About this Virtual Instructor Led Training (VILT)

This 5 half-day Virtual Instructor Led Training (VILT) course is focused on load forecasting in the power industry, a critical aspect of managing electricity generation and distribution with a focus on key areas described  as follows:

Load Forecasting: The course presents advanced load forecasting techniques, which are essential for predicting electricity demand accurately. Load forecasting is critical for grid management and resource planning across all forecasting time horizons. Temporal Granularity: Some regions have transitioned to load forecasts with finer temporal granularity, moving beyond hourly predictions. This shift aims to reduce forecasting uncertainties and improve real-time grid management and generate improved hybrid methodologies Frequency of Updates: As the operation of electric grids becomes more complex, there's a need for more frequent updates in load forecasts, due to the increased penetration of inverter-based resources, which can vary in output rapidly. Weather Sensitivity Analysis: The course examines how weather conditions impact load forecasts. It covers weather sensitivity analysis, which quantifies the influence of meteorological factors on electricity demand. It presents the weather impacts on the load forecasts and the methodologies employed to quantify the weather effect and building a repository of weather normal data. Statistical and Mathematical Models: The course delves into the application of statistical and mathematical models for load forecasting. These models often include time series analysis, regression analysis, and other mathematical tools to make predictions. Artificial Intelligence and Machine Learning (AI/ML): The course highlights the integration of AI and ML techniques in load forecasting. Machine learning algorithms are used for data-driven predictions and pattern recognition, improving forecast accuracy. Grid Complexity: As the power grid becomes more complex due to increased penetration of renewable and inverter-based resources, load forecasts require higher temporal resolution and adaptability to changing conditions. Practical Applications-Industry Examples: It emphasizes practical applications of forecasting methods, supported by real-life examples from large control areas in North America, Australia, Europe. This approach helps professionals understand how to apply these methods effectively. This seminar has a Guest Speaker to provide insights into the most modern aspects of Artificial Intelligence.