Modeling and Forecasting Daily Electricity Load Curves: A Hybrid Approach

Cho, Haeran; Goude, Yannig; Brossat, Xavier; Yao, Qiwei

doi:10.1080/01621459.2012.722900

Cited by 88 publications

(68 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, two different statistical models are used in this study. These models are multiple linear regression model [12][13][14] and Box-Jenkins' autoregressive model of order 1 [15][16][17][18][19]. It also provides the source and method of data collection.…”

Section: Methodsmentioning

confidence: 99%

Statistical Analysis of Electricity Generation in Nigeria Using Multiple Linear Regression Model and Box-Jenkins’ Autoregressive Model of Order 1

Ebukanson¹,

Chidi²,

Iriaoghuan³

2017

IJEPE

View full text Add to dashboard Cite

Abstract:This study presents statistical analysis of electricity generation in Nigeria using two different statistical models, namely; multiple linear regression model and box-Jenkins' autoregressive model of order 1. Two climatic variables (rainfall and temperature) were used as the explanatory variables. Data on electricity generation in Nigeria between 2002 and 2014 were obtained from the Central Bank of Nigeria Statistical Bulletin while Data on rainfall and temperature between 2002 and 2014 were extracted from the National Bureau of Statistics (NBS) abstract. Test of model fitness and forecasting accuracy were done using generic statistical approach which include coefficient of determination and root mean square error. The prediction accuracy of the two statistical models was compared and the best model was selected. Furthermore, correlation between power generation and the two climatic variables (rainfall and temperature), were carried out and the result reveals that the amount of rainfall has significant and positive relationship with power generation in Nigeria. Specifically, rainfall has correlation value of r = 0.927 with the power generation at probability, p = 0.000 and the relationship was significant at 1% (p<0.01). However, temperature although it is positively correlated, does not significantly affect power generation. Temperature has correlation value of t = 0.136 with power generation at probability, p = 0.658 (p>0.05) and the relationship was significant at 5% (p<0.05). Among the two statistical models, multiple linear regression model was selected as the best model as it gave the highest value of coefficient of determination (r 2 =99.77%) and the least Root Mean Square Error (60.27%).

show abstract

Section: Methodsmentioning

confidence: 99%

Statistical Analysis of Electricity Generation in Nigeria Using Multiple Linear Regression Model and Box-Jenkins’ Autoregressive Model of Order 1

Ebukanson¹,

Chidi²,

Iriaoghuan³

2017

IJEPE

View full text Add to dashboard Cite

show abstract

“…Soared and Medeiros had incorporated the effects of different types of days to the model as holiday, working day after and before holiday, Saturday after a holiday, working only during the mornings, working only during the afternoons, Special holiday and the seven days of the week 7 . Borges, Penya and Fernandez also had used similar type days and weekends 5 while Cho et al 3 also had used day types and bank holidays. They also had performed a principal component analysis according to the day type and a segmentation scheme based on the first principal direction.…”

Section: A Incorporating Additional Factorsmentioning

confidence: 99%

“…When considering meteorological conditions, temperature has been used by many of the researches in different ways; average daily temperature 2 , weekly average temperature and weekly 3 . Rather than slecting a single value for the temperature reading, some authors had considered temperature inputs of several cities in tropical, moderate, cold and hot areas to represent the varied weather conditions 4 .…”

Section: A Incorporating Additional Factorsmentioning

confidence: 99%

“…Cho et al had proposed the first level of forecasting by modeling the overall trend and seasonality by fitting a generalized additive model to the weekly averages of the load and the second level by modeling the dependence structure across consecutive daily loads via curve linear regression 3 . At the first level, trends from weekly average loads had been extracted using a generalized additive model, where temperature and other meteorological factors are included as additional explanatory variables.…”

Section: B Techniques Used In the Literaturementioning

confidence: 99%

See 1 more Smart Citation

A Study of the Dynamic Behaviour of Daily Load Curve for Short Term Predictions

Deshani

Liyanage²,

Attygalle³

et al. 2014

Proceedings of the International Symposium for Next Generation Infrastructure

View full text Add to dashboard Cite

Electricity demand is one of the most controversial topics in Sri Lanka as the price of electricity increases rapidly, due to the scarcity of electricity generation sources to meet the demand. Fulfilling the peak demand, starting around 6.30p.m and ending around 9.30p.m, of the load curve is identified as the most crucial aspect that needs to be addressed. During this period, high cost power plants are used to generate electricity, which cannot be met using other low cost options such as hydro power. The Ceylon Electricity Board has to bear a huge loss in order to accommodate this high demand at peak times. Therefore, it is an essential task for a developing country as Sri Lanka to consider developing strategically approached mechanisms to provide a reliable electricity supply at an affordable price. This research focuses on studying the statistical nature of the daily load curve for different consumer categories and for different days of the week to capture the dynamics of electricity usage. An extensive literature is carried out to identify similar research and methodologies used to arrive at a solution by dynamically predicting the daily load curve and smoothing the peak using Demand Side Management strategies.

show abstract

“…There are few studies that apply methods from functional data analysis to load forecasting, amongst which are Shang (2013), Goia et al (2010) and Antoch et al (2008). Others like Cho et al (2013) reduce dimension using a hybrid approach that combines a generalized additive 2 model for the weekly averages of the load and curve linear regression models for the dependence structure across consecutive daily loads.…”

Section: Introductionmentioning

confidence: 99%

Forecasting Generalized Quantiles of Electricity Demand: A Functional Data Approach

Cabrera

Schulz

2017

Journal of the American Statistical Association

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte.

show abstract

Modeling and Forecasting Daily Electricity Load Curves: A Hybrid Approach

Cited by 88 publications

References 37 publications

Statistical Analysis of Electricity Generation in Nigeria Using Multiple Linear Regression Model and Box-Jenkins’ Autoregressive Model of Order 1

Statistical Analysis of Electricity Generation in Nigeria Using Multiple Linear Regression Model and Box-Jenkins’ Autoregressive Model of Order 1

A Study of the Dynamic Behaviour of Daily Load Curve for Short Term Predictions

Forecasting Generalized Quantiles of Electricity Demand: A Functional Data Approach

Contact Info

Product

Resources

About