Machine learning based weighted scheduling scheme for active power control of hybrid microgrid

Kanwal, Sidra; Khan, Bilal; Ali, Sahibzada Muhammad

doi:10.1016/j.ijepes.2020.106461

Cited by 16 publications

(19 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, making the model much more compact. The methodology used in [23] is K-means clustering on customer net electricity data to extract critical information from limited input net/gross energy data, which is then used in a techno-economic simulation model to estimate the best battery size.…”

Section: Related Workmentioning

confidence: 99%

“…Mixed-integer linear programming (MILP) is an optimization technique that employs the solvers to work for the real numbers with the equations restricted for both the linear inequalities and equalities. The solver will work within the various objective function that is normally described for either minimization or a maximization function [23]. The use of the MILP has been widely adopted for numerous optimization problems.…”

Section: Dataset Generation Using Mixed Interger Linear Programming (...mentioning

confidence: 99%

“…The solar-based grid power systems heavily rely on battery systems that can provide power to the systems when the sun peak is low. The Hoppecke 6 OPzS 300 is a 300Ah battery, with dimensions of about 147 × 208 × 420 mm, and weighs about 24.9 kg [30]. The battery is a vented lead-acid type of cell that has a longer life span of up to 18 years on the model [30].…”

Section: Hoppecke 6 Opzs 300mentioning

confidence: 99%

“…The Hoppecke 6 OPzS 300 is a 300Ah battery, with dimensions of about 147 × 208 × 420 mm, and weighs about 24.9 kg [30]. The battery is a vented lead-acid type of cell that has a longer life span of up to 18 years on the model [30]. The applicational use of the cell includes the mobile phone stations and the BTS stations.…”

Section: Hoppecke 6 Opzs 300mentioning

confidence: 99%

“…It is the lifetime of the battery in years that is worked out by dividing the energy level by the duration [30]. A good performance battery would be able to give a better Battery Throughput.…”

Section: Battery Throughputmentioning

confidence: 99%

See 4 more Smart Citations

Analyzing Optimal Battery Sizing in Microgrids Based on the Feature Selection and Machine Learning Approaches

Khan¹,

Nizami²,

Qaisar³

et al. 2022

Preprint

View full text Add to dashboard Cite

Microgrids are becoming popular nowadays because they provide clean, efficient, and low-cost energy. To use the stored energy in times of emergency or peak loads, microgrids require bulk storage capacity. Since microgrids are the future of renewable energy, the energy storage technology employed should be optimized to generate electricity. Batteries play a variety of essential roles in daily life and are used at peak hours and during a time of emergency. There are different types of batteries i.e., lion batteries, lead-acid batteries, etc. Optimal battery sizing of microgrids is a challenging problem, that limits modern technologies such as electric vehicles, etc. It is important to know different battery features such as battery life, battery throughput, and battery autonomy to get optimal battery sizing for microgrids. Mixed-integer linear programming (MILP) is an established technique for the integration and optimization of different energy sources and parameters for optimal battery sizing. A new MILP based dataset is introduced in this work. Support vector machine (SVM) is the machine learning application used to estimate the optimum battery size. The impact of feature selection algorithms on the proposed machine learning-based model is evaluated. The performance of the six best-performing feature selection algorithms is analyzed. The experimental results show that the feature selection algorithms improve the performance of the proposed methodology. Ranker search shows the best performance with a Spearman’s rank-ordered correlation constant of 0.9756, linear correlation constant of 0.9452, Kendall correlation constant of 0.8488 and root mean squared error of 0.0525.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Dataset Generation Using Mixed Interger Linear Programming (...mentioning

confidence: 99%