Load estimation for microgrid planning based on a self-organizing map methodology
read more
Citations
Computational Intelligence Approaches for Energy Load Forecasting in Smart Energy Management Grids: State of the Art, Future Challenges, and Research Directions
Machine Learning and Deep Learning in smart manufacturing: The Smart Grid paradigm
Computational intelligence approaches for energy load forecasting in smart energy management grids: state of the art, future challenges, and research directionsand Research Directions
Hybrid soft computing approach based on clustering, rule mining, and decision tree analysis for customer segmentation problem: Real case of customer-centric industries
Day-ahead spatio-temporal forecasting of solar irradiation along a navigation route
References
The self-organizing map
Trends in Microgrid Control
Clustering of time series data-a survey
Demand side management: Benefits and challenges ☆
Self organization of a massive document collection
Related Papers (5)
Frequently Asked Questions (2)
Q2. What have the authors stated for future works in "Load estimation for microgrid planning based on a self-" ?
The main contribution is the proposed methodology based on clustering algorithms that utilize information about similar 452 communities that have a permanent electricity supply to estimate the future load profiles of families without a current permanent 453 supply. An SOM 456 enables the automatic presentation of a map in which an intuitive description of the similarities among the data can be observed 457 and the distance between two neighborhoods can be calculated. However, for k-means, a 459 sensitivity step can be subsequently performed to determine the appropriate cluster number, which requires greater 460 computational effort. The estimated profiles were used in the planning of a microgrid that is in the design stages ; the results can be 464 validated with actual data when the grid becomes operational.