Machine learning for agile and self-adaptive congestion management in active distribution networks

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Uittreksel

Although congestion management via Demand Response (DR) has gain sufficient popularity recently, there are still some fundamental impediments to achieve a trade-off between demand flexibility scheduling and demand flexibility dispatch for congestion management. To find a solution to the challenge, the paper introduces the concept and design of an Agile Net, which is an agile control strategy for congestion management. The model of Agile Net has triple cores. First, it percepts the network environment by using the concept of demand elasticity. Second, it possesses an online model-free learning technique for the management of network externality, such as congestion. Third, it enables distributed system scalability. The efficiency of the proposed Agile Net is investigated by extending the simulation tool for DR paradigm for a generic low-voltage network of the Netherlands. Simulation results reveal a significant reduction in congestion over a year while confirming expected levels of performance.

TaalEngels
Titel2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe)
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
Aantal pagina's6
ISBN van elektronische versie9781728106526
DOI's
StatusGepubliceerd - 1 aug 2019
Evenement19th IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019 - Genoa, Italië
Duur: 11 jun 201914 jun 2019

Congres

Congres19th IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe, EEEIC/I and CPS Europe 2019
LandItalië
StadGenoa
Periode11/06/1914/06/19

Vingerafdruk

Distribution Network
Electric power distribution
Congestion
Learning systems
Machine Learning
Flexibility
Externalities
Low Voltage
Scalability
Elasticity
Simulation Tool
Scheduling
Control Strategy
Distributed Systems
Trade-offs
Paradigm
Demand
Sufficient
Electric potential
Model

Trefwoorden

    Citeer dit

    Babar, M., Roos, M., & Nguyen, P. (2019). Machine learning for agile and self-adaptive congestion management in active distribution networks. In 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe) [8783624] Piscataway: Institute of Electrical and Electronics Engineers. DOI: 10.1109/EEEIC.2019.8783624
    Babar, Muhammad ; Roos, Martijn ; Nguyen, Phuong. / Machine learning for agile and self-adaptive congestion management in active distribution networks. 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). Piscataway : Institute of Electrical and Electronics Engineers, 2019.
    @inproceedings{cd1f10216e944f41ae81c9a353374690,
    title = "Machine learning for agile and self-adaptive congestion management in active distribution networks",
    abstract = "Although congestion management via Demand Response (DR) has gain sufficient popularity recently, there are still some fundamental impediments to achieve a trade-off between demand flexibility scheduling and demand flexibility dispatch for congestion management. To find a solution to the challenge, the paper introduces the concept and design of an Agile Net, which is an agile control strategy for congestion management. The model of Agile Net has triple cores. First, it percepts the network environment by using the concept of demand elasticity. Second, it possesses an online model-free learning technique for the management of network externality, such as congestion. Third, it enables distributed system scalability. The efficiency of the proposed Agile Net is investigated by extending the simulation tool for DR paradigm for a generic low-voltage network of the Netherlands. Simulation results reveal a significant reduction in congestion over a year while confirming expected levels of performance.",
    keywords = "Agile demand response, Model-Free, Multi- agent system, Reinforcement learning, Transactive energy",
    author = "Muhammad Babar and Martijn Roos and Phuong Nguyen",
    year = "2019",
    month = "8",
    day = "1",
    doi = "10.1109/EEEIC.2019.8783624",
    language = "English",
    booktitle = "2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe)",
    publisher = "Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Babar, M, Roos, M & Nguyen, P 2019, Machine learning for agile and self-adaptive congestion management in active distribution networks. in 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe)., 8783624, Institute of Electrical and Electronics Engineers, Piscataway, Genoa, Italië, 11/06/19. DOI: 10.1109/EEEIC.2019.8783624

    Machine learning for agile and self-adaptive congestion management in active distribution networks. / Babar, Muhammad; Roos, Martijn; Nguyen, Phuong.

    2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). Piscataway : Institute of Electrical and Electronics Engineers, 2019. 8783624.

    Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

    TY - GEN

    T1 - Machine learning for agile and self-adaptive congestion management in active distribution networks

    AU - Babar,Muhammad

    AU - Roos,Martijn

    AU - Nguyen,Phuong

    PY - 2019/8/1

    Y1 - 2019/8/1

    N2 - Although congestion management via Demand Response (DR) has gain sufficient popularity recently, there are still some fundamental impediments to achieve a trade-off between demand flexibility scheduling and demand flexibility dispatch for congestion management. To find a solution to the challenge, the paper introduces the concept and design of an Agile Net, which is an agile control strategy for congestion management. The model of Agile Net has triple cores. First, it percepts the network environment by using the concept of demand elasticity. Second, it possesses an online model-free learning technique for the management of network externality, such as congestion. Third, it enables distributed system scalability. The efficiency of the proposed Agile Net is investigated by extending the simulation tool for DR paradigm for a generic low-voltage network of the Netherlands. Simulation results reveal a significant reduction in congestion over a year while confirming expected levels of performance.

    AB - Although congestion management via Demand Response (DR) has gain sufficient popularity recently, there are still some fundamental impediments to achieve a trade-off between demand flexibility scheduling and demand flexibility dispatch for congestion management. To find a solution to the challenge, the paper introduces the concept and design of an Agile Net, which is an agile control strategy for congestion management. The model of Agile Net has triple cores. First, it percepts the network environment by using the concept of demand elasticity. Second, it possesses an online model-free learning technique for the management of network externality, such as congestion. Third, it enables distributed system scalability. The efficiency of the proposed Agile Net is investigated by extending the simulation tool for DR paradigm for a generic low-voltage network of the Netherlands. Simulation results reveal a significant reduction in congestion over a year while confirming expected levels of performance.

    KW - Agile demand response

    KW - Model-Free

    KW - Multi- agent system

    KW - Reinforcement learning

    KW - Transactive energy

    UR - http://www.scopus.com/inward/record.url?scp=85070799845&partnerID=8YFLogxK

    U2 - 10.1109/EEEIC.2019.8783624

    DO - 10.1109/EEEIC.2019.8783624

    M3 - Conference contribution

    BT - 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe)

    PB - Institute of Electrical and Electronics Engineers

    CY - Piscataway

    ER -

    Babar M, Roos M, Nguyen P. Machine learning for agile and self-adaptive congestion management in active distribution networks. In 2019 IEEE International Conference on Environment and Electrical Engineering and 2019 IEEE Industrial and Commercial Power Systems Europe (EEEIC / I&CPS Europe). Piscataway: Institute of Electrical and Electronics Engineers. 2019. 8783624. Beschikbaar vanaf, DOI: 10.1109/EEEIC.2019.8783624