Strategies for Network-Safe Load Control With a Third-Party Aggregator and a Distribution Operator

Ross, Stephanie C.; Mathieu, Johanna L.

doi:10.1109/tpwrs.2021.3052958

Cited by 23 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future work, we wish to use AMAFQI for networksafe demand response [36] in unknown electric grids and investigate approaches to reduce the number of N iterations performed in AMAFQI before convergence, for example, by considering the growing batch learning paradigm [2] in which an exploration policy is used, and new observed transitions are periodically incorporated in the batch data before recomputing the qj -functions.…”

Section: Discussionmentioning

confidence: 99%

Approximated Multi-Agent Fitted Q Iteration

Lesage‐Landry¹,

Callaway²

2021

Preprint

View full text Add to dashboard Cite

We formulate an efficient approximation for multi-agent batch reinforcement learning, the approximate multi-agent fitted Q iteration (AMAFQI). We present a detailed derivation of our approach. We propose an iterative policy search and show that it yields a greedy policy with respect to multiple approximations of the centralized, standard Q-function. In each iteration and policy evaluation, AMAFQI requires a number of computations that scales linearly with the number of agents whereas the analogous number of computations increase exponentially for the fitted Q iteration (FQI), one of the most commonly used approaches in batch reinforcement learning. This property of AMAFQI is fundamental for the design of a tractable multiagent approach. We evaluate the performance of AMAFQI and compare it to FQI in numerical simulations. Numerical examples illustrate the significant computation time reduction when using AMAFQI instead of FQI in multi-agent problems and corroborate the similar decision-making performance of both approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

Approximated Multi-Agent Fitted Q Iteration

Lesage‐Landry¹,

Callaway²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Jia et al (2019) and Yao et al (2019) suggested that loads are also a key factor of modern power system economic dispatch. Ross and Mathieu (2021) and Harishma et al (2022) demonstrated that power system safe operation also depends on load characteristics. Therefore, although challenging, it is important to figure out an effective way of analyzing load in the power system field.…”

Section: Introductionmentioning

confidence: 99%

An improved deep learning algorithm in enabling load data classification for power system

Ziyao

Li²,

Wu³

2022

Front. Energy Res.

View full text Add to dashboard Cite

Load behaviors significantly impact the planning, dispatching, and operation of the modern power systems. Load classification has been proved as one of the most effective ways of analyzing the load behaviors. However, due to the issues of data collection, transmission, and storage in current power systems, data missing problems frequently occur, which prevents the load classification tasks from precisely identifying the load classes. Simultaneously, because of the diversities of the load categories, different loads contribute various amounts of data, which causes the class imbalance issue. The traditional load data classification algorithms lack the ability to solve the aforementioned issues, which may deteriorate the load classification accuracy. Therefore, this study proposed an improved deep learning algorithm based on the load classification approach in terms of raising the classification performances with solving the data missing and class imbalance issues. First, the LATC (low-rank autoregressive tensor completion) algorithm is used to solve the data missing issue to improve the quality of the training dataset. A Borderline-SMOTE algorithm is further adopted to improve the class distribution in the training dataset to improve the training performances of biGRU (bidirectional gated recurrent unit). Afterward, to improve the classification accuracy in the classification task, the biGRU algorithm, combined with the attention mechanism, is used as the underlying infrastructure. The experimental results show the effectiveness of the proposed approach.

show abstract

“…In [18], the authors study the impacts of secondary frequency control provided by thermostatic loads, concluding that network impacts tend to be relatively minor. The same authors subsequently develop a method of controlling thermostatic loads to follow a dynamic frequency regulation signal whilst accounting for steady-state thermal and voltage constraints [19]. Similarly, [20] proposes a method to enable the maximum frequency response whilst respecting network constraints, although only MV level constraints are considered explicitly.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Network Impacts of Frequency Containment Provided by Domestic-Scale Devices Using Matrix Factorization

Deakin

Greenwood

Taylor

et al. 2021

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

This paper studies the distribution network impacts of frequency containment services derived from domestic-scale devices. Risk metrics considering the likelihood and severity of violations are proposed, given uncertainty in the location of these devices. A novel linearization approach is proposed to enable detailed simulations of large-scale networks, capturing MV-LV coupling in European-style networks of over 100,000 nodes. The approach combines a novel factorization of the power flow Jacobian matrix and an efficient linearization update step. The first of these innovations improves the scalability and practicality of the linearization, reducing the memory and computational requirements by as much as twenty times, whilst the latter reduces the median linearization error by at least 50% in all networks studied. It is demonstrated that rapid voltage change (RVC) and overvoltage constraints could limit the uptake of these devices to just a fraction of one percent of customers if the response is not managed. Sensitivity analysis demonstrates that both the likelihood and severity of constraint violations increases rapidly with the size of the devices used for frequency response.

show abstract

Strategies for Network-Safe Load Control With a Third-Party Aggregator and a Distribution Operator

Cited by 23 publications

References 27 publications

Approximated Multi-Agent Fitted Q Iteration

Approximated Multi-Agent Fitted Q Iteration

An improved deep learning algorithm in enabling load data classification for power system

Analysis of Network Impacts of Frequency Containment Provided by Domestic-Scale Devices Using Matrix Factorization

Contact Info

Product

Resources

About