Ultra-short-term multi-node load forecasting – a composite approach

Han, Xue; Han, Li; Gooi, Hoay Beng; Pan, Zhi Yuan

doi:10.1049/iet-gtd.2011.0524

Cited by 24 publications

(13 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Han et al [15] propose a composite approach for ultra-short term load forecasting using two well-known methods: recursive least square support vector machine algorithm and Takagi-Sugeno fuzzy control. Hong, Wilson and Xie [16] propose statistical methods to predict long term probabilistic forecasts, also including linear regression with multiple factors.…”

Section: Day Ahead Electricity Price and Price Predictionmentioning

confidence: 99%

Benefits of Stochastic Optimisation with Grid Price Prediction for Electric Vehicle Charging

Mody¹,

Steffen²

2017

SAE Technical Paper Series

View full text Add to dashboard Cite

The goal of grid friendly charging is to avoid putting additional load on the electricity grid when it is heavily loaded already, and to reduce the cost of charging to the consumer. In a smart metering system, Day Ahead tariff (DA) prices are announced in advance for the next day. This information can be used for a simple optimization control, to select to charge at cheapest times. However, the balance of supply and demand is not fully known in advance and the Real-Time Prices (RTP) are therefore likely to be different at times. There is always a risk of a sudden price change, hence adding a stochastic element to the optimization in turn requiring dynamic control to achieve optimal time selection. A stochastic dynamic program (SDP) controller which takes this problem into account has been made and proven by simulation in a previous paper.Since there are differences between the DA and the RTP tariff, this paper proposes a (1) predictor to create an unbiased estimate of the RTP tariff based on available data. It uses a regression on historical data to find the best prediction of the expected price. Finally, a (2) case study based on data from the Illinois Electricity Grid prices is presented to validate the SDP controller over several years of data. The stochastic optimization uses the RTP prices effectively, getting very close to the globally optimal charging price. However, the predictor achieves only a slight reduction in prediction uncertainty with this data sate, and it has a negligible effect on cost. This means that DA prices can be used as a fair prediction of RTP charging cost here. The SDPM successfully reacts in the case study and leads to savings on charging costs over the years presented.

show abstract

Section: Day Ahead Electricity Price and Price Predictionmentioning

confidence: 99%

Benefits of Stochastic Optimisation with Grid Price Prediction for Electric Vehicle Charging

Mody¹,

Steffen²

2017

SAE Technical Paper Series

View full text Add to dashboard Cite

show abstract

“…Constraint (11) imposes that the downward bound of the synergistic capability should be less than the lower limit of the system uncertainty set, and constraint (12) imposes that the upward bound of the synergistic capability should be more than the upper limit of the system uncertainty set. Constraints (11) and (12) indicate that the synergistic capability should cover the variation range of loads and wind power.…”

Section: Constraintsmentioning

confidence: 99%

“…Some use advanced mathematical techniques to model the uncertainties, including probabilistic distribution [6,7], fuzzy arithmetic [8,9] and interval arithmetic [10,11]. The former two descriptions require the knowledge of membership functions or probability distribution whereas the uncertainties can be easily described by interval arithmetic with upper and lower bounds, which coincides with the available load or wind power forecast methods [12,13]. Furthermore, the use of interval arithmetic is commensurate with the available robust optimization techniques [14,15].…”

Section: Introductionmentioning

confidence: 99%

Frequency aware robust economic dispatch

Sun

Han

Zhang

et al. 2016

J. Mod. Power Syst. Clean Energy

View full text Add to dashboard Cite

This paper proposes a novel frequency aware robust economic dispatch (FARED) approach to exploit the synergistic capability of accommodating uncertain loads and renewable generation by accounting for both the frequency regulation effect and optimal participation mechanism of secondary regulation reserves for conventional units in response to uncertainties in the robust optimization counterpart of security constrained economic dispatch. The FARED is formulated as a robust optimization problem. In this formulation the allowable frequency deviation and the possible load or renewable generation curtailments are expressed in terms of variable uncertainty sets. The variables in the formulation are described as interval variables and treated in affine form. In order to improve the computational tractability, the dominant constraints which can be the candidates of tight transmission constraints are determined by complementarity constraints. Then the robust optimization problem is simplified to a bilinear programming problem based on duality theory. Finally, the effectiveness and efficiency of the proposed method are illustrated based on several study cases.

show abstract

“…According to the related papers [1][2][3]with author's own research experience, the definition of multi-node load forecasting can be summarized as follows: multi-node load forecasting is a distributed load forecasting in units of node which takes different sources of factors into consideration like the types of load, the electricity price and traffic condition. A node is a part of the network with common features (single user, whole of part of feeder line, substation etc.…”

Section: Models Of Multi-node Load Forecastingmentioning

confidence: 99%

“…Additionally, the author divided the methods into local load forecasting, global load forecasting and participation factor forecasting. Reference [2] constructed a framework of self-adapting dynamic load models of ultra-short-term forecasting for multi-node active and reactive load based on the ideas of "hierarchy" and sub-area. Reference [3] used fuzzy-rough sets to determine the initial weights of artificial neural networks for short term load forecasting in order to select the most significant input variables.…”

Section: Introductionmentioning

confidence: 99%

A novel algorithm for multi-node load forecasting based on big data of distribution network

Hou¹,

Xu²,

Yin³

et al. 2016

Proceedings of the 2016 International Conference on Advanced Electronic Science and Technology (AEST 2016)

View full text Add to dashboard Cite

Abstract. Effective load forecasting for different scales of loads is essential for the planning and operation of distribution network. The extending scale of the network, the diversity of load types and the rapid increase of data volume are some of the facing problems. In this paper, we propose a novel method for multi-node load forecasting, AR-ANN, which takes those problems into consideration. This new algorithm makes a combination of AR method and BP neural network method while eliminating their disadvantages. Comparing to traditional bottom-up method, a top-down method is more applicable when considering the limitation of measurement equipment in distribution network. Both top-down method and bottom-up method are tested in this paper by using AR-ANN algorithm. The data processing speed and the forecasting accuracy of AR-ANN is validated by several tests: an ordinary single-node load forecast, two multi-node load forecasts by traditional bottom-up method and by the new top-down method.

show abstract

Ultra-short-term multi-node load forecasting – a composite approach

Cited by 24 publications

References 17 publications

Benefits of Stochastic Optimisation with Grid Price Prediction for Electric Vehicle Charging

Benefits of Stochastic Optimisation with Grid Price Prediction for Electric Vehicle Charging

Frequency aware robust economic dispatch

A novel algorithm for multi-node load forecasting based on big data of distribution network

Contact Info

Product

Resources

About