Inferring operating rules for reservoir operations using fuzzy regression and ANFIS

摘要: The methods of ordinary least-squares regression (OLSR), fuzzy (FR), and adaptive network-based inference system (ANFIS) are compared in inferring operating rules for a reservoir operations optimization problem. Dynamic programming (DP) is used as an example tool to provide the input-output data set be by OLSR, FR, ANFIS models. coefficients FR model found solving linear (LP) objective function LP minimize total fuzziness model, which related width model. Before applying problem, two formulations interval (IR) first examined simple tutorial example. also derive IF-THEN rules. based then simulated on their performance simulation. applied long-term planning problem well medium-term implicit stochastic results indicate that useful where imperfect partial information available. beneficial it able extract important features from generated represent those general