Bayesian Learning of Consumer Preferences for Residential Demand Response

Goubko, Mikhail; Kuznetsov, Sergei O.; Neznanov, Alexey; Ignatov, Dmitry I.

doi:10.1016/j.ifacol.2016.12.184

Cited by 10 publications

(6 citation statements)

References 21 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robustness, sensitivity, and responsiveness are also evaluation standards in the literature. Experimental implementations of HEMS are also validated using various optimization methods, such as LP [100], GA [108], machine learning [47], and search algorithm [152].…”

Section: Discussion About Applications and Challengesmentioning

confidence: 99%

Home Energy Management Systems: A Review of the Concept, Architecture, and Scheduling Strategies

et al. 2023

View full text Add to dashboard Cite

Growing electricity demand, the deployment of renewable energy sources and the widespread use of smart home appliances provide new opportunities for home energy management systems (HEMSs), which can be defined as systems that improve the overall energy production and consumption of residential buildings by controlling and scheduling the use of household equipment. By saving energy, reducing residential electricity costs, optimizing the utilization rate and reliability of utility companies' power systems, and reducing air pollution for society, HEMSs lead to an enhancement in the socioeconomic development of low-carbon economies. This review aims to systematically analyze and summarize the development trends and challenges of HEMSs in recent years. This paper reviews the development history of the HEMS architecture and discusses the characteristics of several major communication technologies in the current HEMS infrastructure. In addition, the common objectives and constraints related to scheduling optimization are classified, and several optimization methods in the literature, including various intelligent algorithms, have been introduced, compared, and critically analyzed. Furthermore, experimental studies and challenges in the real world are also summarized and recommendations are given. This paper reveals the trend from simple to complex in the architecture and functionality of HEMSs, discusses the challenges for future improvements in modeling and scheduling, and shows the development of various modeling and scheduling methods. Based on this review, researchers can gain a comprehensive understanding of current research trends in HEMSs and open up ideas for developing new modeling and scheduling approaches by gaining insight into the trade-offs between optimum solutions and computational complexity.INDEX TERMS Demand response, home appliances, home energy management system, optimization, renewable energy resources, smart grid.

show abstract

Section: Discussion About Applications and Challengesmentioning

confidence: 99%

Home Energy Management Systems: A Review of the Concept, Architecture, and Scheduling Strategies

et al. 2023

View full text Add to dashboard Cite

show abstract

“…There are two primary ways to determine what people want. An intelligent algorithm, which may be either predefined [144], [145] or learnt [155], [156], can be used to reflect human preferences for the operation of household appliances. The second strategy involves putting limits on what is considered a realistic timeline [149], [150], [151].…”

Section: ) Load Scheduling and Control At The Customer Levelmentioning

confidence: 99%

“…TCLs, such as heat pumps [144], [148], [157] and water heaters [144], [157], air conditioners [144], [158], [159], battery storage systems [144], [160] and electric vehicles [144], [160], [161], [162] are common examples of appliances that are controlled in a DR setting. Although most papers [150], [151], [155] focus on residential buildings as consumers, there is a lot of research literature focusing on scheduling like for scheduling of different loads at small commercial buildings level is presented in [162], while charging points for smart Electric Vehicles may got overloaded at peak hours, so they need to schedule their loads and customers while considering the customer level load scheduling in order to provide a better DR service [162], and also at industrial level optimization model which consisted of multivariable price function has been used to mitigate the load problems [163].…”

Section: ) Load Scheduling and Control At The Customer Levelmentioning

confidence: 99%

Artificial Intelligence Enabled Demand Response: Prospects and Challenges in Smart Grid Environment

et al. 2023

View full text Add to dashboard Cite

Demand Response (DR) has gained popularity in recent years as a practical strategy to increase the sustainability of energy systems while reducing associated costs. Despite this, Artificial Intelligence (AI) and Machine Learning (ML), have recently developed as critical technologies for demand-side management and response due to the high complexity of tasks associated with DR, as well as huge amount of data management to take decisions very near to real time implications. Selecting the best group of users to respond, learning their attitude toward consumptions and their priorities, price optimization, monitoring and control of devices, learning to engage more and more consumers in the DR schemes, and learning how to remunerate them fairly and economically are all problems that can be tackled with the help of AI techniques. This study presents an overview of AI approaches used for DR applications. Both the Artificial Intelligence and Machine Learning algorithm(s) are employed while discussing commercial efforts (from both new and existing businesses) and large-scale innovation projects that have applied AI technologies for energy DR. Different kind of DR programs implemented in different countries are also discussed. Moreover, it also discusses the application of blockchain for DR schemes in smart grid paradigm. Discussion of the strengths and weaknesses of the evaluated AI methods for various DR tasks, as well as suggestions for further study, round out the work.INDEX TERMS Artificial intelligence, blockchain, demand response, demand side management, demand response, Internet of Things (IoT), smart grids, machine learning.

show abstract

“…Dana Van Aken et al [11] (2014) developed an automated approach for tuning that draws on previous knowledge and collects new data. Mikhail V et al [14] (2016) presented a Bayesian classification model for estimating the comfort level potential based on system use history. According to Dennis M et al [15] (2018), there is a pressing need to expand the use of such novel strategies in MPSE and to initiate the transformation of emerging education, which is necessary for the techniques' sustained implementation.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In any case, an astute database provides you with more choices for answering problems that are longer and therefore more resilient. If the recipient slots in a direct quote as a question, for example, the repository will return a list of hits based on the probability that various hypothetical's provide a useful response [14]. AI Databases can address speculated blunders made by the client, show equivalent words or antonyms for catchphrases and expressions.…”

Section: Improved Ai/db Interfacementioning

confidence: 99%

AI Based Learning Model Management Framework for Private Cloud Computing

Dhaya¹,

Dhaya²,

Kanthavel³

2022

Journal of Internet Technology

View full text Add to dashboard Cite

<p>Artificial Intelligence (AI) systems are computational simulations that are “educated” using knowledge and individual expert participation to replicate a decision that a professional would make provided the same data. A model tries to simulate a specific decision loop that several scientists would take if they had access to all kinds of knowledge. To convey a model, you make a model asset in AI Platform Prediction, make a variant of that model and, at that point, interface the model form to the model record put away in Cloud Storage. AI and DB information sharing are essential for cutting-edge processing for DBMS innovation. The inspirations promoting their incorporation advances incorporate the requirement for admittance to a lot of data that is shared information handling, effective administration of data as information, and astute preparation of information. Notwithstanding these inspirations, the plan for a smart information base interface (IDI) was likewise spurred by the craving to save the considerable speculation spoke to by most existing data sets. A few general ways to deal with the connectivity of AI and databases and different improvements in the area of clever information bases were already examined and announced in this paper.</p> <p> </p>

show abstract

Bayesian Learning of Consumer Preferences for Residential Demand Response

Cited by 10 publications

References 21 publications

Home Energy Management Systems: A Review of the Concept, Architecture, and Scheduling Strategies

Home Energy Management Systems: A Review of the Concept, Architecture, and Scheduling Strategies

Artificial Intelligence Enabled Demand Response: Prospects and Challenges in Smart Grid Environment

AI Based Learning Model Management Framework for Private Cloud Computing

Contact Info

Product

Resources

About