Crowdsourced Electricity Demand Forecast

We propose a new approach to forecasting the demand for a commodity in which the supplier asks each consumer to forecast its own demand in return for a monetary reward that is proportional to the accuracy of the forecast. Such an approach is applicable when demand for a perishable commodity is uncertain and forecast error leads to waste for suppliers. In this paper, we apply this approach to forecast residential electricity demand over 24 hours, i.e., short-term load forecasting (STLF). Accurate STLF is vital to meeting the large daily fluctuations in the demand for electricity in a reliable and economical way. Improving STLF accuracy can reduce the variable costs incurred by power system operators and energy retailers through more precise generation scheduling and energy purchasing. We propose a new method to model both the true demand profiles for individual residential electricity consumers, and their own forecasts of those demand profiles. This work is a first step in understanding interactions between the consumer-forecaster and the supplier-rewarder.