Power load forecasting using support vector machine and ant colony optimization

Niu, Dongxiao; Wang, Yongli; Wu, Desheng Dash

doi:10.1016/j.eswa.2009.08.019

Cited by 334 publications

(119 citation statements)

References 17 publications

Supporting

Mentioning

118

Contrasting

Unclassified

Order By: Relevance

“…(3) Economic factors: Economic perspective such as a rate of population growth or activation of economies [12] has relevance to load demand. These include random disturbance loads such as vehicle chargers, sudden load changes.…”

Section: Factors Influencing the Load Patternsmentioning

confidence: 99%

Short-Term Load Forecast in Microgrids using Artificial Neural Networks

Chung¹,

Yang²,

You³

et al. 2017

The Transactions of The Korean Institute of Electrical Engineer

View full text Add to dashboard Cite

-This paper presents an artificial neural network (ANN) based model with a back-propagation algorithm for short-term load forecasting in microgrid power systems. Owing to the significant weather factors for such purpose, relevant input variables were selected in order to improve the forecasting accuracy. As remarked above, forecasting is more complex in a microgrid because of the increased variability of disaggregated load curves. Accurate forecasting in a microgrid will depend on the variables employed and the way they are presented to the ANN. This study also shows numerically that there is a close relationship between forecast errors and the number of training patterns used, and so it is necessary to carefully select the training data to be employed with the system. Finally, this work demonstrates that the concept of load forecasting and the ANN tools employed are also applicable to the microgrid domain with very good results, showing that small errors of Mean Absolute Percentage Error (MAPE) around 3% are achievable.

show abstract

Section: Factors Influencing the Load Patternsmentioning

confidence: 99%

Short-Term Load Forecast in Microgrids using Artificial Neural Networks

Chung¹,

Yang²,

You³

et al. 2017

The Transactions of The Korean Institute of Electrical Engineer

View full text Add to dashboard Cite

show abstract

“…These previous studies were based mainly on traditional statistical analyses such as multiple regression techniques; however, air temperature or related variables such as heating degree-days have been incorporated into the regression models (e.g., Papalexopoulos and Hesterberg, 1990;Park et al, 1991;Soliman et al, 1997;Ružić et al, 2003;Al-Hamadi and Soliman, 2004;Mirasgedis et al, 2006;Niu et al, 2010). In such linear regression studies, only one or two weather parameters other than temperature were considered, and therefore, it is difficult to assess the independent relationships between electric power demand and weather conditions properly.…”

Section: Introductionmentioning

confidence: 99%

Weather impacts on electric power load: partial phase synchronization analysis

Hong

Kim

2015

Meteorological Applications

View full text Add to dashboard Cite

Electricity demand is influenced by atmospheric conditions, and, therefore it is important to quantify their relationships suitably for accurate electricity demand forecasting and the implementation of power-saving policies. However, interdependencies and characteristics of covariance among meteorological variables within the same periodicities hinder the quantification of their direct and indirect impacts on electric power load. To investigate the strength of the direct correlation between atmospheric conditions and electric power load, this study harnessed a new partialization analysis method based on a partial phase synchronization index combined with wavelet transformation. The advantage of the proposed method is that it can be used to evaluate the degree of independent contribution of the variables over different spatiotemporal scales. Compared with traditional statistical analyses, this new partialization analysis shows that air temperature is the principal variable associated directly with electricity demand, but that the strength of the relationship varies with season and time scale. Relative humidity and wind speed have strong direct correlations with electricity in summer and winter, respectively. Insolation is directly coupled to the electric power load only on sub-diurnal time scales. This investigation indicates that for accurate forecasting of electricity demand, changes in the coupling strengths of different atmospheric variables should be incorporated into the electric power load forecasting process. The study shows that a partial phase synchronization index, combined with wavelet transformation, is a useful tool that could be used in other studies to assess complex interacting atmospheric oscillations that cannot be assessed properly by traditional approaches.

show abstract

“…Meanwhile, the high demand for energy and its production causes degradation of the environment as most energy resources are non-renewable [2]. Allied to the fact that big changes are currently happening to the in the utility industry due to deregulation and an increase in competition, policy makers and utilities are continuously seeking to identify ways to increase energy efficiency and alternate energy sources [3].…”

Section: Introductionmentioning

confidence: 99%