This paper presents the development of a deep neu-ral network architecture based on stacked LSTM and T ime2Vec layers for predicting electricity prices several steps ahead (8 hours) to feed future decision-making tools. The proposed model was tested with hourly wholesale electricity price data from Colombia, and the results were compared with some state-of-art time series based statistical forec...Show More
Power grids all over the world are transitioning towards a decentralized structure. Under such a transition, blockchain technology is emerging as a potential solution for technical, deployment and decentralization issues, given its security, integrity, decentralized nature and required infrastructure. Moreover, blockchain technology offers excellent features like non-repudiation and immutability w...Show More
Large amounts of renewable generation are participating into network-constrained electricity networks. The uncertainty and volatility associated to renewable resources are imposing new challenges for power system operation. Additionally, the integration of demand response resources represent a new challenge, creating new complexities in the power system operation. The operation decisions in power ...Show More
Wind forecasting errors bring great uncertainty to the system operation, since the real-time wind power output may be very different from what is forecasted. Wind generation can increase or decrease its value at a rate that will require that conventional generators adapt their output to follow that ramp to keep the demand-supply balance. The quantification of ramping reserves is addressed in this ...Show More
