Hierarchical Classification of Load Profiles Based on Their Characteristic Attributes in Frequency Domain

Zhong, Shiyin; Tam, Kwa-Sur

doi:10.1109/tpwrs.2014.2362492

Cited by 87 publications

(28 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature extraction refers to mapping a high-dimensional data to a low-dimensional space, which includes linear dimensionality reduction method such as Principal Component Analysis (PCA) [30], and non-linear dimensionality reduction techniques such as Sommon Mapping, Curvilinear Component Analysis (CCA) [26] and deep learning [31]. Since the data of electricity consumption is essentially a time series, there are also some studies applying the idea of time series analysis to the data mining of electricity consumption, such as Discrete Fourier Analysis [32], Discrete Wavelet Analysis [33], Symbolic Aggregate Approximation [34] and Hidden Markov Model [35].…”

Section: Potential Estimation Of Demand Responsementioning

confidence: 99%

From demand response to integrated demand response: review and prospect of research and application

Huang

Zhang

Chen

et al. 2019

Prot Control Mod Power Syst

216

View full text Add to dashboard Cite

In the traditional power system demand response, customers respond to electricity price or incentive and change their original power consumption pattern accordingly to gain additional benefits. With the development of multienergy systems (MES) in which electricity, heat, natural gas and other forms of energy are coupled with each other, all types of energy customers are able to participate in demand response, leading to the concept of integrated demand response (IDR). In IDR, energy consumers can response not only by reducing energy consumption or opting for off-peak energy consumption but also by changing the type of the consumed energy. Taking the traditional demand response in power system as a starting point, the studies of the fundamental theory, framework design and potential estimation of demand response in power system are reviewed, and the practical cases and software development of demand response are introduced. Finally, the current theoretical research and application of IDR are assessed.

show abstract

Section: Potential Estimation Of Demand Responsementioning

confidence: 99%

From demand response to integrated demand response: review and prospect of research and application

Huang

Zhang

Chen

et al. 2019

Prot Control Mod Power Syst

216

View full text Add to dashboard Cite

show abstract

“…Three machine learning methods, including Nonlinear Regression, Support Vector Machine, and Classification And Regression Tree are used to train the QoS model in this paper. It means that the correlation between input X and output Y is explored through the methods above.…”

Section: Qos Model Trainingmentioning

confidence: 99%

Self‐learning and self‐adaptive resource allocation for cloud‐based software services

Chen

Lin

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary In the presence of scale, dynamism, uncertainty, and elasticity, cloud engineers face several challenges when allocating resources for cloud‐based software services. They should allocate appropriate resources in order to guarantee good quality of services as well as low cost of resources. Self‐adaptive ability is needed in this process because engineers' intervention is difficult. Traditional self‐adaptive resource allocation methods are policy‐driven. Thus, cloud engineers usually have to develop separate sets of rules for each systems in order to allocate resources effectively, which leads to high administrative cost and implementation complexity. Machine learning has made great achievements in many fields, and it can be also applied to resource allocation. In this paper, we present a self‐learning and self‐adaptive approach to resource allocation for cloud‐based software services. For a given cloud‐based software service, its QoS model is firstly trained on history data, which is capable to predict the QoS value as output by using the information on workload and allocated resources as inputs. Then, on‐line decision‐making on resource allocation can be carried out automatically based on genetic algorithm, which is aimed to search reasonable resource allocation plan by using the QoS model. We evaluate our approach on RUBiS benchmark, demonstrating the accuracy of the QoS model over 90% and the improvement of resource utilization by 10%‐30%.

show abstract

“…The evaluation criterion of the effectiveness of a load‐shedding program is the ability to recover the frequency and voltage in the faulty system into the permissible range in minimum time by shedding as little load as possible. An accurate knowledge of load characteristics at the moment of fault would help in achieving the quick recovery of frequency and voltage and the minimization of load‐shedding amount. To obtain the load characteristics, the following factors need to be considered: the differences in regulating characteristics between loads with different spatial distribution, and the interactions among frequency, voltage, active power, reactive power, and other electrical quantities.…”

Section: Load Control Sensitivity Index Combining Various Influence Fmentioning

confidence: 99%

An optimization method of UFLS/UVLS considering the interaction of system state information

Tang

Wang

et al. 2018

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Because of the differences of grid network architecture, generator parameters, and load characteristics, frequency and voltage at grid nodes show certain spatial distribution characteristics when faults happen. Therefore, the same stability control measures may result in different control effects if applied at different nodes. Meanwhile, in order to improve the control effect and reduce stable control cost, the impacts of the interactions between strongly coupled factors, such as frequency, voltage, active power, reactive power and other quantities, on the effects of stability control measures need to be considered. A new optimization control strategy of under‐frequency load shedding/under‐voltage load shedding is proposed in this paper based on the load control sensitivity index. The method takes into consideration the spatial distribution characteristics of frequency and voltage, as well as the real‐time interaction characteristics of the coupled electrical quantities. Compared with the traditional load‐shedding scheme, the proposed scheme can achieve better control results. The effectiveness of the proposed method is verified through a time‐domain simulation of two actual provincial power grids. © 2018 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

Hierarchical Classification of Load Profiles Based on Their Characteristic Attributes in Frequency Domain

Cited by 87 publications

References 13 publications

From demand response to integrated demand response: review and prospect of research and application

From demand response to integrated demand response: review and prospect of research and application

Self‐learning and self‐adaptive resource allocation for cloud‐based software services

An optimization method of UFLS/UVLS considering the interaction of system state information

Contact Info

Product

Resources

About