Garuda - Garba Rujukan Digital

Comparison of Solar Radiation Intensity Forecasting Using ANFIS and Multiple Linear Regression Methods Hadi Suyono; Rini Nur Hasanah; R. A. Setyawan; Panca Mudjirahardjo; Anthony Wijoyo; Ismail Musirin
Bulletin of Electrical Engineering and Informatics Vol 7, No 2: June 2018
Publisher : Institute of Advanced Engineering and Science

Solar radiation forecasting is important in solar energy power plants (SEPPs) development. The electrical energy generated from the sunlight depends on the weather and climate conditions in the area where the SEPPs are installed. The condition of solar irradiation will indirectly affect the electrical grid system into which the SEPPs are injected, i.e. the amount and direction of the power flow, voltage, frequency, and also the dynamic state of the system. Therefore, the prediction of solar radiation condition is very crucial to identify its impact into the system. There are many methods in determining the prediction of solar radiation, either by mathematical approach or by heuristic approach such as artificial intelligent method. This paper analyzes the comparison of two methods, Adaptive Neuro Fuzzy Inference (ANFIS) method, which belongs into the heuristic methods, and Multiple Linear Regression (MLP) method, which uses a mathematical approach. The performance of both methods is measured using the root mean square error (RMSE) and the mean absolute error (MAE) values. The data of the Swiss Basel city from Meteoblue are used to test the performance of the two methods being compared. The data are divided into four cases, being classified as the training data and the data used as predictions. The solar radiation prediction using the ANFIS method indicates the results which are closer to the real measurement results, being compared to the the use MLP method. The average values of RMSE and MAE achieved are 123.27 W/m2 and 90.91 W/m2 using the ANFIS method, being compared to 138.70 W/m2 and 101.56 W/m2 respectively using the MLP method. The ANFIS method gives better prediction performance of 12.51% for RMSE and 11.71% for MAE with respect to the use of the MLP method.

Comparison of Solar Radiation Intensity Forecasting Using ANFIS and Multiple Linear Regression Methods Hadi Suyono; Rini Nur Hasanah; R. A. Setyawan; Panca Mudjirahardjo; Anthony Wijoyo; Ismail Musirin
Bulletin of Electrical Engineering and Informatics Vol 7, No 2: June 2018
Publisher : Institute of Advanced Engineering and Science

Solar radiation forecasting is important in solar energy power plants (SEPPs) development. The electrical energy generated from the sunlight depends on the weather and climate conditions in the area where the SEPPs are installed. The condition of solar irradiation will indirectly affect the electrical grid system into which the SEPPs are injected, i.e. the amount and direction of the power flow, voltage, frequency, and also the dynamic state of the system. Therefore, the prediction of solar radiation condition is very crucial to identify its impact into the system. There are many methods in determining the prediction of solar radiation, either by mathematical approach or by heuristic approach such as artificial intelligent method. This paper analyzes the comparison of two methods, Adaptive Neuro Fuzzy Inference (ANFIS) method, which belongs into the heuristic methods, and Multiple Linear Regression (MLP) method, which uses a mathematical approach. The performance of both methods is measured using the root mean square error (RMSE) and the mean absolute error (MAE) values. The data of the Swiss Basel city from Meteoblue are used to test the performance of the two methods being compared. The data are divided into four cases, being classified as the training data and the data used as predictions. The solar radiation prediction using the ANFIS method indicates the results which are closer to the real measurement results, being compared to the the use MLP method. The average values of RMSE and MAE achieved are 123.27 W/m2 and 90.91 W/m2 using the ANFIS method, being compared to 138.70 W/m2 and 101.56 W/m2 respectively using the MLP method. The ANFIS method gives better prediction performance of 12.51% for RMSE and 11.71% for MAE with respect to the use of the MLP method.

Analisis Injeksi Pembangkit Hybrid Tenaga Surya-Angin pada Sistem GI Sengkaling Penyulang Pujon LUKMAN HAKIM; HADI SUYONO; HARRY SOEKOTJO DACHLAN
Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems) Vol. 11 No. 1 (2017)
Publisher : Fakultas Teknik, Universitas Brawijaya

Amanat undang-undang tentang Energi menyatakan bahwa penyediaan energi dilakukan melalui: diversifikasi, konservasi, dan intensifikasi sumber energi dan energi [1]. Upaya diversivikasi energi yang bersumber dari energi baru dan terbarukan pada makalah ini yaitu berupa pembangkit hybrid surya-angin. Penelitian dilakukan di Gunung Banyak Kota Batu tepatnya pada koordinat latitude -7.861087Â° dan longitude 112.503948Â° elevasi + 941 dpl. Tulisan ini menyajikan analisis potensi dan analisis teknis pembangkit hybrid surya-angin terhubung grid dengan sistem distribusi eksisting 20kV Â PT PLN. Potensi energi matahari dan angin diukur secara langsung di lokasi Gunung Banyak kota Batu. Hasil pengukuran menunjukkan radias1 matahari rata-rata sebesar 5,19 kW/m2. Sedangkan kecepatan angin rata-rata 2,9 m/detik pada ketinggian 10 meter diatas permukaan tanah. Secara teknis, injeksi pembangkit hybrid surya-angin pada sistem GI Sengkaling Penyulang Pujon memperbaiki drop tegangan hingga 5,15% dari tegangan nominal 20kV, dan menurunkan rugi-rugi daya sistem. Simulasi dilakukan dengan menggunakan perangkat software PSAT 2.1.8.

Konsolidasi Beban Kerja Kluster Web Server Dinamis dengan Pendekatan Backpropagation Neural Network Alan Stevrie Balantimuhe; Sholeh Hadi Pramono; Hadi Suyono
Jurnal EECCIS Vol 12, No 2 (2018)
Publisher : Fakultas Teknik, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (415.045 KB)

Meningkatnya permintaan pengguna applikasi WWW telah menyebabkan peningkatan yang sepadan dalam penggunaan sumber daya server kluster. Penelitian ini mengkaji tentang penyediaan sumber daya server Web berdasarkan parameter beban kerja server (load average CPU). Data yang digunakan adalah akses terhadap web server yang melayani applikasi Sistem Informasi Akademik Mahasiswa Universitas Brawijaya (SIAM-UB). Penggunaan sumber daya server secara maksimal (beban puncak) terjadi pada periode registrasi mahasiswa, yaitu lebih dari 65000 mahasiswa akan mengakses server SIAM secara bersamaan. Jumlah permintaan yang dilayani server dalam 1 hari dapat mencapai 1.7juta permintaan. Pada penelitian ini, penyediaan sumber daya server diprediksi untuk mendapatkan beban kerja CPU dalam kluster web server yang optimal. Prediksi beban kerja server diklasifikasikan menjadi 3 kelas, yaitu: Min (0-2), Medium (3-6), Maximum >7. Metode backpropagation neural network (BNN) digunakan untuk memprediksi kelas beban kerja server berdasarkan parameter input penggunaan CPU, memory, jaringan (throughput) dan jumlah IP akses. Arsitektur BNN dengan 32 input, 2 hidden layer dengan jumlah neuoron h1 512; h2 32, 3 output, dan learning rate 0.0001, menghasilkan bobot yang mampu melakukan klasifikasi dengan tingkat precision 90%, tingkat sensitivity 0.9, dan tingkat akurasi 93%.

KLASIFIKASI MUTU MUTIARA BERDASARKAN BENTUK DAN UKURAN MENGGUNAKAN K-NEAREST NEIGHBOR Ardiyallah Akbar; Bambang siswojo; hadi Suyono
CESS (Journal of Computer Engineering, System and Science) Vol 2, No 2 (2017): Juli 2017
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/cess.v2i2.6473

Dalam industri fashion khususnya mutiara, proses klasifikasi mutiara dilakukan secara manual dengan pengamatan visual. Hal tersebut tentu akan memakan waktu yang lama dan menghasilkan produk dengan mutu yang salah karena keterbatasan visual dan kelelahan manusia. Untuk itu dibutuhkan suatu teknologi untuk melakukan proses klasifikasi yang cepat dan akurat. Teknologi yang dapat diterapkan adalah pengolahan citra digital dan metode k-nearest neighbor. Sistem ini menggunakan beberapa proses pengolahan citra digital ,seperti thereshold yaitu dengan cara memisahkah objek dan latar belakang mutiara dan selanjutnya konten yang digunakan adalah bentuk dan ukuran yang diektraksi dari citra mutiara dengan metode regionprops.Hasil akhir dari sistem ini adalah mampu menentukan kelas dan kualitas mutiara. Dari data sebanyak 25 yang terdiri dari 10 mutiara kualitas A, 10 mutiara kualitas AA, dan 5 mutiara kualitas AAA. Dengan menggunakan Metode K-NN (K-Nearest Neighbor) dan nilai K=1 mampu menghasilkan tingkat akurasi mencapai 92,30%.

Comparison of Solar Radiation Intensity Forecasting Using ANFIS and Multiple Linear Regression Methods Hadi Suyono; Rini Nur Hasanah; R. A. Setyawan; Panca Mudjirahardjo; Anthony Wijoyo; Ismail Musirin
Bulletin of Electrical Engineering and Informatics Vol 7, No 2: June 2018
Publisher : Institute of Advanced Engineering and Science

Solar radiation forecasting is important in solar energy power plants (SEPPs) development. The electrical energy generated from the sunlight depends on the weather and climate conditions in the area where the SEPPs are installed. The condition of solar irradiation will indirectly affect the electrical grid system into which the SEPPs are injected, i.e. the amount and direction of the power flow, voltage, frequency, and also the dynamic state of the system. Therefore, the prediction of solar radiation condition is very crucial to identify its impact into the system. There are many methods in determining the prediction of solar radiation, either by mathematical approach or by heuristic approach such as artificial intelligent method. This paper analyzes the comparison of two methods, Adaptive Neuro Fuzzy Inference (ANFIS) method, which belongs into the heuristic methods, and Multiple Linear Regression (MLP) method, which uses a mathematical approach. The performance of both methods is measured using the root mean square error (RMSE) and the mean absolute error (MAE) values. The data of the Swiss Basel city from Meteoblue are used to test the performance of the two methods being compared. The data are divided into four cases, being classified as the training data and the data used as predictions. The solar radiation prediction using the ANFIS method indicates the results which are closer to the real measurement results, being compared to the the use MLP method. The average values of RMSE and MAE achieved are 123.27 W/m2 and 90.91 W/m2 using the ANFIS method, being compared to 138.70 W/m2 and 101.56 W/m2 respectively using the MLP method. The ANFIS method gives better prediction performance of 12.51% for RMSE and 11.71% for MAE with respect to the use of the MLP method.

Audit dan Rancangan Implementasi Sistem Manajemen Energi berbasis ISO 50001 di Universitas Brawijaya Malang Fajariyah Mulyani; Hadi Suyono; Rini Nur Hassanah
Jurnal EECCIS Vol 12, No 2 (2018)
Publisher : Fakultas Teknik, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (563.772 KB)

Jurnal ini membahas tentang Audit Energi dan perancangan Implementasi Sistem Manajemen Energi Berbasis ISO 50001 di universitas Brawijaya Malang. Hasil Audit akan digunakan sebagai acuan Best practices serta upaya-upaya efisiensi energi yang sedang dan akan terus dilakukan oleh Universitas Brawijaya. Dari Hasil audit energi diperoleh informasi intensitas konsumsi energi terbesar adalah Ac 30%, lain-lain 22,84%, komputer 17,94% serta penerangan dan alat laboratorium sebesar 12,83% dan 12,45%. Hal ini bertujuan untuk mengevaluasi penggunaan energi listriksignificant di Universitas Brawijaya, serta menghitung gambaran kebutuhan energi listrik saat ini dan yang akan datang hingga membangun dasar-dasar sistem manajemen energi yang mengarah ke standar internasional ISO 50001. Kata Kunci – audit energi, intensitas konsumsi energi, perancangan SME berbasis ISO 50001

Peningkatan Keandalan Sistem Distribusi dengan Relokasi Penempatan Fuse-Recloser Optimal karena Injeksi Pembangkit Tersebar Moch Fahrulrozi; Hadi Suyono; Abraham Lomi
Jurnal EECCIS Vol 13, No 2 (2019)
Publisher : Fakultas Teknik, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstrak— Sistem yang paling dekat dengan pelanggan dalam sistem tenaga adalah sistem distribusi. Sistem perlindungan digunakan untuk melokalkan dan mengisolasi area yang bermasalah, dan karena itu jumlah pelanggan yang terputus akan berkurang dan sistem distribusi juga akan meningkat. Peralatan Fuse-recloser adalah perangkat yang biasa digunakan untuk meningkatkan sistem distribusi yang memungkinkan sistem untuk dibuka kembali setelah dibuka karena masalah sistem. Selain itu, sistem yang diperbarui juga akan meningkat dengan injeksi generasi yang terdistribusi dalam sistem distribusi. Namun, penggunaan sekering-recloser perlu dievaluasi dengan injeksi dari generasi yang dikeluarkan dalam sistem distribusi.Solusi optimal untuk relokasi fuse-reclosers yang digunakan adalah metode Particle Swarm Optimization (PSO). Berdasarkan analisis yang dilakukan, dengan injeksi generasi terdistribusi, sistem rilis naik 0,014% dengan SAIFI 2,4073 kali / tahun dan SAIDI sebesar 104,9991 jam / tahun dibandingkan dengan kondisi yang ada.Persyaratan Indeks - sekering-recloser, berjuang, Generasi Terdistribusi, Optimalisasi Kawanan Partikel

PENENTUAN LOKASI PENEMPATAN TCSC PADA SISTEM KELISITRIKAN SULAWESI SELATAN DAN BARAT MENGGUNAKAN INDEKS SENSITIVITAS Nur Vidya Ramadhani; Rini Nur Hasanah; Hadi Suyono
Jurnal Media Elektro Vol 11 No 1 (2022): April 2022
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jme.v0i0.5958

The transmission line that functions to distribute energy from the generating center to the load center must function efficiently. However, the extensive network allows the line operation to be inefficient. This allows the occurrence of power losses and voltage drop in the system. Therefore, efforts are needed to effectively utilize the available power system capacity, one of which is by installing new devices such as TCSC (Thyristor Controlled Series Capacitor). The method used is the Sensitivity Index. Power flow analysis using PSAT (Power System Analysis Toolbox) program. Based on the data analysis that has been done, it was found that the most sensitive line is Pngkep70kV–Mndai. After the installation of the TCSC device on the sensitive line, there was a decrease in power losses and an increase in voltage stability in the system compared to before the installation of TCSC. Thus it can be concluded that the installation of TCSC provides a positive performance on the electricity system of South and West Sulawesi.

Pemodelan Fuzzy Logic Control untuk Pengendali PWM pada Buck Converter Helmy Mukti Himawan; Onny Setyawati; Hadi Suyono
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 5 No 1: Februari 2016
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1177.736 KB)

Recently the switching mode used in a buck converter is controlled by pulse width modulation (PWM) which has relatively higher efficiency compared to a linear power supply system. In general, there are two problems that often occur in the buck converter, First, the difficulties in controlling inductor current which has considerably large ripple, and second, a transient output voltage that appears at the start-up. By using fuzzy logic control in PWM switching mode, the inductor current and output voltage of the buck converter can be controlled. Using Mamdani method fuzzy logic with 2 inputs, i.e. Error and Change of Error, the system produces 1 output, which is duty ratio. The results showed that the fuzzy logic control decreased the error of the output voltage of buck converter by 3%, and decreased the ripple in the inductor current by 1.5% up to 3%.

Title

Found 17 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 17 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 17 Documents
Search