A Scenario-Driven Bi-Level Programming Model for Optimal Distributed Generation Planning: Integrating Fuzzy C-Means (FCM) Clustering and Enhanced Whale Optimization (EWOA)

Energy conservation and environmental protection are increasingly critical in the power grid sector as traditional distribution networks transition to active, eco-friendly systems. However, this shift introduces challenges like voltage fluctuations and higher network losses due to the integration of...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2024 4th International Conference on Smart City and Green Energy (ICSCGE) s. 207 - 212
Hlavní autori: Zhang, Boyang, Zhang, Chenxi, Yang, Yi, Qiu, Jing
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 10.12.2024
Predmet:
Active Distribution Network (ADN)
Adaptation models
Bi-level programming (BLP)
Clustering algorithms
Costs
Distributed power generation
Enhanced Whale Optimization Algorithm (EWOA)
Fuzzy C-Means(FCM) clustering
Optimization
Optimization models
Planning
Programming
Voltage fluctuations
Whale optimization algorithms
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Energy conservation and environmental protection are increasingly critical in the power grid sector as traditional distribution networks transition to active, eco-friendly systems. However, this shift introduces challenges like voltage fluctuations and higher network losses due to the integration of distributed generation (DG). This paper introduces a bi-level optimization model to tackle these issues, with a focus on planning at the first level and operational efficiency at the second. The model optimizes DG investment costs, voltage deviations, and active power losses, utilizing the Enhanced Whale Optimization Algorithm (EWOA) and Fuzzy C-Means (FCM) clustering for wind and photovoltaic (PV) data. Simulations on the IEEE 33bus system, across four seasonal scenarios, confirm the model's effectiveness in minimizing voltage deviations, reducing network losses, and lowering overall costs, while proving adaptable to different operating conditions.
DOI:10.1109/ICSCGE64239.2024.11064206