English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Decarbonizing the energy supply is essential and urgent to mitigate theincreasingly visible climate change. Its basis is identifying emissionresponsibility during power allocation by the carbon emission flow (CEF) model.However, the main challenge of CEF application is the intractable nonlinearrelationship between carbon emission and power allocation. So this paperleverages the high approximation capability and the mixed-integer linearprogramming (MILP) representability of the deep neural networks to tackle thecomplex CEF model in carbon-electricity coordinated optimization. The compactconstraint learning approach is proposed to learn the mapping from powerinjection to bus emission with sparse neural networks (SNNs). Then the trainedSNNs are transformed equivalently as MILP constraints in the downstreamoptimization. In light of the ``high emission with high price'' principle, theblocked carbon price mechanism is designed to price emissions from the demandside. Based on the constraint learning and mechanism design, this paperproposes the carbon-aware energy management model in the tractable MILP form tounlock the carbon reduction potential from the demand side. The case studyverifies the approximation accuracy and sparsity of SNN with fewer parametersfor accelerating optimization solution and reduction effectiveness ofdemand-side capability for mitigating emission.

Encoding Carbon Emission Flow in Energy Management: A Compact Constraint Learning Approach