This report describes the activities conducted to integrate, into RSE’s Big Data platform, the innovative applications developed during previous research years for power quality analysis. In particular, applications developed by RSE based on artificial intelligence were implemented in the platform, with the aim to improve the evaluation of data validity and the origin of voltage dips: the DELFI (DEep Learning for False voltage dips Identification) classifier, the FExWaveS + SVM (Features Extraction Waveform Segmentation + Support Vector Machine classifier) classifier, and their integrations with the QuEEN monitoring system through the QuEEN PyService application. The potential and tools offered by the Big Data platform made it possible to significantly reduce the time for the training phase of the model based on Deep Learning techniques. In detail, using GPUs allowed training such model with significantly higher performance: the training was achieved in 1 hour and 23 minutes against the 22 hours and 58 minutes obtained using only the CPU of the machine. In addition, the Big Data platform is prepared for possible future developments in the research activity: artificial intelligence-based models can be updated and retrained with new data from the field using adequate computing power and storage space.