Constrained Thompson Sampling for Real-Time Electricity Pricing With Grid Reliability Constraints

Tucker, Nathaniel; Moradipari, Ahmadreza; Alizadeh, Mahnoosh

doi:10.1109/tsg.2020.3004770

Cited by 14 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different approaches have been proposed to solve the issue. Statistical methods include a time series analysis [1][2][3][4] and a regression analysis [5][6][7] but the forecasting results lack accuracy. With the development of machine learning research, technologies such as the neural network [8,9] and the support vector machine [10,11] are gradually introduced into the daily load forecasting model of power systems.…”

Section: Previous Workmentioning

confidence: 99%

“…With the increasing diversification of the production method and lifestyle, an accurate short-term load prediction on a residential level can greatly promote the operation of the power system. To integrate the increasing volume of intermittent renewable generation into modern power grids, integrators are exploring ways to manipulate residential and commercial loads in real-time [1]. Therefore, various demand response (DR) frameworks that can shape power demand by broadcasting time-varying signals to customers are becoming more and more popular.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Short-Term Residential Load Forecasting Model Based on LSTM Recurrent Neural Network Considering Weather Features

2021

View full text Add to dashboard Cite

With economic growth, the demand for power systems is increasingly large. Short-term load forecasting (STLF) becomes an indispensable factor to enhance the application of a smart grid (SG). Other than forecasting aggregated residential loads in a large scale, it is still an urgent problem to improve the accuracy of power load forecasting for individual energy users due to high volatility and uncertainty. However, as an important variable that affects the power consumption pattern, the influence of weather factors on residential load prediction is rarely studied. In this paper, we review the related research of power load forecasting and introduce a short-term residential load forecasting model based on a long short-term memory (LSTM) recurrent neural network with weather features as an input.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Short-Term Residential Load Forecasting Model Based on LSTM Recurrent Neural Network Considering Weather Features

2021

View full text Add to dashboard Cite

show abstract

“…TS has been shown to be an efficient algorithm for DLA policies and empirical studies have shown that TS is highly competitive to address the exploration-exploitation tradeoff in online learning problems (Chapelle and Li, 2011). TS has also been adapted to constrained online optimization problems such as linear-quadratic control (Abeille and Lazaric, 2018), online network revenue management (Ferreira et al, 2018) and real-time energy pricing (Tucker et al, 2020).…”

Section: Online Vaccine Allocation By Thompson Samplingmentioning

confidence: 99%

Vaccine allocation policy optimization and budget sharing mechanism using Thompson sampling

Rey¹,

Hammad²,

Saberi³

2021

Preprint

View full text Add to dashboard Cite

The optimal allocation of vaccines to population subgroups over time is a challenging health care management problem. In the context of a pandemic, the interaction between vaccination policies adopted by multiple agents and the cooperation (or lack thereof) creates a complex environment that affects the global transmission dynamics of the disease. In this study, we take the perspective of decision-making agents that aim to minimize the size of their susceptible populations and must allocate vaccine under limited supply. We assume that vaccine efficiency rates are unknown to agents and we propose an optimization policy based on Thompson sampling to learn mean vaccine efficiency rates over time. Furthermore, we develop a budget-balanced resource sharing mechanism to promote cooperation among agents. We apply the proposed framework to the COVID-19 pandemic. We use a raster model of the world where agents represent the main countries worldwide and interact in a global mobility network to generate multiple problem instances. Our numerical results show that the proposed vaccine allocation policy achieves a larger reduction in the number of susceptible individuals, infections and deaths globally compared to a population-based policy. In addition, we show that, under a fixed global vaccine allocation budget, most countries can reduce their national number of infections and deaths by sharing their budget with countries with which they have a relatively high mobility exchange. The proposed framework can be used to improve policy-making in health care management by national and global health authorities.

show abstract

“…Customers receive the price information and can choose to lower their consumption when rates are high. There are several pricing methods, including time-of-use (ToU) [ 12 ], critical-peak pricing (CPP) [ 13 ], peak-load pricing (PLP) [ 14 ], and real-time pricing (RTP) [ 15 ]. These demand response strategies can be either centralised [ 16 ] or decentralised [ 17 ].…”

Section: Introductionmentioning

confidence: 99%

Optimum Energy Management for Air Conditioners in IoT-Enabled Smart Home

Philip

Islam

Phillips³

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper addresses the optimal pre-cooling problem for air conditioners (AC) used in Internet of Things (IoT)-enabled smart homes while ensuring that user-defined thermal comfort can be achieved. The proposed strategy utilises renewable energy generation periods and moves some of the air conditioning loads to these periods to reduce the electricity demand. In particular, we propose a multi-stage approach which maximises the utilisation of renewable energy at the first stage to satisfy air conditioning loads, and then schedules residual energy consumption of these loads to low price periods at the second stage. The proposed approach is investigated for the temperature and renewable generation data of NSW, Australia, over the period 2012−2013. It is shown that the approach developed can significantly reduce the energy consumption and cost associated with AC operation for nearly all days in summer when cooling is required. Specifically, the proposed approach was found to achieve a 24% cost saving in comparison to the no pre-cooling case for the highest average temperature day in January, 2013. The analysis also demonstrated that the proposed scheme performed better when the thermal insulation levels in the smart home are higher. However, the optimal pre-cooling scheme can still achieve reduced energy costs under lower thermal insulation conditions compared to the no pre-cooling case.

show abstract

Constrained Thompson Sampling for Real-Time Electricity Pricing With Grid Reliability Constraints

Cited by 14 publications

References 33 publications

A Short-Term Residential Load Forecasting Model Based on LSTM Recurrent Neural Network Considering Weather Features

A Short-Term Residential Load Forecasting Model Based on LSTM Recurrent Neural Network Considering Weather Features

Vaccine allocation policy optimization and budget sharing mechanism using Thompson sampling

Optimum Energy Management for Air Conditioners in IoT-Enabled Smart Home

Contact Info

Product

Resources

About