Residential demand response: Experimental evaluation and comparison of self-organizing techniques

Dusparić, Ivana; Taylor, Adam; Marinescu, Andrei; Golpayegani, Fatemeh; Clarke, Siobhán

doi:10.1016/j.rser.2017.07.033

Cited by 38 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It can be noticed that P‐MARL agents lead to a much smoother overall grid demand, as they adapt to the baseload and intermittent wind availability, and thus avoid generating peaks in demand. In fact, the performance obtained by P‐MARL is near‐optimal with respect to the demand‐smoothing target, in line with the optimal valley‐filling algorithm presented in Dusparic et al The comparison in Dusparic et al presents the evaluation of a number of solutions on a similar problem. The near‐optimal performance of P‐MARL while considering sequential agent actions has been previously demonstrated in and is an outcome of the predictive analytics and simulated environment modules of P‐MARL.…”

Section: Evaluation Of Dr Algorithmsupporting

confidence: 72%

“…The near‐optimal performance of P‐MARL while considering sequential agent actions has been previously demonstrated in and is an outcome of the predictive analytics and simulated environment modules of P‐MARL. This outperforms the solutions presented in Dusparic et al, as it is not only closer to optimal but also presents much smoother demand patterns on aggregate.…”

Section: Evaluation Of Dr Algorithmmentioning

confidence: 62%

See 1 more Smart Citation

Optimising residential electric vehicle charging under renewable energy: Multi‐agent learning in software simulation and hardware‐in‐the‐loop evaluation

et al. 2019

Self Cite

View full text Add to dashboard Cite

Summary The integration of intermittent renewable energy sources coupled with the increasing demand of electric vehicles (EVs) poses new challenges to the electrical grid. To address this, many solutions based on demand response have been presented. These solutions are typically tested only in software‐based simulations. In this paper, we present the application in hardware‐in‐the‐loop (HIL) of a recently proposed algorithm for decentralised EV charging, prediction‐based multi‐agent reinforcement learning (P‐MARL), to the problem of optimal EV residential charging under intermittent wind power and variable household baseload demands. P‐MARL is an approach that can address EV charging objectives in a demand response aware manner, to avoid peak power usage while maximising the exploitation of renewable energy sources. We first train and test our algorithm in a residential neighbourhood scenario using GridLAB‐D, a software power network simulator. Once agents learn optimal behaviour for EV charging while avoiding peak power demand in the software simulator, we port our solution to HIL while emulating the same scenario, in order to decrease the effects of agent learning on power networks. Experimental results carried out in a laboratory microgrid show that our approach makes full use of the available wind power, and smooths grid demand while charging EVs for their next day's trip, achieving a peak‐to‐average ration of 1.67, down from 2.24 in the baseline case. We also provide an analysis of the additional demand response effects observed in HIL, such as voltage drops and transients, which can impact the grid and are not observable in the GridLAB‐D software simulation.

show abstract

Section: Evaluation Of Dr Algorithmsupporting

confidence: 72%

Section: Evaluation Of Dr Algorithmmentioning

confidence: 62%

Optimising residential electric vehicle charging under renewable energy: Multi‐agent learning in software simulation and hardware‐in‐the‐loop evaluation

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Decentralized algorithms distribute decision-making at the local level and allow communication between agents for coordination [ 25 ] or learning [ 26 ]. In this paper, we focus on localized algorithms, a type of decentralized algorithms that operate only on local knowledge, without assuming the availability of specialized hardware for communication [ 27 ].…”

Section: Evaluation Of Contribution Strategiesmentioning

confidence: 99%

“…Finally, localized algorithms empower the users to choose autonomously about their own actions and to keep ownership of data. A more in-depth comparison of centralized and decentralized algorithms is provided in [ 26 ].…”

Section: Related Workmentioning

confidence: 99%

Volunteers in the Smart City: Comparison of Contribution Strategies on Human-Centered Measures

Bennati

Dusparić

Shinde

et al. 2018

Sensors

Self Cite

View full text Add to dashboard Cite

Provision of smart city services often relies on users contribution, e.g., of data, which can be costly for the users in terms of privacy. Privacy risks, as well as unfair distribution of benefits to the users, should be minimized as they undermine user participation, which is crucial for the success of smart city applications. This paper investigates privacy, fairness, and social welfare in smart city applications by means of computer simulations grounded on real-world data, i.e., smart meter readings and participatory sensing. We generalize the use of public good theory as a model for resource management in smart city applications, by proposing a design principle that is applicable across application scenarios, where provision of a service depends on user contributions. We verify its applicability by showing its implementation in two scenarios: smart grid and traffic congestion information system. Following this design principle, we evaluate different classes of algorithms for resource management, with respect to human-centered measures, i.e., privacy, fairness and social welfare, and identify algorithm-specific trade-offs that are scenario independent. These results could be of interest to smart city application designers to choose a suitable algorithm given a scenario-specific set of requirements, and to users to choose a service based on an algorithm that matches their privacy preferences.

show abstract

“…Distintas innovaciones tecnológicas entre los cuales tenemos: los vehículos eléctricos de batería, vehículos eléctricos híbridos y vehículos de pila de combustible de hidrógeno [6], la alta posibilidad y riesgo de degradación de las baterías, es decir, la vida útil de la batería se acorta cada vez más dependiendo de la relación de carga y descarga que se realice.…”

Section: Introductionunclassified

Asignación de recursos para la recarga de vehículos eléctricos en estaciones de servicios basado en la respuesta a la demanda

Cartagena

Torres

2018

I+D Tecnológico

View full text Add to dashboard Cite

La Respuesta a la Demanda (DR), dirigida a la carga de la red eléctrica ocasionada al incorporar Vehículos Eléctricos (EVs), es considerada de gran importancia debido a un alto impacto que provocan dichos vehículos a los sistemas eléctricos. El presente trabajo tiene como finalidad desarrollar asignación de recursos energéticos para la recarga de EVs en estaciones de servicio y así atenuar el impacto que los mismos generan, además de los distintos tipos de carga ante la red eléctrica con varios escenarios. Se plantea un modelo heurístico que se basa en la respuesta a la demanda por medio del algoritmo Húngaro, es decir, se consiguió la adecuada asignación de recursos energéticos para la carga de EVs.

show abstract

Residential demand response: Experimental evaluation and comparison of self-organizing techniques

Cited by 38 publications

References 27 publications

Optimising residential electric vehicle charging under renewable energy: Multi‐agent learning in software simulation and hardware‐in‐the‐loop evaluation

Optimising residential electric vehicle charging under renewable energy: Multi‐agent learning in software simulation and hardware‐in‐the‐loop evaluation

Volunteers in the Smart City: Comparison of Contribution Strategies on Human-Centered Measures

Asignación de recursos para la recarga de vehículos eléctricos en estaciones de servicios basado en la respuesta a la demanda

Contact Info

Product

Resources

About