Smart Power Grid System Research Articles

Classification of intrusion cyber‐attacks in smart power grids using deep ensemble learning with metaheuristic‐based optimization

AbstractThe most advanced power grid design, known as a ‘smart power grid’, integrates information and communication technology (ICT) with a conventional grid system to enable remote management of electricity distribution. The intelligent cyber‐physical architecture enables bidirectional, real‐time data sharing between electricity suppliers and consumers through smart meters and advanced metering infrastructure (AMI). Data protection issues, such as data tampering, firmware exploitation, and the leakage of sensitive information arise due to the smart power grid's substantial reliance on ICT. To maintain reliable and efficient power distribution, these issues must be identified and resolved quickly. Intrusion detection is essential for providing secure services and alerting system administrators in the case of adversary attacks. This paper proposes an intrusion classification scheme that identifies several types of cyber attacks on modern smart power grids. Grey‐Wolf metaheuristic optimization‐based feature selection is used to learn non‐linear, overlapping, and complex electrical grid properties. An extended deep‐stacked ensemble technique is advanced by putting predictions from weak learners (CNNs) into a meta‐learner (MLP). The outcomes of this approach are explained and confirmed using explainable AI (XAI). The publicly available dataset from Mississippi State University and Oak Ridge National Laboratory (MSU‐ORNL) is used to conduct experiments. The experimental results show that the proposed method achieved a peak accuracy of 96.6% while scrutinizing the original MSU‐ORNL data feature set and a maximum accuracy of 99% when analysing the selected feature set. Therefore, the proposed intrusion classification scheme may protect smart power grid systems against cyber security attacks.

Lightweight Authenticated Key Agreement Protocol for Smart Power Grid Systems Using PUF

Lightweight Authenticated Key Agreement Protocol for Smart Power Grid Systems Using PUF

Observer-Based Event-Triggered Composite Anti-Disturbance Control for Multi-Agent Systems Under Multiple Disturbances and Stochastic FDIAs

This article aims to investigate the security consensus and composite anti-disturbance problems for a class of nonlinear multi-agent systems subjected to stochastic false data injection attacks (FDIAs) and multiple disturbances under a directed communication topology. To attenuate and reject of the negative effects of two types of disturbances, a disturbance observer (DO) is designed to counteract the disturbance produced by exogenous system, and the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\mathcal {H}_\infty $ </tex-math></inline-formula> control method is adopted to attenuate the bounded errors and variables caused by the other type of disturbances and FDIAs simultaneously. To ensure the consensus performance of MASs, an observer-based control strategy is designed, and a novel adaptive compensation technique is proposed to not only evaluate the upper bounds of the unknown but bounded disturbances but also improve the accuracy of the state observer. Furthermore, a novel event-triggered mechanism (ETM) without requiring continuous communication among neighboring agents is developed to reduce the controller update frequency and the communication burden. Meanwhile, Zeno behavior is excluded. Finally, numerical simulations are provided to verify the availability of the designed method. Note to Practitioners—In multi-agent systems, network security is very important. For example, in smart power grid systems, it is necessary to use the method of state estimation to observe the system to guarantee its safe operation. However, the measured value of the instrument may be affected by FDIAs in the transmission process, thus changing the result of state estimation and causing misjudgment of the system. Similarly, in multi-vehicle systems, FDIAs may destroy the location information of vehicles and cause serious accidents. In addition, the system will be subjected to different types of disturbances in practice, thus reducing the performance of the system. In view of the threat of FDIAs and disturbances to the MAS, a composite anti-disturbance method and an observer-based control strategy are proposed. Meanwhile, to avoid the limitation of communication bandwidth in reality, a novel ETM is developed to save network resources.

An artificial intelligence-based electric multiple units using a smart power grid system

EMU stands for electric multiple units and refers to a train of self-propelled cars pushed by electricity. Energy from renewable sources such as solar and wind can be stored in battery storage systems (BESS) and released when consumers need it most. Electric traction motors are built inside one or more of the carriages of an EMU, eliminating the need for a separate engine. Electric trains can go further and quicker than those propelled by steam engines. There are several advantages to using electric trains, such as efficiently converting fuel into kinetic energy. Rail travel is affected by fluctuations in electrical power. With AI, energy waste and prices might be reduced, and the deployment of clean, renewable energy sources could be facilitated and accelerated in power systems globally. Artificial intelligence (AI) can benefit from the design, operation, and management of power systems. Voltage fluctuations occur if a large number of electricity gadgets are utilized simultaneously. Voltage fluctuations, especially in extreme circumstances, can be extremely hazardous to the safety and other possessions. The researchers devised the EMU-AI-BESS approach to address these problems. Trains powered by lithium-ion batteries can go on both kinds of track. Battery-electric technology has been used to expand electrified metro lines in several cities throughout the globe, and many more are contemplating it. Renewable energy sources like solar, wind, and hydrogen can be effectively managed and distributed due to smart grid technologies. The smart grid links a wide range of distributed energy resources to the power grid.AI can assist in minimizing traffic congestion, detecting dangers, managing transportation, analyzing travel demand, and potentially cutting greenhouse gas emissions. AI is being utilized in today’s rail applications to increase asset management and train schedules, train speed control, and other factors. AI’s primary goal is to give computers to execute mental functions, including decision-making, problem-solving, perception, and communication comprehension. Artificial intelligence will be needed to manage decentralized grids as the world transitions to renewable energy. Using AI, power supply and demand can be balanced in real-time, optimizing energy consumption and storage to minimize rates.

Multi-Agent Systems Based Adaptive Protection for Smart Distribution Network

The smart power grid has been developed and improved constantly to be able to incorporate protection, automation, communication, and advanced control methods. As a result, the smart power grid system protection is expected to be modernized and given the ability to handle the future complexity that emanates from the integration of Distributed Generations (DGs). An Adaptive Multi-Agent System (MAS) can enhance power system protection and make it more reliable, faster, selective, and robust. In this paper, a novel MAS-based adaptive protection technique that suits smart grid applications is proposed. The proposed protection technique consists of agents that communicate with each other and their environment. The agents used in the proposed technique are Short Circuit Current Calculation Agent (SCCA), Load Flow Calculation Agent (LFA), Setting Calculation Agent (SCA), Logic and Operating Agent (LOA), Coordination and Optimization Agent (COA), and Network Configuration Mapping Agent (NCMA). The proposed technique can adapt to the changing conditions in the smart grid. The DigSILENT PowerFactory software is used to verify the proposed technique using a real Distribution Network in the Antalya vicinity of Turkey. The achieved results show that the method can provide fast and selective protection for the smart grid with increased integration of DGs.

Building construction based on video surveillance and deep reinforcement learning using smart grid power system

New trendy neighborhoods require trimming scientific and technological methods and equipment. Smart buildings (SB) use resources efficiently, save energy, and provide services to the community more easily for their occupants while reducing their environmental footprint. Smart cities have benefited from this growth in terms of smart buildings. Maximum accuracy and reduced latency are both required for smart building monitoring systems. Poor scheduling rules can lead to network congestion and latency that is too high for real-time monitoring on construction sites, which have restricted computing and networking capabilities. These devices can collect the data on on-site actions, achievements, and circumstances and send it back to the central dashboard for analysis. Model predictive control and Deep Reinforcement Learning (DRL) have significant drawbacks, and DRL addresses some drawbacks. Researchers are intrigued by DRL, a brand-new approach to quality control. The most important considerations for developing smart power grid systems are energy conservation, renewable energy integration, and a streamlined control system. Experiments have shown that the new video surveillance has a low loss rate and a consistent latency. The DRL-SB-IoT technique can successfully track multiple cameras in a wide monitoring situation. This technique results in excellent tracking performance and meets the criteria for developing an intelligent campus in the best way possible. Researchers analyzed studies using supervised learning to solve common building issues, such as health monitoring, security on building sites, accommodation modeling, and energy consumption prediction. Reinforcement learning has been used to solve these issues. The proposed method advances the smart gateway channel of 97.5%, the energy storage ratio of 96.9%, and the overall surveillance performance ratio of 98.6%.

Intelligent Intrusion Detection Scheme for Smart Power-Grid Using Optimized Ensemble Learning on Selected Features

The smart grid has gained a reputation as the advanced paradigm of the power grid. It is a complicated cyber-physical system that combines information and communication technology (ICT) with a traditional grid that can remotely control operations. It provides the medium for exchanging real-time data between the company and users through the advanced metering infrastructure (AMI) and smart meters. However, smart grids have many security and privacy concerns, such as intruding sensitive data, firmware hijacking, and modifying data due to the high reliance on ICT. To protect the power-grid system from these counteracts and for reliable and efficient power distribution, early and accurate identification of these issues needs to be addressed. The intrusion detection in a smart grid system plays an essential role in providing a secure service and transmitting the high priority alert message to the system admin about the detection of adversary attacks. This paper proposes an intelligent intrusion detection scheme to accurately classify various attacks on smart power grid systems. The proposed scheme used the binary grey wolf optimization-based feature selection. It optimized the ensemble classification approach to learn the non-linear, overlapping, and complex electrical grid features taken from publicly available Mississippi State University and Oak Ridge National Laboratory (MSU-ORNL) dataset. The experimental results using a 10-fold cross-validation setup and selected feature subset for two class and three class problems reveal the proposed method's promising performance. Further, the significantly superior performance compared to the existing benchmark methods justified the robustness of the proposed scheme.

Design of type-2 fuzzy fractional-order proportional-integral-derivative controller and multi-objective parameter optimization under load reduction condition of the pumped storage unit

Pumped storage unit (PSU) is an effective regulation tool of the smart power grid system. The inherent “S” characteristics caused by the reversible design of the pump-turbine will make the PSU run into a state of instability, resulting in severe hydraulic fluctuation, unit speed, and frequency oscillation. PSU load reduction is an operation condition often encountered in the process of peak load regulation and frequency regulation. The operation stability of this condition is very important to the safety of the power station and power grid. Firstly, a mathematical model suitable for the numerical calculation of all working conditions transition process in the power generation direction of pumped storage unit regulating system (PSURS) is established. Further, the load reduction condition under typical water heads is selected. Through numerical calculation and analysis, it is found that when the PSU operates in the low water head-small load area and encounters load reduction to no-load, the PSURS is easy to fall into an unstable state. Therefore, an interval type-2 fuzzy fractional-order proportional-integral-derivative (PID) controller is proposed for the load reduction condition of the PSU under low water head and small load operation. And a multi-objective joint optimization strategy is proposed for tuning controller parameters. The experimental results show that the interval type-2 fuzzy fractional-order PID controller after parameters optimization has better control performance than traditional controllers. Compared with the PID control method, the double objective optimal result index is reduced by 0.025 and 47.98 respectively, the rotational speed regulation time of the PSU is reduced by 20.27 s, the maximum water hammer pressure is reduced by 9.2 m. The novel method effectively solves the instability problem of PSU under low water head load reduction conditions.

IEC 61850 Compatible OpenPLC for Cyber Attack Case Studies on Smart Substation Systems

Programmable Logic Controllers (PLCs) are essential components for enabling remote monitoring and automated control in industrial control systems. Recently PLCs are often utilized in a modernized power grid system for implementing an additional layer of automated control, such as operation of circuit breakers under specific conditions. Thus, in order to create a software-based smart grid testbed (or ‘cyber range’ for cyber security experiments); emulation of the PLC is imperative. OpenPLC is a software widely used for emulating PLCs, but unfortunately it does not support IEC 61850 standard, which is the globally adopted standard for substation automation in smart power grid systems. Thus, in this paper, the enhancement of OpenPLC to support IEC 61850 protocol and information models is discussed. The performance of the implementation has been validated to corroborate its application for use cases in the smart grid paradigm. Subsequently, the implementation is demonstrated in a smart grid cyber range to evaluate the impacts of attacks and thereby, the effectiveness of security measures and robustness of PLC control logic. The implementation, named ‘OpenPLC61850’, is made available as an open-source project for the wider research and industry community.

Privacy-Preserving Multi-Authority Attribute-Based Data Sharing Framework for Smart Grid

In smart power grid systems, real-time electricity data sharing can bring many benefits. However the security and privacy challenges have been a concern. This is because shared data may contain some private and sensitive information of data owners or users. So it has been an important issue to balance data utilization, data privacy and users privacy. Privacy-preserving multi-authority attribute-based encryption (MA-ABE) is a promising tool to tackle this issue, but it cannot be directly applied to addressed scenario of smart power grid systems. In this paper, we propose a framework to achieve secure data sharing in smart grid. The scheme uses the technique of inner product encryption (IPE). Under this framework, the access policy and the attribute set are fuzzy by converting them into two vectors. Only when the two vectors are orthogonal, users can successfully obtain the sharing data. Besides, our scheme allows that the threshold access policy only involves attribute name indexes, and sensitive attribute values are not sent along with the shared data so the attribute privacy is preserved. In addition, in order to improve efficiency, our scheme adds a testing phase to avoid the unnecessary operation before recovering data. Finally, our performance analysis and experiments confirm the merits of the proposed framework.

Privacy-Preserving Energy Scheduling for Smart Grid With Renewables

We consider joint demand response and power procurement to optimize the average social welfare of a smart power grid system with renewable sources. The renewable sources such as wind and solar energy are intermittent and fluctuate rapidly. As a consequence, the demand response algorithm needs to be executed in real time to ensure the stability of a smart grid system with renewable sources. We develop a demand response algorithm that converges to the optimal solution with superlinear rates of convergence. In the simulation studies, the proposed algorithm converges roughly thirty time faster than the traditional subgradient algorithm. In addition, it is fully distributed and can be realized either synchronously or in asynchronous manner, which eases practical deployment.

Enhanced Hybrid Algorithm for Optimal Phasor Measurement Unit Placement Problem on Smart Power Grid System

Enhanced Hybrid Algorithm for Optimal Phasor Measurement Unit Placement Problem on Smart Power Grid System

Efficient Optimization and Placement using Enhanced GHB-IC Approach in Smart Power grid System

Generally, the observation of power system is carried out with minimum region unit for the optimal PMUs placement of the Smart power grid system. In world level, the power system of electrical is the major system and the power loss is the key issues in the transmission line. In order to have an efficient process with the optimal approach, GA based Enhanced Harmony and Binary Search Algorithm (GA-EHBSA) is implemented with the optimization of Improved Imperialistic Competitive (IIC) approach for complete power network observability of PMU optimal placement. The combined process is defined as Enhanced GHB-IC. It utilized with the improvement to have least PMU placement and better optimization approach for finding the optimal location. Also, it provides improvement in redundancy index, cost function and less power loss with efficient optimization. However, the process of placement and connection of the buses is considered at various places with the same cost of installation. It provides significant improvement in the profile of voltage and optimal structure for efficient optimal system. The simulation results are evaluated and compared with existing algorithm to show the efficient process of optimal PMUs placement with better optimization, minimum cost and redundancy than the existing.

Achieving Effective Power System Observability in Optimal PMUs Placement Using GA-EHBSA

Normally, the power system observation is carried out for the optimal PMUs placement with minimum use of unit in the region of the Smart power grid system. By advanced tool, the process of protection and management of the power system is considered with the measurement of time-synchronized of the voltage and current. In order to have an efficient placement solution for the issue, a novel method is needed with the optimal approach. For complete power network observability of PMU optimal placement a new method is implemented. However, the process of placement and connection of the buses is considered at various places with the same cost of installation. GA based Enhanced Harmony and Binary Search Algorithm (GA-EHBSA) is proposed and utilized with the improvement to have least PMU placement and better optimization approach for finding the optimal location. To evaluate the optimal placement of PMUs the proposed approach is implemented in the standard test systems of IEEE 14-bus, IEEE 24-bus, IEEE 30-bus, IEEE 39-bus and IEEE 57-bus. The simulation results are evaluated and compared with existing algorithm to show the efficient process of optimal PMUs placement with better optimization, minimum cost and redundancy than the existing.

Efficient Desynchronization of Thermostatically Controlled Loads

This paper considers demand side management in smart power grid systems containing significant numbers of thermostatically controlled loads such as air conditioning systems, heat pumps, etc. Recent studies have shown that the overall power consumption of such systems can be regulated up and down centrally by broadcasting small setpoint change commands without significantly impacting consumer comfort. However, sudden simultaneous setpoint changes induce undesirable power consumption oscillations due to sudden synchronization of the on/off cycles of the individual units. In this paper, we present a novel algorithm for counter-acting these unwanted oscillations, which requires neither central management of the individual units nor communication between units. We present a formal proof of convergence of homogeneous populations to desynchronized status, as well as simulations that indicate that the algorithm is able to effectively dampen power consumption oscillations for both homogeneous and heterogeneous populations of thermostatically controlled loads.

Economic Analysis of the Investment in Smart Substation

Intelligent Substation as one of the core components converting and managing energy within sturdy and smart power grid system coordinates electricity generation, transformation, transmission, distribution, usage and dispatching. In this paper, a thorough contrast was made between intelligent and conventional substation in terms of technical deployment, investment scale etc. Using life-span cycle technique, the economic analysis of intelligent substation revealed some key factors that dictate economy level. Finally, some rational proposals for decision makes to promote smart grid were given to improve economy of intelligent substation with a reasonable construction scale and sequence.