Open Radio Access Network (O-RAN) adopts a flexible, open, and virtualized architecture with standardized interfaces, reducing dependency on a single supplier. O-RAN hosts many intelligent applications known as eXtended Applications (xApps). xApps are applications deployed at the RAN Intelligent Controller (RIC) that leverage advanced Artificial Intelligence/Machine Learning (AI/ML) algorithms to make dynamic decisions for network optimization. Each application operates with distinct optimization objectives and is managed by independent operators while accessing shared network resources. Conflicts in this context occur when a deployed xApp's objective interferes with another xApp, resulting in incompatible actions or decisions that may negatively impact network performance. The lack of a unified mechanism to coordinate and prioritize the actions of different applications can create three types of conflicts (direct, indirect, and implicit). Conflict prediction in O-RAN refers to the proactive analytical process through which potential interactions or behaviors that may lead to conflicts between network applications are identified in advance, prior to their manifestation within the operational system. In our paper, we introduce a novel data-driven Graph Convolutional Network (GCN)-based method called GRAPH-based Intelligent xApp Conflict Prediction and Analysis (GRAPHICA). It predicts three types of conflicts (direct, indirect, and implicit) and pinpoints the root causes (xApps). GRAPHICA captures the complex and hidden dependencies among the xApps, controlled parameters, and key performance indicators (KPIs) in O-RAN to predict possible conflicts. Then, it identifies the root causes (xApps) contributing to the predicted conflicts. The proposed method is evaluated using highly imbalanced synthetic datasets, in which conflict instances constitute between 40% and merely 10% of the data. This evaluation setting is designed to reflect realistic operational environments where conflicts are infrequent, thereby enabling a comprehensive assessment of the model's performance under real-world conditions. Experimental results demonstrate a high F1-score over 98% for the synthesized datasets with different levels of class imbalance.

Artificial Intelligence (AI) agents capable of autonomous learning and independent decision-making hold great promise for addressing complex challenges across various critical infrastructure domains, including transportation, energy systems, and manufacturing. However, the surge in the design and deployment of AI systems, driven by various stakeholders with distinct and unaligned objectives, introduces a crucial challenge: How can uncoordinated AI systems coexist and evolve harmoniously in shared environments without creating chaos or compromising safety? To address this, we advocate for a fundamental rethinking of existing multi-agent frameworks, such as multi-agent systems and game theory, which are largely limited to predefined rules and static objective structures. We posit that AI agents should be empowered to adjust their objectives dynamically, make compromises, form coalitions, and safely compete or cooperate through evolving relationships and social feedback. Through two case studies in critical infrastructure applications, we call for a shift toward the emergent, self-organizing, and context-aware nature of these multi-agentic AI systems.

The smart grid is a highly complex cyber-physical system of heterogeneous components with sensory, control, computation, and communication. Its complexity, dimensionality, uncertainty, and strong cyber-physical coupling have made it inefficient to discover critical vulnerabilities at system or infrastructure levels manually. To enhance the security of smart grids, this work explores the attackers’ perspective and proposes a deep reinforcement learning (DRL)-based penetration testing (PT) framework to identify critical vulnerabilities in smart grids efficiently. Specifically, this paper takes replay attacks as an example of PT and formulates its optimization as a Partially Observable Markov Decision Process (POMDP) for DRL agents with three actions (stop, record, and replay): a partial observation model is created to mimic a real scenario where the pen-tester can only access limited intelligence. A reward function considering the PT’s multiple goals is designed to optimize the timing and ordering of replay attacks. Knowledge of the grid is further utilized to estimate the full state of the system and transform the POMDP into a Markov Decision Process (MDP) to be solved by DRL. A software-based co-simulation platform for DRL-based PT on the smart grid (GridBattleSim) was developed to validate our proposed PT framework.

Automated penetration testing (AutoPT) powered by large language models (LLMs) has gained attention for its ability to automate ethical hacking processes and identify vulnerabilities in target systems by leveraging the inherent knowledge of LLMs. However, existing LLM-based AutoPT frameworks often underperform compared to human experts in challenging tasks for several reasons: the imbalanced knowledge used in LLM training, short-sightedness in the planning process, and hallucinations during command generation. Moreover, the trial-and-error nature of the PT process is constrained by existing frameworks lacking mechanisms to learn from previous failures, restricting adaptive improvement of PT strategies. To address these limitations, we propose a knowledge-informed, selfreflective PT framework powered by LLMs, called RefPentester. This AutoPT framework is designed to assist human operators in identifying the current stage of the PT process, selecting appropriate tactics and techniques for each stage, choosing suggested actions, providing step-by-step operational guidance, and reflecting on and learning from previous failed operations. We also modeled the PT process as a seven-state Stage Machine to integrate the proposed framework effectively. The evaluation shows that RefPentester can successfully reveal credentials on Hack The Box’s Sau machine, outperforming the baseline GPT40 model by $16.7 \%$. Across PT stages, RefPentester also demonstrates superior success rates on PT stage transitions.

BACKGROUND: Narrative electronic medical records (EMR), which include textual notes created by clinicians within healthcare environments, represent a significant resource for documenting various facets of patient care. This form of text exhibits distinctive characteristics, such as the occurrence of grammatically incorrect sentences, abbreviations, frequent acronyms, specialized characters with particular meanings, negation expressions, and sporadic misspellings. As a result, a primary goal in processing these textual notes is to implement effective preprocessing techniques that enhance data quality and ensure consistency across all entries. Recent advancements in algorithms and methodologies within the fields of natural language processing (NLP), machine learning (ML), and large language models (LLM) have prompted researchers to leverage narrative EMR for the detection of hospital adverse events (HAE). METHODS: The scoping review adhered to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. A scoping review protocol was developed and utilized to guide the research process, clearly outlining the eligibility criteria, information sources, search strategies, data management, selection process, data collection procedures, data items, outcomes and prioritization, data synthesis, and meta-bias considerations. The search strategy was implemented across nine engineering and medical electronic databases. RESULTS: The results have indicated that from a total of 3,264 studies retrieved, 48 unique studies were included in the review. Responses to the research questions were systematically extracted from these studies. The review has identified challenges associated with the preprocessing of narrative texts in EMR for HAE identification. Additionally, three research gaps have been identified: (1) the imperative need for a pipeline to preprocess narrative EMR for the identification of HAE, (2) the necessity for a robust system capable of managing the extensive volume of narrative EMR data, and (3) the requirement for temporal event system, which are essential for effective HAE detection. The study also has underscored the essential role of preprocessing tasks in enhancing the performance of HAE detection. The study has emphasized the importance of extracting N-grams from clinical text, normalizing these N-grams through lemmatization and/or stemming, and establishing semantic feature extraction in preprocessing tasks that significantly affect HAE detection performance. While LLM-based systems naturally incorporate tokenization and normalization processes within their frameworks, it remains crucial to address features that hold semantic relevance to the specific type of HAE during preprocessing. CONCLUSION: This scoping review has provided valuable insights for researchers focused on HAE detection utilizing narrative EMR data. It has elucidated how preprocessing tasks can elevate the performance of HAE detection and draws attention to neglected research gaps within the field. Addressing these gaps will necessitate further investigation in subsequent research endeavors.

To combat the growing IoT malware threat, many studies propose ML-based classification solutions, but the lack of comprehensive evaluations limits insights for developing new solutions and selecting models. Given this necessity, this work evaluates IoT malware classification models under three key challenges: temporal, architectural, and spatial inconsistencies between development and deployment datasets, which can be regarded as variables characterizing the dataset, and the challenges arise from the variable values inconsistency between the two stages. To improve the conclusions’ comprehensiveness, effectiveness, and generalizability, the evaluation is organized hierarchically across three levels based on model generation, sample variation, and inconsistency assumptions. Given the complexity of the model development pipeline, our evaluation treats each model individually and aims to conclude impacts across all models. The analysis reveals that temporal and architectural inconsistencies significantly degrade model performance, with architectural inconsistency having a greater impact, despite cross-architecture designs. Temporal inconsistency effects vary with temporal value differences, while spatial inconsistency has minimal impact, even with substantial spatial variation. Furthermore, we use one-way ANOVA to identify features contributing to family distinguishability, temporal stability, and architectural generalizability that benefit future solution design. Meanwhile, we studied a specific example to study the model performance degradation under architectural inconsistency. Finally, we summarize the lessons learned and outline potential research directions to address these challenges.

OBJECTIVES: Adverse event detection from Electronic Medical Records (EMRs) is challenging due to the low incidence of the event, variability in clinical documentation, and the complexity of data formats. Pulmonary embolism as an adverse event (PEAE) is particularly difficult to identify using existing approaches. This study aims to develop and evaluate a Large Language Model (LLM)-based framework for detecting PEAE from unstructured narrative data in EMRs. MATERIALS AND METHODS: We conducted a chart review of adult patients (aged 18-100) admitted to tertiary-care hospitals in Calgary, Alberta, Canada, between 2017-2022. We developed an LLM-based detection framework consisting of three modules: evidence extraction (implementing both keyword-based and semantic similarity-based filtering methods), discharge information extraction (focusing on six key clinical sections), and PEAE detection. Four open-source LLMs (Llama3, Mistral-7B, Gemma, and Phi-3) were evaluated using positive predictive value, sensitivity, specificity, and F1-score. Model performance for population-level surveillance was assessed at yearly, quarterly, and monthly granularities. RESULTS: The chart review included 10 066 patients, with 40 cases of PEAE identified (0.4% prevalence). All four LLMs demonstrated high sensitivity (87.5-100%) and specificity (94.9-98.9%) across different experimental conditions. Gemma achieved the highest F1-score (28.11%) using keyword-based retrieval with discharge summary inclusion, along with 98.4% specificity, 87.5% sensitivity, and 99.95% negative predictive value. Keyword-based filtering reduced the median chunks per patient from 789 to 310, while semantic filtering further reduced this to 9 chunks. Including discharge summaries improved performance metrics across most models. For population-level surveillance, all models showed strong correlation with actual PEAE trends at yearly granularity (r=0.92-0.99), with Llama3 achieving the highest correlation (0.988). DISCUSSION: The results of our method for PEAE detection using EMR notes demonstrate high sensitivity and specificity across all four tested LLMs, indicating strong performance in distinguishing PEAE from non-PEAE cases. However, the low incidence rate of PEAE contributed to a lower PPV. The keyword-based chunking approach consistently outperformed semantic similarity-based methods, achieving higher F1 scores and PPV, underscoring the importance of domain knowledge in text segmentation. Including discharge summaries further enhanced performance metrics. Our population-based analysis revealed better performance for yearly trends compared to monthly granularity, suggesting the framework's utility for long-term surveillance despite dataset imbalance. Error analysis identified contextual misinterpretation, terminology confusion, and preprocessing limitations as key challenges for future improvement. CONCLUSIONS: Our proposed method demonstrates that LLMs can effectively detect PEAE from narrative EMRs with high sensitivity and specificity. While these models serve as effective screening tools to exclude non-PEAE cases, their lower PPV indicates they cannot be relied upon solely for definitive PEAE identification. Further chart review remains necessary for confirmation. Future work should focus on improving contextual understanding, medical terminology interpretation, and exploring advanced prompting techniques to enhance precision in adverse event detection from EMRs.

High penetration in distributed photovoltaics (PVs) enhances the resilience of distribution network operations. However, it brings many uncertain issues such as the voltage and harmonic fluctuations that may affect the distribution network stability. Therefore, the determination of the PV location and capacity is of vital importance for smart distribution network planning. Considering the fluctuation of PV outputs and the robustness of optimization results, this paper proposes an adjustable robust optimization method for large-scale PV planning in smart distribution networks. The AC power flow is first converted into a convex program by the linearization theory, and the bi-level optimization is converted to a single-layer optimization problem using the strong duality theory. A hybrid algorithm based on the integration of grey wolf optimization (GWO) and improved particle swarm optimization (IPSO), named GWO-IPSO, is proposed to determine the robust optimal location and the capacity of distributed PVs. The proposed method is verified based on the IEEE 69–bus radial distribution network case study. The proposed method efficiently adapts to parameter uncertainties resulting from extreme scenarios and delivers better performance than general heuristic methods.

The evolution of IoT malware has ignited interest in the creation of malware family classification models. Nonetheless, these models encounter security concerns stemming from issues related to their interpretability and vulnerabilities exposed within the training pipeline. Recent research highlighted the limitations of learning-based malware classifiers, which are susceptible to backdoor attacks due to relying on human-engineered features to simplify the mapping from features to binary perturbations. In contrast, our study aligns with the current trajectory of the malware classification field, where we emphasize the detection of backdoor attacks targeted at models employing features extracted from within the model itself. To thoroughly assess model vulner-abilities, we have devised a dynamic trigger generation method based on sample features, which we refer to as “BENIGN”. This approach is used to contaminate and launch attacks on the model while also implementing a tailored training process to achieve specific attack objectives. Through experiments, we analyze the impact of variables involved in its training procedures on the attack stability and success rates. Last, we evaluate mitigation methods and emphasize the challenges and adaptability needed to defend against these attack strategies.

Knowledge distillation aims to train a compact student network using soft supervision from a larger teacher network and hard supervision from ground truths. However, determining an optimal knowledge fusion ratio that balances these supervisory signals remains challenging. Prior methods generally resort to a constant or heuristic-based fusion ratio, which often falls short of a proper balance. In this study, we introduce a novel adaptive method for learning a sample-wise knowledge fusion ratio, exploiting both the correctness of teacher and student, as well as how well the student mimics the teacher on each sample. Our method naturally leads to the \textit{intra-sample} trilateral geometric relations among the student prediction ($\mathcal{S}$), teacher prediction ($\mathcal{T}$), and ground truth ($\mathcal{G}$). To counterbalance the impact of outliers, we further extend to the \textit{inter-sample} relations, incorporating the teacher's global average prediction ($\mathcal{\bar{T}})$ for samples within the same class. A simple neural network then learns the implicit mapping from the intra- and inter-sample relations to an adaptive, sample-wise knowledge fusion ratio in a bilevel-optimization manner. Our approach provides a simple, practical, and adaptable solution for knowledge distillation that can be employed across various architectures and model sizes. Extensive experiments demonstrate consistent improvements over other loss re-weighting methods on image classification, attack detection, and click-through rate prediction.

Automated penetration testing (AutoPT) based on reinforcement learning (RL) has proven its ability to improve the efficiency of vulnerability identification in information systems. However, RL-based PT encounters several challenges, including poor sampling efficiency, intricate reward specification, and limited interpretability. To address these issues, we propose a knowledge-informed AutoPT framework called DRLRM-PT, which leverages reward machines (RMs) to encode domain knowledge as guidelines for training a PT policy. In our study, we specifically focus on lateral movement as a PT case study and formulate it as a partially observable Markov decision process (POMDP) guided by RMs. We design two RMs based on the MITRE ATT&CK knowledge base for lateral movement. To solve the POMDP and optimize the PT policy, we employ the deep Q-learning algorithm with RM (DQRM). The experimental results demonstrate that the DQRM agent exhibits higher training efficiency in PT compared to agents without knowledge embedding. Moreover, RMs encoding more detailed domain knowledge demonstrated better PT performance compared to RMs with simpler knowledge.

Artificial intelligence (AI) plays an imperative role in next-generation critical infrastructures like the smart grid, whose power can be harnessed by not only operators, but also cyber adversaries. This article investigates a potential threat from adversarial AI in blind false data injection attacks (FDIA) targeting the ac state estimators in the smart grid. Assuming no access to the grid topology required in most FDIA, we propose an adversarial model based on artificial neural networks (ANNs) to infer grid topology from historical measurements. Following the topology inference, a substitute bad data detector (BDD) model is further proposed in the attack model to filter the false data before injection, reducing the risk of detection given potential bad data in normal operations. We also refine the common evaluation of FDI stealthiness by including the presence of bad data among normal and false data when assessing the detection performance. Simulations on the IEEE 30-bus system reveal that significant deviations can be inflicted stealthily by the proposed blind FDI attack. Detailed analyses of the stealthiness, impacts, and parameters are also presented to shed more light on the threats for further studies and effective countermeasures.

Graph-based semi-supervised node classification has been shown to become a state-of-the-art approach in many applications with high research value and significance. Most existing methods are only based on the original intrinsic or artificially established graph structure which may not accurately reflect the “true” correlation among data and are not optimal for semi-supervised node classification in the downstream graph neural networks. Besides, while existing graph-based methods mostly utilize the explicit graph structure, some implicit information, for example, the density information, can also provide latent information that can be further exploited. To address these limitations, this paper proposes the Dual Hypergraph Neural Network (DualHGNN), a new dual connection model integrating both hypergraph structure learning and hypergraph representation learning simultaneously in a unified architecture. The DualHGNN first leverages a multi-view hypergraph learning network to explore the optimal hypergraph structure from multiple views, constrained by a consistency loss proposed to improve its generalization. Then, DualHGNN employs a density-aware hypergraph attention network to explore the high-order semantic correlation among data points based on the density-aware attention mechanism. Extensive experiments are conducted in various benchmark datasets, and the results demonstrate the effectiveness of the proposed approach.

The fast expansion of interconnectivity in cyber-physical critical infrastructures like smart grids has given rise to concerning exposures and vulnerabilities. Although penetration testing (PT) has been an effective approach to searching for vulnerabilities in software, devices, and networks from the attacker's view, the strong cyber-physical coupling in these large-scale infrastructures has made it challenging to manually pinpoint critical vulnerabilities, particularly at system levels due to the complexity, dimensionality, and uncertainty therein. To better protect the security of cyber-physical systems, this paper proposes a deep reinforcement learning (DRL)-based PT framework to efficiently and adaptively identify critical vulnerabilities in smart grids. Using replay attacks as an example, the paper models the attack as a Markov Decision Process with three actions - stop, record, and replay - to learn the optimal timing and ordering of replays in different operating scenarios. A cyber-physical co-simulation platform with dedicated simulators for the physical part, cyber part, control part, and attacker part of a smart distribution grid was developed as a sandbox environment to train the DRL agent. Scenarios with different levels of difficulty are tested to validate the learning capability and performance in finding critical attack paths of the DRL-based PT. The simulation results show that DRL-based PT can learn to find the optimal attack path against system stability when the grid is under high load demand, solar power generation, and weather variation. These results are promising first steps toward a highly customizable framework to pen-test complex cyber-physical systems with automatic DRL agents and various attack schemes.

Music generation, as a creativity problem, attracts growing attention from artificial intelligence researchers. Among the challenging tasks, lyrics-conditional melody generation aims to leverage natural language processing (NLP) techniques to generate music from texts, for which Generative Adversarial Networks (GAN) has become a promising unsupervised solution. The adversarial training of two agents, i.e., generator and discriminator, allows GAN to achieve a better generation performance and has been proven effective in conditional generation tasks. In this paper, we propose the multi-criteria relational GAN (MRGAN), which includes a relation memory-based generator and two discriminators with a unique discrimination criterion each. The relational memory in the generator is adopted for long-time dependency modeling. Meanwhile, the two discriminators can judge both musical quality and conditional correspondence. Based on the bilingual evaluation understudy (BLEU) score, a new metric, named Music-BLEU, has also be designed to evaluate the lyrics-conditional melody generation. Experimental results verify that MRGAN outperforms existing approaches in related key metrics.

The security of wireless Internet of Things (IoT) communication is a complex challenge due to not only growing attack surfaces and threats but also the limitations of energy consumption. As a significant portion of the IoT market is composed of both security- and energy-critical sectors, e.g., smart homes and e-health, there is a pressing demand for solutions to secure billions of IoT devices while minimizing energy footprint. To this end, this article proposes a transport layer security (TLS) extension to integrate a lightweight and self-monitored mechanism that dynamically balances communication security and power consumption according to the IoT device’s current battery level. Integrated within the TLSv1.3 protocol, the secure extension automatically adjusts the encryption round number of the negotiated cipher according to an operator-defined policy while ensuring the minimum required security level. A Proof-of-Concept (PoC) has been implemented on the wolfSSL library and a real-world IoT platform, on which the performance of the proposed mechanism has been reported for various lightweight ciphers. The results showed an energy reduction of encryptions by 57.1% and a battery saving of 9.4% when encrypting at 4 kBps with reduced-round encryption, demonstrating the potential of the proposed extension into the TLS protocol.

In this article, we investigate the self-learning robust control synthesis and tracking design of general uncertain dynamical systems. Based on the adaptive critic learning, the robust stabilization method is developed with the help of conducting problem transformation. In addition, by considering the optimal control solution with a discounted cost function, the established method is extended to address the robust trajectory tracking design problem. The Lyapunov stability analysis is also conducted for proving the robustness of the related control plants. Finally, the simulation verification with the three case studies is provided in terms of robust stabilization and trajectory tracking, respectively.

The operation of smart grids heavily relies on secure and accurate meter measurements provided by phasor measurement units (PMUs). Therefore, the optimal PMU placement (OPP) aiming to achieve the complete system observability of smart grids with as few PMUs as possible has been extensively investigated. Although many existing studies have focused on the OPP, few of them are concerned with the placement order of PMUs. To protect as many buses as possible in smart grids when installing PMUs in stages owing to high cost, this paper proposes the attack-resilient OPP strategy which places PMUs in order by using reinforcement learning guided tree search, where the sequential decision making of reinforcement learning is utilized to explore placement orders. The least-effort attack model is carried out to screen vulnerable buses such that the buses adjacent to these buses can be placed PMUs in advance to reduce the state space and action space of the large-scale smart grid environment. Based on that, the reinforcement learning guided tree search approach is used to explore the key buses which need placing PMUs, where the repeated exploration of the agent is avoided by tree search. Then, a reasonable placement order of PMUs is obtained according to the action sequence the proposed method provides. Finally, the effectiveness of the proposed method is verified on various IEEE standard test systems and the comparison results with existing methods are provided.

Highway charging scheduling for battery electric vehicles is a complex research issue depending on the fast charging capacity provided and the information available in coordinating drivers’ multiple charges at charging stations. Moreover, user’s partially-known preferences and potential dynamic events remain extra challenges in maximizing user’s satisfaction, improving the revenue of highway charging stations and utilizing the limited charging capacities. In such separate and simultaneous markets, users are reasonably modelled as the self-interested agents who aim to advance their own benefits but negotiable on their charging schedules. In this paper, we propose a simultaneous multi-round auction to address the highway charging scheduling problem, where users are allowed to bid and compromise on their preferred stops, charging time and energy simultaneously at separate charging stations. The objective is to maximize the total revenue of these stations. In the course of auction, users can gradually figure out how can their charges fit together by adaptively adjusting their bids placed at different stations. As a result, high-quality solutions are obtained and user’s privacy can be preserved by progressively eliciting their private preferences as necessary. In addition, we also develop a dynamic scheduling algorithm to address the changes of user’s reserved charges and unexpected arrivals of other vehicles. We conduct extensive experiments to validate our approach, the results demonstrate that it can achieve high efficiency with partial private information, as well as a higher revenue with dynamic scheduling algorithm. It can also greatly reduce the total waiting time of users against the first-come-first-serve policy.

Photovoltaics intelligent edge terminals (PV IETs) are new devices for data acquisition and management of PV power station. However, due to the massive, scattered, and disordered nature of PV stations and the expensive price of PV IET, installing a PV IET at each PV station has prohibited for large-scale adoption. Therefore, to reduce the life cycle cost of PV IET in a region, this paper proposes an optimal configuration method for PV IET. We propose a mathematical model for the optimal configuration of PV IETs. For a given regional grid, the model aims to obtain the optimal number and location of PV IETs and the connection mode between PV IETs and PV power stations. In addition, an improved Harris hawk optimization (IHHO) is proposed to solve the nonlinear mathematical model. A case study is carried out under different problem sizes, boundary and devices parameters. The simulation results show that under different case, the PV IET configuration method in this paper can obtain lower life cycle cost than the conventional method, and IHHO has higher accuracy than other algorithms. The optimal configuration method in this article can effectively solve the problem of the optimal configuration of PV IET.

In interconnected industrial control networks like smart grids, topology attacks on physical grids can lead to severe cascading failures and large-scale blackouts. Effective defense on vulnerable devices can significantly reduce the risk of cascading failures and improve overall system robustness. In this paper, we investigate the vulnerability analysis problem from a graph theoretical classification perspective. By calculating a node vulnerability vector composed of features based on complex network theory, node embedding, extended betweenness and power flow distribution, we propose a node vulnerability analysis method based on XGBoost classifier. A cascading failure simulation model based on DC power flow is used to simulate the smart grid behaviours under topology attacks and create the dataset for the XGBoost classifier. The effectiveness of the proposed XGBoost-based method with newly-introduced features is demonstrated by case studies.

This article investigates adaptive control problems for unknown second-order nonlinear multiagent systems (MASs) via an event-triggered approach. An adaptive event-triggered consensus controller is given to second-order MAS with unknown nonlinear dynamics. We prove that the proposed consensus controller is free from Zeno behavior. Next, an adaptive event-triggered tracking controller is developed for leader-follower MAS with the leader having bounded nonzero control input. Both consensus and tracking controllers are fully distributed, which means that event-triggered controllers only use local cooperative information. Finally, an unknown second-order nonlinear MAS is used to verify the given event-triggered controllers.

By using the event-triggered technique, we study the distributed control of a class of nonlinear multiagent systems (MASs) with aperiodic sample information. Taking advantage of the combinational sample measurements, we first present an event-triggered consensus algorithm for the leaderless MAS. Thereafter, we design the event-triggered tracking algorithm for the leader–follower MAS with a leader having bounded input. Furthermore, we prove that both consensus and tracking controllers do not exist Zeno behavior. Finally, a numerical example is given to verify the designed event-triggered consensus algorithm.

False data injection attacks (FDIA) have drawn significant interests recently after the discovery of vulnerabilities of bad data detectors (BDD) deployed in the smart grid. While most FDIA analyses focused separately on the aspects of stealthiness, knowledge, resources, or expected consequences of the attack, few have evaluated the relationship and tradeoffs among these factors to identify the worst-case scenario in realistic operations. To fill the gap, this paper investigates a strictly stealthy FDIA scheme with multi-objective evolutionary optimization, which could compromise a small set of meters to inflict large impacts on the smart grid in realistic scenarios. Compared with existing attack schemes that relax the problem with the ℓ1-norm, the paper introduced the Improved Strength Pareto Evolutionary Algorithm (SPEA2) as the solver to directly obtain the ℓ0-sparse attack vector. Meanwhile, the unobservability is ensured by not only bypassing the BDD but also satisfying the physical and operational constraints. A three-step constraint handling technique is also proposed for the SPEA2 to ensure the stealthiness and improve the efficiency of attack vector identification in the worst-case scenario. Simulation results on the IEEE 14-bus and 30-bus systems demonstrate that the new multi-objective formulation discovers highly sparse attack vectors with significant impacts on the system without triggering immediate emergency responses. The influence of alternative objectives and constraints has also been evaluated to reveal the trade-offs among the attack's stealthiness, sparsity, and impact. The results are expected to facilitate better-informed risk assessment and mitigation with refined worst-case understandings.

Securing the wireless Internet of Things (IoT) is a challenging issue do to their technological constraints: limited computing power, restricted batteries or inconsistent energy supply. With more than 26 billion devices connected in 2019, the expected 75 billion things by 2025 will require an even higher energy supply. Meanwhile, as smarts cities, industry and healthcare represent more than 75% of the IoT market share, these devices must be secured while limiting the impact on energy consumption. The lifetime of specific devices such as Wearable or Implantable Medical Devices (WMDs, IMDs) can then be significantly impacted. In this paper, we propose a generic design that dynamically reduces the energy consumption required by the addition of security within the IoT networks, according to the local level of battery use. This self-monitored, fully-automated, low-cost and remotely configurable mechanism adjusts the number of encryption rounds of the cryptographic primitive while guaranteeing the minimum level of security required. This method has been integrated into the Constrained Application Protocol (CoAP) with the Datagram Transport Layer Security (DTLS) using the AES-128 encryption standard, with 10 rounds (full) to 7, and can be implemented on other protocol stacks. We show a reduction in CPU power consumption of a Raspberry Pi of 19.67%. Finally, we estimate its efficiency by simulating the discharge of multiple batteries with different capacities. Our mechanism increases operating time up to 33 minutes and 15 seconds for a 10,000mAh Raspberry Pi battery when 150 messages of 4Kb per second are exchanged with an operator.

Reinforcement learning has become an important scheduling solution with many successes in markets with dynamic pricing options, e.g., electric vehicle charging in a deregulated electricity market. However, the highly-uncertain requests and partially-unknown individual preferences remain major challenges to effective demand responses in the user-centric environment. For charging stations who aim to maximize the long-term revenue in this fast-growing market, an accurate estimate of user's sensitivity, or acceptance, of the prices they offered to the potential customers is the key to the success of dynamic pricing. While most existing pricing schemes assume users will consistently follow stable patterns that are observable or inferrable by the charging service provider, it remains crucial to consider how users may be influenced by historic prices they have observed and react strategically to decide optimal charging demands that can maximize their utilities. To overcome this limitation, this paper presents a new framework based on reinforcement mechanism design to determine the optimal charging price in a mechanism design setting, which can optimize the long-term revenue of charging stations as well as the social welfare of users with private utility functions. Specifically, the strategic interaction between the station and users is modelled as a discrete finite Markov decision process, a Q-learning-based dynamic pricing mechanism is proposed to explore how price affects users' demands over a sequence of time. The experiments demonstrate that our pricing mechanism outperforms the predetermined time-of-use pricing in maximizing the long-term revenue of the charging station.

The smart grid faces with increasingly sophisticated cyber-physical threats, against which machine learning (ML)-based intrusion detection systems have become a powerful and promising solution to smart grid security monitoring. However, many ML algorithms presume that training and testing data follow the same or similar data distributions, which may not hold in the dynamic time-varying systems like the smart grid. As operating points may change dramatically over time, the resulting data distribution shifts could lead to degraded detection performance and delayed incidence responses. To address this challenge, this paper proposes a semi-supervised framework based on domain-adversarial training to transfer the knowledge of known attack incidences to detect returning threats at different hours and load patterns. Using normal operation data of the ISO New England grids, the proposed framework leverages adversarial training to adapt learned models against new attacks launched at different times of the day. Effectiveness of the proposed detection framework is evaluated against the well-studied false data injection attacks synthesized on the IEEE 30-bus system, and the results demonstrated the superiority of the framework against persistent threats recurring in the highly dynamic smart grid.

This paper considers an electric vehicle charging scheduling setting where vehicle users can reserve charging time in advance at a charging station. In this setting, users are allowed to explicitly express their preferences over different start times and the length of charging periods for charging their vehicles. The goal is to compute optimal charging schedules that maximize the social welfare of all users given their time preferences and the state of charge of their vehicles. Assuming that users are self-interested agents who may behave strategically to advance their own benefits rather than the social welfare of all agents, we propose an iterative auction, which computes high-quality schedules and, at the same time, preserves users' privacy by progressively eliciting their preferences as necessary. We conduct a game theoretical analysis on the proposed iterative auction to prove its individual rationality and the best response for agents. Through extensive experiments, we demonstrate that the iterative auction can achieve high-efficiency solutions with a partial value information. Additionally, we explore the relationship between scheduling efficiency and information revelation in the auction.

This paper presents a coordinated booking mechanism for highway electric vehicle charging management. The mechanism improves charging facility utilization and user satisfaction through coordinating users' charging schedules based on their travel time flexibility and required charging time for their trip. Given that users compete for limited charging resources to obtain their preferred schedules, we model them as self-interested agents who consider their flexibility as their private information and may be reluctant to reveal it to the scheduler. In order to compute high-quality schedules, we propose a market-based scheduling mechanism which motivates users to reveal their flexibility. This mechanism is implemented using an iterative bidding procedure which allows users to progressively reveal their feasible travel time windows as needed. The goal is to maximize the number of served users given limited charging capacity and users' travel time window constraints. Our computational study shows that the proposed booking mechanism achieves on average 90% efficiency compared with optimal solutions. We also observe that high efficiency solutions usually require more flexibility information to be revealed by the users.

Accurate state estimation is crucial to smart grid operations. Following the identification of false data injection attacks (FDIA), numerous research has been proposed, yet most of them assume the worst-case scenario where attackers face few constraints on the full knowledge of the system topology or on the attack resource they can leverage to compromise the meters. In this work, we formulate attacker's knowledge and resource as two critical constraints and propose an FDIA model that generates the attack vector with no prior knowledge of the grid topology and minimal access to the measurements. The work adopts the existing solution based on principal component analysis (PCA) to generate the stealth attack vector and leverages particle swarm optimization (PSO) to directly minimize the ℓ0-norm of the attack vector. Considering the feasibility of practical attacks, our work also enforces constraints on the convergence of state estimation and the significance of induced error, so that the generated attack vector is guaranteed undetectable yet impactful. Simulation results on the IEEE 30bus system have demonstrated the minimized sparsity with topology-blindness, attack-stealthiness, and significant impact on the state variables of the proposed FDIA scheme, which will help refine the risk evaluation and inform better mitigation efforts against such threats.

This paper presents a functional model predictive control (MPC) approach based on an adaptive dynamic programming (ADP) algorithm with the abilities of handling control constraints and disturbances for the optimal control of nonlinear discrete-time systems. In the proposed ADP-based nonlinear MPC (NMPC) structure, a neural-network-based identification is established first to reconstruct the unknown system dynamics. Then, the actor-critic scheme is adopted with a critic network to estimate the index performance function and an action network to approximate the optimal control input. Meanwhile, as the MPC strategy can effectively determine the current control by solving a finite horizon open-loop optimal control problem, in the proposed algorithm, the infinite horizon is decomposed into a series of finite horizons to obtain the optimal control. In each finite horizon, the finite ADP algorithm solves the optimal control problem subject to the terminal constraint, the control constraint, and the disturbance. The uniform ultimate boundedness of the closed-loop system is verified by the Lyapunov approach. Finally, the ADP-based NMPC is conducted on two different cases and the simulation results demonstrate the quick response and strong robustness of the proposed method.

Clustering of data with high dimension and variable densities poses a remarkable challenge to the traditional density-based clustering methods. Recently, entropy, a numerical measure of the uncertainty of information, can be used to measure the border degree of samples in data space and also select significant features in feature set. It was used in our new framework based on the sparsity-density entropy (SDE) to cluster the data with high dimension and variable densities. First, SDE conducts high-quality sampling for multidimensional data and selects the representative features using sparsity score entropy (SSE). Second, the clustering results and noises are obtained adopting a new density-variable clustering method called density entropy (DE). DE automatically determines the border set based on the global minimum of border degrees and then adaptively performs cluster analysis for each local cluster based on the local minimum of border degrees. The effectiveness and efficiency of the proposed SDE framework are validated on synthetic and real data sets in comparison with several clustering algorithms. The results showed that the proposed SDE framework concurrently detected the noises and processed the data with high dimension and various densities.

Recent studies on sequential attack schemes revealed new smart grid vulnerability that can be exploited by attacks on the network topology. Traditional power systems contingency analysis needs to be expanded to handle the complex risk of cyber-physical attacks. To analyze the transmission grid vulnerability under sequential topology attacks, this paper proposes a Q-learning-based approach to identify critical attack sequences with consideration of physical system behaviors. A realistic power flow cascading outage model is used to simulate the system behavior, where attacker can use the Q-learning to improve the damage of sequential topology attack toward system failures with the least attack efforts. Case studies based on three IEEE test systems have demonstrated the learning ability and effectiveness of Q-learning-based vulnerability analysis.

The threat of false data injection (FDI) attacks have raised wide interest in the research and development of smart grid security. This paper presents a comparative study on the utilization of supervised learning classifiers to detect direct and stealth FDI attacks in the smart grid. A detailed formulation of the problem for detection with classifiers is first described with proper assumptions and justifications. Three widely used supervised learning (SL) based classifiers are chosen to design corresponding FDI detectors. The performance are tested against false measurement data (direct FDI attack) and false state data (stealth FDI attack) on both balanced and imbalanced cases, with consideration of the influence of FDI resources and magnitudes. Simulations on IEEE 30-bus system have shown that the SL based detectors can effectively detect both direct and stealth FDI attacks, especially for the more severe attacks with large amount or magnitude of compromised measurements.

Recently, the sequential attack, where multiple malignant contingencies are launched by attackers sequentially, has revealed power grid vulnerability under cascading failures. This paper systematically analyzes properties and features of N-k cascaded- based sequential line-switching attacks using a DC power flow based cascading failure simulator (DC- CFS). This paper first explains the key factors behind cascade-based attacks, then compares three adopted metrics with an original line-margin metric to compute vulnerability indexes and design sequential attacks. Two target search schemes, i.e., offline and online target search in sequential attacks, are also presented. Simulation results of N-2 to N-4 line-switching attacks have suggested that the proposed line margin metric produces stronger sequential attacks, and online target search is more effective than offline search. Reasons behind counter-intuitive load loss resulting from different metrics are also analyzed to facilitate future study on the risk of sequential attacks.

We introduce a new parallel computing and communication architecture, Reflex-Tree, with massive sensing, data processing, and control functions suitable for future smart cities. The central feature of the proposed Reflex-Tree architecture is inspired by a fundamental element of the human nervous system: reflex arcs, the neuromuscular reactions and instinctive motions of a part of the body in response to urgent situations. At the bottom level of the Reflex-Tree (layer 4), novel sensing devices are proposed that are controlled by low power processing elements. These "leaf" nodes are then connected to new classification engines based on machine learning techniques, including support vector machines (SVM), to form the third layer. The next layer up consists of servers that provide accurate control decisions via multi-layer adaptive learning and spatial-temporal association, before they are connected to the top level cloud where complex system behavior analysis is performed. Our multi-layered architecture mimics human neural circuits to achieve the high levels of parallelization and scalability required for efficient city-wide monitoring and feedback. To demonstrate the utility of our architecture, we present the design, implementation, and experimental evaluation of a prototype Reflex-Tree. City power supply network and gas pipeline management scenarios are used to drive our prototype as case studies. We show the effectiveness for several levels of the architecture and discuss the feasibility of implementation.

Power grids are often run near the operational limits because of increasing electricity demand, where even small disturbances could possibly trigger major blackouts. The attacks are the potential threats to trigger large-scale cascading failures in the power grid. In particular, the attacks mean to make substations/transmission lines lose functionality by either physical sabotages or cyber attacks. Previously, the attacks were investigated from substation-only/transmission-line-only perspectives, assuming attacks can occur only on substations/transmission lines. In this paper, we introduce the joint substation-transmission line perspective, which assumes attacks can happen on substations, transmission lines, or both. The introduced perspective is a nature extension to substation-only and transmission-line-only perspectives. Such extension leads to discovering many joint substation-transmission line vulnerabilities. Furthermore, we investigate the joint substation-transmission line attack strategies. In particular, we design a new metric, the component interdependency graph (CIG), and propose the CIG-based attack strategy. In simulations, we adopt IEEE 30 bus system, IEEE 118 bus system, and Bay Area power grid as test benchmarks, and use the extended degree-based and load attack strategies as comparison schemes. Simulation results show the CIG-based attack strategy has stronger attack performance.

Vulnerability analysis on the power grid has been widely conducted from the substation-only and transmission-line-only perspectives. In order words, it is considered that attacks can occur on substations or transmission lines separately. In this paper, we naturally extend existing two perspectives and introduce the joint-substation-transmission-line's perspective, which means attacks can concurrently occur on substations and transmission lines. Vulnerabilities are referred to as these multiple-component combinations that can yield large damage to the power grid. One such combination consists of substations, transmission lines, or both. The new perspective is promising to discover more power grid vulnerabilities. In particular, we conduct the vulnerability analysis on the IEEE 39 bus system. Compared with known substation-only/transmission-line-only vulnerabilities, joint-substation-transmission-line vulnerabilities account for the largest percentage. Referring to three-component vulnerabilities, for instance, joint-substation-transmission-line vulnerabilities account for 76.06%; substation-only and transmission-line-only vulnerabilities account for 10.96% and 12.98%, respectively. In addition, we adopt two existing metrics, degree and load, to study the joint-substation-transmission-line attack strategy. Generally speaking, the joint-substation-transmission-line attack strategy based on the load metric has better attack performance than comparison schemes.

The vulnerability analysis is vital for safely running power grids. The simultaneous attack, which applies multiple failures simultaneously, does not consider the time domain in applying failures, and is limited to find unknown vulnerabilities of power grid networks. In this paper, we discover a new attack scenario, called the sequential attack, in which the failures of multiple network components (i.e., links/nodes) occur at different time. The sequence of such failures can be carefully arranged by attackers in order to maximize attack performances. This attack scenario leads to a new angle to analyze and discover vulnerabilities of grid networks. The IEEE 39 bus system is adopted as test benchmark to compare the proposed attack scenario with the existing simultaneous attack scenario. New vulnerabilities are found. For example, the sequential failure of two links, e.g., links 26 and 39 in the test benchmark, can cause 80% power loss, whereas the simultaneous failure of them causes less than 10% power loss. In addition, the sequential attack is demonstrated to be statistically stronger than the simultaneous attack. Finally, several metrics are compared and discussed in terms of whether they can be used to sharply reduce the search space for identifying strong sequential attacks.

Due to the intermittent power generation from renewable energy in the smart grid (i.e., photovoltaic (PV) or wind farm), large frequency fluctuation occurs when the load-frequency control (LFC) capacity is not enough to compensate the unbalance of generation and load demand. This problem may become worsen when the system is in island operating. Meanwhile, in the near future, electric vehicles (EVs) will be widely used by customers, where the EV station could be treated as dispersed battery energy storage. Therefore, the vehicle-to-grid (V2G) power control can be applied to compensate for inadequate LFC capacity, thus improving the island smart grid frequency stability. In this paper, an on-line learning method, called goal representation adaptive dynamic programming (GrADP), is adopted to coordinate control of units in an island smart grid. In the controller design, adaptive supplementary control signals are provided to proportional-integral (PI) controllers by online GrADP according to the utility function. Simulations on a benchmark smart grid with micro turbine (MT), EVs and PVs demonstrate the superior control effect and robustness of the proposed coordinate controller over the original PI controller and fuzzy controller.

The security issue of complex networks has drawn significant concerns recently. While pure topological analyzes from a network security perspective provide some effective techniques, their inability to characterize the physical principles requires a more comprehensive model to approximate failure behavior of a complex network in reality. In this paper, based on an extended topological metric, we proposed an approach to examine the vulnerability of a specific type of complex network, i.e., the power system, against cascading failure threats. The proposed approach adopts a model called extended betweenness that combines network structure with electrical characteristics to define the load of power grid components. By using this power transfer distribution factor-based model, we simulated attacks on different components (buses and branches) in the grid and evaluated the vulnerability of the system components with an extended topological cascading failure simulator. Influence of different loading and overloading situations on cascading failures was also evaluated by testing different tolerance factors. Simulation results from a standard IEEE 118-bus test system revealed the vulnerability of network components, which was then validated on a dc power flow simulator with comparisons to other topological measurements. Finally, potential extensions of the approach were also discussed to exhibit both utility and challenge in more complex scenarios and applications.

The modern society increasingly relies on electrical service, which also brings risks of catastrophic consequences, e.g., large-scale blackouts. In the current literature, researchers reveal the vulnerability of power grids under the assumption that substations/transmission lines are removed or attacked synchronously. In reality, however, it is highly possible that such removals can be conducted sequentially. Motivated by this idea, we discover a new attack scenario, called the sequential attack, which assumes that substations/transmission lines can be removed sequentially, not synchronously. In particular, we find that the sequential attack can discover many combinations of substation whose failures can cause large blackout size. Previously, these combinations are ignored by the synchronous attack. In addition, we propose a new metric, called the sequential attack graph (SAG), and a practical attack strategy based on SAG. In simulations, we adopt three test benchmarks and five comparison schemes. Referring to simulation results and complexity analysis, we find that the proposed scheme has strong performance and low complexity.

Security issues related to power grid networks have attracted the attention of researchers in many fields. Recently, a new network model that combines complex network theories with power flow models was proposed. This model, referred to as the extended model, is suitable for investigating vulnerabilities in power grid networks. In this paper, we study cascading failures of power grids under the extended model. Particularly, we discover that attack strategies that select target nodes (TNs) based on load and degree do not yield the strongest attacks. Instead, we propose a novel metric, called the risk graph, and develop novel attack strategies that are much stronger than the load-based and degree-based attack strategies. The proposed approaches and the comparison approaches are tested on IEEE 57 and 118 bus systems and Polish transmission system. The results demonstrate that the proposed approaches can reveal the power grid vulnerability in terms of causing cascading failures more effectively than the comparison approaches.

In the study of power grid security, the cascading failure analysis in multi-contingency scenarios has been a challenge due to its topological complexity and computational cost. Both network analyses and load ranking methods have their own limitations. In this paper, based on self-organizing map (SOM), we propose an integrated approach combining spatial feature (distance)-based clustering with electrical characteristics (load) to assess the vulnerability and cascading effect of multiple component sets in the power grid. Using the clustering result from SOM, we choose sets of heavy-loaded initial victims to perform attack schemes and evaluate the subsequent cascading effect of their failures, and this SOM-based approach effectively identifies the more vulnerable sets of substations than those from the traditional load ranking and other clustering methods. As a result, this new approach provides an efficient and reliable technique to study the power system failure behavior in cascading effect of critical component failure.