Edgar Bahilo Rodríguez's repositories
seasonalview
Graphical User Interface for Seasonal Adjustment
cortana-intelligence-energy-demand-forecasting
Energy industry solutions using the Cortana Intelligence Suite with end-to-end walkthrough.
PyomoGettingStarted
IPython notebooks that illustrate the Pyomo optimization modeling software
mlr
mlr: Machine Learning in R
economic_dispatch_sim
Lagrange multiplicators, linear regression for optimal energy dispatch
IndustrialScheduling
Optimal scheduling for industrial plants.
Australian-National-Electricity-Market-with-and-without-flexible-ramping-products
Australia's goals of increased penetration of renewable energy such as wind energy will inevitably lead to increased variability and uncertainty of the ramps in net load (load minus non-dispatchable renewable generation). This increased variability and uncertainty requires conventional generators to be more flexible, but currently this flexibility is not fully integrated in market processes. The provision of additional flexibility may cause a reduction in economic efficiency, consumer surplus and/or producer surplus as conventional generators may need to modify their output from the optimal level in order to provide flexibility to account for future variability and uncertainty. As a solution to this problem, the Midwest and Californian Independent System Operators have proposed flexible ramping products as a mechanism to manage the uncertainty and variability in net load ramps in an economically preferable manner. The mechanism essentially aims to schedule conventional generators to provide enough ramping capability, or "flexibility", to satisfy a flexible ramping capability requirement. This requirement is designed to ensure a certain range of ramps in the next interval could be met, whether the ramps actually occur or not. This study aims to explore the implementation of flexible ramping products in the specific context of the Australian National Electricity Market (NEM), to determine whether or not they can be an effective mechanism for integrating variable renewable energy in Australia in the coming decades. This model is a simplified model of the Australian NEM, in which a unit commitment and economic dispatch is designed with flexible ramping products and a flexible ramping requirement. The simplification of the NEM includes a grouping of the five states into two regions, and an aggregation of generators by offered ramping speed and actual marginal costs. Actual load and wind generation data from the 2014/15 financial year is implemented in the model to attempt to simulate the market in a realistic manner.
sanger-machine-learning-workshop
Code for machine learning workshop given to Sanger Systems group
multilevel_modeling
Tutorial on multilevel modeling, using Gelman radon example
predictionio-load-forecasting
This is a PredictionIO engine for electric load forecasting.
predictionio-template-recommendation-sparklingwater
PredictionIO recommendation engine template (Scala-based parallelized engine)
elec_cap_planning
Electricity Generation Unit Commitment Model for the state of Georgia (gurobipy)
Optimizador_MINLP
Ejemplo de optimizador MINLP con R y Pyomo