HTM-OPF: A software tool for Optimal Power Flow Studies Based on the Hierarchical Temporal Memory

Abstract

In this paper, a new software tool for HTM Optimal Power Flow (HTM-OPF) studies based on an emerging artificial intelligence technology called Hierarchical Temporal Memory (HTM) is presented. The HTM is based on the Cortical Learning Algorithm which is a significant improvement on the artificial neuron-based networks (ANN’s) models and offers meta-cognition capabilities building more advanced neural model solutions with both active and predictive output states. HTM explores the best features of the neo-cortex by providing a set of column-like feed-forward activators with good inferential qualities to solve a specific set of generic problems. For the OPF problem, cost minimization prediction and classification were achieved using a collection of HTM cells working concurrently in order to compensate for energy losses and reduce overall systems costs based on data-driven technique. The tool was applied to a sample data obtained from three different plants to validate its predictive efficacy considering classification accuracies and percent variation in training data. The simulation results showed that increasing training data leads to higher classification accuracies but this may impact the computational run-times.