SearcharxivSearch

arXiv subjects

Cesar Marcondes

Publications and source records attributed to Cesar Marcondes.

2 recordsLinked to original sources

Permissioned Blockchain in Advanced Air Mobility: A Performance Analysis for UTM

The integration of Uncrewed Aerial Vehicles (UAVs) into low-altitude airspace has led authorities to adopt distributed Uncrewed Traffic Management (UTM) architectures that ensure interoperability and safety. Blockchain has been proposed as an enabler for trustworthy coordination among UTM stakeholders. Yet, its real-time performance under aeronautical constraints remains insufficiently characterized. This paper presentes a quantitative benchmark comparing two regulation compliant distributed architectures: the federated InterUSS platform maintained by the Linux Foundation and a permissioned blockchain based on Hyperledger Fabric. Both systems were evaluated through Operational Intent Reference (OIR) registration work loads generated via Hyperledger Caliper, measuring throughput, latency, and transaction loss under loads up to 50 transactions per second. Results show that InterUSS sustained sub-second latency and stable performance up to 30 TPS. At the same time, Fabric exhibited exponential degradation with median latency exceeding 3 s and tail latencies above 15 s beyond that point. These findings demonstrate that blockchain-based architectures must be redesigned to meet aeronautical timing and scalability requirements, suggesting that hybrid models combining distributed ledgers for auditability with federated frameworks for real-time coordination are more suitable for future UTM deployments.

cs.NI

Modelling Energy Consumption based on Resource Utilization

Power management is an expensive and important issue for large computational infrastructures such as datacenters, large clusters, and computational grids. However, measuring energy consumption of scalable systems may be impractical due to both cost and complexity for deploying power metering devices on a large number of machines. In this paper, we propose the use of information about resource utilization (e.g. processor, memory, disk operations, and network traffic) as proxies for estimating power consumption. We employ machine learning techniques to estimate power consumption using such information which are provided by common operating systems. Experiments with linear regression, regression tree, and multilayer perceptron on data from different hardware resulted into a model with 99.94\% of accuracy and 6.32 watts of error in the best case.

cs.LG