Convolutional gated recurrent neural network-based detection of cyber-attacks in power systems

With the increasing reliance on gas supply, the operating security of power systems is dependent on the natural gas system. Traditional contingency analysis of individual power system constraints is insufficient and may produce a large error. The aim of this paper is to study the impact of failures in natural gas system on the operating security of power system. In order to analyze it, the operating status of the power system and the anticipated contingency set of the natural gas system were proposed. Case studies demonstrated that the failure of natural gas system would adversely affect the operation security of power system. Therefore, coupled security analysis is of great significance.

Maintenance schedule of generators in an interconnected power system presents multifaceted challenges, two important ones being optimal operation cost and secure operation. When a generator is scheduled for maintenance, achieving optimal generation scheduling for the committed generators is necessary but it is not sufficient for secure operation of power systems. This problem is decomposed into two subproblems: i) Finding the optimal set points for the generators; ii) Validating secure operation with those set points from i). Both these subproblems [i) and ii)] have been studied extensively in the literatures. However, the research here focuses on incorporating battery energy storage systems (BESS) in power operation, a renewable generation that can provide smooth and flexible reserves of power, an area that has not yet been fully explored. In addition, incorporating BESS while considering both the cost implications and addressing secure operation has not yet been addressed in previous literatures. The purpose of this paper is to present both secure and optimal operation besides improving the longevity of the BESS. Feasibility of the proposed approach is demonstrated on Tabuk region—an isolated northwest grid of Saudi Arabia.

In the detection process of server network storm attack, the traditional method takes the signal detection algorithm, because the attack number is large, the detection error is big.According to the problem, an improved server network storm attack detection method is proposed based on improved density clustering algorithm, the server network storm attack detection problem is transformed into a multi class classification problem, wrapper features selection model is taken, IDBC network connection record distance calculation method is combined, based on DBSCAN clustering results, the data clustering and attack detection is obtained.Simulation results show that, the improved density clustering algorithm is applied in detection of server network storm attack, it can reduce the detection error, the performance of the detection system is improved.

Unit commitment is important in economy and security of power system operation. However, Large penetration of wind power integrated into power system increases the uncertainty on unit commitment. How to efficiently accommodate the uncertainty has been researched widely. In this paper, a new interval unit commitment (UC) formulation based on interval optimization is proposed in which the uncertain wind power is described as fluctuant intervals. Then, the interval UC with uncertainty is transformed into a deterministic form by using order relation of interval number and degree of satisfaction. The transformed model is a two-stage and multi-objective optimization problem. Therefore, the intergeneration projection genetic algorithm is developed to deal with the transformed deterministic model. Finally, the case study with IEEE 39-bus system demonstrated the effectiveness and advantages of the proposed model.

Out of step with the rapid growth of China's electricity load demand, the infrastructure of power grid in many areas is not strong enough to insure the security of power system operation. In this case, considering the strict N-1 conditions of lines and transformers, the situation that there is no feasible solution for the security-constrained unit commitment (SCUC) might occasionally occur. In order to address this issue, a homogenized-overload model based on SCUC is proposed in this paper. The homogenized-overload model could obtain a reasonable, suboptimal solution reducing the security risks by lowering the average overload level and reducing the number of overload lines without sacrificing the economy of unit commitment. To identify the overload line set, an identifying method based on the Benders decomposition algorithm is also proposed. The homogenized-overload model and the identifying method are tested respectively in a 6-bus system case and a real provincial power system in China. Simulation results show the validity of the model and the method.

There are growing interests in electric vehicles because of environment concern. When a large number of EVs are introduced a power system, there will be extensive impacts on the security and economy of power system operation. Given this background, a dispatch optimization model is built in this paper to mitigate the peak-to-valley ratio of equivalent loads and reduce the active power losses of the distributed grid, based on the driving characteristics of EVs and other demands in power system. Particle swarm optimization algorithm is adopted to solve this optimization problem. The proposed model and algorithm are applied to the IEEE 33-bus test system, and the simulation results indicate the feasibility and efficiency.

In February 1998 a new and unique form of power generator, the Powerformer TM , was introduced into the marketplace. The Powerformer can be operated at transmission system level voltage without the need for a step up transformer and consequently has unique system support capabilities. The aim of the research work, presented in this thesis, was to investigate the unique aspects of the Powerformer from a power system perspective, in order to facilitate optimal power system operation and security.The main focus of the research undertaken by the author of this thesis was to investigate the impact of Powerformer on the relative voltage stability of a power system. The driving force behind the author's desire to look at the impact of the Powerformer on power system voltage stability and security was the realisation that voltage stability issues are becoming increasingly important. The focus for today's modem power transmission systems is undergoing a radical shift from a purely publicly provided service to a financially driven commodity. This ultimately means that power systems are increasingly under pressure to be utilised to their fullest capacity without the need to install new, expensive and sometimes socially unpopular system equipment and facilities. The problem with this situation is that a system's stability can be affected greatly by loading conditions. When a system is heavily loaded the voltage stability limit, rather than the transient angle stability limit constrains its operation. It is for this reason that voltage stability concerns in particular are increasingly being discussed in the literature and becoming an issue for power system operators. A number of different static and dynamic system analysis techniques have been reviewed and compared in this thesis, with the results of these comparisons presented and discussed in this thesis. Amongst the methods discussed in this thesis, methods for use in voltage stability analysis and assessment have been proposed and presented by the author of this thesis. The most suitable techniques are being utilised to determine how the Powerformer can aid in safe system operation under a number of different system contingencies in a number of different test systems, including the 600+ bus Queensland Transmission System. Particular emphasis has been placed in this research on long-term system dynamics. Two major aspects of the Powerformer that differ it from conventional are the lack of a step up transformer and the ability of the Powerformer stator to be overloaded for longer periods than conventional power generators. The lack of a step up transformer means that power that would normally be lost can be supplied to the system and that the high voltage bus, normally on the opposite side of the step up transformer, is directly controlled. The overload capability of the Powerformer means that it can supply reactive power support to the power system for a longer period than a conventional generator. Investigations undertaken into the Powerformer have shown it to have a potentially beneficial ability to allow greater system loading capability and therefore system security margins and a potentially beneficial impact on the time to voltage collapse following a system contingency.

Recently, wide concern of extreme risk events in power system has been aroused due to several big blackouts at home and abroad. The present study is designed to assess the extreme risk of power system considering cyber attacks, which can not be reflected by using traditional risk assessment method. Based on the theory of value at risk(VaR) and extreme value theory(EVT) in financial terms, a method to evaluate and quantize extreme risk of power system is proposed to determine the potential risk resulted from extreme events with low probabilities and serious consequences. The method is applied to evaluate the extreme risk of cyber attacks in power system and comparisons between evaluation results of commom risk and extreme risk are conducted. Statistically significant results have justified the validity of extreme risk assessment method, which could be regarded as a complement and improvement to traditional risk assessment. It is recommended that further study is needed to be conducted for risk prevention so as to enhance the operation security and reliability of power system.

In recent decades, voltage instability has become an important contributor to large-scale power outages globally. Periodic voltage security assessments are key for the secure operation of power systems. There are various indicators which have been implemented in different types and complexity of systems to provide a measure of closeness to voltage collapse, but some of these algorithms may require advanced computational resources or may not perform well, depending on the prevailing conditions. Expanding interconnected power systems is needed like never before due to the increasing world demand for electricity, and voltage stability is therefore a worth consideration. The growing demand penetration of solar photovoltaic (PV) systems has some potential stability challenges due to their intermittent characteristics. Existing research evaluates the test systems of voltage stability and does not optimize using Intelligent models, which have variable power generation from Solar PV and Wind, as well as uncertainties in load demand and the initial step considering the evaluation of the model have to cover either inputs. A feed–forward back propagation artificial neural network (ANN) for voltage stability assessment to classify the operating scenario of a power system into one of two states, i.e. safe or unsafe. Neural network input data is generated from load flow analysis using Newton-Raphson (NR), and stability indices are computed over different scenarios. Line Stability Index (Lmn), counts the stability of a transmission line in power systems and provides an indication of its potential voltage collapse. The Fast Voltage Stability Index (FVSI), which also estimates line stability through reactive power and impedance characteristics. Voltage Collapse Proximity Index (VCPI) assesses system proximity to voltage collapse and identifies weak transmission lines. Values approaching 1 suggest voltage collapse conditions. The FVSI, VCPI, and Lmn are compared to a baseline NR stability index. Moreover, self-organizing map (SOM) neural network is used for stability results classification. Multi-objective grasshopper optimization algorithm (MOGOA) has been employed as an optimization network on the dual axis solar PV and wind turbine-based hybrid power generation system to analyze technical, economic, as well as environmental relations of energy conversion. The findings reveal that the adapted grid-tied solar-wind composite power system substantially mitigates the power deficiencies, reduces the real-power outages, diminishes the motion voltage small amendments, maximizes voltage prosperity, and improves power system resilience. The main findings show a significant reduction in real power loss, which went from 289,391.30 kW to only 5.43 kW, and a remarkable decrease in voltage deviation, which reduced from 0.56 p.u to 0.0493 p.u. Ensures Improved Service Quality and Enhanced Equipment Protection While gas generation costs increased by a small amount, it is important to note that this is an acceptable trade-off for a more robust and sustainable system, with costs per kWh of $0.142 vs $0.2881 per kWh, respectively. In addition, stability index was substantially decreased from 0.7666 to 0.0768, indicating better grid and resilience to disturbances. Findings emphasize the contribution of embedding MOGOA in conjunction with machine learning models including ANN and Self Organizing Maps (SOM) to fulfill the primal requisites of stability, efficiency and sustainability in modernized power systems, illustrating a coupled advancement in the realm of power systems engineering and optimization.

Guest Editorial: Situational awareness of integrated energy systems

As a typical grid-forming control method, virtual synchronous generator (VSG) control enhances system inertia but introduces frequency oscillation issues. This problem becomes particularly severe in multi-VSG parallel systems when inconsistent virtual inertia exists among power sources, significantly compromising the security and stability of power system operation. Virtual inertia control can directly regulate the rate of change of frequency (RoCoF) under constant torque difference conditions to suppress frequency oscillations, offering faster response characteristics. Therefore, this paper proposes a distributed virtual inertia control strategy for multi-VSG parallel systems. First, a small-signal model of the multi-machine parallel system is established, and its small-signal stability is demonstrated. Second, a neighbor-communication-based distributed virtual inertia coordination control method is proposed. Through neighbor information exchange and local decision-making, this method enables dynamic adjustment of each unit's virtual inertia, driving frequency synchronization among all units in the system. This effectively suppresses post-disturbance frequency oscillations and enhances the dynamic performance of low-inertia power systems. Furthermore, the stability of the proposed control strategy is rigorously proven through the construction of a Lyapunov energy function. Finally, MATLAB/Simulink simulations verify that the proposed virtual inertia control strategy can effectively mitigate frequency oscillations while reducing their settling time.

Boosting efficiency in state estimation of power systems by leveraging attention mechanism

The complexity of the Internet and the volume of network traffic have dramatically increased in the last few years, making it more challenging to design scalable Network Traffic Monitoring and Analysis (NTMA) systems. Critical NTMA applications such as the detection of network attacks and anomalies require fast mechanisms for on-line analysis of thousands of events per second, as well as efficient techniques for off-line analysis of massive historical data. The high-dimensionality of network data provided by current network monitoring systems opens the door to the massive application of machine learning approaches to improve the detection and classification of network attacks and anomalies, but this higher dimensionality comes with an extra data processing overhead. In this paper we present Big-DAMA, a big data analytics framework (BDAF) for NTMA applications. Big-DAMA is a flexible BDAF, capable to analyze and store big amounts of both structured and unstructured heterogeneous data sources, with both stream and batch processing capabilities. Big-DAMA uses off-the-shelf big data storage and processing engines to offer both stream data processing and batch processing capabilities, decomposing separate engines for stream, batch and query, following a Data Stream Warehouse (DSW) paradigm. Big-DAMA implements several algorithms for anomaly detection and network security using supervised and unsupervised machine learning (ML) models, using off-the-shelf ML libraries. We apply Big-DAMA to the detection of different types of network attacks and anomalies, benchmarking multiple supervised ML models. Evaluations are conducted on top of real network measurements collected at the WIDE backbone network, using the well-known MAWILab dataset for attacks labeling. Big-DAMA can speed up computations by a factor of 10 when compared to a standard Apache Spark cluster, and can be easily deployed in cloud environments, using hardware virtualization technology.

Multi-objective optimal load dispatch of microgrid with stochastic access of electric vehicles

Decentralized transfer of contingency reserve: Framework and methodology