Journal of Intelligent Systems and Internet of Things JISIoT 2690-6791 2769-786X 10.54216/JISIoT https://www.americaspg.com/journals/show/744 2019 2019 University of Colombo, SRILANKA Navod Neranjan .. University of Colombo, SRILANKA Rohan .. Charles Sturt University, AUSTRALIA Mohan Krishna .. Stamford international university, THAILAND Surekha .. Gomal University, PAKISTAN; Hussain Ahmad In the 21st century, the Smart Grid (SG), also known as the next-generation power grid, arose as a substitute for inefficient power systems, ensuring a reliable and efficient power supply. It is projected to improve the reliability and efficiency of energy distribution while having minimal side effects because it is coupled with modern communication and computation capabilities. The huge infrastructure it possesses, as well as the system's underlying communication network, has resulted in a large number of data that necessitates the use of diverse approaches for proper analysis and decision making. When it comes to analyzing this huge amount of data and generating significant insights from it, big data analytics, machine learning (ML), and deep learning (DL), all play a key role. These insights are useful for anomaly detection, fraud detection, price confirmation, fault detection, monitoring energy consumption, and so on. Hence constant and continuous data analysis is an essential part, of the modern smart grid, for its existence. Inspired by providing a reliable and efficient energy distribution, this paper explores and surveys the smart grid architectural elements, ML and DL based applications, and approaches in the context of SG.  In addition in terms of ML and DL based data analytics, this paper highlights the limitations of the current research and, highlights future directions as well. 2021 2021 32 42 10.54216/JISIoT.030103 https://www.americaspg.com/articleinfo/18/show/744