Electrical power demands have increased significantly over the last years due to rapid increase in air conditioning units and home appliances per domestic unit, particularly in Iraq. Having an uninterrupted power supply is essential for the continuity of power-generated home services and industrial platforms. Currently, in Iraq, electrical power interruption has become a big concern to the utility suppliers. Despite successive attempts to put an end to this dilemma, the issue still prevails. One of the main factors in power outages in local zones is persistent faults in distribution transformers (DTs). DT is considered one of the main elements in the electrical network that is essential for the reliability of the grid supply. Due to the internal lack of monitoring system and periodic maintenance, DT is relentlessly subject to faults due to high overhead utilization. Therefore, in order to enhance the grid reliability, transformer health check, and maintenance practices, we propose a remote condition Internet of Things monitoring and fault prediction system that is based on a customized software-defined networking (SDN) technology. This approach is a transition to smart grid implementation by fusing the power grid with efficient and real-time wireless communication architecture. The SDN implementation is considered in two phases: one is a controller installed per local zone and the other is the main controller that is installed between zones and connected to the core network. The core network consists of redundant links to recover from any future fails. Furthermore, we propose a prediction system based on an artificial neural network algorithm, called distribution transformer fault prediction, that is installed in the management plane for periodic prediction based on real-time sensor traffic to our proposed cloud. Moreover, we propose a communication protocol in the local zone called local SDN-sense. The SDN-sense ensures a reliable communication and local node selection to relay DT sensor data to the main controller. Our proposed architecture showcases an efficient approach to handle future interruption and faults in power grid using cost-effective and reliable infrastructure that can predict and provide real-time health monitoring indices for the Iraqi grid network with minimal power interruptions. After extensive testing, the prediction accuracy was about 96.1%.