Short-Term Energy Forecasting Framework Using an Ensemble Deep Learning Approach

Abstract

Industrial and building sectors demand efficient smart energy strategies, techniques of optimization, and efficient management for reducing global energy consumption due to the increasing world population. Nowadays, various artificial intelligence (AI) based methods are utilized to perform optimal energy forecasting, different simulation tools, and engineering methods to predict future demand based on historical data. Nevertheless, nonlinear energy demand modeling is still unfledged for a better solution to handle short-term and long-term dependencies and avoid static nature because it is purely on historical datadriven. In this paper, we propose an ensemble deep learning-based approach to predict and forecast energy demand and consumption by using chronological dependencies. Our system initially processes the data, cleaning, normalization, and transformation to ensure the model performance. Furthermore, the preprocess data is fed to propose the ensemble model to extract hybrid discriminative features by using convolution neural network (CNN), stacked, and bi-directional long-short term memory (LSTM) architectures. We trained our proposed system on the historical data to forecast the energy demand and consumption with a different time interval. In the proposed technique, we utilized the concept of active learning based on moving windows to ensure and improve the prediction performance of the system. The proposed system could be applicable to employ energy consumption in industrial and building sectors to demonstrate their significance and effectiveness. We evaluated the proposed system by using benchmark, residential UCI, and local Korean commercial building datasets. We conducted different extensive experimentation to show the error rate and used various kinds of evaluation matrices, which indicate the lower error rate of the proposed system.

The Attitudes of K–12 Schools’ Teachers in Serbia towards the Potential of Artificial Intelligence

“…We have found similarities in the results obtained from the other studies we have analysed [44][45][46]. McKinsey's study showed, similar to ours, that teachers save the most time when they use technology to do their pre-class preparations, which are the most time-consuming tasks [35].…”

“…Many fields, such as forensic science [45], customer service call review and analysis, mental health surveillance, intelligent systems, and educational quality evaluations, pay greater attention to speechbased emotion identification tasks. Deep learning has made it easier to detect emotions in speech, but there are still issues with the study on SER, such as a lack of training data and an insufficient model [46,47]. Speech real-time emotion depends on speakers, cultures, genders, ages, and dialects [48].…”

The Efficacy of Deep Learning-Based Mixed Model for Speech Emotion Recognition

“…In particular, the use of deep learning algorithms shows promising in solving recognition or detection challenges such as speech recognition, emotion recognition, face recognition, gesture recognition, and object detection [19]. Nowadays, in addition to the single deep learning model, the hybrid ensemble deep learning model [18,20] is being used in a growing number of research studies. In this regard, the researchers have used several models for emotion recognition, including Convolution Neural network, Deep Belief Network (DBN), Recurrent Neural Networks (RNNs), and Long Short-Term Memory (LSTM) [2,5,7,8].…”

Deep learning-based load forecasting considering data reshaping using MATLAB\Simulink

“…Some of these studies [33] added the impact of COVID-19 on load forecasting using lockdown information as another sequence input. Others [40] use bidirectional LSTM as a learning component. Concerning the previous studies applied to the test data of Kurdistan regional load demand, several studies [46,47] are present.…”