Cloud-Based Machine Learning for Voltage and Frequency Control in Transactive Energy Markets

To improve transactive energy market voltage and frequency control management using Cloud-Based Machine Learning methods. Because of its superior capacity to learn complicated relationships over time, the Long Short-Term Memory (LSTM) algorithm was chosen to represent the predicted dynamics of the energy market. To better manage the massive volumes of data in energy markets, the research proposes migrating to a cloud-based architecture, tapping into the processing power of distributed systems. The suggested method solves today's problems with voltage and frequency regulation and looks forward to what will be required by tomorrow's advanced energy infrastructures. To contribute to the establishment of smarter and more adaptable energy networks. To enhance grid stability and responsiveness by combining innovative machine learning techniques and cloud computing. It provides useful information on how Cloud-Based machine learning may help the long-term development of transactive energy markets. It may benefit from improved voltage and frequency management using LSTM in the cloud, which leads to a 20% decrease in deviations and increased grid stability, efficiency, and dependability, contributing to more environmentally friendly power distribution.