Electric load forecasting: evaluating the novel hierarchical neuro-fuzzy BSP model

Vellasco, Marley; Pacheco, Marco Aurélio Cavalcanti; Neto, Luiz Sabino Ribeiro; Souza, F.J. de

doi:10.1016/s0142-0615(03)00060-7

Cited by 34 publications

(15 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Sebanyak tiga sistem peramalan cerdas diuji dan dibandingkan yaitu: jaringan saraf, neuro-fuzzy, dan sistem saraf/neurofuzzy. Hasil mengungkapkan potensi model neurofuzzy dan neural/neuro-fuzzy yang diusulkan untuk memperkirakan beban, bila dibandingkan dengan saraf jaringan kesalahan persentase absolut rata-rata bervariasi antara 0,44 dan 1,95%, tergantung pada studi kasus yang dihadapi (Vellasco et al, 2004) Fuzzy Wavelet Neuro Network (FWNN) untuk memperkirakan konsumsi energi tinggi di daerah urban. FWNN dinyatakan meramalkan fluktuasi energi dengan sedikit kesalahan.…”

Section: Tinjauan Pustakaunclassified

Aplikasi Penentuan Tarif Listrik Menggunakan Metode Fuzzy Sugeno

Santoso

2014

J. Sistem Info. Bisnis

View full text Add to dashboard Cite

This reasearch applied Sugeno fuzzy method for determining electricity tariff based on the data of electric customers 450 VA and 900 VA from PLN APJ South Semarang. Tariff of PLN clasifications calculation is done in a progressive way with three block/ classification tariff . This method is considered less representative because many users who consume less or more electrical energy (kWh) in one block/class charged or valued equally. Electric customer data during the 5 months from May to September 2012, which contains a large kWh consumption is then calculated by means of progressive tariff . The data is then performed clustering with FCM method (Mean C Fuzz) into 5 groups, thus obtained cluster centers or power usage and price rates. The power usage and price of the cluster centers are used as a reference manufacture and fed into the membership function of fuzzy inference system built by Sugeno method. This research used the triangular shape of the curve membership function.The system built in the form of application Sugeno fuzzy method which is tested by inserting a number of sample test data . The results are the tariff to be paid by electricity customers . The tariff is resulting from the calculation of the system compared to the tariff calculated in a progressive way of PLN. The difference in total tariff to customers for power of 450 VA Rp 93.3107 or 0.004%, while for the 900 VA at Rp 3503.2 or 0.12 %. The tariff were calculated using Sugeno fuzzy method from this research is more fair to the consumer there is increase in revenue for PLN. Keywords : Fuzzy Sugeno; Tariff classification; Calculation AbstractPenelitian ini telah mengaplikasikan metode fuzzy Sugeno untuk menentukan tarif listrik berdasarkan data pelanggan listrik 450 VA dan 900 VA dari PLN APJ Semarang Selatan. Tarif dari perhitungan klasifikasi PLN dilakukan secara progresif dengan tiga klasifikasi tarif. Cara ini dipandang kurang representative karena pengguna sedikit kWh dan banyak kWh dalam satu kelas tarif dihargai sama besar. Data di dalam penelitian menggunakan data pelanggan listrik selama 5 bulan dari Mei sampai September 2012. Data kWh kemudian dikelompokkan dengan metode FCM (Fuzzy C Mean) menjadi 5 kelompok, sehingga didapatkan pusat-pusat cluster penggunaan daya dan harga. Pusat cluster kWh digunakan sebagai referensi pembuatan fungsi keanggotaan lalu diumpankan kedalam system inferensi fuzzy metode Sugeno yang dibangun. Pada penelitian ini digunakan fungsi keanggotan bentuk kurva segitiga dan kurva traspesium. Sistem yang dibangun berupa aplikasi metode fuzzy Sugeno yang diuji dengan memasukkan sejumlah sampel data uji penggunaan daya dan hasilnya berupa tarif listrik yang harus dibayarkan pelanggan. Tarif yang dihasilkan dari perhitungan system dibandingkan dengan tarif yang dihitung dengan cara progresif dari PLN. Selisih tarif atau biaya untuk pelanggan daya 450 VA sebesar Rp 93.3107 atau 0.004% sedangkan untuk 900 VA sebesar Rp 3503.2 atau 0.12%. Tarif yang dihitung menggunakan metode fuzzy Sugeno dari penelitian ini d...

show abstract

Section: Tinjauan Pustakaunclassified

Aplikasi Penentuan Tarif Listrik Menggunakan Metode Fuzzy Sugeno

Santoso

2014

J. Sistem Info. Bisnis

View full text Add to dashboard Cite

show abstract

“…The research is based on the main hybrid learning algorithms found in literature [15][16][17][18][19][20][21][22][23] , among others.…”

Section: Epilepsymentioning

confidence: 99%

A neuro-fuzzy system to support in the diagnostic of epileptic events and non-epileptic events using different fuzzy arithmetical operations

Carvalho

Nassar

Azevedo

et al. 2008

Arq. Neuro-Psiquiatr.

View full text Add to dashboard Cite

-Objective: To investigate different fuzzy arithmetical operations to support in the diagnostic of epileptic events and non epileptic events. Method: A neuro-fuzzy system was developed using the NEFCLASS (NEuro Fuzzy CLASSIfication) architecture and an artificial neural network with backpropagation learning algorithm (ANNB). Results: The study was composed by 244 patients with a bigger frequency of the feminine sex. The number of right decisions at the test phase, obtained by the NEFCLASS and ANNB was 83.60% and 90.16%, respectively. The best sensibility result was attained by NEFCLASS (84.90%); the best specificity result were attained by ANNB with 95.65%. Conclusion: The proposed neuro-fuzzy system combined the artificial neural network capabilities in the pattern classifications together with the fuzzy logic qualitative approach, leading to a bigger rate of system success.KEY WORDS: epileptic events, non epileptic events, artificial neural network, fuzzy logic. Um sistema neuro-difuso para auxiliar no diagnóstico de eventos epilépticos e eventos não epilépticos utilizando diferentes operações aritméticas difusasResumo -Objetivo: Investigar diferentes operações aritméticas difusas para auxíliar no diagnóstico de eventos epilépticos e eventos não-epilépticos. Método: Um sistema neuro-difuso foi desenvolvido utilizando a arquitetura NEFCLASS (NEuro Fuzzy CLASSIfication) e uma rede neural artificial com o algoritmo de aprendizagem backpropagation (RNAB). Resultados: A amostra estudada foi de 244 pacientes com maior freqüência no sexo feminino. O número de decisões corretas na fase de teste, obtidas através do NEFCLASS e RNAB foi de 83,60% e 90,16%, respectivamente. O melhor resultado de sensibilidade foi obtido com o NEFCLASS (84,90%); o melhor resultado de especificidade foi obtido com a RNAB (95,65%). Conclusão: O sistema neuro-difuso proposto combinou a capacidade das redes neurais artificiais na classificação de padrões juntamente com a abordagem qualitativa da logica difusa, levando a maior taxa de acertos do sistema. PALAVRAS-CHAVE: eventos epilépticos, eventos não epilépticos, rede neural artificial, lógica difusa.

show abstract

“…In this scenario, the research community is studying novel energy efficient production strategies [2], [3], efficient buildings [4], smart grid technologies [5], and techniques for predicting electric loads [6] to determine the optimal price of renewable energy [7]. Among these topics, increasing renewable energy production and improving distribution are of paramount importance to the global economy.…”

Section: Introductionmentioning

confidence: 99%

A Decision Support System for Wind Power Production

Labati

Genovese

Piuri

et al. 2020

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

Abstract-Renewable energy production is constantly growing worldwide, and some countries produce a relevant percentage of their daily electricity consumption through wind energy. Therefore, decision support systems that can make accurate predictions of wind-based power production are of paramount importance for traders operating in the energy market and for managers in charge of planning the non-renewable energy production. In this paper, we present a decision support system that can predict electric power production, estimate a variability index for the prediction, and analyze wind farm production characteristics. The main contribution of this paper is a novel system for long-term electric power prediction based solely on weather forecasts; thus, it is suitable for wind farms that cannot collect or manage real-time data acquired by sensors. Our system is based on neural networks and on novel techniques for calibrating and thresholding the weather forecasts based on the distinctive characteristics of wind farm orography. We tuned and evaluated the proposed system using data collected from two wind farms over a two-year period and achieved satisfactory results. We studied different feature sets, training strategies, and system configurations before implementing this system for a player in the energy market. This company evaluated the power production prediction performance and impact of our system at ten different wind farms under real-world conditions and achieved a significant improvement with respect to their previous approach.

show abstract

Electric load forecasting: evaluating the novel hierarchical neuro-fuzzy BSP model

Cited by 34 publications

References 20 publications

Aplikasi Penentuan Tarif Listrik Menggunakan Metode Fuzzy Sugeno

Aplikasi Penentuan Tarif Listrik Menggunakan Metode Fuzzy Sugeno

A neuro-fuzzy system to support in the diagnostic of epileptic events and non-epileptic events using different fuzzy arithmetical operations

A Decision Support System for Wind Power Production

Contact Info

Product

Resources

About