I am trying to implement neural networks - LSTMs - to implement a Time Series concept. I have 3 years of hourly data of production and I plan to use 2 years of data to train the model and predict for the third year of data to test the model.
I want to make a prediction(target variable - Production) for each hour, given that I have 1 independent variable which varies monthly(say the 'Price'), another which varies hourly(say the 'Demand') and a couple of other variables which vary with different categories present in my data. I also have a couple of other continuous value variables which do not necessarily vary with time, there is no fixed pattern with respect to time.
Can I use time series for such data? If yes, what are the ways to treat the monthly varying quantity('Price'), the hourly varying quantity('Demand'), and time-invariant quantities?
I also have a variable which holds numerical values (say Production capacity of a Unit) that change which a categorical variable (say the Unit name) in a dataset. Do I treat the "Production Capacity" - as a continuous value variable or a category?