Abstract
Over the last decades, load forecasting is used by power companies to balance energy demand and supply. Among the several load forecasting methods, medium-term load forecasting is necessary for grid’s maintenance planning, settings of electricity prices, and harmonizing energy sharing arrangement. The forecasting of the month ahead electrical loads provides the information required for the interchange of energy among power companies. For accurate load forecasting, this paper proposes a model for medium-term load forecasting that uses hourly electrical load and temperature data to predict month ahead hourly electrical loads. For data preprocessing, modified entropy mutual information-based feature selection is used. It eliminates the redundancy and irrelevancy of features from the data. We employ the conditional restricted Boltzmann machine (CRBM) for the load forecasting. A meta-heuristic optimization algorithm Jaya is used to improve the CRBM’s accuracy rate and convergence. In addition, the consumers’ dynamic consumption behaviors are also investigated using a discrete-time Markov chain and an adaptive k-means is used to group their behaviors into clusters. We evaluated the proposed model using GEFCom2012 US utility dataset. Simulation results confirm that the proposed model achieves better accuracy, fast convergence, and low execution time as compared to other existing models in the literature.
Highlights
In the energy sector, load forecasting assists the utility to estimate the energy needed to balance energy supply and demand
In mutual information (MI)-based feature selection (FS) process of [21], the downsized inputs do not further reduce the training time; here, information loss is observed. This is due to the unstable convergence of the modified enhanced differential evolution algorithm (mEDE) and inefficiency of the model to train on massive amount of data
Many methods of Medium-term load forecasting (MTLF) exist in the literature that focus on the forecasting of daily peak load, daily energy consumption, and annual peak load consumption
Summary
Load forecasting assists the utility to estimate the energy needed to balance energy supply and demand. Load forecasting provides information that is used for easy energy interchange with other utilities. Long-term load forecasting (LTLF) of more than a year ahead is required to determine the grid’s regulatory policies and prices as well as the planning and construction of new electricity generation capacity. Short-term load forecasting (STLF) of a few hours to couple of weeks ahead is required for economic planning of electricity generation capacity, security analysis, fuel purchases and short-term maintenance of grid. Very short-term load forecasting (VSTLF) of a few minutes to couple of hours ahead is required for real-time evaluation of security and Entropy 2020, 22, 68; doi:10.3390/e22010068 www.mdpi.com/journal/entropy. Medium-term load forecasting (MTLF) of few weeks to couple of months ahead is required for grid’s maintenance planning, settings of electricity prices and harmonization of the energy sharing arrangement. We propose a MTLF method especially for month ahead load forecasting
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
