RANCANG BANGUN SMART METER BERBASIS NILM UNTUK MEMANTAU PEMAKAIAN ENERGI LISTRIK PADA SEKTOR RUMAH TANGGA MENGGUNAKAN NEURAL NETWORK
Abstract
In this study carried out using household electrical loads, such as televisions, lights, water pumps, irons, fans,
and dispensers. The use of the Neural Network algorithm is used as a load identification method. In its application there
are several procedures / steps taken to make a neuron that can recognize and decide on an action. The procedure is
training and neuron testing to be made. Matlab software has a Neural Network tool, which in this study will be used.
Load sampling data is used as input data for neural network training. As output / target load classification is used. Load
classification method, where 1 for TV load classification, 2 for fan load, 3 for ironing load, 4 for water pump load, 5 for
lamp load, 6 for dispenser load, and 7 for load combination of fan iron. The total load is 6 single loads and 1 combination
load. One load combination is chosen because, on the combination load characteristics when the fan has characteristics
that are not the same as the others. The sampling of current data for each load will be used as neural network training.
Load data used is 30 samples or for 30 seconds, with each minute the data is taken. From the results of the training it can
be seen, that the biggest training error is found in the seventh data, which is the identification of the load in the fan-iron
load classification. This is because the current pattern on the iron and fan with the iron or fan itself has almost the same
characteristics. However, for this process networks will be used and then the PSO optimization method is used to reduce
the error, in the next study. From the test results it is shown that by varying the input data of each load, networks have
been able to identify well.
and dispensers. The use of the Neural Network algorithm is used as a load identification method. In its application there
are several procedures / steps taken to make a neuron that can recognize and decide on an action. The procedure is
training and neuron testing to be made. Matlab software has a Neural Network tool, which in this study will be used.
Load sampling data is used as input data for neural network training. As output / target load classification is used. Load
classification method, where 1 for TV load classification, 2 for fan load, 3 for ironing load, 4 for water pump load, 5 for
lamp load, 6 for dispenser load, and 7 for load combination of fan iron. The total load is 6 single loads and 1 combination
load. One load combination is chosen because, on the combination load characteristics when the fan has characteristics
that are not the same as the others. The sampling of current data for each load will be used as neural network training.
Load data used is 30 samples or for 30 seconds, with each minute the data is taken. From the results of the training it can
be seen, that the biggest training error is found in the seventh data, which is the identification of the load in the fan-iron
load classification. This is because the current pattern on the iron and fan with the iron or fan itself has almost the same
characteristics. However, for this process networks will be used and then the PSO optimization method is used to reduce
the error, in the next study. From the test results it is shown that by varying the input data of each load, networks have
been able to identify well.
Full Text:
PDFRefbacks
- There are currently no refbacks.