The Paris Agreement aims to limit global average temperature rise to well below 2°C above pre-industrial levels and "to pursue efforts to limit temperature rise to 1.5°C". To achieve this goal, emission of greenhouse gases must fall to zero in the upcoming few years. This goal can be achieved by empowering the existing renewable energy technologies. One of these technologies is concentrated solar power technology (CSP). CSP plants can be empowered by employing performance monitoring systems at the plant location. There are various performance monitoring systems in place to monitor the key performance indicators of the power plants which help in the optimization and increase in efficiency of operations at a power plant. The traditional approach to develop these performance monitoring systems is to model the entire power plant mathematically and simulate the expected behaviour of the various components of the power plant. The goal of this thesis is to explore an approach that involves the use of a machine learning algorithm to simulate and thus predict the values associated with the key performance indicators of the concentrated solar power tower and the parabolic trough power plant. A Long Short-Term Memory (LSTM) machine learning algorithm has been used to make the predictions of the pre-selected key performance indicators in this study. The predicted values have been compared to the actual values and are evaluated based on the root mean squared error score and the mean absolute error score.