Probabilistic load models for simulating the impact of load management

Chen, P.; Bak‐Jensen, Birgitte; Chen, Z.

doi:10.1109/pes.2009.5275828

Cited by 7 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…2, the green band is generated using 500 random cases under a specific load composition. The value distributions of two snapshots are also presented and assumed to be Gaussian [23]- [24].…”

Section: F Identify the Composition Of The Composite Loadmentioning

confidence: 99%

See 1 more Smart Citation

Two-Stage WECC Composite Load Modeling: A Double Deep Q-Learning Networks Approach

Wang

Shi

et al. 2020

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

With the increasing complexity of modern power systems, conventional dynamic load modeling with ZIP and induction motors (ZIP + IM) is no longer adequate to address the current load characteristic transitions. In recent years, the WECC composite load model (WECC CLM) has shown to effectively capture the dynamic load responses over traditional load models in various stability studies and contingency analyses. However, a detailed WECC CLM model typically has a high degree of complexity, with over one hundred parameters, and no systematic approach to identifying and calibrating these parameters. Enabled by the wide deployment of PMUs and advanced deep learning algorithms, proposed here is a double deep Q-learning network (DDQN)-based, two-stage load modeling framework for the WECC CLM. This two-stage method decomposes the complicated WECC CLM for more efficient identification and does not require explicit model details. In the first stage, the DDQN agent determines an accurate load composition. In the second stage, the parameters of the WECC CLM are selected from a group of Monte-Carlo simulations. The set of selected load parameters is expected to best approximate the true transient responses. The proposed framework is verified using an IEEE 39-bus test system on commercial simulation platforms.Index Terms-Load modeling, double deep Q-learning network, load component identification, measurement-based.

show abstract

“…2, the green band is generated using 500 random cases under a specific load composition. The value distributions of two snapshots are also presented and assumed to be Gaussian [23]- [24].…”

Section: F Identify the Composition Of The Composite Loadmentioning

confidence: 99%

“…Function 𝑄 𝐴 (𝑠, 𝑎) updates at every step following (22), but function 𝑄 𝐵 (𝑠, 𝑎) updates every C (C≫1) step. In such a way, the temporal difference (TD) error is created, which serves as the optimization target for the agent, as shown in (23).…”

Section: A Ddqn Agent Training Setupmentioning

confidence: 99%

Two-Stage WECC Composite Load Modeling: A Double Deep Q-Learning Networks Approach

Wang

Shi

et al. 2020

IEEE Trans. Smart Grid

View full text Add to dashboard Cite

show abstract

“…The strong cross-correlation of the load in area A and the load in area B are caused by the diurnal period of the load as well as the similar temperature in the two areas. In this paper, the load model developed in [7] is adopted for the simulation. The model is based on an AR process and takes into account the seasonal variation, weekday/weekend and diurnal period of loads.…”

Section: Load Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…As discussed in [7], the hourly load demand usually has a Gaussian distribution. Thus, the load demand can be modeled by a multivariate Gaussian distribution or a standard autoregressive moving-average (ARMA) process [7]. In contrast, WPG is a non-Gaussian and non-stationary stochastic process, which makes it more challenging to apply standard multivariate probability distributions or ARMA models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Stochastic Optimization of Wind Turbine Power Factor Using Stochastic Model of Wind Power

Chen

Siano

Bak‐Jensen

et al. 2010

IEEE Trans. Sustain. Energy

View full text Add to dashboard Cite

This paper proposes a stochastic optimization algorithm that aims to minimize the expectation of the system power losses by controlling wind turbine (WT) power factors. This objective of the optimization is subject to the probability constraints of bus voltage and line current requirements. The optimization algorithm utilizes the stochastic models of wind power generation (WPG) and load demand to take into account their stochastic variation. The stochastic model of WPG is developed on the basis of a limited autoregressive integrated moving average (LARIMA) model by introducing a crosscorrelation structure to the LARIMA model. The proposed stochastic optimization is carried out on a 69bus distribution system. Simulation results confirm that, under various combinations of WPG and load demand, the system power losses are considerably reduced with the optimal setting of WT power factor as compared to the case with unity power factor. Furthermore, an economic evaluation is carried out to quantify the value of power loss reduction. It is demonstrated that not only network operators but also WT owners can benefit from the optimal power factor setting, as WT owners can pay a much lower energy transfer fee to the network operators.

show abstract