A Statistical Framework for District Energy Long-term Electric Load Forecasting

TL;DR

This paper introduces multiple hybrid statistical models for long-term district energy electric load forecasting, capable of accurately predicting demand over 6 to 11 years using limited training data.

Contribution

It develops and verifies new hybrid statistical models combining GAM, SARIMA, MLR, and ARIMA errors for multi-decade load forecasting, addressing a key industry gap.

Findings

Models achieve up to 9.09% normalized RMSE over 11-year forecasts.

Forecast accuracy remains high with limited training data.

Models effectively capture seasonal and weather-related demand variations.

Abstract

An accurate forecast of electric demand is essential for the optimal design of a generation system. For district installations, the projected lifespan may extend one or two decades. The reliance on a single-year forecast, combined with a fixed load growth rate, is the current industry standard, but does not support a multi-decade investment. Existing work on long-term forecasting focuses on annual growth rate and/or uses time resolution that is coarser than hourly. To address the gap, we propose multiple statistical forecast models, verified over as long as an 11-year horizon. Combining demand data, weather data, and occupancy trends results in a hybrid statistical model, i.e., generalized additive model (GAM) with a seasonal autoregressive integrated moving average (SARIMA) of the GAM residuals, a multiple linear regression (MLR) model, and a GAM with ARIMA errors model. We evaluate accuracy based on: (i) annual growth rates of monthly peak loads; (ii) annual growth rates of overall energy consumption; (iii) preservation of daily, weekly, and month-to-month trends that occur within each year, known as the 'seasonality' of the data; and, (iv) realistic representation of demand for a full range of weather and occupancy conditions. For example, the models yield an 11-year forecast from a one-year training data set with a normalized root mean square error of 9.091%, a six-year forecast from a one-year training data set with a normalized root mean square error of 8.949%, and a one-year forecast from a 1.2-year training data set with a normalized root mean square error of 6.765%.