Modeling and forecasting of cooling and electricity load demand

Abstract

h i g h l i g h t sWe propose a model for forecasting cooling and electricity load demand. The model takes the advantage of both time series and regression methods. The model is able to accurately forecast the load demands of the CCHP system. a r t i c l e i n f o t r a c tThe objective of this paper is to extend a statistical approach to effectively provide look-ahead forecasts for cooling and electricity demand load. Our proposed model is a generalized form of a Cochrane-Orcutt estimation technique that combines a multiple linear regression model and a seasonal autoregressive moving average model. The proposed model is adaptive so that it updates forecast values every time that new information on cooling and electricity load is received. Therefore, the model can simultaneously take advantage of two statistical methods, time series, and linear regression in an adaptive way. The effectiveness of the proposed forecast model is shown through a use case. The example utilizes the proposed approach for economic dispatching of a combined cooling, heating and power (CCHP) plant at the University of California, Irvine. The results reveal the effectiveness of the proposed forecast model.

Data-Driven Modeling, Control and Tools for Cyber-Physical Energy Systems

“…Several machine learning approaches [28,29,30] have been utilized before for forecasting electricity load including some which use regression trees. However, there are three significant shortcomings of the work in this area: (a) First, the time-scales at which the load forecasts are generated range from 15−20 min upto an hour; which is too coarse grained for DR events which only last for at most a couple of hours and for real-time electricity prices which exhibit frequent changes.…”

Application of improved artificial neural networks in short-term power load forecasting

“…[8][9][10][11][12][13] The traditional approaches, such as vector autoregressive (VAR) model 3,4 and autoregressive moving average (ARMA) model, [5][6][7] are mainly based on time series analysis. Liang 3 evaluated the effectiveness of VAR approaches for modeling the mean of the hourly load and effectively caught the trend change of the power load.…”

A Hybrid Physics-Based and Data Driven Approach to Optimal Control of Building Cooling/Heating Systems

“…To avoid this problem, we employ the Cochran-Orcutt technique by rewriting (13) as follows: (14) is an independent and identical white noise and is a function of past error terms representing the structure of an autocorrelation. Following [24], we obtain transformed variables: (15) where and are autoregressive operators with orders of and that are applied to both the external temperature and the vector of zonal effective power to find the building total energy demand. Hence, (14) is replaced by (16) This is a typical linear regression with independent error terms and parameters that can be estimated iteratively as proposed in [24].…”