A method for enabling forecasting of key performance indicators, KPIs, in a communication network is presented. The method is performed by a network node and comprises collecting (S100) time series data of KPIs in the communication network, extracting (S110) k-principal components of the collected time series data, determining (S120) a principal component score, PCS, from the collected time series data and the extracted k-principal components, and building (S130) a PCS forecast model from the determined PCS and period of time-attributes. Network nodes and computer program products thereof are also presented.