A hybrid stochastic model based Bayesian approach for long term energy demand managements

Ahmadi, Somayeh; Fakehi, Amir Hossien; Vakili, Ali; Haddadi, Morteza; Iranmanesh, Seyed Hossein

doi:10.1016/j.esr.2020.100462

Cited by 9 publications

(4 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mardani et al (60) as well as Wen and Yuan (61) developed a multistage model for predicting carbon dioxide emissions using machine learning techniques including particle swarm optimization and neural networks. Ahmadi et al (62) employed hybrid stochastic modeling using the Bayesian approach and scenario analysis for forecasting long-term energy demand and greenhouse gas reduction potential. The results revealed that in the long run, carbon emissions will reduce if there is an uptake of energy saving solutions.…”

Section: Artificial Intelligence Modelsmentioning

confidence: 99%

Carbon emissions modeling for smarter carbon footprint decisions: A systematic review

Wofuru-Nyenke

2023

BIJCEES

View full text Add to dashboard Cite

Climate change and environmental deterioration due to greenhouse gas emissions are a major concern around the globe today. This article aims to highlight how various authors have carried out carbon emissions modeling for smarter carbon footprint management and also proffer solutions to the greenhouse gas emissions issue, which is giving rise to global warming and natural disasters across the globe. This study makes use of the Systematic Literature Review (SLR) methodology for identifying, analyzing, and synthesizing articles published from 2015 to 2020, a period of 6 years, on the topic of carbon emissions modeling. The SLR results indicated that there has been a rising interest in the issue of carbon emissions from the period of 2015 to 2020, as seen by the evolution of publications in the area. This can be explained by the increased incidence of natural disasters occurring as a result of the global warming phenomenon due to greenhouse gas emissions. The various ways in which different models have been used for carbon emission analysis and management have been described, while explaining various means by which greenhouse gas emissions can be curtailed to stop the alarming rate of global warming and maintain a sustainable and habitable planet for all.

show abstract

Section: Artificial Intelligence Modelsmentioning

confidence: 99%

Carbon emissions modeling for smarter carbon footprint decisions: A systematic review

Wofuru-Nyenke

2023

BIJCEES

View full text Add to dashboard Cite

show abstract

“…Forecasting target Forecasting Model [20] Iran's demand for energy A hybrid model combines Bayesian approach and scenario analysis [21] Demand for energy in Ireland Covariance matrix adaptation evolutionary strategy [22] Electricity demand in India Long Short-Term Memory network (LSTM) [23] Demand for electricity in New Singapore and South Wales ▪ Variational mode decomposition ▪ Support vector machine ▪ Salp Swarm Algorithm (SSA) [24] Natural gas demand in Germany Functional autoregressive with convolutional neural network [25] Energy demand in China autoregressive distributed lag mixed data sample [26] Residential natural gas demand ▪ Autoregressive integrated moving average model ▪ Artificial neural network ▪ Support vector machine [30] Building energy demand Engineering simulation [31] Heating demand ▪ Artificial neural network with an online learning method [32] Electricity demand ▪ Artificial neural network ▪ Autoregressive integrated moving average model ▪ Multivariate adaptive regression spline [33] Energy load variational mode decomposition with LSTM [34] Natural gas demand ▪ Autoregressive integrated moving average model ▪ Artificial neural network ▪ Extreme learning machine [35] Electricity demand ▪ Adaptive Fourier decomposition ▪ Support vector machine ▪ Fast Fourier transform [36] HVAC system energy demand ▪ Fuzzy with neural network [37] Fans Electricity demand ▪ Artificial neural network [38] Electricity…”

Section: Referencesmentioning

confidence: 99%

Hyperparameter Optimization of Regression Model for Electrical Load Forecasting During the COVID-19 Pandemic Lockdown Period

2023

IJIES

View full text Add to dashboard Cite

Due to global lockdown policies implemented against COVID-19, there has been an impact on electricity consumption. Several countries have emphasized the significance of ensuring electricity supply security during the pandemic to maintain the livelihood of people. Accurate forecasting of electricity demand plays a crucial role in ensuring energy security across all nations; accordingly to achieve this objective, this study employs metaheuristics optimization algorithms to enhance the prediction model's operation, such as Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Random Forest (RF), at an optimized level to minimize errors. Two metaheuristics optimization methods, Particle Swarm Optimization (PSO) and Genetic Algorithms (GA), are utilized. The suggested prediction models are trained using daily power usage data from three US urban regions. In terms of prediction accuracy, the findings show that KNN with PSO surpasses the other models. The COVID-19 pandemic reduced power usage by 20% relative to pre-pandemic levels.

show abstract

“…Figure 6 summarizes the taxonomy of SD in a Venn-Euler diagram. The analysis of energy demand is a vital part of planning studies for meeting the energy needs of a nation and determining their impact on society, the economy, and the environment [107,108]. Table 2 contextualizes the research related to the evaluation of DR and its integration in the planning and operation of electrical systems.…”

Section: Der and Reactive Power Compensationmentioning

confidence: 99%

A Methodological Proposal for Implementing Demand-Shifting Strategies in the Wholesale Electricity Market

et al. 2022

View full text Add to dashboard Cite

The energy transition has shown that fossil generation can be complemented with renewable energy and other resources capable of providing flexibility to the energy system’s operation, in compliance with the wholesale electricity market’s rules. This paper proposes a market-based methodology for introducing flexible demand in the energy dispatch , optimizing the scheduling of electricity system operation in the short-term, and considers the challenge of implementing an incentive scheme for participants in demand-response programs. The scheme includes the criteria of the elasticity of substitution and a renewable energy quota. This methodology is focused on a strategic demand shift to minimize the cost of supply; increase the dispatch of renewable energy; control CO2 emissions; and satisfy the generation, demand, and transmission operating constraints. These conditions encourage the development of a simulation tool that allows a sensitivity analysis to aid decision-making by operators and agents. The proposed methodology optimizes the operational cost of generation supply and specific performance indicators to determine the percentages of demand shift, the amount of CO2 emissions, the ratio of unserved power, the demand benefits obtained from an incentive scheme, and the natural market behavior.

show abstract

A hybrid stochastic model based Bayesian approach for long term energy demand managements

Cited by 9 publications

References 60 publications

Carbon emissions modeling for smarter carbon footprint decisions: A systematic review

Carbon emissions modeling for smarter carbon footprint decisions: A systematic review

Hyperparameter Optimization of Regression Model for Electrical Load Forecasting During the COVID-19 Pandemic Lockdown Period

A Methodological Proposal for Implementing Demand-Shifting Strategies in the Wholesale Electricity Market

Contact Info

Product

Resources

About