{"id":"W3106066138","doi":"10.1109/tsg.2020.3037066","title":"Deep Reinforcement Learning for Demand Response in Distribution Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Smart Grid","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":129,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Demand response; Reinforcement learning; Computer science; Scalability; Scheduling (production processes); Load management; Electricity; Mathematical optimization; Artificial intelligence; Engineering","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002593362,0.0001909116,0.0001816586,0.00008917276,0.000121999,0.00003322491,0.0001104905,0.00008809553,0.00005202332],"category_scores_gemma":[0.00001500754,0.0002180568,0.0001019114,0.0003345577,0.00001835948,0.000125979,0.000001579752,0.000300559,0.00003350555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000203423,"about_ca_system_score_gemma":0.000009408962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007916899,"about_ca_topic_score_gemma":0.00002702634,"domain_scores_codex":[0.9989166,0.00005867829,0.0003059888,0.0002318719,0.000148441,0.0003383913],"domain_scores_gemma":[0.9995255,0.0001534216,0.00002584843,0.0001559877,0.00002305011,0.0001162075],"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":[0.0006474076,0.00001841723,0.00003176701,0.0000329449,0.000046237,0.000004874224,0.0001363718,0.9964561,0.0002252573,0.00001714033,0.001174222,0.00120925],"study_design_scores_gemma":[0.0008495011,0.0002485618,0.0005864416,0.00002454808,0.00002938458,0.000001124456,0.00005224632,0.9692173,0.002997564,0.000003001721,0.02577668,0.0002136515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01606769,0.00004288394,0.9813493,0.0003769222,0.001305388,0.0003658849,0.000005498755,0.0003503621,0.0001359952],"genre_scores_gemma":[0.9988577,0.0000938888,0.0002271528,0.0001711898,0.0002101136,0.0002636655,0.00004933292,0.00004246977,0.00008449129],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.98279,"threshold_uncertainty_score":0.8892098,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01234859639463223,"score_gpt":0.2089434403846324,"score_spread":0.1965948439900002,"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."}}