Siew Eang Lee

Bio: Siew Eang Lee is an academic researcher from National University of Singapore. The author has contributed to research in topics: Energy consumption & Occupancy. The author has an hindex of 19, co-authored 38 publications receiving 2223 citations. Previous affiliations of Siew Eang Lee include Sungkyunkwan University.

A review on time series forecasting techniques for building energy consumption

Abstract: Energy consumption forecasting for buildings has immense value in energy efficiency and sustainability research. Accurate energy forecasting models have numerous implications in planning and energy optimization of buildings and campuses. For new buildings, where past recorded data is unavailable, computer simulation methods are used for energy analysis and forecasting future scenarios. However, for existing buildings with historically recorded time series energy data, statistical and machine learning techniques have proved to be more accurate and quick. This study presents a comprehensive review of the existing machine learning techniques for forecasting time series energy consumption. Although the emphasis is given to a single time series data analysis, the review is not just limited to it since energy data is often co-analyzed with other time series variables like outdoor weather and indoor environmental conditions. The nine most popular forecasting techniques that are based on the machine learning platform are analyzed. An in-depth review and analysis of the ‘hybrid model’, that combines two or more forecasting techniques is also presented. The various combinations of the hybrid model are found to be the most effective in time series energy forecasting for building.

A review on the prediction of building energy consumption

Abstract: The energy performance in buildings is influenced by many factors, such as ambient weather conditions, building structure and characteristics, the operation of sub-level components like lighting and HVAC systems, occupancy and their behavior. This complex situation makes it very difficult to accurately implement the prediction of building energy consumption. This paper reviews recently developed models for solving this problem, which include elaborate and simplified engineering methods, statistical methods and artificial intelligence methods. Previous research work concerning these models and relevant applications are introduced. Based on the analysis of previous work, further prospects are proposed for additional research reference.

Electrochromics for smart windows: thin films of tungsten oxide and nickel oxide, and devices based on these

Abstract: Electrochromic (EC) materials are able to change their optical properties, reversibly and persistently, by the application of an electrical voltage. These materials can be integrated in multilayer devices capable of modulating the optical transmittance between widely separated extrema. We first review the recent literature on inorganic EC materials and point out that today's research is focused on tungsten oxide (colouring under charge insertion) and nickel oxide (colouring under charge extraction). The properties of thin films of these materials are then discussed in detail with foci on recent results from two comprehensive investigations in the authors' laboratory. A logical exposition is obtained by covering, in sequence, structural features, thin film deposition (by sputtering), electronic band structure, and ion diffusion. A novel conceptual model is given for structural characteristics of amorphous W oxide films, based on notions of defects in the ideal amorphous state. It is also shown that the conduction band density of states is obtainable from simple electrochemical chronopotentiometry. Ion intercalation causes the charge-compensating electrons to enter localized states, implying that the optical absorption underlying the electrochromism can be described as ensuing from transitions between occupied and empty localized conduction band states. A fully quantitative theory of such transitions is not available, but the optical absorption can be modeled more phenomenologically as due to a superposition of transitions between different charge states of the W ions (6+, 5+, and 4+). The Ni oxide films were found to have a porous structure comprised of small grains. The data are consistent with EC coloration being a surface phenomenon, most likely confined to the outer parts of the grains. Initial electrochemical cycling was found to transform hydrated Ni oxide into hydroxide and oxy-hydroxide phases on the grain surfaces. Electrochromism in thus stabilized films is consistent with reversible changes between Ni hydroxide and oxy-hydroxide, in accordance with the Bode reaction scheme. An extension of this model is put forward to account for changes of NiO to Ni2O3. It was demonstrated that electrochromism is associated solely with proton transfer. Data on chemical diffusion coefficients are interpreted for polycrystalline W oxide and Ni oxide in terms of the lattice gas model with interaction. The later part of this review is of a more technological and applications oriented character and is based on the fact that EC devices with large optical modulation can be accomplished essentially by connecting W-oxide-based and Ni-oxide-based films through a layer serving as a pure ion conductor. Specifically, we treat methods to enhance the bleached-state transmittance by mixing the Ni oxide with other oxides characterized by wide band gaps, and we also discuss pre-assembly charge insertion and extraction by facile gas treatments of the films, as well as practical device manufacturing and device testing. Here the emphasis is on novel flexible polyester-foil-based devices. The final part deals with applications with emphasis on architectural “smart” windows capable of achieving improved indoor comfort jointly with significant energy savings due to lowered demands for space cooling. Eyewear applications are touched upon as well.

A review of data-driven building energy consumption prediction studies

Abstract: Energy is the lifeblood of modern societies. In the past decades, the world's energy consumption and associated CO 2 emissions increased rapidly due to the increases in population and comfort demands of people. Building energy consumption prediction is essential for energy planning, management, and conservation. Data-driven models provide a practical approach to energy consumption prediction. This paper offers a review of the studies that developed data-driven building energy consumption prediction models, with a particular focus on reviewing the scopes of prediction, the data properties and the data preprocessing methods used, the machine learning algorithms utilized for prediction, and the performance measures used for evaluation. Based on this review, existing research gaps are identified and future research directions in the area of data-driven building energy consumption prediction are highlighted.