With the steady and rapid reliance on solar power as a viable alternative to traditional fuel-based energy, maintenance of solar panels is becoming an unavoidable issue for both producers and consumers. Machine learning techniques are useful in detecting solar panel faults and their life span. In recent years, Machine learning technology has emerged that helps to extract meaningful information and detect the fault in PV Systems. This paper reviews and involves identifying faulty features and predicting the fault in residential PV Systems that causes power degradation. We have built a linear regression model and performed hierarchical clustering to identify the faulty group of data, and from that faulty group, we identified that the features such as Radiation, Module Temperature, and IS values play an important role in the degradation of the power generation in the solar panels. Additionally, in this study fault prediction in a PV system has also been attempted. We evaluated the performance using 6 different models SVM, KNN, Naive Bayes Random Forest, Decision Tree and Logistic Regression. Finally, we concluded that the Random Forest, KNN and Decision Tree performed better in predicting with an accuracy of 99 %.