Mid-term forecasting of urban electricity load to isolate air-conditioning impact

• Hourly regression-model of electricity consumption for the city of Abu Dhabi, UAE.
• Top-down urban level inverse model combined with building level engineering model.
• 57% of the total annual electricity load is due to air-conditioning of indoor spaces.
• Air conditioning is also responsible for 75% of the peak summer demand.

Demand Side Management (DSM) is often one of the most cost-effective approaches toward energy conservation and efficient electricity infrastructure utilization. Identifying total air-conditioning load for assessing targeted interventions is a difficult task given the transient thermal response of buildings, the coupled interaction of multiple sub-systems and the high correlation of demand with weather and other perturbations. An hourly regression-model of electricity consumption was developed for the city of Abu Dhabi, UAE, using measured hourly substation-level data. The fit is exceptionally good, even in a prediction context: Root Mean Squared Error (RMSE) equivalent to 1.54% of the annual peak load and Mean Absolute Percentage Error (MAPE) of 2.01% for the training period (full-year 2010), RMSE of 1.84% and MAPE of 2.64% for the testing period (first-half of 2011). The regression-model was combined with information from Abu Dhabi Urban Planning Council and the National Central Cooling Company (Tabreed) to derive an accurate estimate of the urban cooling load, the main driver of electricity consumption in the region. It was determined that, although only 30% of the annual load is directly weather dependent, air-conditioning explains no less than 57% of the total annual electricity load and 75% of the peak summer demand.