Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm

In this article, a Blockchain Enabled Intelligence of Federated Systems (BELIEFS) is proposed to conduct cooperative control for the multi-regional large-scale power system with a multi-agents system (MAS). By establishing a two levels blockchain, each regional AI agent can simultaneously manage int...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Siyuan Chen, Jun Zhang, Yuyang Bai, Peidong Xu, Tianlu Gao, Huaiguang Jiang, Wenzhong Gao, Xiang Li
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Multi-regional large-scale power system Multi-agents system Blockchain enabled intelligence Attack-tolerant capability Distributed deep reinforcement learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/e5af7b4d97ae4cc1ad0941efbc734b6b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e5af7b4d97ae4cc1ad0941efbc734b6b
record_format	dspace
spelling	oai:doaj.org-article:e5af7b4d97ae4cc1ad0941efbc734b6b2021-12-04T04:34:44ZBlockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm2352-484710.1016/j.egyr.2021.10.113https://doaj.org/article/e5af7b4d97ae4cc1ad0941efbc734b6b2021-11-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S235248472101132Xhttps://doaj.org/toc/2352-4847In this article, a Blockchain Enabled Intelligence of Federated Systems (BELIEFS) is proposed to conduct cooperative control for the multi-regional large-scale power system with a multi-agents system (MAS). By establishing a two levels blockchain, each regional AI agent can simultaneously manage intra-regional controllers and cooperate with other AI agents. Under the consensus mechanism, the agents, which respectively conducted distributed deep reinforcement learning (DDRL) algorithm in multi-regions, can have the tolerant capability of malicious attacks in their training process. The demonstration of the proposed approach is within a multi-regional large-scale interconnected power system. Under the mode of “centralized dispatching and hierarchical management”, this article aims to definite a mathematical model to deal with the control problem of the power systems. With the comparison experiments, the effectiveness and efficiency of our proposed method in the training process are verified. In addition, malicious attacks are set on the main chain and shard chains to verify the attack-tolerant capability. We expect that such approach and results can suggest a new paradigm of attack-tolerant trustable distributed AI deployment.Siyuan ChenJun ZhangYuyang BaiPeidong XuTianlu GaoHuaiguang JiangWenzhong GaoXiang LiElsevierarticleMulti-regional large-scale power systemMulti-agents systemBlockchain enabled intelligenceAttack-tolerant capabilityDistributed deep reinforcement learningElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENEnergy Reports, Vol 7, Iss , Pp 8900-8911 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Multi-regional large-scale power system Multi-agents system Blockchain enabled intelligence Attack-tolerant capability Distributed deep reinforcement learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Multi-regional large-scale power system Multi-agents system Blockchain enabled intelligence Attack-tolerant capability Distributed deep reinforcement learning Electrical engineering. Electronics. Nuclear engineering TK1-9971 Siyuan Chen Jun Zhang Yuyang Bai Peidong Xu Tianlu Gao Huaiguang Jiang Wenzhong Gao Xiang Li Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm
description	In this article, a Blockchain Enabled Intelligence of Federated Systems (BELIEFS) is proposed to conduct cooperative control for the multi-regional large-scale power system with a multi-agents system (MAS). By establishing a two levels blockchain, each regional AI agent can simultaneously manage intra-regional controllers and cooperate with other AI agents. Under the consensus mechanism, the agents, which respectively conducted distributed deep reinforcement learning (DDRL) algorithm in multi-regions, can have the tolerant capability of malicious attacks in their training process. The demonstration of the proposed approach is within a multi-regional large-scale interconnected power system. Under the mode of “centralized dispatching and hierarchical management”, this article aims to definite a mathematical model to deal with the control problem of the power systems. With the comparison experiments, the effectiveness and efficiency of our proposed method in the training process are verified. In addition, malicious attacks are set on the main chain and shard chains to verify the attack-tolerant capability. We expect that such approach and results can suggest a new paradigm of attack-tolerant trustable distributed AI deployment.
format	article
author	Siyuan Chen Jun Zhang Yuyang Bai Peidong Xu Tianlu Gao Huaiguang Jiang Wenzhong Gao Xiang Li
author_facet	Siyuan Chen Jun Zhang Yuyang Bai Peidong Xu Tianlu Gao Huaiguang Jiang Wenzhong Gao Xiang Li
author_sort	Siyuan Chen
title	Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm
title_short	Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm
title_full	Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm
title_fullStr	Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm
title_full_unstemmed	Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm
title_sort	blockchain enabled intelligence of federated systems (beliefs): an attack-tolerant trustable distributed intelligence paradigm
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/e5af7b4d97ae4cc1ad0941efbc734b6b
work_keys_str_mv	AT siyuanchen blockchainenabledintelligenceoffederatedsystemsbeliefsanattacktoleranttrustabledistributedintelligenceparadigm AT junzhang blockchainenabledintelligenceoffederatedsystemsbeliefsanattacktoleranttrustabledistributedintelligenceparadigm AT yuyangbai blockchainenabledintelligenceoffederatedsystemsbeliefsanattacktoleranttrustabledistributedintelligenceparadigm AT peidongxu blockchainenabledintelligenceoffederatedsystemsbeliefsanattacktoleranttrustabledistributedintelligenceparadigm AT tianlugao blockchainenabledintelligenceoffederatedsystemsbeliefsanattacktoleranttrustabledistributedintelligenceparadigm AT huaiguangjiang blockchainenabledintelligenceoffederatedsystemsbeliefsanattacktoleranttrustabledistributedintelligenceparadigm AT wenzhonggao blockchainenabledintelligenceoffederatedsystemsbeliefsanattacktoleranttrustabledistributedintelligenceparadigm AT xiangli blockchainenabledintelligenceoffederatedsystemsbeliefsanattacktoleranttrustabledistributedintelligenceparadigm
_version_	1718373002150674432

Blockchain Enabled Intelligence of Federated Systems (BELIEFS): An attack-tolerant trustable distributed intelligence paradigm

Ejemplares similares