Deep Learning Approach Cum Aggregated Smart Meter Data Based Residential Energy Load Modeling

• Author(s): K. Indhumathi ; Mr. J. Shanmugasundaram ; S. Sivaranjani
• Paper ID: 1701951
• Page: 158-163
• Published Date: 27-02-2020
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 3 Issue 8 February-2020

Abstract

Conventional load forecasting dedicated to the quantity of load growth. The target of spatial load forecasting would be to estimate with reasonable accuracy, and a advanced level of geographic resolution, not just the quantity of load growth, but additionally when and where new load will effective locations for distribution facilities and to plan system growth (e.g., new substations, distribution feeders, transformers, and so on). Spatial load forecasting is conducted on the foundation of small areas, historical load and weather data, land use, and geographic information. The proposed forecasting methods are classified into two major categories: (i) Univariate (time series) forecasting models and (ii) Multivariate forecasting models. The forecasting data classified and analyzed by utilizing Support Vector Machine algorithm. Comparative analysis of those methods can be done in this survey. Furthermore, the forecasting techniques are reviewed from the areas of big data and conventional data by utilizing deep learning approach.

Keywords

SVM (Support Vector Machine), Spatial Load Forecasting and Deep Learning

Citations

IRE Journals:
K. Indhumathi , Mr. J. Shanmugasundaram , S. Sivaranjani "Deep Learning Approach Cum Aggregated Smart Meter Data Based Residential Energy Load Modeling" Iconic Research And Engineering Journals Volume 3 Issue 8 2020 Page 158-163

IEEE:
K. Indhumathi , Mr. J. Shanmugasundaram , S. Sivaranjani "Deep Learning Approach Cum Aggregated Smart Meter Data Based Residential Energy Load Modeling" Iconic Research And Engineering Journals, 3(8)