Continuous monitoring of internet of things (IoT) resources generates a stream of monitoring data and a proactive model works based on the information extracted from this data. Such proactive models often suffer from lack of the availability of relevant data as well as the non-stationary distribution of data. In this work, an incremental deep neural network (DNN) is employed as a predictive model to predict the maintenance notification as instances of data are incrementally added to the existing pool of data. The presented model further addresses the existing challenges through a distribution preserving technique for effective sampling and early detection of the change in data distribution. The proposed model is tested over different benchmark datasets and it shows a fair amount of accuracy in predicting faults. It improves the accuracy at least by 5%–10% in comparison to the existing state-of-the-art methods and the recent fault prediction approaches such as deep small-world neural network (DSWNN), attention octave convolution residual networks (AOC-ResNet50), and distributed log mining using ensemble learning for fault prediction (DLME). The results further demonstrate that the approach is adaptive to imbalance and non-stationary distribution of the monitoring data.