Intelligent reservoir operation system based on evolving artificial neural networks

Chaves, Paulo; Chang, Fi-John

doi:10.1016/j.advwatres.2008.03.002

Cited by 94 publications

(47 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alshaikh and Taher [3], Chaves and Chang [7], Gates and Alshaikh [9], Neelakantan and Pundarikanthan [13], and Simonovic [15] evaluated the efficiency of simulation optimization frameworks by incorporating data driven models with optimization algorithms. In water resources, for development of optimal policies of system operation, different methodologies are employed such as mathematical models, distributed physically-based models, and empirical models.…”

Section: Current Water Reservoir Modelsmentioning

confidence: 99%

Temporal data mining of uncertain water reservoir data

Mohan

Révész

2012

Proceedings of the Third ACM SIGSPATIAL International Workshop on Querying and Mining Uncertain Spatio-Temporal Data

View full text Add to dashboard Cite

This paper describes the challenges of data mining uncertain water reservoir data based on past human operations in order to learn from them reservoir policies that can be automated for the future operation of the water reservoirs. Records of human operations of water reservoirs often contain uncertain data. For example, the recorded amounts of water released and retained in the water reservoirs are typically uncertain, i.e., they are bounded by some minimum and maximum values. Moreover, the time of release is also uncertain, i.e., typically only monthly or weekly amounts are recorded. To increase the effectiveness of data mining of uncertain water reservoir data, temporal data mining with inflow and rainfall data from several prior months was used. The experiments also compared several different data classification methods for robustness in the case of uncertain data.

show abstract

Section: Current Water Reservoir Modelsmentioning

confidence: 99%

Temporal data mining of uncertain water reservoir data

Mohan

Révész

2012

Proceedings of the Third ACM SIGSPATIAL International Workshop on Querying and Mining Uncertain Spatio-Temporal Data

View full text Add to dashboard Cite

show abstract

“…The main benefit of adapting ANNs are that they can effectively extract significant features and trends from complex data structures even if the underlying physics is either unknown or difficult to recognize. In the field of hydrology, various research results that were produced by the ANNs have reported the improvements in the performances of simulations such as rainfall forecasting (Chiang and Chang, 2009;Chiang et al, 2007a;Hung et al, 2009;Nasseri et al, 2008), reservoir operation (Chandramouli and Deka, 2005;Chang and Chang, 2001;Chaves and Chang, 2008), stream flow forecasting (Akhtar et al, 2009;Chang and Chang, 2006;Chiang et al, 2007b;Maity and Kumar, 2008;Sudheer et al, 2008;Toth, 2009;Sahoo et al, 2009;Besaw et al, 2010), and applications in urban drainage systems (Bruen and Yang, 2006;Loke et al, 1997).…”

Section: Introductionmentioning

confidence: 99%

Dynamic neural networks for real-time water level predictions of sewerage systems-covering gauged and ungauged sites

Chiang¹,

Chang²,

Tsai³

et al. 2010

Hydrol. Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. In this research, we propose recurrent neural networks (RNNs) to build a relationship between rainfalls and water level patterns of an urban sewerage system based on historical torrential rain/storm events. The RNN allows signals to propagate in both forward and backward directions, which offers the network dynamic memories. Besides, the information at the current time-step with a feedback operation can yield a time-delay unit that provides internal input information at the next time-step to effectively deal with time-varying systems. The RNN is implemented at both gauged and ungauged sites for 5-, 10-, 15-, and 20-min-ahead water level predictions. The results show that the RNN is capable of learning the nonlinear sewerage system and producing satisfactory predictions at the gauged sites. Concerning the ungauged sites, there are no historical data of water level to support prediction. In order to overcome such problem, a set of synthetic data, generated from a storm water management model (SWMM) under cautious verification process of applicability based on the data from nearby gauging stations, are introduced as the learning target to the training procedure of the RNN and moreover evaluating the performance of the RNN at the ungauged sites. The results demonstrate that the potential role of the SWMM coupled with nearby rainfall and water level information can be of great use in enhancing the capability of the RNN at the ungauged sites. Hence we can conclude that the RNN is an effective and suitable model for successfully predicting the water levels at both gauged and ungauged sites in urban sewerage systems.

show abstract

“…Recently, artificial intelligence methodologies have been developed and applied in order to improve water resources planning and management. Farias et al 7) , Chaves & Chang 8) and Karamouz et al 9) used artificial neural networks to develop operation strategies for water systems. The works of Chaves & Chang 8) and Wang et al 10) are some examples of applications of genetic algorithms to the water resources field.…”

Section: Introductionmentioning

confidence: 99%

“…Farias et al 7) , Chaves & Chang 8) and Karamouz et al 9) used artificial neural networks to develop operation strategies for water systems. The works of Chaves & Chang 8) and Wang et al 10) are some examples of applications of genetic algorithms to the water resources field. This paper proposes a novel model that combines implicit stochastic optimization and genetic algorithms for deriving monthly hedging rules to the reservoir that supplies water to the city of Matsuyama, Japan.…”

Section: Introductionmentioning

confidence: 99%

Use of Implicit Stochastic Optimization and Genetic Algorithms for Deriving Reservoir Hedging Rules

2014

View full text Add to dashboard Cite

Water shortages have been periodically affecting the social and economic development of many regions in the world. Such effects could be mitigated by using techniques that considers the uncertainty of hydrologic variables. This paper aims at developing a model based on implicit stochastic optimization (ISO) and genetic algorithms (GA) for deriving monthly reservoir hedging rules. The ISO-GA procedure consists of optimizing the reservoir system operation under a set of possible inflow scenarios and using the acquired optimal dataset in order to construct discrete hedging rules based on GA. The proposed methodology was applied to the reservoir that supplies water to the city of Matsuyama, Japan. Based on the results, it is concluded that the devised rules are less vulnerable than the standard rules of operations during water shortage periods.

show abstract

Intelligent reservoir operation system based on evolving artificial neural networks

Cited by 94 publications

References 22 publications

Temporal data mining of uncertain water reservoir data

Temporal data mining of uncertain water reservoir data

Dynamic neural networks for real-time water level predictions of sewerage systems-covering gauged and ungauged sites

Use of Implicit Stochastic Optimization and Genetic Algorithms for Deriving Reservoir Hedging Rules

Contact Info

Product

Resources

About