No abstract

This paper proposes Artificial Neural Network (ANN) to determine adjusted baseline energy for quantifying energy savings from an energy efficiency program implemented in an office building. The input data to the ANN includes number of working days and cooling degree days (CDD) each month for one year period before implementation of the retrofitting program. On the other hand, output data is baseline energy use (i.e. energy use before retrofit). Since the input data to the network encompasses of 36 months set of data only, Bootstrap method is used to generate more input data without changing the input and output trend of the original data set. This is performed to increase validity of the training process. Once the optimum training parameters have been obtained, adjusted baseline energy is determined by feeding the number of working days and CDDs in the post-retrofit period (i.e. 12 months set of data) to the network. Energy savings is then calculated by comparing the adjusted baseline energy with the energy use after implementing the retrofit program. The performances of the ANN model are then compared with Multi-regression technique in term of R2, Mean Absolute Percentage Error (MAPE), Mean Square Error (MSE) and Mean Absolute Deviation (MAD). Results show that the proposed ANN model has smaller errors and R2 closer to one compare to Multi-regression technique.

This paper presents the concept of International Performance Measurement and Verification Protocol (IPMVP) for determining energy saving at whole facility level for an office building in Malaysia. Regression analysis is used to develop baseline model from a set of baseline data which correlates baseline energy with appropriate independents variables, i.e. Cooling Degree Days (CDD) and Number of Working Days (NWD) in this paper. In determining energy savings, the baseline energy is adjusted to the same set condition of reporting period using energy cost avoidance approach. Two types of energy saving analyses have been presented in the case study; 1) Single linear regression for each independent variable, 2) Multiple linear regression for each independent variable. Results show that NWD has coefficient of determination, R2 higher than CDD which indicates that NWD has stronger correlation with the energy use than CDD in the building. Finding also shows that the R2 for multiple linear regression model are higher than single linear regression model. This shows the fact that more than one component are affecting the energy use in the building.

The electrification prospect in some rural areas in Malaysia is limited because of no access to grid connection. This challenge has aroused concerns among researchers and energy providers in finding an alternative source of energy. A hybrid renewable energy system (HRES) deems as a good alternative to overcome the problem. This study employs a linear programming model in estimating socioeconomic and techno-economic analysis of HRES at Tanjung Labian. The target location is a residential area in Sabah, with the major source of income comes from timber as most of the residents are engaged in forestry activities. The socioeconomic evaluation of this study reveals the minimum values of expected demand not served (EDNS) and loss of load probability (LOLP) from the hybrid PV-diesel with battery configuration and the result contributes to the highest number of students who passed the examination. Additionally, the results of the study also reveal that hybrid PVdiesel with battery configuration is the most economical and most environmentally friendly system when it is compared to other configurations. The results of this work may encourage the adoption of a hybrid renewable energy system with a battery system by replacing and upgrading existing standalone diesel generators system in Malaysia.

This paper presents a development of Visual Basic based Graphical User Interface (GUI) for an improved of Measurement and Verification Protocol (M&V) Whole Facility framework to quantify an investment in energy savings considering risks. Monte Carlo simulations are presented to assess the risks of an Energy Conservation Measure (ECM) project. The proposed M&V framework produces a continuous range of savings and rate of return of the investment with associated probabilities instead of a single value assessment without margin of error. The GUI was tested for a commercial building using three different variables that are affecting the energy use: 1) Cooling Degree Days (CDD), 2) Number of Working Days (NWD) and 3) Multi-Variable that combining CDD and NWD. From the findings, it shows that the proposed Visual Basic based GUI of M&V with Monte Carlo simulation provides a more comprehensive overview of energy savings investment in a building.