Evolutionary Multiobjective Optimization of Kernel-Based Very-Short-Term Load Forecasting

Alamaniotis, Miltiadis; Ikonomopoulos, A.; Tsoukalas, Lefteri H.

doi:10.1109/tpwrs.2012.2184308

Cited by 76 publications

(40 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, power demand also needs to be considered as an uncertain parameter, but in comparison to the wind power, its demand value is more predictable in the application of online optimization. Many approaches have been developed for very short-term load forecasting aiming at prediction ranges of a few minutes to an hour [32][33][34][35]. In [32], it is shown that the mean absolute percentage error (MAPE) can be less than 0.2% for a 120-s prediction horizon.…”

Section: Problem Formulationmentioning

confidence: 99%

A Framework for Real-Time Optimal Power Flow under Wind Energy Penetration

Mohagheghi

Gabash

2017

Energies

View full text Add to dashboard Cite

Developing a suitable framework for real-time optimal power flow (RT-OPF) is of utmost importance for ensuring both optimality and feasibility in the operation of energy distribution networks (DNs) under intermittent wind energy penetration. The most challenging issue thereby is that a large-scale complex optimization problem has to be solved in real-time. Online simultaneous optimization of the wind power curtailments of wind stations and the discrete reference values of the slack bus voltage which leads to a mixed-integer nonlinear programming (MINLP) problem, in addition to considering variable reverse power flow, make the optimization problem even much more complicated. To address these difficulties, a two-phase solution approach to RT-OPF is proposed in this paper. In the prediction phase, a number of MINLP OPF problems corresponding to the most probable scenarios of the wind energy penetration in the prediction horizon, by taking its forecasted value and stochastic distribution into account, are solved in parallel. The solution provides a lookup table for optional control strategies for the current prediction horizon which is further divided into a certain number of short time intervals. In the realization phase, one of the control strategies is selected from the lookup table based on the actual wind power and realized to the grid in the current time interval, which will proceed from one interval to the next, till the end of the current prediction horizon. Then, the prediction phase for the next prediction horizon will be activated. A 41-bus medium-voltage DN is taken as a case study to demonstrate the proposed RT-OPF approach.

show abstract

Section: Problem Formulationmentioning

confidence: 99%

A Framework for Real-Time Optimal Power Flow under Wind Energy Penetration

Mohagheghi

Gabash

2017

Energies

View full text Add to dashboard Cite

show abstract

“…Alamaniotis et al proposed an evolutionary multiobjective optimization algorithm to predict a five-minute load [9], but the predicted time is too short to fit the need. Some literatures used wavelet neural networks to predict a short-term load forecasting [10] and [11], but this method introduces too much computation overhead and thus affects its feasibility.…”

Section: Related Workmentioning

confidence: 99%

A Load-Balancing Based Charging Management Mechanism for Electric Vehicles

Huang¹,

Chen²,

Hu³

et al. 2013

IJMO

View full text Add to dashboard Cite

Abstract-This work proposes an EV charging management mechanismand utilizes the scheduling systems for the charging stations to determine when to store electricity into batteries according to the real-time electricity price and charging requirement of EVs. A charging suggestion module is presented in this work to locate the most suitable charging station or battery exchange station for the EVs according to the available information in hand. When an EV cannot reach at any charging station due to the lack of electricity, a mobile charging vehicle management module is used to assisting the EV in finding a suitable mobile charging vehicle for recharging. The experimental results show that the proposed work can balance the loading of battery charging and exchange stations, and lower the load peak to make electricity cost down. Besides, the proposed charging suggestion module can decrease the driving distance of EVs for finding the charging stations and the waiting time wasted while charging. The mobile charging vehicle management module can effectively prevent EVs from halting on the road owing to running out of the electricity.

show abstract

“…For VSTLF, Taylor used the observations of minute-by-minute British electricity demand to evaluate various methods including autoregressive integrated moving average (ARIMA) models and two exponential smoothing methods [9]. Alamaniotis et al proposed an ensemble of kernel-based Gaussian processes [10]. Guan et al pre-filtered the spikes in load series and decomposed the load series using wavelet prior to feeding it into a neural network [11].…”

Section: Introductionmentioning

confidence: 99%

Real-time anomaly detection for very short-term load forecasting

Luo

Hong

Yue

2018

J. Mod. Power Syst. Clean Energy

View full text Add to dashboard Cite

Although the recent load information is critical to very short-term load forecasting (VSTLF), power companies often have difficulties in collecting the most recent load values accurately and timely for VSTLF applications. This paper tackles the problem of real-time anomaly detection in most recent load information used by VSTLF. This paper proposes a model-based anomaly detection method that consists of two components, a dynamic regression model and an adaptive anomaly threshold. The case study is developed using the data from ISO New England. This paper demonstrates that the proposed method significantly outperforms three other anomaly detection methods including two methods commonly used in the field and one state-of-the-art method used by a winning team of the Global Energy Forecasting Competition 2014. Finally, a general anomaly detection framework is proposed for the future research.

show abstract

Evolutionary Multiobjective Optimization of Kernel-Based Very-Short-Term Load Forecasting

Cited by 76 publications

References 23 publications

A Framework for Real-Time Optimal Power Flow under Wind Energy Penetration

A Framework for Real-Time Optimal Power Flow under Wind Energy Penetration

A Load-Balancing Based Charging Management Mechanism for Electric Vehicles

Real-time anomaly detection for very short-term load forecasting

Contact Info

Product

Resources

About