On stochastic heating load prediction

The authors previously (1991) derived the density function of the duty cycle of a residential thermostat-controlled heating unit using a physically based stochastic load model. In this paper they use this density function to determine the maximum likelihood duty cycle using real data. This duty cycle is used to predict the energy demand of a space conditioning load. The prediction is found to track the actual duty cycle much better than deterministic and steady-state duty cycles.<
>