Redills: Deep Learning-Based Secure Data Analytic Framework for Smart Grid Systems
| Autor: | Aparna Kumari, Sudeep Tanwar, Rajesh Gupta, Darshan Vekaria |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Consumption (economics)
business.industry Computer science Deep learning 05 social sciences 050801 communication & media studies Energy consumption Reliability engineering Demand response 0508 media and communications Smart grid 0502 economics and business Production (economics) 050211 marketing Electricity Artificial intelligence business Energy (signal processing) |
| Zdroj: | ICC Workshops |
| DOI: | 10.1109/iccworkshops49005.2020.9145448 |
| Popis: | With the increasing demand for electricity and the smart grids (SG) systems, it becomes essential for them to realize the need for accurate energy demand at the demand response management (DRM). It directly impacts the consumer's lifestyle and also helps to reduce the electricity bill. Motivated from these facts, This paper proposes a priority analyzer to determine energy usage in the best time-slots. By employing a time-of-use (ToU) based data analytic approach, this paper predicts energy load expectation and gives analysis for the economical use of electrical appliances to reduce bills (Redills). The Redills offers a solution to the requirements of the user to save energy at the demand side and reduce energy production at the supply side of the DRM system. Redills accurately predicts the future load consumption based on the historical data using deep learning (DL)-based LSTM model, and then passes the prediction to the priority analyzer system to generate the monthly and season based priority list of ToU. Based on the time-slot priority list, the consumer can use the devices in the effective time slots for the economical use of the appliance. The simulation results show that Redills predicts energy consumption more accurately as compared to the state-of-art approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|