Predicate |
Object |
assignee |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_5a3af8c0eb98fa32c9867f1657fdd194 |
classificationCPCAdditional |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2009-45583 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/Y02D10-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2009-45591 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2209-5011 |
classificationCPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-5072 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-4881 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-126 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-45558 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F9-5077 |
classificationIPCInventive |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F9-455 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F9-50 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F9-48 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-12 |
filingDate |
2022-05-17-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor |
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1f5f0e7ef581de322ee2a6e9deb00f17 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_aace79bef53d448e3a59f78ae2f69ade http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6afe499e9bcf6a271643696b3a34f97f http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a82c76515664f77bd83166faa1bd6275 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4ae22b0d2a6815bccf5831ab597ef699 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_6bc81821c0ffb17bb8149bfc8e3c9522 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1149da8baaf9ae07061f9c93c2255f01 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_581f36c8e12023a25a70a9a874240bcb |
publicationDate |
2022-08-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber |
CN-114860385-A |
titleOfInvention |
A Parallel Cloud Workflow Scheduling Method Based on Evolutionary Reinforcement Learning Strategy |
abstract |
The invention discloses a parallel cloud workflow scheduling method based on an evolutionary reinforcement learning strategy. The workflow execution time and cost are respectively optimized by using two populations, and individual populations are designed as reinforcement learning agents. Interactive learning and network parameter update based on particle swarm optimization algorithm realize the two-level optimization of the agent network; during the training process of the reinforcement learning model, through the parallel interaction and iterative learning of multiple agents in the population and the environment, a The rich and diverse action selection experience sequences improve the diversity of search; at the same time, a complementary heuristic mechanism is designed, which uses the external target advantage information of the scheduling scheme to fine-tune and correct the agent's action selection probability to better balance the work. The optimization between flow execution time and cost improves global search capability. |
priorityDate |
2022-05-17-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type |
http://data.epo.org/linked-data/def/patent/Publication |