Development of Fuzzy Based Autoregressive Moving Average Exogenous Input Model for Water Flow in Nigerian Kanji Hydro-Power Dam

Abstract

Design of robust control system for any system requires model-driven approach. Therefore, it becomes imperative to develop a dynamic  model suitable for controller design on safety operation of hydropower dam for power production in Kanji dam in Nigeria. Model for  reservoir flow was developed in MATLAB environment using Fuzzy Based Autoregressive Moving Average Exogenous Input (FARMAX)  model structure in this study. The data used for model development covered a period of ten years (2003-2013). It consists of water inflow  (WI), water outflow (WO) and spillage (S). WI and S are input variables while WO was the output variable. The model obtained using the  unsmoothed data with an outlier gave -14.115%, - 0.302 and 610.317 for fit, R² and RMSE, respectively. Unsmoothed data with no outlier  gave -13.802%, - 0.295 and 608.643 corresponding to fit, R² and RMSE, respectively. The model obtained using the smoothed data in the  presence of an outlier gave 80.533%, 0.962 and 104.113 for fit, R2 and RMSE, respectively. Smoothed data in the absence of outlier gave  81.533%, 0.962 and 99.637 for to fit, R² and RMSE, respectively. FARMAX has the best fit value of 87.8774% when number of rules was  equal to 3 with optima model order of 3 1 4 3. The model can serve as a decision support system in evaluating the optimal reservoir   operation policies in real time.