Smart Meter Forecasting from One Minute to One Year Horizons

• DOI: 10.3390/en11123520
• Publication Date: 2018-12-18T08:12:30Z
• Authors: Luca Massidda; Marino Marrocu
• Keywords: Probabilistic Forecasting; Smart meter; Metering mode; Consumption

The ability to predict consumption is an essential tool for the management of a power distribution network. availability advanced metering infrastructure through smart meters makes it possible produce forecasts down level individual user and introduce intelligence control at every grid. While aggregate load forecasting mature technology, single more difficult problem address due multiple factors affecting consumption, which are not always easily predictable. This work presents hybrid machine learning methodology based on random forest (RF) linear regression (LR) deterministic probabilistic forecast household different time horizons resolutions. approach separation long term effects from short ones (LR), producing forecasts. proposed procedure applied public dataset, achieving accuracy much higher than other methodologies, in all scenarios analyzed. covers one minute year, highlights great added value provided by forecasting.