Eduardo Castillo-Guerra

Eduardo Castillo-Guerra

Auto-generated profile, based on publicly available information

Eduardo Castillo-Guerra

Department of Electrical and Computer Engineering, University of New Brunswick, Fredericton, NB, Canada

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
25 January 2022 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
MCMuhammad R. A. Chowdhury
Muhammad R. A. Chowdhury
SSSaleh A. Saleh
Saleh A. Saleh
OBOsleni Antonio Betancourt
Osleni Antonio Betancourt
Julian Luciano Cardenas BarreraJulian Luciano Cardenas Barrera
Julian Luciano Cardenas Barrera
ECEduardo Castillo-Guerra
Eduardo Castillo-Guerra
This article presents the employment of battery storage systems (BSSs) to improve power system survivability. This application of BSSs is based on setting BSS charging/discharging as responses to integrating distributed generation units and/or adjusting load demands (load-side activities). The improvement of power system survivability is quantified by the survivability index $\Gamma$ , which can exceed its boundary values due to load-side activities. The improvement of power system survivability is achieved by maintaining $\Gamma$ within its boundary values post a load-side activity. The proposed approach to improve power system survivability is implemented and tested for the Barbados power system. Tests are conducted for integrating solar power generation units, and implementing demand response. Test results show that accurate BSS charging/discharging can maintain the index $\Gamma$ within its boundary values post-load-side activities.

5 June 2023 in IEEE Access
Verified
Journal Article
Open access
CDCarlos Lester Duenas
Carlos Lester Duenas
AMAhmad Mezher
Ahmad Mezher
JAJuan Astudillo
Juan Astudillo
Julian Luciano Cardenas BarreraJulian Luciano Cardenas Barrera
Julian Luciano Cardenas Barrera
EGEduardo Castillo Guerra
Eduardo Castillo Guerra
PMPatricia Meng
Patricia Meng
This research explores the potential of Machine Learning (ML) to enhance wireless communication networks, specifically in the context of Wireless Smart Grid Networks (WSGNs). We integrated ML into the well-established Routing Protocol for Low-Power and Lossy Networks (RPL), resulting in an advanced version called ML-RPL. This novel protocol utilizes CatBoost, a Gradient Boosted Decision Trees (GBDT) algorithm, to optimize routing decisions. The ML model, trained on a dataset of routing metrics, predicts the probability of successfully reaching a destination node. Each node in the network uses the model to choose the route with the highest probability of effectively delivering packets. Our performance evaluation, carried out in a realistic scenario and under various traffic loads, reveals that ML-RPL significantly improves the packet delivery ratio and minimizes end-to-end delay, making it a promising solution for more efficient and responsive WSGNs.

20 August 2019 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
XGXun Gong
Xun Gong
Julian Luciano Cardenas BarreraJulian Luciano Cardenas Barrera
Julian Luciano Cardenas Barrera
ECEduardo Castillo-Guerra
Eduardo Castillo-Guerra
BCBo Cao
Bo Cao
SSSaleh A. Saleh
Saleh A. Saleh
LCLiuchen Chang
Liuchen Chang
Domestic Electric Water Heaters (DEWHs) can provide operational flexibility for load control due to their energy storage capacity. Load forecasting for aggregated DEWHs is important for providing information of baseline load and controlling electricity demand profile without negative impact to the normal end use. Advanced Metering Infrastructures (AMI) nowadays provide more possibilities to further enhance forecasting with bottom-up method. This paper proposes a bottom-up forecasting with Markov-based error reduction method to predict power consumption of aggregated DEWHs for multiple forecast horizons. DEWHs are randomly divided into small aggregations, whose power consumption is forecasted by independent forecast engines. In this paper, the engines are K-means and wavelet decomposition-based neural networks (KWNN). After summing all forecasting of small aggregations up, a new Markov-based error reduction method is proposed to extract features in residuals and mitigate forecasting error accumulation introduced by the summation, providing opportunities to further improve forecasting accuracy for the total DEWH load. Differing from traditional Markov-based error reduction, two new compensation parameters (Compensation Coefficient, and Compensation Threshold) are proposed. They are determined by using Particle Swarm Optimization (PSO) algorithm. Experiments on real and simulated DEWH loads verified the effectiveness of the proposed forecasting method. The proposed method improved the forecast accuracy over selected benchmark algorithms by about 20% to 80%, according to four performance metrics: MAE, MAPE, RMSE, NRMSE. The aggregation effects on performance were also analyzed in theory and tested with simulated DEWHs, providing a good indication of the forecast dependence on the aggregation size.

4 December 2019 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
SSSaleh A. Saleh
Saleh A. Saleh
EOEmre Ozkop
Emre Ozkop
ECEduardo Castillo-Guerra
Eduardo Castillo-Guerra
PPPetrus C. Pijnenburg
Petrus C. Pijnenburg

7 February 2020 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
SSSaleh A. Saleh
Saleh A. Saleh
JWJeffery Wo
Jeffery Wo
XSXavier F. St-Onge
Xavier F. St-Onge
ECEduardo Castillo-Guerra
Eduardo Castillo-Guerra

14 July 2021 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
SSSaleh A. Saleh
Saleh A. Saleh
Julian Luciano Cardenas BarreraJulian Luciano Cardenas Barrera
Julian Luciano Cardenas Barrera
ECEduardo Castillo-Guerra
Eduardo Castillo-Guerra
JMJulian Meng
Julian Meng
BABasim Alsayid
Basim Alsayid
LCLiuchen Chang
Liuchen Chang
This article develops a method for planning smart grid functions (peak-demand management, direct load control, and demand response) for residential loads. The proposed planning method is developed based on modeling the thermal energy stored in thermostatically controlled appliances (TCAs) as energy charged into a virtual (fictitious) equivalent battery storage unit (VE-BSU) at the distribution transformer that feeds these TCAs. The thermal energy stored in TCAs can reduce their power demands during peak-demand times. These reductions in power demands of TCAs can be modeled as discharging energy from the VE-BSU. The energy charged and discharged by the VE-BSU can be used to plan smart grid functions to maximize storing thermal energy in TCAs during off-peak-demand times (short time horizons). This feature is due to the ability to store thermal energy in TCAs, and completely use it over short time intervals. The VE-BSU-based planning method is implemented and tested for residential loads fed by five different distribution transformers. Test results demonstrate the ability of the proposed method to plan effective and stable actions of smart grid functions, with minor sensitivity to the number of residential loads and/or seasonal variations in their power demands.