Forecasting Uganda’s Net Electricity Consumption Using a Hybrid PSO-ABC Algorithm

Kasule, Abdal; Ayan, Kürşat

doi:10.1007/s13369-018-3383-z

Cited by 9 publications

(5 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similarly, from Figure 8 , it can be seen that among the records of documents that reach HAP, the average MAPE value is lower in the frameworks that implement hybrid models of ML and multivariate dependency, such as those developed in [ 6 , 27 , 73 , 74 , 75 , 76 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 ]. To verify the hypotheses of the differences in the means and variances in the MAPE, three hypothesis tests are carried out.…”

Section: Evaluation Of Model Accuracymentioning

confidence: 85%

A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score

Vivas

Allende‐Cid

Salas

2020

Entropy

View full text Add to dashboard Cite

Electric power forecasting plays a substantial role in the administration and balance of current power systems. For this reason, accurate predictions of service demands are needed to develop better programming for the generation and distribution of power and to reduce the risk of vulnerabilities in the integration of an electric power system. For the purposes of the current study, a systematic literature review was applied to identify the type of model that has the highest propensity to show precision in the context of electric power forecasting. The state-of-the-art model in accurate electric power forecasting was determined from the results reported in 257 accuracy tests from five geographic regions. Two classes of forecasting models were compared: classical statistical or mathematical (MSC) and machine learning (ML) models. Furthermore, the use of hybrid models that have made significant contributions to electric power forecasting is identified, and a case of study is applied to demonstrate its good performance when compared with traditional models. Among our main findings, we conclude that forecasting errors are minimized by reducing the time horizon, that ML models that consider various sources of exogenous variability tend to have better forecast accuracy, and finally, that the accuracy of the forecasting models has significantly increased over the last five years.

show abstract

Section: Evaluation Of Model Accuracymentioning

confidence: 85%

A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score

Vivas

Allende‐Cid

Salas

2020

Entropy

View full text Add to dashboard Cite

show abstract

“…(11) and 12, is the number of observations, is the observed electricity consumption and is the forecasted electricity. To use the trained ANFIS model to forecast electricity consumption, forecasted input variables obtained using multilayer perceptron network for time series forecasting were used [27].…”

Section: Model Performance Assessmentmentioning

confidence: 99%

Using PSO and Genetic Algorithms to Optimize ANFIS Model for Forecasting Uganda’s Net Electricity Consumption

Kasule

Ayan

2020

Sakarya University Journal of Science

Self Cite

View full text Add to dashboard Cite

Uganda seeks to transform its society from a peasant to a modern and largely urban society by the year 2040. To achieve this, electricity as a form of modern and clean energy has been identified as a driving force for all the sectors of the economy. For this reason, electricity consumption forecasts that are realistic and accurate are key inputs to policy making and investment decisions for developing Uganda's electricity sector. In this study, we present an ANFIS long-term electricity forecasting model that is easy to interpret. We use the model to forecast Uganda's electricity consumption. The ANFIS model takes population, gross domestic product, number of subscribers and average electricity price as input variables and electricity consumption as the output. We use particle swarm optimization (PSO) algorithm and genetic algorithm (GA) to optimize the parameters of the model. A forecast accuracy of 94.34% is achieved for GA-ANFIS, while 90.88% accuracy is achieved for PSO-ANFIS as compared to 87.79% for multivariate linear regression (MLR) model. Comparison with official forecasts made by Ministry of Energy and Mineral Development (MEMD) revealed low forecast errors.

show abstract

“…[4] Çin'in elektrik tüketimini tahmin etmek için gri tahmin modelini kullanmışlardır. Kasule ve Ayan [5] Uganda'da EET tahmini için PSO ve YAK algoritmalarından oluşan melez bir model geliştirmişlerdir. Kaboli vd.…”

Section: Li̇teratur Taramasi (Literature Review)unclassified

“…Geliştirdikleri yöntemi gerçek hayatta uygulanabilir iki örnek üzerinde test ederek başarılı sonuçlar elde etmişlerdir. Bu çalışmalar incelendiğinde zaman serileri analizi tekniklerinin [2,4] ve meta-sezgisel algoritmaların [5][6][7][8][9][10] EET tahmininde yaygın bir şekilde kullanıldığı ve başarılı sonuçlar verdiği görülmüştür. Dünyada EET tahmininde yaygın olarak kullanılan bir diğer teknik ise YSA'dır.…”

Section: Li̇teratur Taramasi (Literature Review)unclassified

Jaya algoritması ile optimize edilmiş yapay sinir ağlarını kullanarak Türkiye’de elektrik enerjisi tüketiminin tahmini

Uzlu

Dede

2020

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım Ve Teknoloji

View full text Add to dashboard Cite

In this study, Turkey's electric energy consumption was predicted by using artificial neural networks with Jaya algorithm. As shown in Fig. A, three-layer ANN model encompassing GDP, population, and import-export values as entry parameters was formed with electric energy consumption as the exit parameter. Jaya algorithm was employed for network training. Figure A. Proposed ANN model for electric energy consumptionPurpose: The main objective of the present study was to apply ANN (artificial neural network) model with the Jaya algorithm to estimate electric energy consumption (EEC) in Turkey. Theory and Methods:The model estimates EEC based on gross domestic product (GDP), population, import, and export data. Data from 1980 to 2008 were used to develop the model and data from 2009 to 2014 were used to evaluate the model's predictive ability. ANN-Jaya model's performance was compared with the performance of artificial bee colony (ABC) and teaching learning based optimization (TLBO) algorithm-trained ANN models. After defining the best model according to various error criteria, EEC values for Turkey were predicted under two different scenarios.Results: Simulation results show that, ANN-Jaya modeling performed better results than ANN-TLBO or ANN-ABC modeling. According to the root mean square error values obtained for the test set, the proposed ANN-Jaya model performed 58.9% and 43.9% better than the ANN-ABC and ANN-TLBO models, respectively. Conclusion:In this study, the EEC in Turkey between 1980 and 2023 was modeled based on GDP, population, import, and export indicators under two different scenarios. The two scenarios showed that the future EEC of Turkey would vary between 311.5 and 333.6 TWh in 2023.

show abstract

Forecasting Uganda’s Net Electricity Consumption Using a Hybrid PSO-ABC Algorithm

Cited by 9 publications

References 28 publications

A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score

A Systematic Review of Statistical and Machine Learning Methods for Electrical Power Forecasting with Reported MAPE Score

Using PSO and Genetic Algorithms to Optimize ANFIS Model for Forecasting Uganda’s Net Electricity Consumption

Jaya algoritması ile optimize edilmiş yapay sinir ağlarını kullanarak Türkiye’de elektrik enerjisi tüketiminin tahmini

Contact Info

Product

Resources

About