Indonesian Journal of Electrical Engineering and Computer Science Vol. 8, No. 2, November 2017, pp. 399 ~ 406 DOI: 10.11591/ijeecs.v8.i2.pp399-406  399 Received July 29, 2017; Revised September 30, 2017; Accepted October 14, 2017 Online Performance Monitoring of Grid-Connected Photovoltaic System using Hybrid Improved Fast Evolutionary Programming and Artificial Neural Network Puteri Nor Ashikin Megat Yunus 1 , Shahril Irwan Sulaiman 2 , Ahmad Maliki Omar 3 Faculty of Electrical Engineering Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia. *Corresponding author, e-mail: pu3kibi@yahoo.com 1 , shahril_irwan2004@yahoo.com 2 , ambomaliki@gmail.com 3 Abstract This paper presents the development of online performance monitoring methods for grid- connected photovoltaic (GCPV) system based on hybrid Improved Fast Evolutionary Programming and Artificial Neural Network (IFEP-ANN). The approach has been developed and validated using previous predicted data measurement. Solar radiation (SR), module temperature (MT) and ambient temperature (AT) has been employed as the inputs, and AC output power (PAC) as the sole output to the neural network model. The actual data from the server has been called and uploaded every five minute interval into Matlab by using FTP (File Transfer Protocol) and the predicted AC output power has been produced based on the prediction developed in the training stages. It is then compared with the actual AC output power by using Average Test Ratio, AR. Any predicted AC output power less than the threshold set up, indicates an error has been occurred in the system. The obtained results show that the hybrid IFEP-ANN gives good performance by producing a sufficiently high correlation coefficient, R value of 0.9885. Besides, the proposed technique can analyse and monitor the system in online mode. Keywords: PV (photovoltaic); ANN (Artificial Neural Network); RMSE (Root Mean Square Error); AR (Average Test Ratio); FTP (File transfer protocol) Copyright © 2017 Institute of Advanced Engineering and Science. All rights reserved. 1. Introduction Grid connected photovoltaic (PV) system becomes an important part of the electrical system around the world, especially in more developed countries. The substantial growth of the global PV market is still expected due to strong PV technology prices and the increase in electricity prices generated by conventional resources along with the clear advantages of green energy and renewable as PV on delivering safe and clean energy. However, the number of monitored PV system is not aligned with the growing trend, as more PV plants, especially the smaller ones, which operating without proper monitoring system [1]. Most of the PV systems operating without any supervisory mechanism, especially PV systems for output power below than 25 kWp. Perhaps the reason is that monitoring systems are only implemented in large PV generators, where it represents a very small increase in the overall price of the system, but without the help of a minimum monitoring system, it is impossible to develop any effective supervision, diagnostic or control of the PV systems [2]. Nowadays, many techniques are developed to monitor PV systems. The conventional wired monitoring system provides reliable solutions in data transmission but have some limitations [3]. Besides, the physical constraints when placing data cables and the use of these cables also increases the cost of installation and maintenance. Hardware implementation also have been proposed in monitoring system [4-7]. However, all these proposed methods need additional device and also tend to increase the cost. Some researcher used cable Ethernet in their proposed system. Dhimish in [8] proposed six monitoring subsystem which composed of Arduino Ethernet to send the data from the maximum power point tracker to the server/PC. This method utilizes IoT technology to integrate PV and environmental data monitoring. The same method also proposed in [9] which