Year-end Sale % OFF 
Abstract
Peak load demand forecasting is important in building unit sectors, as climate change, technological development, and energy policies are causing an increase in peak demand. Thus, accurate peak load forecasting is a critical role in preventing a blackout or loss of energy. This paper presents a study forecasting peak load demand for an institutional building in Seoul. The dataset were collected from campus area consisting of 23 buildings. ARIMA models, ARIMA-GARCH models, multiple seasonal exponential smoothing, and ANN models are used. We find an optimal model with moving window simulations and step-ahead forecasts. Also, including weather and holiday variables is crucial to predict peak load demand. The ANN model with external variables (NARX) worked best for 1-h to 1-d ahead forecasting.
Highlights
Peak load demand forecasting is a critical issue at the national scale for smaller-scale building units (Yao et al, 2003; Kavousian et al, 2013)
The Auto Regressive Integrated Moving Average (ARIMA)-General ARCH (GARCH) model is defined as φp (l) ΦP (1 − l)d (1 − ls)D yt = c + θq (l) ΘQ εt εt = zt σt, zt ∼ i.i.d. with E = 0, Var = 1 q p σt2 = a0 + ∑ aiσt2−i + ∑ bjσt2−j i=1 j=1 where yt and polynomial components represent those as defined in Model 3.1. p is the order of GARCH process, q is the order of autoregressive conditional heteroskedasticity (ARCH) process. a0, ai and bj are constants, εt is the error term, σt2 is the conditional variance of εt, zt is a standardized error term
K ψt = (1 − l)d (1 − ls)D yt − ∑ βi (1 − l)d (1 − ls)D xti i=1 where yt is the original series before differencing, γ is a matrix of constants, ωt is a matrix of error terms and conditional variance, βi is the coefficient of predictors χti, and the other components are the same as those in Reg-ARIMA model and ARIMA-GARCH model
Summary
Peak load demand forecasting is a critical issue at the national scale for smaller-scale building units (residential, commercial, and industrial) (Yao et al, 2003; Kavousian et al, 2013). It was reported that the government of Korea made a decision in 8th basic Plan for Power Supply and Demand to reduce coalfired and nuclear plant capacity and replace with RE and LNG, based on the results of the predicted demand, that is expected to decrease from a long-term point of view (Ministry of Trade, 2017) This affects a country’s policies and economy, and environmental conventions such as reducing fine dust and carbon dioxide emissions worldwide. After a review of the variable prediction studies, we compared the effectiveness of forecasting peak load demand for an institutional building using statistical and artificial intelligence (AI)-based models under various scenarios including exogenous variables.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
