A Cascaded Adaptive Network-Based Fuzzy Inference System for Hydropower Forecasting

Abstract

Hydropower stands as a crucial source of power in the current world, and there is a vast range of benefits of forecasting power generation for the future. This paper focuses on the significance of climate change on the future representation of the Samanalawewa Reservoir Hydropower Project using an architecture of the Cascaded ANFIS algorithm. Moreover, we assess the capacity of the novel Cascaded ANFIS algorithm for handling regression problems and compare the results with the state-of-art regression models. The inputs to this system were the rainfall data of selected weather stations inside the catchment. The future rainfalls were generated using Global Climate Models at RCP4.5 and RCP8.5 and corrected for their biases. The Cascaded ANFIS algorithm was selected to handle this regression problem by comparing the best algorithm among the state-of-the-art regression models, such as RNN, LSTM, and GRU. The Cascaded ANFIS could forecast the power generation with a minimum error of 1.01, whereas the second-best algorithm, GRU, scored a 6.5 error rate. The predictions were carried out for the near-future and mid-future and compared against the previous work. The results clearly show the algorithm can predict power generation's variation with rainfall with a slight error rate. This research can be utilized in numerous areas for hydropower development.

Keywords: Cascaded-ANFIS; GRU; LSTM; RNN; Sri Lanka; forecasting; hydropower; regression.

Figure 1

Rainfall gauges at Samanalawewa catchment.

Figure 2

Flowchart of the Cascaded ANFIS.

Figure 3

Hydropower prediction Cascaded ANFIS structure.

Figure 4

Coefficients of Determination $\left(R^2\right)$ of Rain Fall Test dataset for (a) KNN, (b) MLP, (c) ANFIS (d) PSO-ANFIS, and (e) GA-ANFIS.

Figure 5

Coefficients of Determination $\left(R^2\right)$ of Rain Fall Test dataset for (a) linear regression, (b) lasso regression, (c) ridge regression (d) RNN, (e) LSTM, and (f) GRU.

Figure 6

Cascaded ANFIS behavior for different levels. (a) Level 1, (b) level 10, (c) level 20.

Figure 7

Power generation predictions from year 2021 to 2040.

Figure 8

Power generation predictions from 2041 to 2099.

Figure 9

Hydropower predictions from Khaniya et al. (2020) [12].