A Review on the Prediction of Energy Consumption in the Industry Sector Based on Machine Learning Approaches

Bahij, Mouad; Labbadi, Moussa; Cherkaoui, Mohamed; Chatri, Chakib; Elkhatiri, Ali; Elouerghi, Achraf

doi:10.1109/isaect53699.2021.9668559

Cited by 5 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM and ANN provided more reliable results in terms of root mean square error (RMSE) than MLR and adaptive neuro-fuzzy inference system for long- and short-term electricity demand forecasting in Cyprus [ 11 ]. MLR performed best with a lower mean absolute percentage error (MAPE) than other ML algorithms for predicting energy consumption in industry in Morocco [ 12 ]. Deep Learning algorithms have been shown to improve the prediction performance of machine tool energy [ 13 ] and building cooling load [ 14 ] compared to popular techniques used in previous studies in the same fields.…”

Section: Introductionmentioning

confidence: 99%

Digital twin with augmented state extended Kalman filters for forecasting electric power consumption of industrial production systems

Baldassarre,

Dion,

Peyret

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Digital twin with augmented state extended Kalman filters for forecasting electric power consumption of industrial production systems

Baldassarre,

Dion,

Peyret

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…Accurate consumption forecasting improves grid operations and power system planning, and it also has major repercussions on the environment and the economy, like diminishing power dissipate and hastening the decarbonization of the power precinct. Despite established models, estimating residential electric consumption is difficult owing to tenants' unpredictability [13] [14]. The pursuit of a model that can deliver precise energy forecasts is ongoing.…”

Section: Introductionmentioning

confidence: 99%

Context-Aware Clustering and the Optimized Whale Optimization Algorithm: An Effective Predictive Model for the Smart Grid

Ahire

Patil

2023

IJRITCC

View full text Add to dashboard Cite

For customers to participate in key peak pricing, period-of-use fees, and individualized responsiveness to demand programmes taken from multi-dimensional data flows, energy use projection and analysis must be done well. However, it is a difficult study topic to ascertain the knowledge of use of electricity as recorded in the electricity records' Multi-Dimensional Data Streams (MDDS). Context-Aware Clustering (CAC) and the Optimized Whale Optimization Algorithm were suggested by researchers as a fresh power usage knowledge finding model from the multi-dimensional data streams (MDDS) to resolve issue (OWOA). The proposed CAC-OWOA framework first performs the data cleaning to handle the noisy and null elements. The predictive features are extracted from the novel context-aware group formation algorithm using the statistical context parameters from the pre-processed MDDS electricity logs. To perform the energy consumption prediction, researchers have proposed the novel Artificial Neural Network (ANN) predictive algorithm using the bio-inspired optimization algorithm called OWOA. The OWOA is the modified algorithm of the existing WOA to overcome the problems of slow convergence speed and easily falling into the local optimal solutions. The ANN training method is used in conjunction with the suggested bio-inspired OWOA algorithm to lower error rates and boost overall prediction accuracy. The efficiency of the CAC-OWOA framework is evaluated using the publicly available smart grid electricity consumption logs. The experimental results demonstrate the effectiveness of the CAC-OWOA framework in terms of forecasting accuracy, precision, recall, and duration when compared to underlying approaches.

show abstract

“…Moreover, the analysis and exact forecasting of energy consumption utilizing multi-dimensional data streams are vital for consumer participation in time-of-use tariffs, critical peak pricing, and user-specific demand response operations. Achieving accurate consumption forecasts helps to enhance power system planning and ensure dependable grid operations, in addition to having significant economic and environmental repercussions, such as reducing energy waste and accelerating the decarbonisation of the energy sector Energy consumption forecasting is a prominent issue in research; despite the availability of proven models, estimating electric consumption in residential buildings remains difficult due to the unpredictability of tenant energy use behavior [13] [14]. As a result, the search for an appropriate model for making exact predictions about energy usage continues.…”

mentioning

confidence: 99%

CAC-WOA: context aware clustering with whale optimization algorithm for knowledge discovery from multidimensional space in electricity application

Ahire

Patil

2023

Cluster Comput

View full text Add to dashboard Cite

Due to the widespread use of smart metering infrastructure, multidimensional data on home electric consumption is easily available for studying its dynamics at finely resolved geographical and temporal scales. Effective forecasting and analysis of electric consumption are crucial for customer participation in time-of-use tariffs, critical peak pricing, and userspecific demand response programs derived from multidimensional data streams. Along with the enormous economic and sustainability ramifications, such as energy waste and the decarbonisation of the energy industry, precise consumption forecasts enable power system planning and reliable grid operations. Energy consumption forecasting is a hot field of research; despite the number of developed models, projecting electric consumption in residential buildings remains problematic owing to the significant unpredictability of occupant energy use behaviour. Discovering the electricity consumption knowledge from the Multi-Dimensional Data Streams (MDDS) of electricity logs is a challenging research problem. To end this, a novel electricity knowledge discovery model proposed from the MDDS using clustering and machine learning. Context-Aware Clustering with Whale Optimization Algorithm (CAC-WOA) is designed and explained in this research article. The CAC-WOA consists of two phases context-aware groups formation and WOA-based machine learning predictive model. In the CAC algorithm, group's formation using electricity contextual information to estimate the robust predictive features are proposed. Using such predictive features, the predictive model using the WOA-based Artificial Neural Network (ANN) is built. The modified ANN technique using the WOA algorithm is used to reduce the error rates and improve the prediction accuracy. The experimental outcomes using publically available electricity consumption datasets prove the efficiency of the CAC-WOA model.

show abstract

A Review on the Prediction of Energy Consumption in the Industry Sector Based on Machine Learning Approaches

Cited by 5 publications

References 22 publications

Digital twin with augmented state extended Kalman filters for forecasting electric power consumption of industrial production systems

Digital twin with augmented state extended Kalman filters for forecasting electric power consumption of industrial production systems

Context-Aware Clustering and the Optimized Whale Optimization Algorithm: An Effective Predictive Model for the Smart Grid

CAC-WOA: context aware clustering with whale optimization algorithm for knowledge discovery from multidimensional space in electricity application

Contact Info

Product

Resources

About