Ingrid Oliveros

Prof. Ingrid Oliveros

Universidad del Norte

Research Focus & Metrics

Academic Career Length

26Years (2001-Present)

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

Representative Publications

View All Publications
22 August 2019 in Computation
Verified
Journal Article
Open access
PDF file
JGJordan Guillot
Jordan Guillot
DRDiego Restrepo
Diego Restrepo
CRCarlos Robles-Algarín
Carlos Robles-Algarín
IOIngrid Oliveros
Ingrid Oliveros
In the field of engineering when a situation is not resolved analytically, efforts are made to develop methods that approximate a possible solution. These efforts have originated the numerical methods known at present, which allow formulating mathematical problems that can be solved using logical and arithmetic operations. This paper presents a comparison between the numerical optimization algorithms golden section search and simulated annealing, which are tested in four different scenarios. These scenarios are functions implemented with a feedforward neural network, which emulate a partial shading behavior in photovoltaic modules with local and global maxima. The presence of the local maxima makes it difficult to track the maximum power point, necessary to obtain the highest possible performance of the photovoltaic module. The programming of the algorithms was performed in C language. The results demonstrate the effectiveness of the algorithms to find global maxima. However, the golden section search method showed a better performance in terms of percentage of error, computation time and number of iterations, except in test scenario number three, where a better percentage of error was obtained with the simulated annealing algorithm for a computational temperature of 1000.

1 October 2023 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
JGJordan Guillot
Jordan Guillot
DRDIEGO RESTREPO-LEAL
DIEGO RESTREPO-LEAL
CRCarlos Robles-Algarín
Carlos Robles-Algarín
IOIngrid Oliveros
Ingrid Oliveros
PSPaola Andrea Niño Suarez
Paola Andrea Niño Suarez
The monitoring of wind installations is key for predicting their future behavior, due to the strong dependence on weather conditions and the stochastic nature of the wind. However, in some places, in situ measurements are not always available. In this paper, active power predictions for the city of Santa Marta-Colombia using a nonlinear autoregressive exogenous model (NARX) network were performed. The network was trained with a reliable dataset from a wind farm located in Turkey, because the meteorological data from the city of Santa Marta are unavailable or unreliable on certain dates. Three training and testing cases were designed, with different input variables and varying the network target between active power and wind speed. The dataset was obtained from the Kaggle platform, and is made up of five variables: date, active power, wind speed, theoretical power, and wind direction; each with 50,530 samples, which were preprocessed and, in some cases, normalized, to facilitate the neural network learning. For the training, testing and validation processes, a correlation coefficient of 0.9589 was obtained for the best scenario with the data from Turkey, while the best correlation coefficient for the data from Santa Marta was 0.8537.

28 November 2020 in Energies
Verified
Journal Article
Open access
PDF file
LLLuis Lopez
Luis Lopez
IOIngrid Oliveros
Ingrid Oliveros
LTLuis Torres
Luis Torres
LSLácides Antonio Ripoll Solano
Lácides Antonio Ripoll Solano
JSJose Soto
Jose Soto
SCSantiago Cantillo
Santiago Cantillo
This paper presents a methodology to calculate day-ahead wind speed predictions based on historical measurements done by weather stations. The methodology was tested for three locations: Colombia, Ecuador, and Spain. The data is input into the process in two ways: (1) As a single time series containing all measurements, and (2) as twenty-four separate parallel sequences, corresponding to the values of wind speed at each of the 24 h in the day over several months. The methodology relies on the use of three non-parametric techniques: Least-squares support vector machines, empirical mode decomposition, and the wavelet transform. Moreover, the traditional and simple auto-regressive model is applied. The combination of the aforementioned techniques results in nine methods for performing wind prediction. Experiments using a matlab implementation showed that the least-squares support vector machine using data as a single time series outperformed the other combinations, obtaining the least root mean square error (RMSE).

21 May 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
VOVictor Jose Olivero
Victor Jose Olivero
IOIngrid Oliveros
Ingrid Oliveros
CRCarlos Robles-Algarín
Carlos Robles-Algarín
The prediction of lithium-ion battery capacity degradation is crucial for enhancing the reliability, efficiency, and sustainability of energy storage systems. This study proposes a data-driven approach to model capacity degradation in 18650 lithium-ion cells, supporting the long-term performance and responsible management of battery technologies. A systematic search was conducted to identify publicly available experimental datasets reporting charge/discharge processes, leading to the selection of the MIT-BIT Battery Degradation Dataset (Fixed Current Profiles and Arbitrary Use Profiles). This dataset was chosen for its extensive degradation data, variability, and adaptability to real-world applications. Of the 77 tested cells, 73 were included after filtering data completeness; cells with missing critical information, such as temperature, were excluded. A subset of cells tested under a 1C–2C charge/discharge profile was analyzed, and cell 52 was selected for its comprehensive structure. Using this dataset, a predictive model was developed to estimate the battery capacity based on the current, voltage, and temperature, with capacity as the target variable. A neural network was implemented using TensorFlow and Keras, incorporating ReLU activation, Adam optimization, and multiple loss functions. The dataset was standardized using MinMaxScaler, StandardScaler, and RobustScaler, and the training–test split was 75–25%. The model achieved a prediction error of 3.35% during training and 3.48% during validation, demonstrating robustness and efficiency. These results highlight the potential of data-driven models in accurately predicting lithium-ion battery degradation and underscore their relevance for promoting sustainable energy systems through improved battery health forecasting, optimized second-life use, and extended operational lifetimes of storage technologies.

25 November 2025 in IEEE Access
Verified
Journal Article
Open access
VOVictor Jose Olivero
Victor Jose Olivero
IOIngrid Oliveros
Ingrid Oliveros
CRCarlos Robles-Algarín
Carlos Robles-Algarín
This work analyzes and models degradation in 18650 lithium-ion cells using segmented experimental charge–discharge data (99 cycles under two cycling profiles, 3C/1C and 2C/2C). Beyond raw electrical and thermal measurements (voltage, current, and temperature), we derive operational indicators—mainly cycle time (charge/discharge duration) and internal impedance—to capture nonlinear relationships with capacity. Gaussian Process Regression (GPR) with multiple kernels (RBF, Rational Quadratic, Matérn, plus white noise) is used to predict capacity from these features. Quantitative results indicate that cycle-time features are the most predictive variables. During charging, the top configurations achieve RMSE values of 2.217–4.606 mAh and MAE values of 1.411–3.290 mAh across two cells. During discharge, the best models reach RMSE values of 3.166–3.518 mAh and MAE of 2.186–2.192 mAh. In contrast, impedance-only settings produce significantly higher errors — RMSE approximately 138–182 mAh during charging and roughly 11.281–11.683 mAh during discharging (MAE approximately 9.159–9.416 mAh) — demonstrating their limited usefulness when used alone under the studied regimes. These results confirm the effectiveness of the proposed GPR plus operational features methodology and show that feature selection has a greater impact on accuracy than kernel choice. The approach delivers low absolute error, stable predictive distributions, and consistent phase performance, supporting SOH/RUL estimation and second-life cell screening. The cycle segmentation based on fragmentation further improves interpretability and model design, offering a practical route toward reliable battery management and sustainable second-life applications.

1 September 2018
Verified
Conference Paper
Closed access
PHPaula De la Hoz
Paula De la Hoz
EJElvin Jimenez
Elvin Jimenez
IOIngrid Oliveros
Ingrid Oliveros
ASAndrea Silva
Andrea Silva
RCRafael Castillo-Sierra
Rafael Castillo-Sierra
MPMauricio Pardo
Mauricio Pardo
This paper presents the analysis of an actual scaled-IEEE-13 distribution feeder under different operating conditions including the modelling and simulation of variating solar energy contribution. The actual distribution feeder was built under the Universidad del Norte strategic energy area as a laboratory; therefore, the scaling and generator-load modules where carried out given the particular conditions of the university. This project becomes an actual test bench to fully explore strategies to many needs that exists today such as: energy efficiency, increased use of renewable energy, reduction of greenhouse gas emissions, increased safety of the supply and minimization of electrical losses. The main result of the present work is to defined the amount of solar energy that can be injected to a conventional power system, so that it can keep operation under a regulatory frame even under island operation, which allows to possibility to become a solution for lack of power from the network operator and/or explore schemes of distributed generation.