Intelligent control for modeling of real-time reservoir operation, part II: artificial neural network with operating rule curves

Abstract

Abstract:To bridge the gap between academic research and actual operation, we propose an intelligent control system for reservoir operation. The methodology includes two major processes, the knowledge acquired and implemented, and the inference system. In this study, a genetic algorithm (GA) and a fuzzy rule base (FRB) are used to extract knowledge based on the historical inflow data with a design objective function and on the operating rule curves respectively. The adaptive network-based fuzzy inference system (ANFIS) is then used to implement the knowledge, to create the fuzzy inference system, and then to estimate the optimal reservoir operation. To investigate its applicability and practicability, the Shihmen reservoir, Taiwan, is used as a case study. For the purpose of comparison, a simulation of the currently used M-5 operating rule curve is also performed. The results demonstrate that (1) the GA is an efficient way to search the optimal input-output patterns, (2) the FRB can extract the knowledge from the operating rule curves, and (3) the ANFIS models built on different types of knowledge can produce much better performance than the traditional M-5 curves in real-time reservoir operation. Moreover, we show that the model can be more intelligent for reservoir operation if more information (or knowledge) is involved.

Prediction Of Flow Through Rockfill Dams Using A Neuro-fuzzy Computing Technique

“…In recent years, artificial intelligence technique such as neuro-fuzzy has become increasingly popular in hydrology and water resources among researchers and practicing engineers. For instance; neuro-fuzzy has been used successfully for prediction of suspended sediment ( [24], [8], [26], [37]), evaporation and evapotranspiration modeling ( [23], [25], [3], [30]), real time reservoir operation ( [6], [7], [36]), ground-water vulnerability [10], modeling stage-discharge relationship ( [9], [28]), water quality problems [29], estimation of scour depth near pile groups [49], short-term flood forecasting [33], rainfall-runoff modeling ( [14], [20]), prediction of water level in reservoir [5], modeling hydrological time series ([32], [13]). …”

A stochastic approach to the operative control of flood flows through a reservoir

“…A variety of case studies has been published in which the decision-making phase of the selected control model involves the use of artificial intelligence methods, including genetic algorithms, fuzzy logic and neural networks, e.g. Chang and Chang (2001), Dubrovin et al (2002) and Chang et al (2005). The application of the above methods in the development of control algorithms is also tested during normal operation of the reservoir, with the main criteria being to ensure the necessary volume and quality of water (Butcher, 1971;Chandramouli and Nanduri, 2011;Chaves et al, 2004), especially during flood situations (Chang et al, 2011).…”

A spatial neural fuzzy network for estimating pan evaporation at ungauged sites

“…The nonlinear characteristics of ANNs often serve as a viable tool for physical or stochastic models in various hydrological fields (Antar et al, 2006;Chen and Chang, 2009;Chiang and Chang, 2009;Chang et al, 2005;Kim and Barros, 2001). In recent years, the applications of ANN to evaporation estimation were presented in many studies (Trajkovic et al, 2003;Keskin and Terzi, 2006;Kisi, 2006;Kisi and Ozturk, 2007;Gonzalez-Camacho et al, 2008;Chang et al, 2010).…”