Programs
- M. Tech. in Automotive Engineering -
- Clinical Fellowship in Laboratory Genetics & Genomics - Fellowship
Publication Type : Book Chapter
Publisher : Springer, Cham
Source : In: Sumithra, M.G., Sathyamoorthy, M., Manikandan, M., Dhanaraj, R.K., Ouaissa, M. (eds) Computational Intelligence in Internet of Agricultural Things, Studies in Computational Intelligence, vol 1170. Springer, Cham, 2024. https://doi.org/10.1007/978-3-031-67450-1_17
Url : https://link.springer.com/chapter/10.1007/978-3-031-67450-1_17
Campus : Bengaluru
School : School of Engineering
Department : Electrical and Electronics
Year : 2024
Abstract : One of the causes of global warming is the burning of fossil fuels. Increasing the usage of renewable energy sources is a key strategy for combating global warming and greenhouse gases. The photovoltaic (PV) system employs solar energy, which is a form of renewable energy is environmentally friendly and sustainable; however, it is challenging to generate power with this technology. The best solution to this issue is to use efficient algorithms that improves the solar power generation. Use of solar power is one of the approaches for energy optimization. Agriculture is one of the most important domains in India and utilization of smart and efficient technological solutions are the way to sustainable future. The pumped hydro technology helps conserve water and produces energy when demand is at its highest. It meets the water and energy requirements of a farm. It incorporates the best water controller with fantastic water-saving technology to account for the present and future needs of the farmhouses. When to irrigate, how much water must be stored, and how much hydropower needs to be pumped are all determined by this system. The water controller obtains the sensor readings and the farmstead's current condition to alter the power drawn from the pump and the turbine flow rate with maximum efficiency. It is possible to provide farmers with accurate information using sensors that send data directly to them. The proposed system has undergone a simulated study first. According to the results, this system might sustainably utilize its conserved water. However, managing the pump and turbine can be more cost-effective. So, a farmer may have all the knowledge about his farm's requirements and productivity at his fingertips by utilizing sensors and the Internet of Things. Because they didn't have to worry about the plant's water supply, farmers benefited from this whenever they went out to work on other projects. The hardware prototype of the proposed system with IoT application has also been implemented, and the results are analysed. In addition to the deployment of technologies to optimize the utilization of resources, agriculture section also demands the intervening of technologies for improving the yield. The Agriculture Industry is facing challenges in meeting the increasing demand for food production with limited resources. Machine learning algorithms and IoT devices have the potential to revolutionize traditional farming practices and optimize crop yield. The proposed works presents a location-specific approach for crop prediction using soil moisture and DHT sensors integrated with machine learning algorithms. The proposed system provides real-time monitoring of environmental variables and predicts the optimal crop to be grown at a specific location. The NodeMCU module has been used to collect and transmit data from the sensors, and a DC motor pump is used for irrigation purposes. The proposed system has significant potential to enable farmers to optimize their crop yield, conserve resources, and reduce costs.
Cite this Research Publication : Konduru Vandana, Singampalli Sravya, Mucherla Supriya, N. Gunavardhan Reddy, John Babu Bale, I. V. Satyanarayana Sarma & P. V. Manitha, "Case Study on Smart Irrigation Using Internet of Things and XAI Techniques," In: Sumithra, M.G., Sathyamoorthy, M., Manikandan, M., Dhanaraj, R.K., Ouaissa, M. (eds) Computational Intelligence in Internet of Agricultural Things, Studies in Computational Intelligence, vol 1170. Springer, Cham, 2024. https://doi.org/10.1007/978-3-031-67450-1_17