Redills: Deep Learning-Based Secure Data Analytic Framework for Smart Grid Systems

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.

[1]  Christian Beecks,et al.  Incremental Deep-Learning for Continuous Load Prediction in Energy Management Systems , 2019, 2019 IEEE Milan PowerTech.

[2]  Sumit Kumar,et al.  Energy Load Forecasting using Deep Learning Approach-LSTM and GRU in Spark Cluster , 2018, 2018 Fifth International Conference on Emerging Applications of Information Technology (EAIT).

[3]  Sara Atef,et al.  Real-Time Load Consumption Prediction and Demand Response Scheme Using Deep Learning in Smart Grids , 2019, 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT).

[4]  Jie Gu,et al.  Short-term load forecasting using a long short-term memory network , 2017, 2017 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe).

[5]  Mohammad S. Obaidat,et al.  Fog Computing for Smart Grid Systems in the 5G Environment: Challenges and Solutions , 2019, IEEE Wireless Communications.

[6]  Sudeep Tanwar,et al.  Energy Optimization in Smart Grid using Tensor Decomposition , 2017 .

[7]  Ali Nauman,et al.  Smart Contract Privacy Protection Using AI in Cyber-Physical Systems: Tools, Techniques and Challenges , 2020, IEEE Access.

[8]  Wei-Chiang Hong,et al.  Machine Learning Adoption in Blockchain-Based Smart Applications: The Challenges, and a Way Forward , 2020, IEEE Access.

[9]  Radu Prodan,et al.  DRUMS: Demand Response Management in a Smart City Using Deep Learning and SVR , 2018, 2018 IEEE Global Communications Conference (GLOBECOM).

[10]  Yonghai Xu,et al.  Analysis and Accurate Prediction of User’s Response Behavior in Incentive-Based Demand Response , 2019, IEEE Access.

[11]  Pierluigi Mancarella,et al.  A short-term load forecasting model for demand response applications , 2014, 11th International Conference on the European Energy Market (EEM14).

[12]  Mohammad S. Obaidat,et al.  Data Consumption-Aware Load Forecasting Scheme for Smart Grid Systems , 2018, 2018 IEEE Globecom Workshops (GC Wkshps).

[13]  Sudeep Tanwar,et al.  Capacity Estimation of Electric Vehicle Aggregator for Ancillary Services to the Grid , 2019, Energy Conservation for IoT Devices.

[14]  Sachin Kumar,et al.  The Role of Internet of Things and Smart Grid for the Development of a Smart City , 2018 .

[15]  Ran Li,et al.  Deep Learning for Household Load Forecasting—A Novel Pooling Deep RNN , 2018, IEEE Transactions on Smart Grid.

[16]  Sudeep Tanwar,et al.  Machine Learning-based Voltage Dip Measurement of Smart Energy Meter , 2018, 2018 Fifth International Conference on Parallel, Distributed and Grid Computing (PDGC).

[17]  Anish Jindal.  Data Analytics of Smart Grid Environment for Efficient Management of Demand Response , 2018 .

[18]  Andrea Garulli,et al.  Models and Techniques for Electric Load Forecasting in the Presence of Demand Response , 2015, IEEE Transactions on Control Systems Technology.

[19]  Stefan Ungureanu,et al.  Industrial load forecasting using machine learning in the context of smart grid , 2019, 2019 54th International Universities Power Engineering Conference (UPEC).

[20]  Neeraj Kumar,et al.  Machine Learning Models for Secure Data Analytics: A taxonomy and threat model , 2020, Comput. Commun..

[21]  Patrick Hosein,et al.  Load forecasting using deep neural networks , 2017, 2017 IEEE Power & Energy Society Innovative Smart Grid Technologies Conference (ISGT).

[22]  Marimuthu Palaniswami,et al.  Improving load forecasting based on deep learning and K-shape clustering , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).