This paper highlights a new approach using high-quality ground measured data to forecast the hourly power output values for grid-connected photovoltaic (PV) systems located in the tropics. A case study using the 1-year database consisting of PV power output, global irradiance, module temperature, and other relevant variables obtained from Universiti Teknikal Malaysia Melaka is used to develop forecast models for three typical weather conditions—clear, cloudy, and overcast sky conditions. A machine learning method (Support Vector Regression—SVR) and an Artificial Neural Network method (nonlinear autoregressive) are used to produce the models and the results are compared with a benchmark model using the persistence method. Comparison with all the variables suggests that tilted global horizontal irradiance (GHItilt) and module temperature (Tmod) are the essential input variables to forecast the PV power output. It has also been observed that SVR performs well across all types of sky conditions, with the forecasting skill values between 0.65 and 0.79 when compared to the benchmark persistence method.

No abstract

This paper proposed a new swarm-based optimization technique for tuning conventional proportional-integral (PI) controller parameters of a static var compensator (SVC) which controls a synchronous generator in a single machine infinite bus (SMIB) system. As one of the Flexible Alternating Current Transmission Systems (FACTS) devices, SVC is designed and implemented to improve the damping of a synchronous generator. In this study, two parameters of PI controller namely proportional gain, K_P and integral gain, K_I are tuned with a new optimization method called Whale Optimization Algorithm (WOA). This technique mimics the social behavior of humpback whales which is characterized by their bubble-net hunting strategy in order to enhance the quality of the solution. Validation with respect to damping ratio and eigenvalues determination confirmed that the proposed technique is more efficient than Evolutionary Programming (EP) and Artificial Immune System (AIS) in improving the angle stability of the system. Comparison between WOA, EP and AIS optimization techniques showed that the proposed computation approach gives better solution and faster computation time.

Electricity bill is one of the major operating expenses in most of the commercial buildings and industrial plants. Thus, the buildings’ energy management system is an essential element that should be utilized to optimize the energy usage and hence, contributes to carbon footprint reduction. To achieve this, one needs to first understand how the energy is being used in the buildings before any saving measures can be identified and proposed. Therefore, this paper presents the development of an Internet of Things (IoT) enabled device that can communicate with different digital energy meters through modbus protocol. The prototype has been successfully installed in three locations in the main campus of Universiti Teknikal Malaysia Melaka (UTeM). The proposed solution enables the campus-wide energy usage to be monitored and stored efficiently and economically as opposed to the capital-intensive SCADA system.