdemar Vicente Graciano Neto
Valdemar Vicente Graciano Neto
The modernization of business processes have pressured Software-Intensive Information Systems (IS) to interoperate with several types of systems, such as cyberphysical systems, drones, satellites, and mobiles, arising a new type of complex systems so-called Systems-of-Information Systems (SoIS). Despite the novelty of the area as it has been known, it follows a trend of previous complex systems, such as Federated Information Systems and Large-Scale Information Systems. However, operational and managerial independence of IS constituents have created a new type of system that must be understood to suitably support new business and modernize old ones, such as pizza delivery via drone swarms. Hence, to sustain the area and achieve advances, it is necessary to externalize the state of the art and practice of the area. However, the lack of literature mappings on this topic can hamper the evolution of the area and pose difficulties to its progress, besides making it difficult to obtain relevant information about existing gaps and advances that could be made in the future. This paper presents results of a Systematic Mapping (SM) carried out to investigate the status quo of SoIS domain. We bring a panorama of this research topic and also indicate research perspectives. From a set of 212 studies, 25 were selected, analyzed and had their data extracted. Results reveal that interoperability between different IS is still a challenge and the low number of studies referring to languages, techniques and tools for modeling SoIS architectures points to an important area of study to be researched in the next years.