On the Classification of low voltage feeders for network planning and hosting capacity studies

Benoît Bletterie, Serdar Kadam, Herwig Renner

    Research output: Contribution to journalArticleResearchpeer-review

    Abstract

    The integration of large amounts of generation into distribution networks faces some limitations. By deploying reactive power-based voltage control concepts (e.g., volt/var control with distributed generators), the voltage rise caused by generators can be partly mitigated. As a result, the network hosting capacity can be accordingly increased, and costly network reinforcement might be avoided or postponed. This works however only for voltage-constrained feeders (opposed to current-constrained feeders). Due to the low level of monitoring in low voltage networks, it is important to be able to classify feeders according to the expected constraint in order to avoid the overloading risk. The main purpose of this paper is to investigate to which extent it is possible to predict the hosting capacity constraint (voltage or current) of low voltage feeders on the basis of a large network data set. Two machine-learning techniques have been implemented and compared: clustering (unsupervised) and classification (supervised). The results show that the general performance of the classification or clustering algorithms might be considered as rather poor at a first glance, reflecting the diversity of real low voltage feeders. However, a detailed analysis shows that the benefit of the classification is significant.

    Original languageEnglish
    Article number651
    JournalEnergies
    Volume11
    Issue number3
    DOIs
    Publication statusPublished - 25 Feb 2018

    Fingerprint

    Network Planning
    Low Voltage
    Voltage
    Planning
    Electric potential
    Generator
    Unsupervised Clustering
    Capacity Constraints
    Distribution Network
    Reinforcement
    Classification Algorithm
    Clustering Algorithm
    Machine Learning
    Classify
    Monitoring
    Reactive power
    Electric power distribution
    Clustering algorithms
    Predict
    Voltage control

    Keywords

    • Classification
    • Hosting capacity
    • Low voltage feeders
    • Reactive power
    • Voltage control

    ASJC Scopus subject areas

    • Renewable Energy, Sustainability and the Environment
    • Energy Engineering and Power Technology
    • Energy (miscellaneous)
    • Control and Optimization
    • Electrical and Electronic Engineering

    Cite this

    On the Classification of low voltage feeders for network planning and hosting capacity studies. / Bletterie, Benoît; Kadam, Serdar; Renner, Herwig.

    In: Energies, Vol. 11, No. 3, 651, 25.02.2018.

    Research output: Contribution to journalArticleResearchpeer-review

    @article{cfa4720932f0411990787d5553ea313d,
    title = "On the Classification of low voltage feeders for network planning and hosting capacity studies",
    abstract = "The integration of large amounts of generation into distribution networks faces some limitations. By deploying reactive power-based voltage control concepts (e.g., volt/var control with distributed generators), the voltage rise caused by generators can be partly mitigated. As a result, the network hosting capacity can be accordingly increased, and costly network reinforcement might be avoided or postponed. This works however only for voltage-constrained feeders (opposed to current-constrained feeders). Due to the low level of monitoring in low voltage networks, it is important to be able to classify feeders according to the expected constraint in order to avoid the overloading risk. The main purpose of this paper is to investigate to which extent it is possible to predict the hosting capacity constraint (voltage or current) of low voltage feeders on the basis of a large network data set. Two machine-learning techniques have been implemented and compared: clustering (unsupervised) and classification (supervised). The results show that the general performance of the classification or clustering algorithms might be considered as rather poor at a first glance, reflecting the diversity of real low voltage feeders. However, a detailed analysis shows that the benefit of the classification is significant.",
    keywords = "Classification, Hosting capacity, Low voltage feeders, Reactive power, Voltage control",
    author = "Beno{\^i}t Bletterie and Serdar Kadam and Herwig Renner",
    year = "2018",
    month = "2",
    day = "25",
    doi = "10.3390/en11030651",
    language = "English",
    volume = "11",
    journal = "Energies",
    issn = "1996-1073",
    publisher = "MDPI AG",
    number = "3",

    }

    TY - JOUR

    T1 - On the Classification of low voltage feeders for network planning and hosting capacity studies

    AU - Bletterie, Benoît

    AU - Kadam, Serdar

    AU - Renner, Herwig

    PY - 2018/2/25

    Y1 - 2018/2/25

    N2 - The integration of large amounts of generation into distribution networks faces some limitations. By deploying reactive power-based voltage control concepts (e.g., volt/var control with distributed generators), the voltage rise caused by generators can be partly mitigated. As a result, the network hosting capacity can be accordingly increased, and costly network reinforcement might be avoided or postponed. This works however only for voltage-constrained feeders (opposed to current-constrained feeders). Due to the low level of monitoring in low voltage networks, it is important to be able to classify feeders according to the expected constraint in order to avoid the overloading risk. The main purpose of this paper is to investigate to which extent it is possible to predict the hosting capacity constraint (voltage or current) of low voltage feeders on the basis of a large network data set. Two machine-learning techniques have been implemented and compared: clustering (unsupervised) and classification (supervised). The results show that the general performance of the classification or clustering algorithms might be considered as rather poor at a first glance, reflecting the diversity of real low voltage feeders. However, a detailed analysis shows that the benefit of the classification is significant.

    AB - The integration of large amounts of generation into distribution networks faces some limitations. By deploying reactive power-based voltage control concepts (e.g., volt/var control with distributed generators), the voltage rise caused by generators can be partly mitigated. As a result, the network hosting capacity can be accordingly increased, and costly network reinforcement might be avoided or postponed. This works however only for voltage-constrained feeders (opposed to current-constrained feeders). Due to the low level of monitoring in low voltage networks, it is important to be able to classify feeders according to the expected constraint in order to avoid the overloading risk. The main purpose of this paper is to investigate to which extent it is possible to predict the hosting capacity constraint (voltage or current) of low voltage feeders on the basis of a large network data set. Two machine-learning techniques have been implemented and compared: clustering (unsupervised) and classification (supervised). The results show that the general performance of the classification or clustering algorithms might be considered as rather poor at a first glance, reflecting the diversity of real low voltage feeders. However, a detailed analysis shows that the benefit of the classification is significant.

    KW - Classification

    KW - Hosting capacity

    KW - Low voltage feeders

    KW - Reactive power

    KW - Voltage control

    UR - http://www.scopus.com/inward/record.url?scp=85051404569&partnerID=8YFLogxK

    U2 - 10.3390/en11030651

    DO - 10.3390/en11030651

    M3 - Article

    VL - 11

    JO - Energies

    JF - Energies

    SN - 1996-1073

    IS - 3

    M1 - 651

    ER -