APLIKASI SISTEM CERDAS UNTUK PREDIKSI ENERGI LISTRIK PEMAKAIAN SENDIRI DI PT INDONESIA POWER SUB UNIT PLTA KABUPATEN WONOGIRI

2017 ◽  
Vol 8 (2) ◽  
pp. 489
Author(s):  
Herliyani Hasanah ◽  
Nurmalitasari Nurmalitasari
Keyword(s):  
Fuzzy Inference System ◽  
Input Data ◽  
Fuzzy Inference ◽  
Percentage Error ◽  
Inference System ◽  
Fuzzy C Means ◽  
Neuro Fuzzy ◽  
Fuzzy Input

Kebutuhan akan energi listrik menjadi kebutuhan primer nasional. Dalam keberlangsungan proses produksi energi listrik pada pembangkitan – pembangkitan diperlukan energi listrik untuk pemakaian sendiri. Dalam penelitian ini dibangun sebuah aplikasi sistem cerdas untuk memprediksi energi listrik pemakaian sendiri di PT Indonesia Power sub unit PLTA Wonogiri. Pada penelitian ini menggunakan 2 kelompok input, yaitu input FIS (Fuzzy Inference System) dan input pada NN (Neuro Fuzzy). Input data  merupakan data produksi harian energi listrik di PLTA Wonogiri selama kurun waktu 2010 – 2016. Variabel data yang digunakan dalam penelitian ini adalah data produksi listrik untuk pemakaian PLTA Wonogiri adalah energi listrik yang dihasilkan PLTA Wonogiri dengan satuan KwH (f), elevasi muka air waduk dengan satuan meter (a1) dan debit air yang masuk ke turbin dengan satuan /detik (a2).  Output yang diperoleh adalah pusat centroid (m), derajat keanggotaan (mf), bobot (w) dan konsekuen parameter ( c ). Dari hasil pengujian diperoleh keluaran dengan performansi yang optimal pada saat Fuzzy C Means 2 kelas dengan parameter laju pembelajaran 0.4, momentum 0.6 dengan bessar Mean Percentage Error 0.377970875.  Kata kunci:  prediksi, pemakaian sendiri, energi listrik, fuzzy inference system, neuro fuzzy

scholarly journals Adaptive neuro-fuzzy inference system for temperature and humidity profile retrieval from microwave radiometer observations

2015 ◽  
Vol 8 (1) ◽  
pp. 369-384 ◽  
Author(s):  
K. Ramesh ◽  
A. P. Kesarkar ◽  
J. Bhate ◽  
M. Venkat Ratnam ◽  
A. Jayaraman
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Microwave Radiometer ◽  
Percentage Error ◽  
Computational Techniques ◽  
Temperature Profiles ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Temperature And Humidity ◽  
Rainy Days

Abstract. The retrieval of accurate profiles of temperature and water vapour is important for the study of atmospheric convection. Recent development in computational techniques motivated us to use adaptive techniques in the retrieval algorithms. In this work, we have used an adaptive neuro-fuzzy inference system (ANFIS) to retrieve profiles of temperature and humidity up to 10 km over the tropical station Gadanki (13.5° N, 79.2° E), India. ANFIS is trained by using observations of temperature and humidity measurements by co-located Meisei GPS radiosonde (henceforth referred to as radiosonde) and microwave brightness temperatures observed by radiometrics multichannel microwave radiometer MP3000 (MWR). ANFIS is trained by considering these observations during rainy and non-rainy days (ANFIS(RD + NRD)) and during non-rainy days only (ANFIS(NRD)). The comparison of ANFIS(RD + NRD) and ANFIS(NRD) profiles with independent radiosonde observations and profiles retrieved using multivariate linear regression (MVLR: RD + NRD and NRD) and artificial neural network (ANN) indicated that the errors in the ANFIS(RD + NRD) are less compared to other retrieval methods. The Pearson product movement correlation coefficient (r) between retrieved and observed profiles is more than 92% for temperature profiles for all techniques and more than 99% for the ANFIS(RD + NRD) technique Therefore this new techniques is relatively better for the retrieval of temperature profiles. The comparison of bias, mean absolute error (MAE), RMSE and symmetric mean absolute percentage error (SMAPE) of retrieved temperature and relative humidity (RH) profiles using ANN and ANFIS also indicated that profiles retrieved using ANFIS(RD + NRD) are significantly better compared to the ANN technique. The analysis of profiles concludes that retrieved profiles using ANFIS techniques have improved the temperature retrievals substantially; however, the retrieval of RH by all techniques considered in this paper (ANN, MVLR and ANFIS) has limited success.

scholarly journals Early Warning System for Flood Disaster Prediction in Wetland Area in Greater Yola Using Adaptive Neuro Fuzzy Inference System

2019 ◽  
pp. 1-19
Author(s):  
Ishaya Bitrus ◽  
P. B. Zirra ◽  
Sarjiyus Omega
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Human Life ◽  
Warning System ◽  
Flood Disaster ◽  
Percentage Error ◽  
Flood Prediction ◽  
Inference System ◽  
Flood Level ◽  
Neuro Fuzzy

Natural calamity disrupts our daily life activities; thereby bring many sufferings in our life. One of the natural disasters is the flood. Flood is one of the most catastrophic disasters. However, too much rainfall courses environmental hazard. These prompted to flood prediction in order to help communities and Government with the necessary tool to take precaution to safe human life and properties. This work was developed using an (ANFIS) Adaptive Neuro-Fuzzy Inference System to compare some weather parameter (temperature and relative humidity) with rainfall to forecast the amount of rainfall capable of coursing flood in the study area. From the above graph (Fig. 22) it can be seen that the actual and the forecasted rainfall followed the same pattern from 2008 to 2010 with slight decrease in 2011. A high amount of rainfall in 2012 was forecasted to be flooded during that year and tally with the forecasted rainfall on the above graph in 2012. Based on the results on the graph, it shows that from 2014 to 2017 gives a constant flow between the actual and forecasted rainfall. It is predicted that the maximum amount of rainfall forecasted was 124.0 mm which is far below the recommended flood level of 160.0 mm which reveals that, River Benue would not experience flood disaster in the year ahead. The model developed was validated using (MAPE) Mean Absolute Percentage Error as 4.0% with model efficiency of 96.0% which shows very high excellent prediction accuracy.

scholarly journals Performance of Clustering on ANFIS for Weather Forecasting

2018 ◽  
Vol 12 (1) ◽  
pp. 43
Author(s):  
Candra Dewi
Keyword(s):  
Fuzzy Inference System ◽  
Rainy Season ◽  
Fuzzy Inference ◽  
Weather Forecasting ◽  
Dry Season ◽  
Inference System ◽  
Fuzzy C Means ◽  
Neuro Fuzzy ◽  
Total Data ◽  
Dry Seasons

This paper proposes the comparison of using K-Means and Fuzzy C-Means (FCM) to optimize the premise parameters on Adaptive Neuro-Fuzzy Inference System (ANFIS) for weather forecasting. The ANFIS architecture groups each of the feature inputs in the first layer into three clusters, and uses three rules for the second layer. The comparison is performed based on the RMSE value and the number of iteration. The testing is done on the percentage of 40%, 50%, and 60% of the total data. In addition, the testing is done by grouping the data based on season called rainy and dry seasons. The testing results show that both K-Means and FCM havealmost the same RMSE, except for rainy season where K-Means has better RMSE. However, K-Means requires relatively more iterations to achieve convergence. The use of FCM, in general, gives better results than K-Means. It is also shown that ANFIS provides the best performance for data onto the dry season.

scholarly journals AN ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM FOR FORECASTING AUSTRALIA’S DOMESTIC LOW COST CARRIER PASSENGER DEMAND

Aviation ◽  
2015 ◽  
Vol 19 (3) ◽  
pp. 150-163 ◽  
Author(s):  
Panarat Srisaeng ◽  
Glenn S. Baxter ◽  
Graham Wild
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Learning Algorithm ◽  
Low Cost ◽  
Percentage Error ◽  
Subtractive Clustering ◽  
Data Set ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Partition Method

This study has proposed and empirically tested two Adaptive Neuro-Fuzzy Inference System (ANFIS) models for the first time for predicting Australia‘s domestic low cost carriers‘ demand, as measured by enplaned passengers (PAX Model) and revenue passenger kilometres performed (RPKs Model). In the ANFIS, both the learning capabilities of an artificial neural network (ANN) and the reasoning capabilities of fuzzy logic are combined to provide enhanced prediction capabilities, as compared to using a single methodology. Sugeno fuzzy rules were used in the ANFIS structure and the Gaussian membership function and linear membership functions were also developed. The hybrid learning algorithm and the subtractive clustering partition method were used to generate the optimum ANFIS models. Data was normalized in order to increase the model‘s training performance. The results found that the mean absolute percentage error (MAPE) for the overall data set of the PAX and RPKs models was 1.52% and 1.17%, respectively. The highest R2-value for the PAX model was 0.9949 and 0.9953 for the RPKs model, demonstrating that the models have high predictive capabilities.

scholarly journals Adaptive neuro fuzzy inference system for profiling of the atmosphere

2014 ◽  
Vol 7 (3) ◽  
pp. 2715-2736 ◽  
Author(s):  
K. Ramesh ◽  
A. P. Kesarkar ◽  
J. Bhate ◽  
M. Venkat Ratnam ◽  
A. Jayaraman
Keyword(s):  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Percentage Error ◽  
Computational Techniques ◽  
Temperature Profiles ◽  
Atmospheric Parameters ◽  
Wet Season ◽  
Anfis Model ◽  
Inference System ◽  
Neuro Fuzzy

Abstract. Retrieval of accurate profiles of temperature and water vapor is important for the study of atmospheric convection. However, it is challenging because of the uncertainties associated with direct measurement of atmospheric parameters during convection events using radiosonde and retrieval of remote-sensed observations from satellites. Recent developments in computational techniques motivated the use of adaptive techniques in the retrieval algorithms. In this work, we have used the Adaptive Neuro Fuzzy Inference System (ANFIS) to retrieve profiles of temperature and humidity over tropical station Gadanki (13.5° N, 79.2° E), India. The observations of brightness temperatures recorded by Radiometrics Multichannel Microwave Radiometer MP3000 for the period of June–September 2011 are used to model profiles of atmospheric parameters up to 10 km. The ultimate goal of this work is to use the ANFIS forecast model to retrieve atmospheric profiles accurately during the wet season of the Indian monsoon (JJAS) season and during heavy rainfall associated with tropical convections. The comparison analysis of the ANFIS model retrieval of temperature and relative humidity (RH) profiles with GPS-radiosonde observations and profiles retrieved using the Artificial Neural Network (ANN) algorithm indicates that errors in the ANFIS model are less even in the wet season, and retrievals using ANFIS are more reliable, making this technique the standard. The Pearson product movement correlation coefficient (r) between retrieved and observed profiles is more than 99% for temperature profiles for both techniques and therefore both techniques are successful in the retrieval of temperature profiles. However, in the case of RH the retrieval using ANFIS is found to be better. The comparison of mean absolute error (MAE), root mean square error (RMSE) and symmetric mean absolute percentage error (SMAPE) of retrieved temperature and RH profiles using ANN and ANFIS also indicates that profiles retrieved using ANFIS are significantly better compared to the ANN technique. The error analysis of profiles concludes that retrieved profiles using ANFIS techniques have improved the retrievals substantially; however, retrieval of RH by both techniques (ANN and ANFIS) has limited success.

scholarly journals Adaptive Neuro-Fuzzy Inference System-Based Maximum Power Tracking Controller for Variable Speed WECS

Energies ◽  
2021 ◽  
Vol 14 (19) ◽  
pp. 6275
Author(s):  
Abrar Ahmed Chhipa ◽  
Vinod Kumar ◽  
R. R. Joshi ◽  
Prasun Chakrabarti ◽  
Michal Jasinski ◽  
...  
Keyword(s):  
Wind Speed ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Maximum Power ◽  
Membership Functions ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Fuzzy Input ◽  
Wide Range ◽  
Mppt Controller

This paper proposes an adaptive neuro-fuzzy inference system (ANFIS) maximum power point tracking (MPPT) controller for grid-connected doubly fed induction generator (DFIG)-based wind energy conversion systems (WECS). It aims at extracting maximum power from the wind by tracking the maximum power peak regardless of wind speed. The proposed MPPT controller implements an ANFIS approach with a backpropagation algorithm. The rotor speed acts as an input to the controller and torque reference as the controller’s output, which further inputs the rotor side converter’s speed control loop to control the rotor’s actual speed by adjusting the duty ratio for the rotor side converter. The grid partition method generates input membership functions by uniformly partitioning the input variable ranges and creating a single-output Sugeno fuzzy system. The neural network trained the fuzzy input membership according to the inputs and alter the initial membership functions. The simulation results have been validated on a 2 MW wind turbine using the MATLAB/Simulink environment. The controller’s performance is tested under various wind speed circumstances and compared with the performance of a conventional proportional–integral MPPT controller. The simulation study shows that WECS can operate at its optimum power for the proposed controller’s wide range of input wind speed.

Sign in / Sign up

Export Citation Format

Share Document