This paper provides a comprehensive review of smart meter data analytics, focusing on its applications, methodologies, and challenges. Smart meters have become widespread, enabling the collection of fine-grained electricity consumption data. The deregulation of the power industry has increased the need to use this data to improve the efficiency and sustainability of the power grid. The paper reviews the three stages of data analytics: descriptive, predictive, and prescriptive. Key applications include load analysis, load forecasting, and load management. It discusses techniques and methodologies used for these applications, as well as research trends such as big data, machine learning, new business models, energy system transitions, and data privacy and security. The paper also presents a bibliometric analysis of smart meter data analytics research, showing an increase in publications since 2010. It reviews several existing review articles and highlights the challenges and opportunities in energy data analytics, particularly in terms of privacy and security. Open load datasets are discussed, including those from various projects and initiatives. The paper also presents a taxonomy of smart meter data analytics applications, categorizing them into load analysis, load forecasting, and load management. It discusses the main machine learning techniques used in smart meter data analytics, including time series, dimensionality reduction, clustering, classification, outlier detection, deep learning, and others. The paper identifies key contributions, including a comprehensive literature review of smart meter data analytics on the demand side, a well-designed taxonomy for smart meter data analytics applications, and discussions of open research questions for future research directions. The paper is organized into sections covering load analysis, load forecasting, and load management, as well as other miscellaneous topics and future research issues. It concludes with a summary of the key findings and challenges in smart meter data analytics.This paper provides a comprehensive review of smart meter data analytics, focusing on its applications, methodologies, and challenges. Smart meters have become widespread, enabling the collection of fine-grained electricity consumption data. The deregulation of the power industry has increased the need to use this data to improve the efficiency and sustainability of the power grid. The paper reviews the three stages of data analytics: descriptive, predictive, and prescriptive. Key applications include load analysis, load forecasting, and load management. It discusses techniques and methodologies used for these applications, as well as research trends such as big data, machine learning, new business models, energy system transitions, and data privacy and security. The paper also presents a bibliometric analysis of smart meter data analytics research, showing an increase in publications since 2010. It reviews several existing review articles and highlights the challenges and opportunities in energy data analytics, particularly in terms of privacy and security. Open load datasets are discussed, including those from various projects and initiatives. The paper also presents a taxonomy of smart meter data analytics applications, categorizing them into load analysis, load forecasting, and load management. It discusses the main machine learning techniques used in smart meter data analytics, including time series, dimensionality reduction, clustering, classification, outlier detection, deep learning, and others. The paper identifies key contributions, including a comprehensive literature review of smart meter data analytics on the demand side, a well-designed taxonomy for smart meter data analytics applications, and discussions of open research questions for future research directions. The paper is organized into sections covering load analysis, load forecasting, and load management, as well as other miscellaneous topics and future research issues. It concludes with a summary of the key findings and challenges in smart meter data analytics.