{"id":"W4406895085","doi":"10.1109/icecs61496.2024.10848850","title":"FPGA-based Implementation of Deep Reinforcement Learning for Heat Recovery Chiller Optimization","year":2024,"lang":"en","type":"article","venue":"","topic":"Building Energy and Comfort Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Field-programmable gate array; Chiller; Computer science; Water chiller; Embedded system; Artificial intelligence; Engineering; Mechanical engineering; Heat exchanger; Thermodynamics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001604185,0.0004498981,0.0002228092,0.0002128013,0.0001414834,0.0003697202,0.0006995198,0.0002498128,0.007554313],"category_scores_gemma":[0.0003374553,0.0001536145,0.0001591038,0.0001499662,0.0001422329,0.0002094327,0.0001741676,0.0004538956,0.001104886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004490288,"about_ca_system_score_gemma":0.0005956395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003628864,"about_ca_topic_score_gemma":0.004667351,"domain_scores_codex":[0.9998908,0.00002002808,0.000006804393,0.00002160358,0.00003668779,0.000024048],"domain_scores_gemma":[0.9998966,0.00002971975,0.00001166998,0.00001581086,0.00003789855,0.000008249523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005827504,0.0002586609,0.003018603,0.0004538832,0.0001195051,0.0003816973,0.0001027373,0.5351953,0.06895397,0.01081989,0.01035003,0.369763],"study_design_scores_gemma":[0.00009442486,0.0003126369,0.001096978,0.00002349376,0.00002205118,0.0001211714,0.00001511847,0.9529052,0.03589733,0.0008942022,0.008601689,0.00001573395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1091067,0.0006931837,0.8439306,0.000298976,0.0002545185,0.0002017738,0.0003307482,0.009961026,0.03522238],"genre_scores_gemma":[0.8692522,0.0001322286,0.1244213,0.0001077563,0.00002175579,0.0001131368,0.0002149947,0.0001024825,0.005634223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007554313,"threshold_uncertainty_score":0.02527171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007038984907751712,"score_gpt":0.2315387216991038,"score_spread":0.2244997367913521,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}