Diabetic retinopathy (DR) is a major cause of vision loss in workingage individuals, and automated detection systems can assist clinicians in early diagnosis and treatment.However, existing grading methods trained on high-quality fundus images often exhibit significant performance degradation when applied to low-quality images commonly encountered in clinical practice.To address this issue, we propose IELS-DR, a multi-task collaborative learning framework specifically designed for low-quality fundus images.The framework jointly optimizes three tasks: image enhancement, lesion segmentation, and lesion severity classification.It incorporates a dedicated image enhancement subnet tailored for low-quality images to improve clarity and facilitate downstream tasks.Additionally, we introduce a Cross-task Feature Aggregation (CFA) module, which employs a cross-task, multi-scale CNN architecture to enable deep feature sharing and interaction between lesion segmentation and DR classification tasks.The CFA module enhances multi-scale feature fusion, strengthens lesion feature representation, and promotes effective task collaboration.Experiments on the DDR dataset show that IELS-DR delivers leading performance, with an accuracy of 86.61%, precision of 83.57%, kappa of 82.36%, recall of 85.09%, and F1-score of 84.25%.Furthermore, it delivers competitive results in image enhancement and lesion segmentation tasks.Ablation studies confirm the efficacy of the proposed framework and CFA module in improving robustness for low-quality image analysis and DR grading.

Diabetic retinopathy (DR) is a complication of diabetes.Deep learning techniques play an important role in the automatic grading of DR.However, the significant morphological differences and diverse types of lesions in DR images often lead to the neglect of the dependencies between lesions, which can significantly affect the final grading results.Additionally, traditional convolutional neural networks (CNNs) often lose contextual and discriminative information during feature extraction.To address this issue, this paper proposes a Multi-Scale Contextual Cross-Attention Network (MCCNet) for DR classification.The network includes residual blocks, a Global Context Module (GCM), a Context Attention Fusion Module (CAFM), and a Multi-Scale Feature Module (MSFM).First, the residual blocks and GCM extract lesion features while considering the global contextual information of the lesions.Then, the CAFM fuses global and multi-scale contextual information through a cross-attention mechanism to reduce information loss during the convolution process.Finally, the MSFM learns the dependencies between different lesions through dilated convolutions.DR grading is performed through a classifier.Experimental results show that the proposed method achieves accuracies of 88.93% and 96.04% on the APTOS-2019 and Messidor-2 datasets, respectively, outperforming other methods.

False data injection attacks (FDIA) seriously endanger smart grid security by intentionally manipulating the measurement data critical for power system state estimation. Although existing deep learning-based detection methods can identify such attacks by modeling the spatiotemporal dependencies of the power grids, they still suffer from several limitations. In the spatial dimension, existing approaches focus only on neighboring nodes, failing to effectively capture the global topological correlations among non-adjacent nodes. In spatiotemporal feature fusion, traditional serial architectures tend to cause feature information loss and cannot achieve deep coupling of spatiotemporal features. To overcome these limitations, we propose a FDIA detection model in smart grids using Graphormer and LSTM networks. The model incorporates a dual-branch parallel feature extraction framework, whereby an optimized Graphormer architecture captures global spatial dependencies within the power grid, while LSTM networks extract temporal dynamic features. Furthermore, a novel bidirectional crossattention fusion mechanism is designed to enable interactive and deep integration of spatiotemporal features. Experimental results on standardized IEEE 14-bus and 118-bus test systems indicate that the proposed approach surpasses existing models in multiple performance indicators and exhibits strong robustness.

The technical loss of electricity caused by electricity theft from customers has been a pressing issue for utilities worldwide. With the rapid development of power equipment and artificial intelligence (AI) technology, machine learning (ML)-based electricity theft detection schemes have attracted widespread attention from power companies. However, existing ML-based power theft detection models often can only detect some simple anomalous data and cannot effectively detect fraudulent data generated by evasion attacks. To address these issues, we first use multi-user data as input to extract multi-user electricity usage features and increase the robustness of the detection model. Besides, we propose a CNN-AE-LSTM hybrid model-based electricity theft detection scheme, where the Convolutional Neural Network (CNN) model and the Autoencoder (AE) model are used to extract power data features from the temporal relationships of multi-users, the Long Short-Term Memory (LSTM) model is used to predict electricity theft by learning the relationship between the extracted power features and the temporal sequence of each electricity theft user. Finally, experiments under white-box and black-box settings show that in the face of the three evasion attacks, the detection rate (DR) of the method is 88.1%-89.3% and 92.3%-95.7%, and the false-alarm rate (FA) is 3.1%-6.6% and 2.7%-4%, which is higher than that of several other ML-based electricity theft detection methods.

Addressing the issues of privacy leakage, key escrow, and low computational efficiency in cross-domain authentication for Vehicle-to-Grid (V2G), this paper proposes a dynamic anonymous authentication protocol based on the certificateless cryptographic system.Through the design of a hierarchical key architecture, the device manufacturer's master key is fragmented and stored in regional nodes.By combining dynamic pseudonyms with a dual temporary identity mechanism, cross-domain identity anonymization is achieved, ensuring user identity privacy during cross-regional movement.The scheme employs threshold secret sharing technology to eliminate single-point trust dependence and optimizes the signature process based on lightweight cryptographic primitives, ensuring the efficiency and low resource consumption of the authentication process, making it suitable for resource-constrained vehicular networks.Experiments show that, compared to existing schemes, this protocol has less signature verification time and lower communication overhead, while also being able to resist man-inthe-middle attacks, cross-domain replay attacks, and pseudonym correlation analysis, among other privacy threats.

Due to significant regional variations in electricity consumption, transfer learning methods for detecting electricity theft can effectively address challenges such as limited labeled data and domain shifts in emerging areas. However, these methods often encounter issues related to inadequate boundary feature characterization, underutilization of available data, and substantial computational overhead. To address these challenges, we propose a semi-supervised domain adaptation method for electricity theft detection based on minimax entropy. Specifically, domain-invariant prototype vectors align the feature distributions of labeled data across source and target regions, thereby enhancing cross-domain consistency. This alignment reduces inter-domain differences and improves detection, particularly when labeled data in target regions is scarce. Additionally, the minimax entropy strategy adjusts the prediction confidence of unlabeled data, thereby strengthening intra-class aggregation, enhancing inter-class separability, and optimizing feature distributions to capture discriminative boundary features. Experimental results demonstrate that our method significantly outperforms existing approaches in both detection performance and training efficiency.

Abstract Due to the frequent sourcing of Intelligent Electronic Devices (IEDs) from third-party sources, they are highly susceptible to targeted attacks on Substation Automation Systems (SASs). However, most current anomaly detection methods are ineffective against insider stealthy attacks, which simulate benign operations to mask malicious behavior. Furthermore, the lack of annotated datasets within current SAS environments hinders the training of various detection methods. Therefore, this paper introduces TranRAT, a lightweight anomaly detection model for insider stealthy attacks in SAS, which employs unsupervised learning and deep Transformer to adapt to scene requirements. TranRAT is designed to detect covert internal attacks initiated by untrusted IEDs within SAS environments. Initially, it identifies and extracts thirteen critical features from Generic Object Oriented Substation Event messages, emphasizing system-wide characteristics over individual device specifics. Subsequently, it applies suitable label expansion strategies to capture temporal correlations and employs attention-based sequence encoders to bolster robust adversarial training. Experimental results demonstrate that TranRAT surpasses baseline methods. Compared to leading models for multivariate time-series data, TranRAT achieves a 15%–60% enhancement in F1 scores on complete and limited training datasets, while reducing training duration by up to 99%.

The concept of a smart city is to equip sensors to various objects in urban life to monitor areas and collect sensing data, and make wise decisions based on the collected data. However, some malicious sensor devices may interrupt and interfere with data collection, leading to a reduction in the integrity and availability of information, thereby causing harm to Internet of Things (IoT) applications. Therefore, identifying the credibility of sensor nodes to ensure the credibility of data collection is a challenge. This article proposes a trust-based active game data collection (TAGDC) scheme to collect trust data in the IoT. This TAGDC scheme mainly includes the following parts: (1) An active trust framework plus evolutionary game theory is proposed to encourage high-energy sensors to send detection routes and quickly obtain sensor trust. (2) In order to balance the data security requirements of subnetworks, the number and frequency of detection routes required by subnetworks are estimated through mechanism modeling and fuzzy analytic hierarchy process. (3) The design focuses on the internal trust computing model in the region to evaluate the trust of nodes. The findings of the experiment demonstrate that the TAGDC scheme, as described in this research study, enhances the accuracy of identifying malicious nodes by 20%, reduces the required identification time by 40%, and improves the data collection success rate by 5%.

With the advancement of artificial intelligence, automobiles are progressively transitioning from traditional mechanization to Connected Autonomous Vehicles (CAVs), significantly enhancing driving comfort and safety. As the standard communication protocol in CAVs, the Controller Area Network (CAN) remains vulnerable to attacks due to the lack of robust security mechanisms. While existing deep learning-based vehicle network intrusion detection systems can effectively identify known attacks, their ability to detect unknown attacks is limited due to the same data distribution in the source and target domain. To address this issue, we propose a domain adaptation and time-series imaging-based intrusion detection system (DATI-IDS) to detect known and unknown attacks, where the deep domain adaptation method is used to solve the source and target domain data distribution difference problem by optimizing the multiple kernel maximum mean discrepancy (MK-MMD) between the source domain and target domain images and the classification loss, and the time-series imaging method is used to capture temporal dependencies and improve efficiency by transforming the CAN ID sequence into a two-dimensional gramian angular summation field (GASF) image. The effectiveness of the proposed model is evaluated across nine distinct unknown attack scenarios using the Car-Hacking dataset and the survival analysis dataset. Comparative analysis with previous studies demonstrates superior performance, faster inference times, and reduced model complexity.

Social Internet of Vehicles (SIoVs) is an important information exchange platform to provide comprehensive traffic services by sharing vehicle-aware data. However, traditional data sharing methods can not provide the security of decentralized data sharing, making it possible for some malicious third parties to initiate dishonest behaviors. Additionally, the lack of access control for data sharing in SIoVs easily leads to unauthorized data sharing, thus user privacy is threatened and the source of false data is difficult to be traced. In this paper, we propose a conditional data-sharing privacy-preserving scheme for blockchain-based social internet of vehicles. In our scheme, a lightweight ledger-based blockchain system is designed, which combines with the ciphertext-policy attribute-based encryption method to realize anonymous one-to-many sharing of data with fine-grained access management. Also, a collaborative identity tracing method is constructed to trace malicious users who provide false data. Our scheme can effectively prevent second-hand data sharing and safeguard user privacy. Moreover, related experimental results validate the efficiency of our scheme.

With advancements in renewable energy technologies, microgrids have evolved with distinctive cyber-physical system (CPS) characteristics, providing a dynamic and efficient control framework. However, the susceptibility of agents to false data injection attacks (FDIAs) during information transmission poses a notable security challenge. Existing efforts focus on detecting these attacks through machine learning methods, without regard to the cyber information embedded in the CPS communications. To address this gap, we propose a cyber-physical collaborative detection method (CPCGD) based on gate recurrent unit (GRU) and deep-learning neural network (DNN) to detect FDIAs, where the GRU is employed to capture temporal features in the physical domain, and the DNN is dedicated to capturing statistical features in the cyber domain. Moreover, a hierarchical detection and dynamic thresholding mechanism is presented to compensate for the poor performance of traditional distributed agents in microgrid environments. The experimental results and analysis demonstrate that the FDIA detection accuracy of the proposed scheme is better than several other benchmark detectors, and verify the effectiveness of the proposed scheme in cross-domain information detection.

The growth of distributed generation (DG) has established a connection between photovoltaic power generation and economic benefits. However, some users exploit this by engaging in photovoltaic power theft through network attacks on smart meters (SM) to manipulate power readings for financial gain. To tackle this problem, this paper proposes a data-driven stacking model for detecting photovoltaic power theft. The proposed method involves preprocessing real power generation data and designing attack functions to generate malicious data. Photovoltaic power generation features are categorized using the Person correlation coefficient. The stacking model combines three machine learning(ML) algorithms (Artificial Neural Networks, Random Forest, and XGBoost) as base predictors, with Support Vector Regression acting as the meta-predictor to accurately estimate power readings. The anomaly classification threshold is optimized using Sequential Model-Based Optimization based on residuals. Bayesian probability analysis updates the detection probability and makes decisions regarding power theft. Evaluation results demonstrate that the ensemble models outperform individual nonlinear models, highlighting the effectiveness of the proposed approach. Overall, this research presents a comprehensive solution for detecting photovoltaic power theft using a data-driven stacking model, which surpasses individual nonlinear models in identifying anomalies in photovoltaic power generation data.

As communication networks and the Internet of Things (IoT) converge in water critical infrastructure, it facilitates smart online monitoring of water supply systems, but it also significantly increases the incidence of cyber attacks. Additionally, it becomes especially challenging to detect attacks timely as they become more sophisticated and multifaceted. To address this issue, we propose a stacking ensemble network detection model based on industrial processes in water treatment systems, where the attacks are identified through recognizing anomalies caused by the underlying dynamics of the industrial control system. In the proposed detection model, we utilize a multilayer perceptron (MLP) to facilitate multi-module training, taking into consideration the multi-stage process of the water conservancy system. Furthermore, we adopt Long Short-Term Memory Recurrent Neural Network (LSTM) to effectively integrate the predicted results. To optimize the performance of this model, we leverage a Population Based Training (PBT) of Neural Networks to finetune the parameters. For each sensor parameter, the residuals between the predicted and measured data are classified using a sliding window-based dynamic threshold to identify anomalies. Based on the Real Safe Water Treatment (SWaT) system dataset, we evaluate the accuracy of our proposed scheme with three other schemes. The experimental comparison results show that the accuracy of our scheme is better than those of all the other three schemes.

As traditional automobiles evolve into the Internet of Vehicles (IoV), the increasingly frequent interactions between intelligent vehicles and external environments make cybersecurity a critical issue. While existing machine learning-based automotive intrusion detection methods demonstrate strong detection performance, most rely on supervised learning frameworks. These approaches not only incur high manual data labeling costs but also show significant limitations when handling real-world, unlabeled attack samples. In this paper, we propose an efficient intrusion detection system for in-vehicle networks based on self-supervised contrastive learning. By leveraging data augmentation, we construct positive sample pairs and learn robust feature representations through joint training using both reconstruction loss and contrastive loss. Additionally, we fuse the features extracted from the backbone and core networks into global representations for downstream classification tasks. Experiments on real in-vehicle intrusion datasets show that SSC-IDS achieves strong performance in anomaly detection. Furthermore, we test the model’s robustness under varying rates of anomaly contamination.

In order to solve the problem that the existing methods in the field of diabetic retinopathy (DR) intelligent diagnosis have not fully exploited the effective DR lesion information in the fundus map, as well as the problem that the traditional attention mechanism have not fully explored the influencing factors of different lesion category in DR grading. This paper proposed a diagnostic method that fuses multi-level patch attention and lesion location. The method contains a multi-level patch lesion attention generator (MPAG) and lesion location module (LLM). The MPAG generates a attention map containing the lesion level imformation of different fundus patches, which is weighted with the fundus map and classified by a global network. The LLM is able to indicate lesion and generate a localization-based global attention and increasing the weights of lesion details in the classification network. This paper demonstrated the effectiveness of the proposed method through extensive experiments on the DDR dataset, obtained an accuracy of 0.8064.

In recent years, there has been a great development in the research of automated detection of diabetic retinopathy, and deep learning algorithms have been more and more widely used in this field. In this paper, we propose a channel cross enhancement network based on a two-stream model for diabetic retinopathy severity grading for the detailed performance of diabetic retinopathy images on different channels (RGB). The model takes the features of the full-channel input image as global features and the features extracted from the green channel of the original image as local features, and the local features complement the global features to enhance the model's ability to extract the global channel information of the image. In addition, a channel cross-attention module (CCAM) is designed to achieve the effective extraction of global channel features and the interaction of local channel features with global channel features. The proposed method is validated on the Messidor-2 dataset, and the experimental results show that the proposed method outperforms the existing methods in terms of accuracy and AUC values. After experimental validation, the method proposed in this paper can be effectively used for the auxiliary diagnosis of diabetic retinopathy, helping doctors to provide an effective basis for early clinical treatment.

Abstract Data transmission between smart meters and data center is facing network security threats in advanced metering infrastructure of smart grid. The traditional solution is to move the data to the data center to build a centralized attack detection model, or divide the collected data into several independent and identically distributed datasets to build a distributed attack detection model. However, the long‐distance transmission and the centralized storage of data not only increase the communication overhead and time overhead, but also increase the risk of being attacked, causing privacy disclosure during the process of building the model. In this paper, we propose an efficient intrusion detection framework Fed_ADBN based on federated attention deep belief network and client selection. Clients cooperate with the data center to jointly build a horizontal federated learning framework. Under the premise of protecting data security by keeping data on the clients, we design a client selection algorithm based on client computing power, communication quality and security risks, which can improve the operating efficiency of federated learning. We also deploy a deep belief neural network with attention mechanism in each client to accurately detect possible network attacks in AMI network in real time. Experimental results show that compared with state‐of‐the‐art methods, the proposed framework can not only maintain good detection accuracy but also protect privacy.

Data classification of users’ electricity consumption provides an in-depth analysis for users’ electricity consumption status, which plays a vital role in the management and distribution of electric energy. So, some data classification methods have been proposed to solve the classification problem of electricity consumption data. However, plaintext-based data classification may bring about the privacy leakage of electricity consumption data. In this paper, we propose a privacy-preserving classification scheme for electricity consumption data under fog computing-based smart metering system, which is based on convolutional neural network (CNN) model with fully homomorphic method (CKKS). The target of our proposed scheme is to solve the leakage problem of private electricity consumption data during the classification procedure. In our scheme, an improved K-means-based labeling algorithm is constructed to process historical electricity consumption data, which is used as the sample data to train the CNN classification model by cloud server. Also, the fog nodes are only permitted to obtain the related ciphertext parameters of the trained CNN model, and perform the classification of ciphertext-based electricity consumption data generated by fully homomorphic method. Based on the classical testing data, the experimental results show that our proposed classification scheme can provide the high classification accuracy of electricity data while protecting the privacy of electricity data.

With the growing demand for energy-efficient and environmentally friendly transportation solutions, electric vehicles have become an emerging mode of transportation. However, a large number of security issues have affected its further development. Existing schemes use identity-based restricted partial blind signature technique to implement authentication schemes with high computational cost. Local aggregators suffer from tampering with transaction records. Malicious EVs continuously listen to power transactions to infer the lifestyle of EV users. This scheme designs a cloud-edge collaboration authentication scheme based on V2G short randomizable signature. Specifically, privacy during EV power transactions is guaranteed using lightweight cryptographic primitives. EVs evaluate the reputation value of local aggregators through additive secret sharing. Cloud computing center and edge servers are capable of collaborative authentication and collaborative tracking. This scheme can improve the authentication efficiency of V2G network.

To decrease the loss of stealing electricity on the smart grid, power theft detection (ETD) is widely concerned and studied. Due to missing values, invalid values, and non-linear data relationships in the grid data, existing electricity theft detection methods will generally lead to training errors, non-convergence, and low accuracy. To address those issues, we propose a CNN-BiLSTM-Attention method to detect electricity stealing behavior. Since the number of normal users in the grid is much larger than that of abnormal users, we propose an improved WGAN-GP (LWGAN-GP) algorithm to solve the data imbalance problem. Based on the generated balanced dataset, CNN and BiLSTM are adopted to extract features from current data and historical data, respectively. To further improve the classification accuracy, we use an attention mechanism to assign weights to the relevant features. Moreover, experiments based on real datasets show that the ACC, AUC, and F1 of the proposed CNN-BiLSTM-Attention method are greater than those of the other three machine learning and deep learning models.

In social Internet of Vehicles (SIoVs), vehicles can usually act as data-relaying nodes to forward data. However, vehicle nodes often show their personal and social selfishness in data forwarding (namely vehicle nodes are not willing to forward data), whose selfishness greatly influences the delivery ratio of data forwarding. In this article, we propose a 2-D behavior-marker-based data-forwarding incentive scheme to motivate vehicle nodes to participate in data forwarding in fog-computing-based SIoVs. First, we design a 2-D behavior marker mechanism, which can be used to completely evaluate vehicle nodes. Second, we construct a currency credit-based data-forwarding incentive strategy based on the 2-D marker and the social attributes of vehicle nodes, which is used to deal with vehicular normal behavior, vehicular selfish behavior, and vehicular malicious behavior. Compared with other related schemes, our proposed scheme can completely evaluate the behaviors of vehicle nodes and can further promote the cooperation of data-forwarding between selfish nodes. The experimental results show that our scheme is more efficient and stable in data forwarding in fog-computing-based SIoVs.

Social Internet of vehicles (SIoVs) is a combination of vehicular ad-hoc networks (VANETs) and mobile social networks (MSNs). Although social relationships between vehicle nodes are more stable than location changes of vehicle nodes in SIoVs, there always are the problems of data forwarding optimization and adaptability for dynamic networks. In this paper, we propose a dual-mode data forwarding scheme based on interest tags for fog computing-based SIoVs. In the first data forwarding mode, the vehicle nodes calculate and use the cooperation degrees to select the next cooperative forwarding nodes until the data is forwarded to the destination node. In the second data forwarding mode, the RSUs assist the data forwarding of vehicle nodes based on the RSU ranking mechanism of interests, where the fog servers calculate the RSU ranking table of all the interests and the related RSU selects the top-${k}$RSUs to forward the data according to the RSU ranking table. The experimental results show that our proposed scheme is more efficient and stable than other related schemes by the comparisons of delivery ratio, overhead ratio and average hop count.

Internet of vehicles (IoVs) is a variant of vehicular ad hoc network, which provides an efficient communication method for vehicles. However, some traffic messages usually include sensitive identity information, which is easy to bring about the leakage of vehicular identities during data communications. Further, if vehicular identities are fully protected, then it can lead to trusted authority cannot reveal the real identities of malicious vehicles, which incurs more security issues in IoVs. Therefore, in this article, we propose an efficient conditional identity privacy-preserving authentication scheme based on cooperation of multiple fog servers under fog computing-based IoVs, where fog servers are used to verify (authenticate) the legitimacy of vehicles without revealing their real identities. Further, an associated vehicular identity updating mechanism is constructed to solve the problem that some compromised fog servers may leak their stored verification information to pool real vehicular identities. Additionally, a malicious vehicular identity tracing mechanism is proposed to support related fog servers that receive signed false messages can trace the real identities of malicious vehicles. Compared with other related schemes, our scheme further improves its security. Experimental results show our scheme is efficient under fog computing-based IoVs.

With the popularity of smart devices and the widespread use of machine learning methods, smart edges have become the mainstream of dealing with wireless big data. When smart edges use machine learning models to analyze wireless big data, nevertheless, some models may unintentionally store a small portion of the training data with sensitive records. Thus, intruders can expose sensitive information by careful analysis of this model. To solve this privacy issue, in this paper, we propose and implement a machine learning strategy for smart edges using differential privacy. We focus our attention on privacy protection in training datasets in wireless big data scenario. Moreover, we guarantee privacy protection by adding Laplace mechanisms, and design two different algorithms Output Perturbation (OPP) and Objective Perturbation (OJP), which satisfy differential privacy. In addition, we consider the privacy preserving issues presented in the existing literatures for differential privacy in the correlated datasets, and further provided differential privacy preserving methods for correlated datasets, guaranteeing privacy by theoretical deduction. Finally, we implement the experiments on the TensorFlow, and evaluate our strategy on four datasets, i.e., MNIST, SVHN, CIFAR-10 and STL-10. The experiment results show that our methods can efficiently protect the privacy of training datasets and guarantee the accuracy on benchmark datasets.

The smart grid solves the growing load demand of electrical customers through two-way real-time communication of electricity supply and demand sides and home energy management system (HEMS). However, these technical features also bring network security risks to the real-time price signal of the smart grid. The real-time price attack (RTPA) can maliciously raise the real-time price in smart meter, resulting in an increase in electrical customers load demand, causing the extensive damage to the power transmission lines due to overload. In this paper, we based on the behavioral relationship between load demand of electrical customers and real-time price of electricity suppliers (ES), defined the game relationship between RTPA, ES, and electrical customers, established a price elasticity of electricity demand (PEED) model, and proposed a defensive strategy of real-time price attack based on multiperson zero-determinant strategy (MPZDS). The experimental results show that the combination of MPZDS to some extent cut the expected load demand of electrical customers and protect the safety of power transmission lines.

This paper studies energy harvesting sensor networks in green cities that transmit a variety of data packets with different reward values. With the aim to maximize its long-term average transmission reward, almost all the existing optimal energy management strategies are based on the policy iteration algorithm, which suffers from the curse of dimensionality. By contrast, we focus on developing low-complexity optimal policies that can lead to practical implementation. Our main contribution is to propose a threshold-based scheduling policy for energy harvesting sensor networks achieving long-term average rewards. As a result, a sensor node only requires limited memory to store a few optimal value thresholds to perform energy management. Specifically, we propose an algorithm to compute the optimal thresholds, whose complexity is linear with the size of data and energy storage. Numerical results are studied based on real solar radiation data measured at Queensland and show that the optimal expected reward of our proposed scheduling policy approaches its theoretical offline upper bound.

In this paper, we propose two dependence link addition strategies to enhance the robustness of interdependent Cyber-Physical Systems. One is based on intra-degree and receiving capability difference and the other is based on intra-degree and receiving capability ratio. Numerical simulations demonstrate that the two strategies are better than adding dependence links randomly.