A Novel Accurate and Fast Converging Deep Learning-Based Model for Electrical Energy Consumption Forecasting in a Smart Grid

Abstract

Energy consumption forecasting is of prime importance for the restructured environment of energy management in the electricity market. Accurate energy consumption forecasting is essential for efficient energy management in the smart grid (SG); however, the energy consumption pattern is non-linear with a high level of uncertainty and volatility. Forecasting such complex patterns requires accurate and fast forecasting models. In this paper, a novel hybrid electrical energy consumption forecasting model is proposed based on a deep learning model known as factored conditional restricted Boltzmann machine (FCRBM). The deep learning-based FCRBM model uses a rectified linear unit (ReLU) activation function and a multivariate autoregressive technique for the network training. The proposed model predicts future electrical energy consumption for efficient energy management in the SG. The proposed model is a novel hybrid model comprising four modules: (i) data processing and features selection module, (ii) deep learning-based FCRBM forecasting module, (iii) genetic wind driven optimization (GWDO) algorithm-based optimization module, and (iv) utilization module. The proposed hybrid model, called FS-FCRBM-GWDO, is tested and evaluated on real power grid data of USA in terms of four performance metrics: mean absolute percentage deviation (MAPD), variance, correlation coefficient, and convergence rate. Simulation results validate that the proposed hybrid FS-FCRBM-GWDO model has superior performance than existing models such as accurate fast converging short-term load forecasting (AFC-STLF) model, mutual information-modified enhanced differential evolution algorithm-artificial neural network (MI-mEDE-ANN)-based model, features selection-ANN (FS-ANN)-based model, and Bi-level model, in terms of forecast accuracy and convergence rate.

Machine learning‐based energy efficient technologies for smart grid

“…The enhanced driving force behind the smart grid implementation is to ensure that traditional and renewable energy is produced stably, safely, effectively, economically, and sustainable 5 . A smart grid will provide generators, distributors, and consumers with the following benefits: network stability, demand management, empowering consumers, network reliability, and integration of renewable energy resources 6 . The most protruding renewable energy source is solar energy 7 .…”

“…It is up to the users to use the power sensibly, that is, not to overly enable the system 22 . On the other hand, the device itself should predict when not in use and switch as soon as possible to sleep mode 6,23,24 …”

“…22 On the other hand, the device itself should predict when not in use and switch as soon as possible to sleep mode. 6,23,24 Machine learning is an artificial intelligence branch, in which machines automatically learn from data without direct human involvement. 25 Machine learning algorithms represent techniques that seek patterns and interactions within the data and construct a system that predicts these patterns and interrelations.…”

Distributed Energy Resources and the Application of AI, IoT, and Blockchain in Smart Grids

“…A variety of hybrid forecasting approaches are used to increase predictive accuracy. DL is a subset of ML that has deeper inner hidden layers cascaded into the network, which initially occasioned from a multi-layer ANN [124][125][126].…”

<strong>Online Sequential Extreme Learning Machine: A New Training Scheme for Restricted Boltzmann Machines</strong>

“…In RBM network, each node from the visible layer is connected to every node in the hidden layer. An RBM is considered restricted because no two nodes in the same layer are sharing connections [1]. In the forward pass, the RBM iteratively takes a set of inputs and translate them into a set of number that encodes the input.…”