An ensemble-based enhanced short and medium term load forecasting using optimized missing value imputation.

Area of Science:

• Energy Systems
• Machine Learning
• Data Science

Background:

• Effective electricity load forecasting is essential for utility companies' operational planning, energy management, and market participation.
• Accurate predictions of electricity usage are vital for meeting customer demand and optimizing energy distribution.
• Existing forecasting methods may be limited by data quality issues, such as missing values.

Purpose of the Study:

• To develop and validate a novel electricity load forecasting model using the ensemble voting regressor method.
• To introduce an imputation technique for handling missing values in energy consumption data to improve forecast accuracy.
• To compare the proposed model's performance against state-of-the-art methods using real-time data.

Main Methods:

• An ensemble voting regressor model was implemented for electricity load forecasting.
• A new imputation method was developed and validated for addressing missing data in energy consumption datasets.
• The imputation method's effectiveness was tested using simulated missing data at rates of 10-30% on a real-time dataset.
• Performance was evaluated using metrics such as Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE).

Main Results:

• The proposed imputation method effectively handled missing values in energy consumption data across various missing rates.
• The ensemble voting regressor forecasting model demonstrated significant improvements in prediction accuracy compared to other methods.
• The model achieved superior performance in forecasting electricity load for day-ahead and week-ahead consumption.

Conclusions:

• The developed imputation method enhances the reliability of energy consumption data for forecasting.
• The ensemble voting regressor model offers a robust and accurate solution for electricity load forecasting.
• This methodology provides utility companies with improved tools for energy management and planning.