I need the best machine learning method/algorithm/technique to predict energy consumption. The given training dataset consists of 2 years of energy consumption, with entries every 15 minutes. In addition, weather data (radiation, humidity, temperature and wind speed) are given every hour.
Now as input, I have a few entries with exactly the same format as the training dataset, except, the power consumption has to be predicted as accurately as possible.
The dataset contains several variables: time, day of the week, week of the year, radiation, humidity, temperature, wind speed and power demand
The goal is to be give the same variables but to predict power demand
The algorithm must be:
- supervised machine learning
- interpolated the weather (radiation, humidity, temp and wind speed) before training because they are only given per hour while we need per 15minutes
- divide the historic data into two sets, a training set (from which the application can learn) and a test set, on which to test the accuracy of the forecasts.
- expect that not only weather but also time of day, day of week and week of the year will play an important role in the forecasting
- not expect all the variables will play an equal role, including all possible input variables may even reduce performance
P.S. My apologies guys, I have no experience in machine learning at all, I just need a machine learning method/programming library to forecast the most accurate power comsumption, thanks!!