An implementation of Artificial Neural Reservoir Computing Technique for Inflow Forecasting of Nagarjuna Sagar dam
B. Pradeepakumari1, Kota.Srinivasu2
1
B. Pradeeepakumari, Department of Civil Engg., Acharya Nagarjuna University, Guntur, India.
2K. Srinivasu, Department of Civil Engg., RVR&JC College of Engnn., Guntur, India.

Manuscript received on 01 April 2019 | Revised Manuscript received on 06 May 2019 | Manuscript published on 30 May 2019 | PP: 860-864 | Volume-8 Issue-1, May 2019 | Retrieval Number: A9287058119/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: All over India flash flood or recurring flood is one of the major natural disaster causing life and economic threats. Several times a year, some or the other state disaster management in India have to face this. Forecasting system for inflow of any dam plays a key role in this disaster and its recovery. Current forecasting systems follow conventional, graphical metrological procedures and limited Artificial Neural Network models.This work provides novel model for forecasting inflow of a dam. Proposed model uses Neural Reservoir Computing for forecasting inflow. Forecasts are based on standard dam parameters like inflow. Most importantly, forecasts done are several days ahead of time. This would help disaster management systems to be prepared well in advance to save lives. Proposed system is demonstrated over data from two major dams in Andhra Pradesh. Results are compared with statistical forecasting models like AR, MA, & ARIMA and Artificial Neural Networks (ANN) model. Comparison prove proposed neural reservoir computing model to be better than existing systems.
Keywords: Artificial Neural Reservoir Computing; ARIMA; Inflow forecasting; Nagarjunasagar dam.

Scope of the Article: Artificial Intelligent Methods, Models, Techniques