Incentive-based demand response for smart grid with reinforcement learning and deep neural network

R Lu, SH Hong - Applied energy, 2019 - Elsevier
Balancing electricity generation and consumption is essential for smoothing the power grids.
Any mismatch between energy supply and demand would increase costs to both the service …

Prediction-based multi-agent reinforcement learning in inherently non-stationary environments

A Marinescu, I Dusparic, S Clarke - ACM Transactions on Autonomous …, 2017 - dl.acm.org
Multi-agent reinforcement learning (MARL) is a widely researched technique for
decentralised control in complex large-scale autonomous systems. Such systems often …

Genetic algorithm‐based non‐linear auto‐regressive with exogenous inputs neural network short‐term and medium‐term uncertainty modelling and prediction for …

M Jawad, SM Ali, B Khan, CA Mehmood… - The Journal of …, 2018 - Wiley Online Library
Electrical load and wind power forecasting are a demanding task for modern electrical
power systems because both are closely linked with the weather parameters, such as …

Baseline methodologies for small scale residential demand response

J Jazaeri, T Alpcan, R Gordon… - … -Asia (ISGT-Asia), 2016 - ieeexplore.ieee.org
Demand response (DR) programs are designed to reduce electricity load in periods of peak
electricity demand, which helps avoiding expensive network upgrades. This reduction is …

Accurate and efficient selection of the best consumption prediction method in smart grids

M Frincu, C Chelmis, MU Noor… - 2014 IEEE International …, 2014 - ieeexplore.ieee.org
Smart grids are becoming popular with the advent of sophisticated smart meters. They allow
utilities to optimize energy consumption during peak hours by applying various demand …

A deep learning method for short-term dynamic positioning load forecasting in maritime microgrids

M Mehrzadi, Y Terriche, CL Su, P Xie… - Applied Sciences, 2020 - mdpi.com
Featured Application Application of deep learning techniques to dynamic positioning in
maritime microgrids for power management system. Abstract The dynamic positioning (DP) …

A machine learning approach to modelling escalator demand response

S Uimonen, T Tukia, J Ekström, ML Siikonen… - … Applications of Artificial …, 2020 - Elsevier
This article relates to the topic of the escalator demand response potential. Previous studies
mapped escalators as an unrealized potential for additional demand response. The …

Generating electrical demand time series applying SRA technique to complement NAR and sARIMA models

JL Tena García, E Cadenas Calderón, E Rangel Heras… - Energy Efficiency, 2019 - Springer
Prediction of demand time series is commonly approached to deliver a punctual forecast
model, however, is highly recommended to provide probabilistic models that give a range to …

Decentralised multi-agent reinforcement learning for dynamic and uncertain environments

A Marinescu, I Dusparic, A Taylor, V Cahill… - arXiv preprint arXiv …, 2014 - arxiv.org
Multi-Agent Reinforcement Learning (MARL) is a widely used technique for optimization in
decentralised control problems. However, most applications of MARL are in static …

Flexibility forecast and resource composition methodology for virtual power plants

C Iraklis, J Smend, A Almarzooqi… - … Computer and Energy …, 2021 - ieeexplore.ieee.org
As more distributed generation, of different sizes, is being integrated into the electricity
network, energy systems become more decentralized and therefore need to adapt to the …