Long-Term Load Forecast Using Decision Tree Method

Ding, Qia

doi:10.1109/psce.2006.296529

Cited by 38 publications

(15 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Traditional methods include spatial [3]- [5], trending [6]- [7], and hybrid, while other unique methods include land use suitability maps [8], data mining [9], segmentation [10], neuro-fuzzy logic [11], econometrics [12], and the use of decision trees [13]. Each method has made an important contribution to the discourse and has also fed the development of Geotypical Growth-based Load Forecasting.…”

Section: Overview Of Load Forecasting Methodsmentioning

confidence: 99%

Geotypical Growth-based Load Forecasting: An introduction to an innovative approach

Penton

McKinney²

2012

PES T&D 2012

View full text Add to dashboard Cite

An introduction to Geotypical Growth-based Load Forecasting (GGLF), long-term power distribution load forecasting based on biological concepts and segmented geographies, is presented. Using load data obtained from 165 substations in Southern Idaho and Southeastern Oregon, this document (1) describes the reasoning for using Living Systems Theory (LST) as a basis for long-term distribution load forecasting, (2) shows the relationship between the MW growth rates of the substations to their observed peak loads, (3) provides the rationale for segmenting the substations into their various geographical characteristics (geotypes), and (4) discusses a logistical regression curve-fitting model that represents the load characteristics of five example geotypes. Example geotypes discussed in the document are those common to a high plains geography, semi-arid climate type. Recommendations for additional research that applies GGLF to other climate types and to other MW load densities are also suggested.

show abstract

Section: Overview Of Load Forecasting Methodsmentioning

confidence: 99%

Geotypical Growth-based Load Forecasting: An introduction to an innovative approach

Penton

McKinney²

2012

PES T&D 2012

View full text Add to dashboard Cite

show abstract

“…Decision 33 Tree is a decision support tool that predicts the output of a classification or a regression problem by passing the inputs to a tree-like model. One thing to note about decision tree is that they are very prone to overfitting.…”

Section: Decision Tree Regressionmentioning

confidence: 99%

Impact of Covid19 on electricity load in Haryana (India)

2020

View full text Add to dashboard Cite

Summary As it is known that the whole world is battling against the Corona Virus Disease or COVID19 and trying their level best to stop the spread of this pandemic. To avoid the spread, several countries like China, Italy, Spain, America took strict measures like nationwide lockdown or by cordoning off the areas that were suspected of having risks of community spread. Taking cues from the foreign counterparts, the government of India undertook an important decision of nationwide full lockdown on March 25th which was further extended till May 4th, 2020 (47 days‐full lockdown). Looking at the current situation government of India pushed the lockdown further with eased curbs, divided the nation into green, orange and red zones, rapid testing of citizens in containment area, mandatory wearing of masks and following social distancing among others. The outbreak of the pandemic, has led to the large economic shock to the world which was never been experienced since decades. Moreover it brought a great uncertainty over the world wide electricity sector as to slow down the spread of the virus, many countries have issued restrictions, including the closure of malls, educational institutions, halting trains, suspending of flights, implemented partial or full lockdowns, insisted work from home to the employees. In this paper, the impact analysis of electricity consumption of state Haryana (India) is done using machine learning conventional algorithms and artificial neural network and electricity load forecasting is done for a week so as to aid the electricity board to know the consumption of the area pre hand and likewise can restrict the electricity production as per requirement. Thus, it will help power system to secure electricity supply and scheduling and reduce wastes since electricity is difficult to store. For this the dataset from regional electricity boards of Haryana that is, Dakshin Haryana Bijli Vitran Nigam and Uttar Haryana Bijli Vitran Nigam were analysed and electricity loads of state were predicted using python programming and as per result analysis it was observed that artificial neural network out performs conventional machine learning models.

show abstract

“…Apart from neural network-based models, there are also many machine learning algorithms producing superior abundant results in some applications, such as atmospheric rainfall forecasting [12], financial forecasting [13], and tourism forecasting [14]. e machine learning algorithms mainly include support vector regression (SVR) [12,15,16], decision trees [17][18][19][20], random forest (RT) [21], and gradient boosting regression trees (GBRT) [22]. e SVM can solve the practical problems such as small sample, nonlinear, high, and local minimum point, but this method cannot determine the input variables effectively and reasonably, and it has slow convergence speed and poor forecasting results while suffering from strong random fluctuation time series [15].…”

Section: Introductionmentioning

confidence: 99%

The Short‐Term Load Forecasting for Special Days Based on Bagged Regression Trees in Qingdao, China

Dong

Gao

Fang

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

There are many factors that affect short-term load forecasting performance, such as weather and holidays. However, most of the existing load forecasting models lack more detailed considerations for some special days. In this paper, the applicability of the bagged regression trees (BRT) model combined with eight variables is investigated to forecast short-term load in Qingdao. The comparative experiments show that the accuracy and speed of forecasting have some improvements using the BRT than the artificial neural network (ANN). Then, an indicator variable is newly proposed to capture the abnormal information during special days, which include national statutory holidays, bridging days, and proximity days. The BRT model combined with this indicator variable is tested on the load series measured in 2018. Experiments demonstrate that the improved model generates more accurate predictive results than BRT model combined with previously variables on special days.

show abstract

Long-Term Load Forecast Using Decision Tree Method

Cited by 38 publications

References 5 publications

Geotypical Growth-based Load Forecasting: An introduction to an innovative approach

Geotypical Growth-based Load Forecasting: An introduction to an innovative approach

Impact of Covid19 on electricity load in Haryana (India)

The Short‐Term Load Forecasting for Special Days Based on Bagged Regression Trees in Qingdao, China

Contact Info

Product

Resources

About