| Abstrakt: |
Nowadays, the information based communication technologies help to integrate the smart grid systems with the renewable energies. Also, it improves the process of energy production, quality performance, demand prognosis, and substantiality. In the day-to-day life, the Internet of Things (IoT) plays an essential role that enables the connectedness between many physical devices via internet. Moreover, it enables the data exchange for monitoring and directing the devices across the globe with the use of internet connection. Naturally, the solar Photovoltaic (PV) power generators are highly sensitive to the measures of solar irradiance, and temperature for data analysis and energy prediction. So, most of the traditional works have focused on the integration of IoT platform with the smart grid technologies for PV monitoring and controlling. But, it has the limitations of increased cost consumption, complexity, and inefficiency. In order to solve these issues, this paper intends to develop a new mechanism, named as, Fuzzy Logic based Recompense Scheme (FLRS) for an efficient compensation of solar irradiance and temperature of sensor devices. In addition to that, an energy forecasting is also concentrated in this paper for satisfying the energy demand in future. For this purpose, a Hybrid Ant Colony Optimization - Artificial Neural Network (HAA) technique is implemented, which performs an optimization based energy forecasting. After compensating the sensors error, the energy forecasting can be done with the use of optimization based classification mechanism. During experimentation, the performance of both algorithms such as FLRS and HAA are validated by using various measures, and also it is compared with the existing techniques for proving its superiority. [ABSTRACT FROM AUTHOR] |
