Big Data Analytics for Energy Consumption Prediction in Smart Grid Using Genetic Algorithm and Long Short Term Memory

Abstract

Smart Grids (SG) have smart meters and advance metering infrasturutre (AMI) which generates huge data. This data can be used for predicting energy consumption using big data analytics. A very limited work has been carried out in the literature which shows the utilization of big data in energy consumption prediction. In this paper, the proposed method is based on Genetic Algorithm -Long Short Term Memory (GA-LSTM). LSTM memorises values over an arbitrary interval that manages time series data very effictively while GA is an evolutionary process that is used for optimization. GA combines with LSTM to process hyperparameters such as hidden layers, epochs, data intervals, batchsize and activation functions. Hence, GA creates a new vector for optimum solution that provides minimum error. These methods provide the best performance when compared with existing benchmarks. Moreover, GA-LSTM is used in a multi-threaded environment which increases the speed of convergence. Here, the multi-core platform is operated for solving one-dimensional GA-based inverse scattering problems. The result shows that GA-LSTM provides better convergence as compared to random approach techniques. For validating the results, Pennsylvania-New Jersey-Maryland Interconnection (PJM) energy consumption data has been used while adopting different performance evaluation metrics.

Docking and Molecular Dynamics Simulations of Flavonoids as Inhibitors of Infectious Agents: Rutin as a Coronavirus Protease Inhibitor

“…Structure of the protein and the compounds was prepared using the module of “preparation molecule for docking.” By applying the “Detect cavities” module, appropriate locations on the receptor were determined to interact with the compounds. Grid resolution of 30 Å, maximum iteration of 1500, and maximum population size of 50 were set as docking parameters [21,22] . The internal ES (Internal electrostatic Interaction), sp2‐sp2 torsions, and the internal H‐bond interactions were set to evaluate the binding affinity and interactions of the compounds with the M pro .…”

“…Grid resolution of 30 Å, maximum iteration of 1500, and maximum population size of 50 were set as docking parameters. [21,22] The internal ES (Internal electrostatic Interaction), sp2-sp2 torsions, and the internal H-bond interactions were set to evaluate the binding affinity and interactions of the compounds with the M pro . Simplex evolution was set at maximum steps of 300 with a neighborhood distance factor of 1.…”

A multi-step electricity prediction model for residential buildings based on ensemble Empirical Mode Decomposition technique

“…Bourhnane et al [7] have implemented an energy prediction and scheduling approach for smart buildings using ANN and genetic algorithms. A big data analytics-based energy prediction model has been proposed by Kumari et al [26]. The LSTM model and the genetic algorithm have been applied to estimate the energy consumption of residential buildings.…”

A Method for Assessing the Security of Energy Trading Data Based on Big Data and the Pagerank Algorithm

“…Retaining the amount of information in the security assessment requirements dimension, on the basis of which it corresponds to a valid assessment factor [6][7][8]. First, in the information flow of any security assessment requirement in the energy transaction data space, let a be an individual numerator of a node in that information flow, then the transformation relationship c between an energy transaction data information node and its corresponding assessment numerator is calculated as equation ( 3):…”