I am working in the multivariate time series hourly data, i have five years data i use the first four years as testing set and the last year as validation, my objective is hourly forecast one year mean a matrix of order 24*365, i transform the original data into functional form, through Fourier basis function, i find the functional principle components as dimensional reduction, choosing the first six functional principle components explaining a given a mount of variation.
Then i choose the corresponding functional principle scores and apply vector autoregressive model and then using the forecast function, I extract the forecast values from the forecast result, know my problem start as mentioned earlier that i need to forecast each 24 hours of a single day not only six that are obtained through the forecast result and then generalize the result for the whole year, so please guide how i could do this or suggest me any link through which i solve my problem, for explaining my problem easily my code is also attach, hope you will solve my problem. thanks
- Badges
- Science topic
- Similar topics
- Biological Science
- Bioecology
- Systems Ecology
- Landscape Ecology
- Connectivity