Machine Learning-based Intrusion Detection for Smart Grid Computing: A Survey

Smart grid significantly improves the functions of conventional power networks, but it also makes them more susceptible to attacks of different types. Using smart grid’s vulnerabilities, attackers may compromise the integrity and confidentiality of networks, and obtain access to them as a result. Intrusion Detection System (IDS) constitutes an important means to provide safe and reliable services in a smart grid environment. This paper proposes an intrusion detection model under smart grid environment that is widely distributed in the three-tier architecture of power grid system. The model introduces Random Forest (RF) into machine learning and Particle Swarm Optimization (PSO) into evolutionary computation. To improve the accuracy of the model, this paper taps into the adaptive strategy for continued adjustment concerning the flight attitude of particles, and uses multiple mutation methods to prevent the occurrence of local optimum. The AMPSO algorithm proposed in this paper performs well in benchmarking function tests, thereby providing effective guarantee for the improvement of RF classifier. According to simulation experiments based on test sets of NPL-KDD, the intrusion detection model proposed in this paper is highly effective and practical.

With the rapid advancement of technology and the growing reliance on renewable energy sources, smart grids have emerged as a transformative solution for enhancing the efficiency and reliability of power distribution systems. As the smart grid ecosystem evolves, security concerns become paramount due to the interconnectedness of various components, including advanced metering infrastructure, communication networks, and distributed energy resources. This paper presents a comprehensive analysis of smart grid security, focusing on the challenges, vulnerabilities, and potential threats that must be addressed to ensure the resilience of these intelligent infrastructures. It explores the diverse attack vectors that malicious actors may exploit to compromise smart grid operations and highlights the potential consequences of such security breaches, including power disruptions, data breaches, and financial losses. To counteract these risks, this paper delves into various state-of-the-art security measures and strategies that can be implemented to safeguard smart grids effectively. Moreover, the importance of collaboration between various stakeholders is described, including utility companies, government agencies, researchers, and technology vendors, to foster a holistic approach to smart grid security. By emphasizing the significance of information sharing and collaboration, this paper advocates for a robust and adaptive security framework to respond promptly to emerging threats and vulnerabilities. Furthermore, the paper explores emerging technologies such as artificial intelligence, blockchain, and intrusion detection systems, showcasing their potential contributions in fortifying smart grid defenses. It was noted that the integration of these innovative technologies can enhance anomaly detection, facilitate secure data exchange, and reinforce the resilience of the smart grid against sophisticated cyber-attacks. Towards the end of this paper, insights into future research directions and policy implications to foster a more secure and sustainable smart grid environment is provided. By acknowledging the evolving threat landscape and the dynamic nature of the smart grid domain, this work encourages continuous research and development to stay ahead of adversaries and establish a secure foundation for the future of energy distribution.

A smart grid is an intelligent power grid. In recent years, the smart grid environment and its applications are incorporated into a variety of areas. The smart grid environment, however, can expose much more information than the old environments. In the environment, smart devices can be media in the exposure of various and specific pieces of information as well as energy consumption. This poses a huge risk in that it, combined with other pieces of information, may expose much more information. The current smart grid environment raises a need to develop anonymous signature and authentication techniques to prevent privacy breaches. Trying to meet this need, the principal investigator conducted research for three years. This paper discusses both the research trends investigated by him and the limitations of the development research and future research in need. Smart grid security requires the development of encrypted anonymous authentication that is applicable to power plant security, including nuclear power plants as well as expandable test beds.

Key performance aspects of an LTE FDD based Smart Grid communications network

Developments in information and communication technologies (ICT) achieved new trends such as smart grid (SG). Innovations in ICT bring challenges to our security and expectations of privacy. ICT has such a big attack surface that possess increased risks from cyber-attacks in smart grid. Actually, as a critical infrastructure, the smart grid is more sensitive to cyber-attacks, as monitoring and control of smart grid can be realized over standard internet-based protocols. Therefore, an attacker may achieve financial cost to the service and create loss of electric resources, through breaching the real-time balance between energy production and consumption, by controlling data produced by the smart entities. Therefore, in this study, bagging ensemble classifier is evaluated for intrusion detection in a smart grid with a benchmark data. Experimental results have revealed the practicality of Bagging ensemble classifier by realizing a better performance for the cyber security threats in a smart grid environment. The results indicated that the suggested Bagging ensemble classifier with REP Tree achieved a total classification accuracy of 99.94%.

A new model of power system to identify critical elements for smart and bulk power transmission grid environment is presented in this paper. Proposed bidirectional power flow model under complex network framework can quantify the criticality of nodes whose removal would trigger cascading failure. The proposed model based centrality, which is an extension of nominal power flow based model, is able to find nodes whose removal exerts more stress on the system. Several measures of impact like path length increase, boosted connectivity loss, raised load loss and increase in number of overloaded lines justify the use of bidirectional power flow based model to evaluate the criticality in smart grid environment. Change in direction of power flow in various random lines of the test system has a very little effect on the rank of nodes in the critical list.

MQRP: Mobile sinks-based QoS-aware data gathering protocol for wireless sensor networks-based smart grid applications in the context of industry 4.0-based on internet of things

In this paper, we review and analyze intrusion detection systems for Agriculture 4.0 cyber security. Specifically, we present cyber security threats and evaluation metrics used in the performance evaluation of an intrusion detection system for Agriculture 4.0. Then, we evaluate intrusion detection systems according to emerging technologies, including, Cloud computing, Fog/Edge computing, Network virtualization, Autonomous tractors, Drones, Internet of Things, Industrial agriculture, and Smart Grids. Based on the machine learning technique used, we provide a comprehensive classification of intrusion detection systems in each emerging technology. Furthermore, we present public datasets, and the implementation frameworks applied in the performance evaluation of intrusion detection systems for Agriculture 4.0. Finally, we outline challenges and future research directions in cyber security intrusion detection for Agriculture 4.0.

Cyber physical systems (CPSs) utilised in many of the critical infrastructures including the smart grid. The operational activities of smart grid's CPS use different industrial solution such as industrial control systems (ICS) for monitoring and controlling the physical architecture of smart grid. Therefore, it is quite essential to keep these industrial control systems secure and safe from potential hazards and cyber world as it may be harmful for human safety, strategic infrastructure of a country and also for the economy. The study gathered the scattered guidelines, best practices and policies available from various organisations such as National Institute of Standards and Technology (NIST), ISO, and North American Electric Reliability Corporation (NERC) for the purpose of developing safe and secure ICS security systems and also the knowledge about the issues involved in ICS security and protection. A conceptual framework is proposed and developed to address the shortcomings in-order to protect the ICS systems in a smart grid environment. The proposed framework was developed by reviewing related studies, standards and utilising IT security working experience. This framework will not only expand the horizon of knowledge but also provides pathway for the development of existing activities of CPS applications such as smart grid.

High-data-rate mobile multimedia applications can greatly increase energy consumption, leading to an emerging trend of addressing the “energy efficiency” aspect of mobile networks. Cognitive mobile networks with small cells are important techniques for meeting the high-data-rate requirements and improving the energy efficiency of mobile multimedia communications. However, most existing works do not consider the power grid, which provides electricity to mobile networks. Currently, the power grid is experiencing a significant shift from the traditional grid to the smart grid. In the smart grid environment, only considering energy efficiency may not be sufficient since the dynamics of the smart grid will have significant impacts on mobile networks. In this paper, we study green cognitive mobile networks with small cells in the smart grid environment. Unlike most existing studies on cognitive networks, where only the radio spectrum is sensed, our cognitive networks sense not only the radio spectrum environment but also the smart grid environment, based on which power allocation and interference management for multimedia communications are performed. We formulate the problems of electricity price decision, energy-efficient power allocation, and interference management as a three-stage Stackelberg game. A homogeneous Bertrand game with asymmetric costs is used to model price decisions made by the electricity retailers. A backward induction method is used to analyze the proposed Stackelberg game. Simulation results show that our proposed scheme can significantly reduce operational expenditure and CO2 emissions in cognitive mobile networks with small cells for multimedia communications.

Cyber attack models for smart grid environments

Smart grids are smart grids because they don't only transport electricity but also information that will become an active part of the electricity supply system. Smart grid evolution has, thus, a lot to gain through the exploitation of emerging Future Internet networking technologies for the efficient collection and management of the acquired information. The capabilities for interconnection of numerous intelligent networking devices, the advanced monitoring and control of dynamic networking infrastructures and the efficient handling of large volumes of data are research areas that have direct applicability into the smart grid design and operation. This article presents our insights for the design of a novel and open overlay networking architecture for leveraging end-to-end interconnection of physical or virtual objects, for achieving decentralized data management, and for providing distributed services in smart grid environments. The proposed architecture follows a layered-approach and extends or adapts a set of existing overlay and IP protocols. In addition, a smart grid business-oriented scenario is briefly presented in order to explain how future technologies may be used to fulfill contemporary society needs.

As a critical infrastructure, the electric power grid is vulnerable with respect to malicious physical and cyber attacks. Indeed, the importance of physical and cyber security for smart grids has been highlighted by recent intrusion incidents worldwide. Various types of sensors, instrumentation, information and communications technology (ICT), computational methodologies, and security controls have been developed to enhance the physical and cyber security of the smart grid. In this paper, critical vulnerabilities of a smart grid that can be exploited for physical and cyber intrusions are discussed. A comprehensive survey is conducted on the state‐of‐the‐art research to enhance the physical and cyber security in a smart grid environment. Furthermore, the interdependency of physical and cyber security is illustrated with an intrusion scenario. The emphasis is on the physical and cyber security of power substations. Computer simulation results for a case study are presented. WIREs Energy Environ 2016, 5:519–542. doi: 10.1002/wene.202This article is categorized under: Energy Infrastructure > Systems and Infrastructure

The Smart Grid aims to enhance the electric grid’s reliability, safety, and efficiency by utilizing digital information and control technologies. Real-time analysis and state estimation methods are crucial for ensuring proper control implementation. However, the reliance of Smart Grid systems on communication networks makes them vulnerable to cyberattacks, posing a significant risk to grid reliability. To mitigate such threats, efficient intrusion detection and prevention systems are essential. This paper proposes a hybrid deep-learning approach to detect distributed denial-of-service attacks on the Smart Grid’s communication infrastructure. Our method combines the convolutional neural network and recurrent gated unit algorithms. Two datasets were employed: The Intrusion Detection System dataset from the Canadian Institute for Cybersecurity and a custom dataset generated using the Omnet++ simulator. We also developed a real-time monitoring Kafka-based dashboard to facilitate attack surveillance and resilience. Experimental and simulation results demonstrate that our proposed approach achieves a high accuracy rate of 99.86%.

Electricity theft-induced power loss is a pressing issue in both traditional and smart grid environments. In smart grids, smart meters can be used to track power consumption behaviour and detect any suspicious activity. However, smart meter readings can be compromised by deploying intrusion tactics or launching cyber attacks. In this regard, machine learning models can be used to assess the daily consumption patterns of customers and detect potential electricity theft incidents. Whilst existing research efforts have extensively focused on batch learning algorithms, this paper investigates the use of online machine learning algorithms for electricity theft detection in smart grid environments, based on a recently proposed dataset. Several algorithms including Naive Bayes, K-nearest Neighbours, K-nearest Neighbours with self-adjusting memory, Hoeffding Tree, Extremely Fast Decision Tree, Adaptive Random Forest and Leveraging Bagging are considered. These algorithms are evaluated using an online machine learning platform considering both binary and multi-class theft detection scenarios. Evaluation metrics include prediction accuracy, precision, recall, F-1 score and kappa statistic. Evaluation results demonstrate the ability of the Leveraging Bagging algorithm with an Adaptive Random Forest base classifier to surpass all other algorithms in terms of all the considered metrics, for both binary and multi-class theft detection. Hence, it can be considered as a viable option for electricity theft detection in smart grid environments.