Forecasting an electricity demand threshold to proactively trigger cost saving demand response actions

Aponte, Omar; McConky, Katie

doi:10.1016/j.enbuild.2022.112221

Cited by 8 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This suggests that alterations in the independent data contribute significantly to changes in the dependent. The mathematical expressions for MSE, R 2 , MAE, MAPE, and RMSE can be found in Equations ( 40)-( 44) [3,9,[78][79][80][81][82][83].…”

Section: Error Metricsmentioning

confidence: 99%

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

Saglam,

Lv,

Spataru

et al. 2024

Energies

View full text Add to dashboard Cite

Accurate instantaneous electricity peak load prediction is crucial for efficient capacity planning and cost-effective electricity network establishment. This paper aims to enhance the accuracy of instantaneous peak load forecasting by employing models incorporating various optimization and machine learning (ML) methods. This study examines the impact of independent inputs on peak load estimation through various combinations and subsets using multilinear regression (MLR) equations. This research utilizes input data from 1980 to 2020, including import and export data, population, and gross domestic product (GDP), to forecast the instantaneous electricity peak load as the output value. The effectiveness of these techniques is evaluated based on error metrics, including mean absolute error (MAE), mean square error (MSE), mean absolute percentage error (MAPE), root mean square error (RMSE), and R2. The comparison extends to popular optimization methods, such as particle swarm optimization (PSO), and the newest method in the field, including dandelion optimizer (DO) and gold rush optimizer (GRO). This comparison is made against conventional machine learning methods, such as support vector regression (SVR) and artificial neural network (ANN), in terms of their prediction accuracy. The findings indicate that the ANN and GRO approaches produce the least statistical errors. Furthermore, the correlation matrix indicates a robust positive linear correlation between GDP and instantaneous peak load. The proposed model demonstrates strong predictive capabilities for estimating peak load, with ANN and GRO performing exceptionally well compared to other methods.

show abstract

Section: Error Metricsmentioning

confidence: 99%

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

Saglam,

Lv,

Spataru

et al. 2024

Energies

View full text Add to dashboard Cite

show abstract

“…The study's findings could be used to inform efficient energy management policies in university campuses (Kudela et al, 2020). Aponte and McConky (2022) introduced a new approach allowing electricity users to implement demand response measures, with the goal of reducing demand charges and user inconvenience.…”

Section: Approaches For Sustainable and Renewable Energymentioning

confidence: 99%

“…Despite the promising results, the study had limitations including a limited consumer sample size and lack of consideration for weather forecasts and consumer behavior. The results, however, could potentially be applied to university campuses to decrease demand charges and user inconvenience, leading to considerable cost savings (Aponte and McConky, 2022). Zhou et al (2022) aimed to identify buildings with excessive electricity consumption and high energy-saving potential using data mining methods.…”

Section: Approaches For Sustainable and Renewable Energymentioning

confidence: 99%

Strategic Energy Management and Carbon Footprint Reduction in University Campuses: A Comprehensive Review

Tanavade,

Patil,

Sudhir

et al. 2023

IJEEP

View full text Add to dashboard Cite

This review paper offers a detailed analysis and summary of current studies related to energy management and carbon footprint reduction in university campuses. Using insights from different research papers, the review highlights the necessity for strategic and sustainable energy management approaches. The research reviewed explores a wide range of methodologies, including the examination of energy consumption, the identification of areas for improvement, the application of energy management and optimization techniques, and the use of renewable and sustainable energy strategies. It is evident from the review that successful energy management and carbon footprint reduction depend on energy management systems, integration of renewable energy, encouraging behavioural changes, and efficient resource use. The review paper is divided into six sections: understanding and enhancing energy consumption, Techniques for Energy Management and Optimization, random and systematic approaches to energy management, Energy Management Systems and their Applications, approaches for sustainable and renewable energy and carbon footprint reduction techniques. The review also identifies areas of future research in the field. It aims to serve as a valuable guide for university administrators, energy managers, and researchers seeking to implement sustainable energy practices and reduce carbon emissions on university campuses.

show abstract

“…In other words, it is said that the changes in the dependent variable are caused so much by the changes in the independent variable. The formulas for the R 2 , RMSE, MSE, and MAE are given in Equations ( 14)-( 17) [50][51][52][53][54][55].…”

Section: Error Metricsmentioning

confidence: 99%

Electricity Demand Forecasting with Use of Artificial Intelligence: The Case of Gokceada Island

2022

View full text Add to dashboard Cite

This study reviews a selection of approaches that have used Artificial Neural Networks (ANN), Particle Swarm Optimization (PSO), and Multi Linear Regression (MLR) to forecast electricity demand for Gokceada Island. Artificial Neural Networks, Particle Swarm Optimization, and Linear Regression methods are frequently used in the literature. Imports, exports, car numbers, and tourist-passenger numbers are used as based on input values from 2014 to 2020 for Gokceada Island, and the electricity energy demands up to 2040 are estimated as an output value. The results obtained were analyzed using statistical error metrics such as R2, MSE, RMSE, and MAE. The confidence interval analysis of the methods was performed. The correlation matrix is used to show the relationship between the actual value and method outputs and the relationship between independent and dependent variables. It was observed that ANN yields the highest confidence interval of 95% among the method utilized, and the statistical error metrics have the highest correlation for ANN methods between electricity demand output and actual data.

show abstract

Forecasting an electricity demand threshold to proactively trigger cost saving demand response actions

Cited by 8 publications

References 22 publications

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

Instantaneous Electricity Peak Load Forecasting Using Optimization and Machine Learning

Strategic Energy Management and Carbon Footprint Reduction in University Campuses: A Comprehensive Review

Electricity Demand Forecasting with Use of Artificial Intelligence: The Case of Gokceada Island

Contact Info

Product

Resources

About