6533b7d6fe1ef96bd1266e4a

RESEARCH PRODUCT

Smart load prediction analysis for distributed power network of Holiday Cabins in Norwegian rural area

subject

description

Abstract The Norwegian rural distributed power network is mainly designed for Holiday Cabins with limited electrical loading capacity. Load prediction analysis, within such type of network, is necessary for effective operation and to manage the increasing demand of new appliances (e. g. electric vehicles and heat pumps). In this paper, load prediction of a distributed power network (i.e. a typical Norwegian rural area power network of 125 cottages with 478 kW peak demand) is carried out using regression analysis techniques for establishing autocorrelations and correlations among weather parameters and occurrence time in the period of 2014–2018. In this study, the regression analysis for load prediction is done considering vertical and continuous time approach for day-ahead prediction. The vertical time approach uses seasonal data for training and inference, compared to continuous time approach which utilizes all data in a continuum from the start of the dataset until the time period used for inference. The vertical approach does this with even fewer data than continuous approach. The regression tools can perform using the low amount of data, and the prediction accuracy matches with other techniques. It is observed through load predictive analysis that the autocorrelation by vertical approach with kNN-regressor gives a low Symmetric Mean Absolute Percentage Error. The kNN-regressor is compared with Random Forest Regressor, and it uses autoregression. Autoregression is the simplest and the most straightforward predictive model based on the targeted vector itself. The autoregression indicates the decline and incline of the time-series, and thus gives a finite gradient for the curvature of load profile. It is observed that joint learning of regression tools with autoregression can predict time-series components of the different load profile characteristics. The presented load prediction analysis is going to be useful for distributed network operation, demand-side management, integration of renewable energy sources and distributed generators.