MADDPG-Based Security Situational Awareness for Smart Grid with Intelligent Edge

Wenxin Lei; Hong Wen; Jinsong Wu; Wenjing Hou

doi:10.3390/app11073101

MADDPG-Based Security Situational Awareness for Smart Grid with Intelligent Edge

Applied Sciences ◽

10.3390/app11073101 ◽

2021 ◽

Vol 11 (7) ◽

pp. 3101

Author(s):

Wenxin Lei ◽

Hong Wen ◽

Jinsong Wu ◽

Wenjing Hou

Keyword(s):

Power Systems ◽

Smart Grids ◽

Information Technologies ◽

Situational Awareness ◽

Learning Algorithm ◽

Edge Computing ◽

Security Issues ◽

Computing Paradigm ◽

Processing Cost ◽

Policy Gradient

Advanced communication and information technologies enable smart grids to be more intelligent and automated, although many security issues are emerging. Security situational awareness (SSA) has been envisioned as a potential approach to provide safe services for power systems’ operation. However, in the power cloud master station mode, massive heterogeneous power terminals make SSA complicated, and failure information cannot be promptly delivered. Moreover, the dynamic and continuous situational space also increases the challenges of SSA. By taking advantages of edge intelligence, this paper introduces edge computing between terminals and the cloud to address the drawbacks of the traditional power cloud paradigm. Moreover, a deep reinforcement learning algorithm based on the edge computing paradigm of multiagent deep deterministic policy gradient (MADDPG) is proposed. The minimum processing cost under the premise of minimum detection error rate is taken to analyze the smart grids’ SSA. Performance evaluations show that the algorithm under this paradigm can achieve faster convergence and the optimal goal, namely the provision of real-time protection for smart grids.

Download Full-text

Analysis of Security Issues of Edge Computing Based Internet of Things Applications

10.31219/osf.io/8wzha ◽

2020 ◽

Author(s):

Shamim Muhammad ◽

Inderveer Chana ◽

Supriya Thilakanathan

Keyword(s):

Internet Of Things ◽

Edge Computing ◽

The Internet ◽

Security Vulnerabilities ◽

Computing Power ◽

Security Issues ◽

Computing Paradigm ◽

Improved Performance ◽

The Internet Of Things ◽

Common Security

Edge computing is a technology that allows resources to be processed or executed close to the edge of the internet. The interconnected network of devices in the Internet of Things has led to an increased amount of data, increasing internet traffic usage every year. Also, edge computing is driving applications and computing power away from the integrated points to areas close to users, leading to improved performance of the application. Despite the explosive growth of the edge computing paradigm, there are common security vulnerabilities associated with the Internet of Things applications. This paper will evaluate and analyze some of the most common security issues that pose a serious threat to the edge computing paradigm.

Download Full-text

Situational Awareness Using Edge-Computing Enabled Internet of Things for Smart Grids

2019 IEEE Globecom Workshops (GC Wkshps) ◽

10.1109/gcwkshps45667.2019.9024632 ◽

2019 ◽

Author(s):

Md Abul Hasnat ◽

Md Jakir Hossain ◽

Adetola Adeniran ◽

Mahshid Rahnamay-Naeini ◽

Hana Khamfroush

Keyword(s):

Internet Of Things ◽

Smart Grids ◽

Situational Awareness ◽

Edge Computing

Download Full-text

Reliability of Smart Grid Including Cyber Impact

Computational Methodologies for Electrical and Electronics Engineers - Advances in Computer and Electrical Engineering ◽

10.4018/978-1-7998-3327-7.ch013 ◽

2021 ◽

pp. 163-174

Author(s):

Janavi Popat ◽

Harsh Kakadiya ◽

Lalit Tak ◽

Neeraj Kumar Singh ◽

Mahshooq Abdul Majeed ◽

...

Keyword(s):

Smart Grid ◽

Power Systems ◽

Cyber Security ◽

Smart Grids ◽

Reliability Assessment ◽

Grid Security ◽

Security Issues ◽

Smart Grid Security ◽

Intelligent Electronic Devices ◽

Improve Reliability

Smart grid has changed power systems and their reliability concerns. Along with that, cyber security issues are also introduced due to the use of intelligent electronic devices (IEDs), wireless sensory network (WSN), and internet of things (IoT) for two-way communication. This chapter presents a review of different methods used from 2010 to 2020 focusing on citation as the main criteria for reliability assessment of smart grids and proposals to improve reliability when it comes to assessing a practical transmission system. It shows that evolutionary techniques are the latest trend for smart grid security.

Download Full-text

Deep Reinforcement Learning-Empowered Resource Allocation for Mobile Edge Computing in Cellular V2X Networks

Sensors ◽

10.3390/s21020372 ◽

2021 ◽

Vol 21 (2) ◽

pp. 372

Author(s):

Dongji Li ◽

Shaoyi Xu ◽

Pengyu Li

Keyword(s):

Reinforcement Learning ◽

Energy Consumption ◽

Vehicular Networks ◽

Learning Algorithm ◽

Rapid Development ◽

Dynamic Environment ◽

Edge Computing ◽

Mobile Edge Computing ◽

Computing Paradigm ◽

Cloud Servers

With the rapid development of vehicular networks, vehicle-to-everything (V2X) communications have huge number of tasks to be calculated, which brings challenges to the scarce network resources. Cloud servers can alleviate the terrible situation regarding the lack of computing abilities of vehicular user equipment (VUE), but the limited resources, the dynamic environment of vehicles, and the long distances between the cloud servers and VUE induce some potential issues, such as extra communication delay and energy consumption. Fortunately, mobile edge computing (MEC), a promising computing paradigm, can ameliorate the above problems by enhancing the computing abilities of VUE through allocating the computational resources to VUE. In this paper, we propose a joint optimization algorithm based on a deep reinforcement learning algorithm named the double deep Q network (double DQN) to minimize the cost constituted of energy consumption, the latency of computation, and communication with the proper policy. The proposed algorithm is more suitable for dynamic scenarios and requires low-latency vehicular scenarios in the real world. Compared with other reinforcement learning algorithms, the algorithm we proposed algorithm improve the performance in terms of convergence, defined cost, and speed by around 30%, 15%, and 17%.

Download Full-text

Very Short-Term Load Forecaster Based on a Neural Network Technique for Smart Grid Control

Energies ◽

10.3390/en13195210 ◽

2020 ◽

Vol 13 (19) ◽

pp. 5210

Author(s):

Fermín Rodríguez ◽

Fernando Martín ◽

Luis Fontán ◽

Ainhoa Galarza

Keyword(s):

Neural Network ◽

Power Systems ◽

Smart Grids ◽

Energy Demand ◽

Learning Algorithm ◽

Control Strategies ◽

Absolute Error ◽

Current Control ◽

Electrical Network ◽

Short Term

Electrical load forecasting plays a crucial role in the proper scheduling and operation of power systems. To ensure the stability of the electrical network, it is necessary to balance energy generation and demand. Hence, different very short-term load forecast technologies are being designed to improve the efficiency of current control strategies. This paper proposes a new forecaster based on artificial intelligence, specifically on a recurrent neural network topology, trained with a Levenberg–Marquardt learning algorithm. Moreover, a sensitivity analysis was performed for determining the optimal input vector, structure and the optimal database length. In this case, the developed tool provides information about the energy demand for the next 15 min. The accuracy of the forecaster was validated by analysing the typical error metrics of sample days from the training and validation databases. The deviation between actual and predicted demand was lower than 0.5% in 97% of the days analysed during the validation phase. Moreover, while the root mean square error was 0.07 MW, the mean absolute error was 0.05 MW. The results suggest that the forecaster’s accuracy is considered sufficient for installation in smart grids or other power systems and for predicting future energy demand at the chosen sites.

Download Full-text

An Overview of Fog Computing and Edge Computing Security and Privacy Issues

Sensors ◽

10.3390/s21248226 ◽

2021 ◽

Vol 21 (24) ◽

pp. 8226

Author(s):

Ahmed M. Alwakeel

Keyword(s):

Cloud Computing ◽

Fog Computing ◽

Edge Computing ◽

Security And Privacy ◽

Local Network ◽

Security Issues ◽

Computing Paradigm ◽

Edge And Fog Computing ◽

Cloud Technologies ◽

Privacy Issues

With the advancement of different technologies such as 5G networks and IoT the use of different cloud computing technologies became essential. Cloud computing allowed intensive data processing and warehousing solution. Two different new cloud technologies that inherit some of the traditional cloud computing paradigm are fog computing and edge computing that is aims to simplify some of the complexity of cloud computing and leverage the computing capabilities within the local network in order to preform computation tasks rather than carrying it to the cloud. This makes this technology fits with the properties of IoT systems. However, using such technology introduces several new security and privacy challenges that could be huge obstacle against implementing these technologies. In this paper, we survey some of the main security and privacy challenges that faces fog and edge computing illustrating how these security issues could affect the work and implementation of edge and fog computing. Moreover, we present several countermeasures to mitigate the effect of these security issues.

Download Full-text

Security Issues of Communication Networks in Smart Grid

Security Solutions and Applied Cryptography in Smart Grid Communications - Advances in Information Security, Privacy, and Ethics ◽

10.4018/978-1-5225-1829-7.ch002 ◽

2016 ◽

pp. 29-49

Author(s):

Gurbakshish Singh Toor ◽

Maode Ma

Keyword(s):

Power Generation ◽

Smart Grid ◽

Communication Networks ◽

Smart Grids ◽

Information Technologies ◽

Communication Technologies ◽

Energy Aware ◽

Security Issues ◽

Efficient Power ◽

Electricity Infrastructure

The evolution of the traditional electricity infrastructure into smart grids promises more reliable and efficient power management, more energy aware consumers and inclusion of renewable sources for power generation. These fruitful promises are attracting initiatives by various nations all over the globe in various fields of academia. However, this evolution relies on the advances in the information technologies and communication technologies and thus is inevitably prone to various risks and threats. This work focuses on the security aspects of HAN and NAN subsystems of smart grids. The chapter presents some of the prominent attacks specific to these subsystems, which violate the specific security goals requisite for their reliable operation. The proposed solutions and countermeasures for these security issues presented in the recent literature have been reviewed to identify the promising solutions with respect to the specific security goals. The paper is concluded by presenting some of the challenges that still need to be addressed.

Download Full-text

A Data Driven Approach to Robust Event Detection in Smart Grids Based on Random Matrix Theory and Kalman Filtering

Energies ◽

10.3390/en14082166 ◽

2021 ◽

Vol 14 (8) ◽

pp. 2166

Author(s):

Fujia Han ◽

Phillip M. Ashton ◽

Maozhen Li ◽

Ioana Pisica ◽

Gareth Taylor ◽

...

Keyword(s):

Power Systems ◽

Kalman Filtering ◽

Random Matrix Theory ◽

Random Matrix ◽

Event Detection ◽

Smart Grids ◽

Situational Awareness ◽

Matrix Theory ◽

Data Driven ◽

Detection Approach

Increasing levels of complexity, due to growing volumes of renewable generation with an associated influx of power electronics, are placing increased demands on the reliable operation of modern power systems. Consequently, phasor measurement units (PMUs) are being rapidly deployed in order to further enhance situational awareness for power system operators. This paper presents a novel data-driven event detection approach based on random matrix theory (RMT) and Kalman filtering. A dynamic Kalman filtering technique is proposed to condition PMU data. Both simulated and real PMU data from the transmission system of Great Britain (GB) are utilized in order to validate the proposed event detection approach and the results show that the proposed approach is much more robust with regard to event detection when applied in practical situations.

Download Full-text