arXiv subjects

Adrian Will

Publications and source records attributed to Adrian Will.

3 recordsLinked to original sources

arXiv2025

Equilibrio de carga para transformadores de distribucion electrica mejorando la calidad de servicio en fin de linea

The distribution of electrical energy faces global challenges, such as increasing demand, the integration of distributed generation, high energy losses, and the need to improve service quality. In particular, load imbalance-where loads are not evenly distributed across the circuit phase-can reduce efficiency, shorten equipment lifespan, and increase susceptibility to service interruptions. While methods that involve shifting loads from one phase to another can be costly, they are effective when smart meters are available and implemented efficiently. This work proposes the use of genetic algorithms to optimally identify which loads should be reassigned in order to improve both phase balance and voltage quality at the end nodes of the network while minimizing the number of required changes. The algorithm was evaluated through simulations using PandaPower, a power flow analysis tool, modeling simple networks based on real-world characteristics of the electrical system in Tucuman.

cs.NE↗

arXiv2024

Zorro: A Flexible and Differentiable Parametric Family of Activation Functions That Extends ReLU and GELU

Even in recent neural network architectures such as Transformers and Extended LSTM (xLSTM), and traditional ones like Convolutional Neural Networks, Activation Functions are an integral part of nearly all neural networks. They enable more effective training and capture nonlinear data patterns. More than 400 functions have been proposed over the last 30 years, including fixed or trainable parameters, but only a few are widely used. ReLU is one of the most frequently used, with GELU and Swish variants increasingly appearing. However, ReLU presents non-differentiable points and exploding gradient issues, while testing different parameters of GELU and Swish variants produces varying results, needing more parameters to adapt to datasets and architectures. This article introduces a novel set of activation functions called Zorro, a continuously differentiable and flexible family comprising five main functions fusing ReLU and Sigmoid. Zorro functions are smooth and adaptable, and serve as information gates, aligning with ReLU in the 0-1 range, offering an alternative to ReLU without the need for normalization, neuron death, or gradient explosions. Zorro also approximates functions like Swish, GELU, and DGELU, providing parameters to adjust to different datasets and architectures. We tested it on fully connected, convolutional, and transformer architectures to demonstrate its effectiveness.

cs.LG↗

arXiv2020

A comparison of different types of Niching Genetic Algorithms for variable selection in solar radiation estimation

Variable selection problems generally present more than a single solution and, sometimes, it is worth to find as many solutions as possible. The use of Evolutionary Algorithms applied to this kind of problem proves to be one of the best methods to find optimal solutions. Moreover, there are variants designed to find all or almost all local optima, known as Niching Genetic Algorithms (NGA). There are several different NGA methods developed in order to achieve this task. The present work compares the behavior of eight different niching techniques, applied to a climatic database of four weather stations distributed in Tucuman, Argentina. The goal is to find different sets of input variables that have been used as the input variable by the estimation method. Final results were evaluated based on low estimation error and low dispersion error, as well as a high number of different results and low computational time. A second experiment was carried out to study the capability of the method to identify critical variables. The best results were obtained with Deterministic Crowding. In contrast, Steady State Worst Among Most Similar and Probabilistic Crowding showed good results but longer processing times and less ability to determine the critical factors.

cs.NE↗