An integrated neural network stochastic dynamic programming model for optimizing the operation policy of Aswan high Dam

A. H. El-Shafie, M. S. El-Manadely

    Research output: Contribution to journalArticle

    27 Citations (Scopus)

    Abstract

    Developing optimal release policies of multipurpose reservoirs is very complex, especially for reservoirs within a stochastic environment. Existing techniques are limited in their ability to represent risks associated with deciding a release policy. The risk aspect of the decisions affects the design and operation of reservoirs. A decision-making model is presented that is capable of replicating the manner in which risks associated with reservoir release decisions are perceived, interpreted and compared by a decision-maker. The model is based on Neural Network (NN) theory. This decision-making model can be used with a Stochastic Dynamic Programming (SDP) approach to produce a NN-SDP model. The resulting integrated model allows the attitudes towards risk of a decision-maker to be considered explicitly in defining the optimal release policy. Clear differences in the policies generated from the basic SDP and the NN-SDP models are observed when examining the operation of Aswan High Dam (AHD). The NN-SDP model yields policies that are more reliable and resilient and less vulnerable than those obtained using the SDP model.

    Original languageEnglish
    Pages (from-to)50-67
    Number of pages18
    JournalHydrology Research
    Volume42
    Issue number1
    DOIs
    Publication statusPublished - 2011

    Fingerprint

    dam
    decision making
    policy
    decision

    Keywords

    • Aswan high dam
    • Dam operation
    • Neural network
    • Risk analysis
    • Stochastic dynamic program

    ASJC Scopus subject areas

    • Water Science and Technology

    Cite this

    An integrated neural network stochastic dynamic programming model for optimizing the operation policy of Aswan high Dam. / El-Shafie, A. H.; El-Manadely, M. S.

    In: Hydrology Research, Vol. 42, No. 1, 2011, p. 50-67.

    Research output: Contribution to journalArticle

    @article{c762f9c4efc74a78b8677a2cfb21ea50,
    title = "An integrated neural network stochastic dynamic programming model for optimizing the operation policy of Aswan high Dam",
    abstract = "Developing optimal release policies of multipurpose reservoirs is very complex, especially for reservoirs within a stochastic environment. Existing techniques are limited in their ability to represent risks associated with deciding a release policy. The risk aspect of the decisions affects the design and operation of reservoirs. A decision-making model is presented that is capable of replicating the manner in which risks associated with reservoir release decisions are perceived, interpreted and compared by a decision-maker. The model is based on Neural Network (NN) theory. This decision-making model can be used with a Stochastic Dynamic Programming (SDP) approach to produce a NN-SDP model. The resulting integrated model allows the attitudes towards risk of a decision-maker to be considered explicitly in defining the optimal release policy. Clear differences in the policies generated from the basic SDP and the NN-SDP models are observed when examining the operation of Aswan High Dam (AHD). The NN-SDP model yields policies that are more reliable and resilient and less vulnerable than those obtained using the SDP model.",
    keywords = "Aswan high dam, Dam operation, Neural network, Risk analysis, Stochastic dynamic program",
    author = "El-Shafie, {A. H.} and El-Manadely, {M. S.}",
    year = "2011",
    doi = "10.2166/nh.2010.043",
    language = "English",
    volume = "42",
    pages = "50--67",
    journal = "Nordic Hydrology",
    issn = "0029-1277",
    publisher = "Nordic Association for Hydrology",
    number = "1",

    }

    TY - JOUR

    T1 - An integrated neural network stochastic dynamic programming model for optimizing the operation policy of Aswan high Dam

    AU - El-Shafie, A. H.

    AU - El-Manadely, M. S.

    PY - 2011

    Y1 - 2011

    N2 - Developing optimal release policies of multipurpose reservoirs is very complex, especially for reservoirs within a stochastic environment. Existing techniques are limited in their ability to represent risks associated with deciding a release policy. The risk aspect of the decisions affects the design and operation of reservoirs. A decision-making model is presented that is capable of replicating the manner in which risks associated with reservoir release decisions are perceived, interpreted and compared by a decision-maker. The model is based on Neural Network (NN) theory. This decision-making model can be used with a Stochastic Dynamic Programming (SDP) approach to produce a NN-SDP model. The resulting integrated model allows the attitudes towards risk of a decision-maker to be considered explicitly in defining the optimal release policy. Clear differences in the policies generated from the basic SDP and the NN-SDP models are observed when examining the operation of Aswan High Dam (AHD). The NN-SDP model yields policies that are more reliable and resilient and less vulnerable than those obtained using the SDP model.

    AB - Developing optimal release policies of multipurpose reservoirs is very complex, especially for reservoirs within a stochastic environment. Existing techniques are limited in their ability to represent risks associated with deciding a release policy. The risk aspect of the decisions affects the design and operation of reservoirs. A decision-making model is presented that is capable of replicating the manner in which risks associated with reservoir release decisions are perceived, interpreted and compared by a decision-maker. The model is based on Neural Network (NN) theory. This decision-making model can be used with a Stochastic Dynamic Programming (SDP) approach to produce a NN-SDP model. The resulting integrated model allows the attitudes towards risk of a decision-maker to be considered explicitly in defining the optimal release policy. Clear differences in the policies generated from the basic SDP and the NN-SDP models are observed when examining the operation of Aswan High Dam (AHD). The NN-SDP model yields policies that are more reliable and resilient and less vulnerable than those obtained using the SDP model.

    KW - Aswan high dam

    KW - Dam operation

    KW - Neural network

    KW - Risk analysis

    KW - Stochastic dynamic program

    UR - http://www.scopus.com/inward/record.url?scp=79952294471&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79952294471&partnerID=8YFLogxK

    U2 - 10.2166/nh.2010.043

    DO - 10.2166/nh.2010.043

    M3 - Article

    AN - SCOPUS:79952294471

    VL - 42

    SP - 50

    EP - 67

    JO - Nordic Hydrology

    JF - Nordic Hydrology

    SN - 0029-1277

    IS - 1

    ER -