Merged ETT Dataset for Time Series Forecasting

This dataset is a unified compilation of the Electricity Transformer Temperature (ETT) datasets: ETTh1, ETTh2, ETTm1, and ETTm2. It includes both hourly and minute-level temperature and load data collected from power transformers, which are vital for developing and benchmarking time-series forecasting models. The dataset contains features such as high and medium voltage transformer temperatures (HUFL, HULL, MUFL, MULL) and the operational temperature (OT), which serves as the primary prediction target. By merging the four datasets, researchers and practitioners can explore a more diverse and complex set of temporal patterns. This dataset supports a wide range of applications in energy forecasting, grid optimization, and predictive maintenance using traditional statistical methods and advanced deep learning models like Informer and Transformer.