Source–Load Data-Driven Multi-Objective Siting and Sizing of Distributed Energy Storage in Islanded Microgrids

The variability of renewable generation and load demand complicates energy storage planning for islanded microgrids, particularly when siting, sizing, operating reliability, and economic performance must be considered simultaneously. This paper proposes a source-load data-driven method for siting and sizing distributed energy storage in an islanded microgrid. An improved grey wolf optimiser-gated recurrent unit (IGWO-GRU) model was developed to forecast photovoltaic output and nodal loads under normal and adverse weather conditions. The forecasts were incorporated into a multi-objective planning model that maximised islanded supply reliability and capacity-normalised discharge throughput while minimising annualised planning and operating cost. Continuous state-of-charge evolution, transitions between grid-connected and islanded operation, nodal-voltage limits, line-loading limits, upstream-grid power exchange, and priority supply to critical loads were explicitly considered. NSGA-III was directly coupled with a pandapower full-chronology AC power-flow model so that every candidate configuration was evaluated from its simulated operating performance. In the synthetic PV–BESS IEEE 33-bus case study, the 1319 h chronological assessment yielded 640 feasible configurations, including 10 non-dominated solutions. For this synthetic case and predefined candidate buses, the results illustrate a chronological planning workflow and quantify conditional trade-offs among annualised cost, islanded supply reliability, and capacity utilisation. They do not establish universal forecasting or optimisation superiority.

Authors

Institutions

Publication Details

Journal
Applied Sciences
Published
2026-11-18
DOI
https://doi.org/10.3390/app162211448
Primary Topic
Optimal Power Flow Distribution
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Source–Load Data-Driven Multi-Objective Siting and Sizing of Distributed Energy Storage in Islanded Microgrids

Guanglin Sha, Tao Zhou, Zhong Wang, Yang Yi et al.
1 links
Applied Sciences
Optimal Power Flow Distribution
article

Source–Load Data-Driven Multi-Objective Siting and Sizing of Distributed Energy Storage in Islanded Microgrids

Guanglin Sha, Tao Zhou, Zhong Wang, Yang Yi, Haijun Yu, Jianfang Chen, Jianming Su, Guansen Wang, Guangjing Zhou, Yunzhao Wu
article en

Abstract

The variability of renewable generation and load demand complicates energy storage planning for islanded microgrids, particularly when siting, sizing, operating reliability, and economic performance must be considered simultaneously. This paper proposes a source-load data-driven method for siting and sizing distributed energy storage in an islanded microgrid. An improved grey wolf optimiser-gated recurrent unit (IGWO-GRU) model was developed to forecast photovoltaic output and nodal loads under normal and adverse weather conditions. The forecasts were incorporated into a multi-objective planning model that maximised islanded supply reliability and capacity-normalised discharge throughput while minimising annualised planning and operating cost. Continuous state-of-charge evolution, transitions between grid-connected and islanded operation, nodal-voltage limits, line-loading limits, upstream-grid power exchange, and priority supply to critical loads were explicitly considered. NSGA-III was directly coupled with a pandapower full-chronology AC power-flow model so that every candidate configuration was evaluated from its simulated operating performance. In the synthetic PV–BESS IEEE 33-bus case study, the 1319 h chronological assessment yielded 640 feasible configurations, including 10 non-dominated solutions. For this synthetic case and predefined candidate buses, the results illustrate a chronological planning workflow and quantify conditional trade-offs among annualised cost, islanded supply reliability, and capacity utilisation. They do not establish universal forecasting or optimisation superiority.

Applied SciencesVol. 16(22)
State Grid Corporation of China (China) (CN), Beijing Jiaotong University (CN), Lanzhou Jiaotong University (CN), Shanghai Electric (China) (CN), China Electric Power Research Institute (CN)
Science and Technology Project of State Grid
Affordable and clean energy, Industry, innovation and infrastructure, Climate action
Optimal Power Flow Distribution
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon