Hybrid model-driven and data-driven control method based on machine learning algorithm in energy hub and application

Cai, Qingsen; Luo, Xingqi; Wang, Peng; Gao, Chunyang; Pei-yu, Zhao

doi:10.1016/j.apenergy.2021.117913

Cited by 25 publications

(12 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [189] a deep Q-learning has been used to maximize the long-term profit of the EH's prosumers in both the local energy market and wholesale energy market. A hybrid data-driven and model-driven framework have also been developed by using a machine learning algorithm in [190].…”

Section: Appendix B Application Of Machine Learning To Operation and ...mentioning

confidence: 99%

Operation and Planning of Energy Hubs Under Uncertainty—A Review of Mathematical Optimization Approaches

et al. 2023

View full text Add to dashboard Cite

Co-designing energy systems across multiple energy carriers is increasingly attracting attention of researchers and policy makers, since it is a prominent means of increasing the overall efficiency of the energy sector. Special attention is attributed to the so-called energy hubs, i.e., clusters of energy communities featuring electricity, gas, heat, hydrogen, and also water generation and consumption facilities. Managing an energy hub entails dealing with multiple sources of uncertainty, such as renewable generation, energy demands, wholesale market prices, etc. Such uncertainties call for sophisticated decision-making techniques, with mathematical optimization being the predominant family of decision-making methods proposed in the literature of recent years. In this paper, we summarize, review, and categorize research studies that have applied mathematical optimization approaches towards making operational and planning decisions for energy hubs. Relevant methods include robust optimization, information gap decision theory, stochastic programming, and chance-constrained optimization. The results of the review indicate the increasing adoption of robust and, more recently, hybrid methods to deal with the multi-dimensional uncertainties of energy hubs.

show abstract

Section: Appendix B Application Of Machine Learning To Operation and ...mentioning

confidence: 99%

Operation and Planning of Energy Hubs Under Uncertainty—A Review of Mathematical Optimization Approaches

et al. 2023

View full text Add to dashboard Cite

show abstract

“…SVD is often used in dimensionality reduction algorithms for feature decomposition (Cai et al, 2022). SVD is a decomposition of a matrix into two orthogonal matrices and a diagonal matrix, where the orthogonal matrix corresponds to the rotation transformation and the diagonal matrix corresponds to the expansion transformation.…”

Section: Formentioning

confidence: 99%

Identifying critical energy-water paths and clusters within the urban agglomeration using machine learning algorithm

Ding

Zheng

et al. 2022

Energy

View full text Add to dashboard Cite

“…As a new interdisciplinary technique, ML has attracted profound interest in environment-related fields in recent years. − Further, ML is a data-driven approach without the need for detailed mechanistic support. , Random forest (RF) is an integrated supervised machine learning algorithm based on decision trees, which has strong nonlinear fitting capability. Due to the excellent performance of RF models, RF has been gradually applied to the prediction of environmental pollutants, such as the estimation of the vertical distribution of PM 2.5 and the prediction of the historical PM 2.5 level in some regions. , In addition, some studies have applied RF to small data sets and have achieved excellent predictions, further extending the boundaries of the applicability of the model. − In the work presented here, RF was used to model brake wear PM 2.5 emissions.…”

Section: Introductionmentioning

confidence: 99%

“…27−29 Further, ML is a data-driven approach without the need for detailed mechanistic support. 30,31 Random forest (RF) is an integrated supervised machine learning algorithm based on decision trees, which has strong nonlinear fitting capability. Due to the excellent performance of RF models, RF has been gradually applied to the prediction of environmental pollutants, such as the estimation of the vertical distribution of PM 2.5 and the prediction of the historical PM 2.5 level in some regions.…”

Section: ■ Introductionmentioning

confidence: 99%

Machine Learning Predicts Emissions of Brake Wear PM_2.5: Model Construction and Interpretation

Wei

Jia

Men

et al. 2022

Environ. Sci. Technol. Lett.

View full text Add to dashboard Cite

Brake emissions are generated every time a brake is applied to a vehicle. However, revealing the pattern of brake emissions under different operating conditions is conventionally considered highly challenging. Here, we compiled a brake wear PM2.5 data set collected from brake dynamometer simulation experiments and obtained the mapping relationship between brake emissions and influencing factors through a machine learning (ML) method. The random forest model was devised and displayed good prediction performance with an R 2 of 0.89 on the test set. Model-related (similarity network analysis) and model-unrelated (partial dependence plots and centered-individual conditional expectation plots) interpretation methods were used to break the black box of ML to obtain the marginal contribution of the model input feature parameters (brake energy dissipation, average temperature during braking, brake pad metal content, and brake pad surface area) to the model output results. This study suggests that avoiding rapid braking behavior and using brake pads with a lower metal content are feasible ways to reduce brake wear PM2.5 emissions. The development of a ML-based brake emission model provides novel insights into the accurate assessment and control of brake emissions.

show abstract

Hybrid model-driven and data-driven control method based on machine learning algorithm in energy hub and application

Cited by 25 publications

References 31 publications

Operation and Planning of Energy Hubs Under Uncertainty—A Review of Mathematical Optimization Approaches

Operation and Planning of Energy Hubs Under Uncertainty—A Review of Mathematical Optimization Approaches

Identifying critical energy-water paths and clusters within the urban agglomeration using machine learning algorithm

Machine Learning Predicts Emissions of Brake Wear PM_2.5: Model Construction and Interpretation

Contact Info

Product

Resources

About

Hybrid model-driven and data-driven control method based on machine learning algorithm in energy hub and application

Cited by 25 publications

References 31 publications

Operation and Planning of Energy Hubs Under Uncertainty—A Review of Mathematical Optimization Approaches

Operation and Planning of Energy Hubs Under Uncertainty—A Review of Mathematical Optimization Approaches

Identifying critical energy-water paths and clusters within the urban agglomeration using machine learning algorithm

Machine Learning Predicts Emissions of Brake Wear PM2.5: Model Construction and Interpretation

Contact Info

Product

Resources

About

Machine Learning Predicts Emissions of Brake Wear PM_2.5: Model Construction and Interpretation