Machine learning for solar array monitoring, optimization, and control / Sunil Rao, Sameeksha Katoch, Vivek Narayanaswamy, Gowtham Muniraju, Cihan Tepedelenlioglu, Andreas Spanias, Pavan Turaga, Raja Ayyanar, and Devarajan Srinivasan.

1. Introduction
2. Solar array research testbed
2.1. The SenSIP 18 kW solar array testbed
2.2. Design of the solar array testbed
2.3. The MATLAB simulink model
2.4. The PVWatts dataset
2.5. Summary

3. Fault classification using machine learning
3.1. Faults in PV arrays
3.2. Standard machine learning algorithms
3.3. Neural networks
3.4. Fault detection and computational complexity
3.5. Graph signal processing
3.6. Semi-supervised graph-based classification
3.7. Summary

4. Shading prediction for power optimization
4.1. Partial shading on photovoltaic panels
4.2. Prior work in cloud motion and dynamic texture synthesis
4.3. Dynamic texture prediction model
4.4. Simulation results
4.5. Shading and topology reconfiguration
4.6. Summary

5. Topology reconfiguration using neural networks
5.1. Need for topology reconfiguration
5.2. Prior work
5.3. Machine learning for topology reconfiguration
5.4. Methodology
5.5. Empirical evaluations
5.6. Summary
6. Summary.