Title: Signal processing approach to forecasting seasonal load in electricity markets
Authors: Ritvana Rrukaj - NTNU: Norwegian University of Science and Technology (Norway) [presenting]
Abstract: Medium-term load forecasting is a critical tool utilized by power market system operators for system planning and load-serving entities for procuring power supply contracts. Techniques from the field of signal processing are employed to model seasonal load in the New York wholesale electricity market (NYISO). We begin by using mathematical filtration techniques to smooth raw NYISO load and price data that spans 2006 to 2018. The resulting filtered data series express load and prices as percentage deviations from their annual moving averages. Next, we develop a nonlinear load model in price and time by using the 90-day moving averages of the filtered price and load data and time-dependent periodic terms to capture the cyclicality of the load. In the final step, we model the noisy residuals using an autoregressive (AR) process. We conclude by performing out-of-sample forecasts of our model using test data from 2019 and 2020. The forecasting results reveal that our model can predict seasonal load with a high degree of accuracy and potentially assist market participants with their medium-term planning objectives.