Green Computility scheduling in heterogeneous clusters requires balancing execution efficiency, deadline satisfaction, resource utilization, carbon emissions, and renewable energy usage under dynamic workload and energy conditions. Existing heuristic schedulers are efficient but often rely on fixed hand crafted rules, whereas reinforcement learning (RL) based schedulers may explore inefficiently in large and structured action spaces when no prior guidance is available. To address these challenges, we propose Green-LLM-DQN, a large language model (LLM) guided dueling double deep Q-network (D3QN) framework for trace-driven Green Computility scheduling. The framework uses an LLM to generate a structured and interpretable heuristic prior from the scheduling context, and incorporates this prior into a D3QN backbone for action scoring and selection. This design improves early stage exploration while preserving the adaptability of RL. Experiments on trace driven workloads show that Green-LLM-DQN achieves a competitive overall trade-off among return, carbon emissions, and green energy utilization than classical scheduling heuristics and learning based baselines.
Tao Yin, Cong Wang, Zi-Yu Niu et al.· International Conferences on...· 0 citations
Background Cryptochromes (CRYs) are blue light and ultraviolet A (UV-A) photoreceptors that play pivotal roles in regulating plant development and stress responses through mediating light signaling pathways. However, the evolutionary and functional characteristics of the cryptochrome/photolyase (CRY/PHL) family in wheat (Triticum aestivum L.) remain poorly understood. Results 57 CRY/PHL genes were identified across eight species, including 14 members in hexaploid wheat. Phylogenetic analysis classified CRY/PHLs into four subfamilies. All TaCRY/PHL proteins contain the conserved photolyase homology region (PHR), whereas the cryptochrome C-terminal (CCT) domain is exclusively present in the CRY1 subfamilies. Collinearity analysis revealed extensive synteny among wheat, rice, and maize CRY/PHLs, but not with Arabidopsis, indicating lineage-specific evolution within grasses. Promoters of TaCRY/PHL genes contain multiple predicted light-, hormone-, and stress-responsive cis-elements. Tissue-specific expression profiling demonstrated that subfamily A and C members are predominantly expressed in vegetative tissues, while subfamily B and D members are mainly expressed in reproductive organs. Notably, TaCRY1b expression progressively increased during leaf lamina joint (LJ) development. Subcellular localization demonstrated that TaCRY1b localizes to both the nucleus and cytoplasm, while bimolecular fluorescence complementation assays uncovered direct physical interactions between TaCRY1b and TaLiguless2 (TaLG2s), key regulators of LJ formation. AlphaFold3 prediction showed a putative interaction interface between TaLG2/TaLG2L and TaCRY1b, where multiple complementary residue pairs form polar contacts predominantly within the PHR domain of TaCRY1b. Conclusions This study provides a comprehensive framework for the evolution and functional diversification of the wheat CRY/PHL family and identifies TaCRY1b as a promising candidate regulator of lamina joint development, laying a solid foundation for further investigations into its moltcular function in leaf angle modulation.
Bing-Yan Gu, Yi-Mo Wang, Chang Liu et al.· Frontiers in Plant Science· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
