MIXED-INTEGER LINEAR PROGRAMMING SCHEDULING MODEL FOR MICROGRID DAY-AHEAD POWER PROCUREMENT BASED ON QUANTILE PREDICTION

Targeting the day-ahead dispatching scenario of microgrids featured by pronounced uncertainties in load and photovoltaic generation, in which power deficits will incur emergency electricity acquisition with heavy penalties, this paper develops a mixed-integer linear programming dispatching model grounded on quantile forecasting of historical net load. A rolling historical window is utilized to implement quantile estimation for net-load sequences, and a 7-day retrospective window paired with the 0.8 quantile is finalized as the forecasting setup after parameter tuning with January datasets. Binary decision variables are deployed to impose the mutual-exclusive restriction on battery charging and discharging behaviors. Daily pre-arranged electricity-acquisition and energy-storage operational schemes are computed at midnight, with intra-day responsive adjustment performed in accordance with practical source-load measurements. Closed-loop emulation outcomes spanning 334 days from February to December 2025 demonstrate that the aggregate electricity-acquisition expense across the entire horizon hits 16 034 311.14 CNY. Emergency electricity procurement takes place on 186 days, with the corresponding emergency energy volume amounting to 177 712.73 kWh. The devised model yields viable day-ahead electricity-acquisition tactics under partial source-load information and offers references for economical dispatching of community-scale microgrids furnished with energy-storage facilities.

Authors

Institutions

Publication Details

Journal
World Journal of Engineering Research
Published
2026-11-20
DOI
https://doi.org/10.61784/wjer3141
Primary Topic
Electric Power System Optimization
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

MIXED-INTEGER LINEAR PROGRAMMING SCHEDULING MODEL FOR MICROGRID DAY-AHEAD POWER PROCUREMENT BASED ON QUANTILE PREDICTION

Changwei Song
2 links
World Journal of Engineering Research
Electric Power System Optimization
article

MIXED-INTEGER LINEAR PROGRAMMING SCHEDULING MODEL FOR MICROGRID DAY-AHEAD POWER PROCUREMENT BASED ON QUANTILE PREDICTION

Changwei Song
article en

Abstract

Targeting the day-ahead dispatching scenario of microgrids featured by pronounced uncertainties in load and photovoltaic generation, in which power deficits will incur emergency electricity acquisition with heavy penalties, this paper develops a mixed-integer linear programming dispatching model grounded on quantile forecasting of historical net load. A rolling historical window is utilized to implement quantile estimation for net-load sequences, and a 7-day retrospective window paired with the 0.8 quantile is finalized as the forecasting setup after parameter tuning with January datasets. Binary decision variables are deployed to impose the mutual-exclusive restriction on battery charging and discharging behaviors. Daily pre-arranged electricity-acquisition and energy-storage operational schemes are computed at midnight, with intra-day responsive adjustment performed in accordance with practical source-load measurements. Closed-loop emulation outcomes spanning 334 days from February to December 2025 demonstrate that the aggregate electricity-acquisition expense across the entire horizon hits 16 034 311.14 CNY. Emergency electricity procurement takes place on 186 days, with the corresponding emergency energy volume amounting to 177 712.73 kWh. The devised model yields viable day-ahead electricity-acquisition tactics under partial source-load information and offers references for economical dispatching of community-scale microgrids furnished with energy-storage facilities.

World Journal of Engineering ResearchVol. 4(8)
Shihezi University (CN)
Affordable and clean energy, Industry, innovation and infrastructure
Electric Power System Optimization
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