http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113452026-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_92200e91d55e9f978a9dd19d9925894d
http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_1fefd66fdbc3870bbaa8e5a4f87bdb0a
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/Y04S20-222
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H02J2203-10
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H02J2203-20
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H02J2300-40
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/Y02B70-3225
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H02J3-48
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06Q10-0639
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F30-20
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H02J3-144
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/H02J3-06
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/H02J3-14
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/H02J3-48
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/H02J3-06
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F30-20
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06Q10-06
filingDate 2021-06-29-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_e738040ceed6fe74f9af1976f47a4fd6
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_aae6fe0b71818d2cf201e78e47358f91
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_a8915ac27c24358978c7bb41953e262a
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_567baa02749442110481a3ccee483aba
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_48ac3f1824cab8bab382c829daad2b31
publicationDate 2021-09-28-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-113452026-A
titleOfInvention A power system vulnerability assessment agent training method, assessment method and system
abstract The invention discloses an intelligent body training method, an evaluation method and a system for evaluating power system weakness, belonging to the field of power system weakness evaluation. The invention is based on the deep reinforcement learning algorithm and the power system cascading failure model, the intelligent body based on the deep Q network decides the attack line that is most likely to cause the power system to collapse, and the power flow transfer process after the attacked line is out of operation is simulated based on the power system cascading failure model. Automatically cut off the transmission lines with the most serious power flow violations. Continue to use the agent to decide to attack the line until the outage line or the lost load reaches a certain threshold, determine the power system collapse, and output the attack sequence decided by the agent. During this process, the experience samples needed for reinforcement learning are stored and the update agent is trained. The present invention utilizes the intelligent body trained by the deep reinforcement learning algorithm to effectively decide the attack sequence which is most likely to cause the collapse of the power system under the current power flow condition, so as to evaluate the weakness of the power system.
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114266487-A
priorityDate 2021-06-29-04:00^^<http://www.w3.org/2001/XMLSchema#date>
type http://data.epo.org/linked-data/def/patent/Publication

Incoming Links

Predicate Subject
isDiscussedBy http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID19092
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID414885204

Total number of triples: 36.