Modeling and analysis of residential flexibility: Timing of white good usage

Sadeghianpourhamami, Nasrin; Demeester, Thomas; Benoit, Dries F.; Strobbe, Matthias; Develder, Chris

doi:10.1016/j.apenergy.2016.07.012

Cited by 34 publications

(22 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As time progresses, cars will move towards lower ∆t depart cells, and (if charged) lower ∆t charge and ∆t depart . 3 Given that time-of-day is likely to influence the expected evolution of the state x s (and hence the required response action we should take), we do include the timeslot t as explicit part of the state.…”

Section: A State Spacementioning

confidence: 99%

Definition and Evaluation of Model-Free Coordination of Electrical Vehicle Charging With Reinforcement Learning

Sadeghianpourhamami

Deleu

Develder

2020

IEEE Trans. Smart Grid

108

View full text Add to dashboard Cite

With the envisioned growth in deployment of electric vehicles (EVs), managing the joint load from EV charging stations through demand response (DR) approaches becomes more critical. Initial DR studies mainly adopt model predictive control and thus require accurate models of the control problem (e.g., a customer behavior model), which are to a large extent uncertain for the EV scenario. Hence, model-free approaches, especially based on reinforcement learning (RL) are an attractive alternative. In this paper, we propose a new Markov decision process (MDP) formulation in the RL framework, to jointly coordinate a set of EV charging stations. State-of-the-art algorithms either focus on a single EV, or perform the control of an aggregate of EVs in multiple steps (e.g., aggregate load decisions in one step, then a step translating the aggregate decision to individual connected EVs). On the contrary, we propose an RL approach to jointly control the whole set of EVs at once. We contribute a new MDP formulation, with a scalable state representation that is independent of the number of EV charging stations. Further, we use a batch reinforcement learning algorithm, i.e., an instance of fitted Q-iteration, to learn the optimal charging policy. We analyze its performance using simulation experiments based on a real-world EV charging data. More specifically, we (i) explore the various settings in training the RL policy (e.g., duration of the period with training data), (ii) compare its performance to an oracle all-knowing benchmark (which provides an upper bound for performance, relying on information that is not available or at least imperfect in practice), (iii) analyze performance over time, over the course of a full year to evaluate possible performance fluctuations (e.g, across different seasons), and (iv) demonstrate the generalization capacity of a learned control policy to larger sets of charging stations.

show abstract

Section: A State Spacementioning

confidence: 99%

Definition and Evaluation of Model-Free Coordination of Electrical Vehicle Charging With Reinforcement Learning

Sadeghianpourhamami

Deleu

Develder

2020

IEEE Trans. Smart Grid

108

View full text Add to dashboard Cite

show abstract

“…The timing aspect of the flexibility is greatly influenced by user lifestyle and energy consumption habits. Hence, to derive generative models of user flexibility, its timing aspect is quantified using configuration time and deadline [5]. The configuration time indicates when the users configure their smart appliances flexibly and the deadline is the latest possible start time of the appliance.…”

Section: Introductionmentioning

confidence: 99%

“…Initial studies modeling the energy consumption flexibility avoid the cylindrical representation by defining a heuristic algorithm that identifies the middle of the largest gap on the circular axis to wrap the data around and proceed to modeling using probabilistic models defined on linear scales (e.g., [5] [2]). However, such heuristic algorithms might fail in situations where such a reference point is challenging or impossible to find.…”

Section: Introductionmentioning

confidence: 99%

“…This paper investigates how well WeiSSVM mixtures can model the energy consumption flexibility compared to using distributions defined on the linear scale. The analysis is based on data from year-long measurements in the LINEAR pilot project [3], where [5] previously modeled the user behavior towards smart wet-appliances with Gaussian mixture models (GMM).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Real-World Flexibility of Residential Power Consumption

Sadeghianpourhamami

Benoit

Deschrijver

et al. 2018

Proceedings of the Ninth International Conference on Future Energy Systems

View full text Add to dashboard Cite

A user's power consumption flexibility is defined in terms of amount, time and duration of availability. The timing of flexibility is circular in nature. Therefore, it is natural to adopt circular distributions to model this data. This paper investigates the key research question whether that leads to better generative models than using conventional linear distributions. In particular, it fits Gaussian mixture models and a very flexible recent cylindrical (WeiSSVM) distribution mixture to real-world field trial data. Using a predictive accuracy performance measure, it is found that the latter does not provide substantially better fits. Shortcomings of both models are pointed out and it is concluded that research for appropriate statistical models for the observed data is still open.

show abstract

“…In this section, we address this gap and offer a quantitative analysis of the flexibility exploitation of EVs using various measures. We first define the flexibility using 3 factors [32]: (1) the amount of deferrable energy (i.e., the amount of energy 420 that can be delayed without jeopardizing customer convenience or quality of the task to be fulfilled), (2) the time of availability (i.e., the time at which a customer offers the flexibility for exploitation), and (3) the deadline/permissible duration to exploit the offered flexibility (i.e., the maximum allowable delay for the energy consumption).…”

Section: Measures For Quantification Of Flexibility Utilizationmentioning

confidence: 99%