An Intellectual Energy Device for Household Appliances Using Artificial Neural Network
This article highlights the importance of implementing intelligent monitoring devices with the internet of things (IoT) for observing the amount of charges on different appliances in each household. In India, it has been observed that 20% of power is wasted due to commercial appliances where the amo...
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Hindawi Limited
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/8144ff1314884ba78ab33ddd9b87a086 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | This article highlights the importance of implementing intelligent monitoring devices with the internet of things (IoT) for observing the amount of charges on different appliances in each household. In India, it has been observed that 20% of power is wasted due to commercial appliances where the amount of charge flow is much excess to corresponding appliances. Therefore, to perceive information about the flow of charges, it is necessary to implement an intelligent device, and it is possible to obtain exact information on the flow of charges with the help of wireless sensor networks (WSN). Even most of the researchers have developed an intelligent device for monitoring the amount of charges but delay, energy consumption, and cost of implementation are much higher. It is always necessary to extract precise information at corresponding time periods for reducing the delay in packet transmission of a specific network. To excerpt such real-time data in the network layer, an active procedure should be followed by integrating dissimilar network areas inside a single cluster, and binary coded artificial neural network (BCANN) is introduced to acquire information about hidden layers. To prove the effect of such integration process, several tests have been prepared using online and offline analyses where simulation results prove to be much effective in case of all different scenarios to an extent of 52.4% when compared to existing methods. |
|---|