I am working in hourly multivariate time series forecasting, so due to big data, I made the forecasting through functional time series. The model that I am using is the functional autoregressive model of order more than one, As per my knowledge, there is no statistical package available in R to deal with such a model. So to deal with such a model. I use the functional principal components functions and their associated score as dimension reduction, forecast the scores through multivariate time series method, then multiple the forecasted scores with the functional principle function make reverse back to functional time series, in which each forecasted day is a single curve. my problem starts from here, I want to check the accuracy of the model I want to evaluate the given curve as 24 points as data is hourly data. please suggest to me that how I evaluate such curve.