2021
DOI: 10.1186/s13677-021-00259-1
|View full text |Cite
|
Sign up to set email alerts
|

Power flow adjustment for smart microgrid based on edge computing and multi-agent deep reinforcement learning

Abstract: In current power grids, a massive amount of power equipment raises various emerging requirements, e.g., data perception, information transmission, and real-time control. The existing cloud computing paradigm is stubborn to address issues and challenges such as rapid response and local autonomy. Microgrids contain diverse and adjustable power components, making the power system complex and difficult to optimize. The existing traditional adjusting methods are manual and centralized, which requires many human res… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 17 publications
(6 citation statements)
references
References 27 publications
0
6
0
Order By: Relevance
“…This layer assumes more elaborate data processing tasks, which require considerable computational resources on the part of edge devices. This layer implements sophisticated algorithms in order to analyze the observance of power usage from resources in the cloud and at the edge, including the detection of usage patterns, trends, and anomalies that could indicate inefficiencies or security threats [13]. The cloud layer also delivers mainstream security services, e.g., advanced encryption policies (which are applied to data in flight and data at rest) and global, machine learning (ML)powered anomaly detection systems based on networkwide data, which in turn can be scrutinized in detail with the use of the cloud's computational muscle to handle incident response.…”
Section: Cloud Layermentioning
confidence: 99%
“…This layer assumes more elaborate data processing tasks, which require considerable computational resources on the part of edge devices. This layer implements sophisticated algorithms in order to analyze the observance of power usage from resources in the cloud and at the edge, including the detection of usage patterns, trends, and anomalies that could indicate inefficiencies or security threats [13]. The cloud layer also delivers mainstream security services, e.g., advanced encryption policies (which are applied to data in flight and data at rest) and global, machine learning (ML)powered anomaly detection systems based on networkwide data, which in turn can be scrutinized in detail with the use of the cloud's computational muscle to handle incident response.…”
Section: Cloud Layermentioning
confidence: 99%
“…Nonetheless, it has many flaws, including heterogeneous environments, security and privacy concerns, and limited bandwidth resources [100]. In this context, edge computing shifts the frontier of computation applications away from centralized nodes and toward the communication network's outskirts [101], [102]. Edge computing puts computing resources closer to end users and sensors to do data analytics for smart grid decisions.…”
Section: F Edge Computing or On-device Aimentioning
confidence: 99%
“…The existing cloud computing paradigm is stubborn to address issues and challenges such as rapid response and local autonomy. To address this challenge, the authors of [5] consider a power control framework combining edge computing and reinforcement learning, which makes full use of edge nodes to sense network state and control power equipment to achieve the goal of fast response and local autonomy. Additionally, the authors focus on the non-convergence problem of power flow calculation, and combine deep reinforcement learning and multi-agent methods to realize intelligent decisions, with designing the model such as state, action, and reward.…”
Section: Author Abstractmentioning
confidence: 99%