Relationships between Hydropower Generation and Rainfall-Gauged and Ungauged Catchments from Sri Lanka

Anushka Perera,Upaka Rathnayake

doi:10.1155/2020/9650251

Anushka Perera, Upaka Rathnayake

Open Access

https://doi.org/10.1155/2020/9650251

Copy DOI

Abstract

The relationship between the rainfall and minihydropower generation in a catchment is highly nonlinear. Therefore, the prediction of minihydropower generation is complex. However, the prediction is important in optimizing the control of electricity generation under various environmental conditions. Ongoing climate variabilities have completely changed the minihydropower generation to some parts of the world, and it is significant. Therefore, this paper presents results from two soft-computing studies in searching the relationships between rainfall and the generated hydropower. The first study was carried out for a gauged catchment; however, the second was carried for an ungauged catchment. Results revealed that there is an acceptable correlation in between the rainfall and hydropower generation for the gauged catchment and a marginal contribution to the ungauged catchment.

Highlights

Renewable energy is generated from natural resources including rainwater, wind, sun-light, and ocean tides
Artificial Neural Networks (ANNs) programs consume significant time durations. erefore, the unsuitability of the ANN to predict Erathna hydropower generation based on the rainfall to set 1 rain gauges is established
Artificial neural network results reveal the relationships between rainfall and the hydropower generation of two minihydropower plants in Sri Lanka

Summary

Introduction

Renewable energy is generated from natural resources including rainwater, wind, sun-light, and ocean tides. Use of soft-computing techniques has been popular among researchers to predict the power generation from hydropower systems in the world Softcomputing techniques such as Artificial Neural Networks (ANNs), Data mining (DM), Support vector machines (SVM), Adaptive Neuro-Fuzzy Interference System (ANFIS), and Genetic Programming (GP) have widely been used in power generation prediction models [13,14,15,16,17,18]. Several studies have been carried out in Sri Lanka to investigate the impact of climate variability on the power generation in minihydropower plants. Erefore, as a country which is highly relying on hydropower, predicting the potential hydropower generation in the future years is extremely important to balance the energy demand and the country’s economic model.

Denawaka Ganga and Erathna Minihydropower Plants

Neural Network Models for Catchments

Results and Discussion

Conclusions