Two search methods are currently available for calibrating the HEC-HMS program: the Univariate Gradient (UG) and the Nelder Mead (NM) methods; both having poor performance in continuous models with snowmelt module. In this paper, a novel approach using Melody Search algorithm (MeS) is presented for auto-calibration of HEC-HMS and compared to Self-adaptive Global Harmony Search (SGHS) and Genetic Algorithms (GA). The results show that the suggested approach is able to overcome the poor performance of aforementioned methods yielding more enhanced solutions. While NM and UG reach a Nash Sutcliffe Index (NSE) of −0.33 and 0.105, GA, SGHS and MeS have been able to reach to 0.526, 0.635, and 0.674 respectively. In addition, the improving power of algorithms was tested by starting from the final solution found by the other methods. It was noticed that in all cases MeS and to some degree SGHS are able to substantially improve the solutions found by either UG or NM. Interestingly, while SGHS was able to slightly improve the solution of MeS algorithm, MeS made a substantial improvement on the solution reached by the SGHS. Finally, the novel MeS based multi-objective algorithm proposed here, i.e. NSMeS, and Non-dominated Sorting Genetic Algorithm-II (NSGA-II) are compared with different combinations of objective functions where NSMeS demonstrated better performance.
In this paper, a many-objective optimization algorithm was developed using SPEA2 for a system of four reservoirs in the Karun basin, including hydropower, municipal and industrial, agricultural, and environmental objectives. For this purpose, using 53 years of available data, hedging rules were developed in two modes: with and without applying fuzzy logic. SPEA2 was used to optimize hedging coefficients using the first 43 years of data and the last 10 years of data were used to test the optimized rule curves. The results were compared with those of non-hedging methods, including the standard operating procedures (SOP) and water evaluation and planning (WEAP) model. The results indicate that the combination of fuzzy logic and hedging rules in a many-objectives system is more efficient than the discrete hedging rule alone. For instance, the reliability of the hydropower requirement in the fuzzified discrete hedging method in a drought scenario was found to be 0.68, which is substantially higher than the 0.52 from the discrete hedging method. Moreover, reduction of the maximum monthly shortage is another advantage of this rule. Fuzzy logic reduced 118 million cubic meters (MCM) of deficit in the Karun-3 reservoir alone. Moreover, as expected, the non-hedging SOP and WEAP model produced higher reliabilities, lower average storages, and less water losses through spills.
15 July 2016 in International Journal of River Basin Management
The proper function of artificial neural networks (ANNs) depends on several factors including the suitability of input variables and the amount of information they can add to the model in order to produce the required target output(s). Wavelet transforms and to lesser extent singular spectrum analysis (SSA) are well known and widely applied pre-processing methods to enhance ANN models. An important step in the SSA algorithm and wavelet transform method is choosing the window length (L) and determining the suitable number of decomposition stages, respectively. In most past research, these parameters have been used as granted. Moreover, a research to show the impact of using a combination of wavelet and SSA is absent. This study addresses an approach to optimize window length for SSA and number of decomposition stages for wavelet transform applied in a rainfall-runoff model. Moreover, a hybrid neural network is developed to take the advantage of wavelet and SSA-based ANN models. The results show a significant improvement in model outputs both for optimizing the decomposition parameters and for using the proposed hybrid model.
12 June 2021 in Iranian Journal of Science and Technology, Transactions of Civil Engineering
In recent years, the use of various Artificial Intelligence (AI) methods, such as evolutionary computation, heuristic algorithms, artificial neural networks, and fuzzy theory calculations, has gained popularity in addressing water resources issues. These algorithms have shown great success in solving problems that traditional deterministic methods struggle with. This study focuses on optimizing Dez reservoir operation over a long-term period using a nonlinear loss function through an evolutionary artificial neural network algorithm. The outcomes of this approach are then contrasted with genetic exploration and harmony search algorithms, highlighting the strengths and weaknesses of each method. Ultimately, a combination of the evolutionary artificial neural network method and hedging models is employed for optimal reservoir management, with results compared to the previous approach. Results show the appropriate performance of combining hedging policy with artificial neural network and harmony search algorithm. This combination significantly reduces the vulnerability value with a slight decrease in reliability.
Projecting future inflows under climate change and rapidly growing population has large uncertainty and requires serious attention for proper utilization of limited water resources. Existing algorithms can only optimize the operation policy for a specified scenario (e.g., drought, wet, or normal year; decreased or increased demands) and when established, the system would face serious operational difficulty if the expected scenario does not occur. On the other hand, most of water resources systems involve more than three objectives and demand proper techniques to handle computational complexities in so-called many-objective problems. This paper aims at providing a many-objective optimization algorithm using social choice (SC) and melody search (MeS) algorithms that is able to efficiently derive general system operation rules suitable for all possible future scenarios. In other words, the proposed algorithm overcomes uncertainties in the occurrence of future scenarios and works optimally regardless of future conditions; whether it be variable streamflows and/or increased water demands. To evaluate the performance of the proposed algorithm, a system consisting of five reservoirs in the Tehran region with four objective functions. It is shown that in all cases the general multi-scenario rule derived by the proposed method performs as good as each of the operation rules derived for every specific scenario assuming the occurrence of that scenario. Moreover, the proposed many-objective algorithm is able to handle as many objectives as needed without any computational burden and/or algorithm complexity.