Geographically distributed data centers (DCs) offer significant spatiotemporal flexibility and are ideal candidates for demand response in power systems. This paper proposes a two-stage robust spatiotemporal optimal scheduling model for geographically distributed DCs that accounts for the uncertainty in both renewable energy generation and workload. In the first stage, a day-ahead scheduling approach is employed based on predicted workload and renewable energy generation values to determine pre-scheduling strategies. In the second stage, between the day-ahead and intraday periods, an iterative algorithm is introduced to calculate the number of reserved servers, thereby mitigating the workload overload issues arising from workload uncertainty. Power fluctuations resulting from the uncertainty of the predicted values are balanced using energy storage and generators. Finally, simulation results validate the effectiveness of the proposed algorithm in reducing overcapacity and enhancing the economic efficiency of the scheduling model.

BACKGROUND: Identifying potential associations among food, gut microbiota and disease is fundamental for elucidating interaction mechanisms and advancing personalized healthy dietary strategies. While computational methods have been extensively applied to predict microbiota-disease associations, methods on predicting food-microbiota relationships remain limited, particularly regarding higher-order food-microbiota-disease interactions. RESULTS: In this work, we construct a food-microbe-disease (FMD) database encompassing 190 food items, 219 gut microbiota species, and 163 disease entities, resulting in 17,065 FMD associations. We then propose a lightweight single-view contrastive learning hypergraph neural network (LSCHNN) for FMD association prediction on the sparse FMD dataset. LSCHNN formulates ternary FMD interactions as a hypergraph, in which foods, microbes, and diseases are represented by nodes and FMD triplets are represented by hyperedges, and leverages the biological features of foods, microbes, and diseases as node attributes. Subsequently, a hypergraph neural network is designed to learn the embeddings of foods, microbes, and diseases from the hypergraph and predict potential ternary FMD associations. Additionally, we incorporate a single-view contrastive learning mechanism that enhances the model's ability to extract discriminative features and improves generalization on sparse data. Comprehensive comparison experiments demonstrate that LSCHNN outperforms other state-of-the-art methods in terms of the precision of predicting ternary FMD associations and discovering more potential FMD associations. Case studies on two microbes further confirm the effectiveness of LSCHNN in identifying potential FMD associations. CONCLUSIONS: A novel computational model, LSCHNN, is proposed, marking the first integration of hypergraph neural networks with lightweight single-view contrastive learning for ternary FMD association prediction, providing a groundbreaking framework for precision nutrition and personalized dietary interventions.

With the rapid development of intelligent transportation and vehicular edge computing (VEC), efficient, fair, and interpretable task offloading has become a key challenge in dynamic and resource-constrained environments. Non-orthogonal multiple access (NOMA) can enhance connectivity and spectrum efficiency. However, conventional resource allocation strategies typically rely solely on channel gain ordering while overlooking spatial factors and fairness. In addition, the lack of transparency in multi-agent deep reinforcement learning (MADRL) decision-making raises concerns regarding transparency and trustworthiness. To address these challenges, we propose a NOMA-based task offloading framework that integrates distance and channel-aware resource allocation, and we design a distributed multi-agent decision-making algorithm based on potential games (DACA-MAD4PG), further incorporating Shapley Additive Explanations (SHAP) to improve interpretability. The proposed framework is significantly different from existing NOMA-based task offloading approaches in the following three aspects. First, it introduces a distance and channel-aware joint resource allocation mechanism to enhance both efficiency and fairness in vehicular edge computing. Second, an exact potential game is incorporated to guarantee system stability and the existence of Nash equilibria. Last, SHAP is integrated to provide post hoc interpretability, thereby improving transparency in multi-agent decision-making. Experiments based on real-world DiDi trajectory data demonstrate that the proposed approach significantly reduces task latency, improves service success rate, cumulative reward, and fairness, and outperforms several baselines, thereby providing a stable and interpretable solution for VEC task offloading.

Reliability is a fundamental requirement of power systems. However, uncertainties from renewable energy generators and demand loads bring challenges to the economical and reliable operation of power distribution networks. This paper focuses on an energy management problem for networked microgrid systems (NMSs), aiming at establishing energy management policies for individual microgrids within NMSs to enhance the long-term economy and stability of the entire system. The key challenge is that each microgrid has independent decision-making capability and how to collaborate all microgrids’ decisions in a distributed multi-agent manner such that the entire system goal is optimized. We introduce the mean and variance of the exchanged power between the NMS and the main grid as the indicators of NMS operation profits and power fluctuations, respectively. The energy management problem is formulated as a mean-variance team stochastic game (MV-TSG) model. Because the variance metric is neither additive nor Markovian in a dynamic setting, the dynamic programming principle does not hold for this problem. We analyze the MV-TSG from a view of sensitivity-based optimization and propose a multi-agent policy iteration method by introducing a sequential update scheme. Furthermore, to tackle MV-TSGs with larger scales or unknown environmental parameters, we extend the idea of trust region optimization and develop a novel multi-agent deep reinforcement learning algorithm. The performance of our approaches is verified through numerical experiments using a real dataset in power distribution networks. Note to Practitioners—Energy management is essential for economical and reliable operation of networked microgrid systems (NMSs). NMSs exchange power with the main grid, where positive exchanged power indicates that the NMS is selling power to the main grid and generating profits, while negative exchanged power indicates that the NMS is purchasing power and incurring costs. The long-term average exchanged power between the NMS and the main grid reflects the economical operation of NMSs. However, fluctuations in exchanged power can lead to power quality issues such as frequency deviation and voltage flicker, which affect the reliability of NMS operations. In this paper, we study the economical and reliable operation of NMSs with distributed energy management policies, formulating the problem as a mean-variance team stochastic game (MV-TSG). We propose a multi-agent policy iteration method to address MV-TSGs. We further develop a multi-agent deep reinforcement learning algorithm to tackle MV-TSGs with large scales and in scenarios where environmental models are unknown. Experiments utilizing real data demonstrate that our algorithms effectively promote collaboration among microgrids to control exchanged power. As the weight coefficient increases, power fluctuations are reduced, achieving power smoothing and peak shaving simultaneously in long-term scheduling. Consequently, our algorithms can facilitate the trade-off between economy and reliability in NMS operations. These results provide valuable insights into the energy management challenges of NMSs in power distribution networks.

In intelligent transportation systems (ITS), machine learning is highly effective in anomaly detection for state estimation (SE) in traffic flow measurement, but it requires resource-intensive collection of anomaly samples and overlooks spatial characteristics. Additionally, the original SE in traffic flow measurement exhibits low-frequency characteristics due to computational complexity. Considering these limitations, this paper proposes a fast and efficient anomaly detection framework for SE in traffic flow measurement. Initially, an attention-based spatiotemporal graph convolutional network (ASTGCN) model is utilized to extract both temporal and spatial features of SE. The ASTGCN model is trained using quantile regression, relying solely on normal samples during training. This approach eliminates the need for collecting anomalous samples and reduces computational demands. The model establishes a safe interval for SE that significantly improves anomaly detection capabilities. Furthermore, a teacher-student network is implemented, where the teacher network, trained offline, distills its ability to convert low-frequency SE data into high-frequency representations into a simpler student network. The student network executes real-time reconstruction of high-frequency SE, thus enhancing the precision of anomaly detection without substantial resource expenditure. Finally, the analysis conducted on the California’s 7th district highway measurement system demonstrates the proposed method’s ability to accurately detect anomalous SE in traffic flow measurement.

The development of integrated energy system has promoted the development of the power system into the largest and most complex cyber-physical energy system, where the change in the openness of the load frequency control (LFC) system has also increased its susceptibility to false data injection attacks (FDIAs). This paper porposes an artificial intelligence (AI) based detection and countermeasure strategy to protect LFC systems from FDIAs. First, The levenberg-marquarelt-back propagation (LM-BP) neural networks (NNs) is trained by collecting the historical data of frequency deviation, power deviation of contact line, and active power load deviation. Second, the output control signal of LM-BP NNs is tested against the output of the system controller for residuals to determine whether has FDIAs. Furthermore, to resist the negative effects of FDIAs, the control signal calculated by the LM-BP NNs will replace the traditional proportion integration differentiation (PID) output. Finally, The advantages of the proposed strategy are illustrated by the two interconnected power systems.

Currently, the main challenges of the frameworks for healthcare monitoring are as follows: minimising latency, especially for delay-sensitive diseases such as sudden heart disease; identifying health situation in a timely and accurate manner when correlating physiological indicators and context information; reducing the risk of exposure because health data are highly private. In response to the above, this paper proposes a framework for 5G-secure-smart healthcare monitoring (5GSS) to achieve the following goals: fast and accurate identification of context-aware health situation, blockchain-based secure data sharing, and low-latency services for emergent patients. The framework consists of a data acquisition layer, a diagnosis and security layer (edge cloud), and a health service layer. The proposed framework adopts the following key technologies: a 5G-IPv6 communication network, context-aware health situation identification-based similarity measure, and blockchain-based secure data sharing mechanism. Finally, a prototype system has been implemented to monitor hypertensive heart disease, confirming its effectiveness with respect to a real scenario. Combined with the data of 45 patients, the prototype system can identify health situations with an accuracy of 96.34% at a sensitivity of 92.46% and a specificity of 93.62%, while significantly reducing the latency and improving the data sharing security.

Network pruning facilitates the deployment of convolutional neural networks in resource-limited environments by reducing redundant parameters. However, most of the existing methods ignore the differences in the contributions of the output feature maps. In response to the above, we propose a novel neural network pruning method based on the channel attention mechanism. In this paper, we firstly utilise the principal component analysis algorithm to reduce the influence of noisy data on feature maps. Then, we propose an improved Leaky-Squeeze-and-Excitation block to evaluate the contribution of each output feature map using the channel attention mechanism. Finally, we effectively remove lower contribution channels without reducing the model performance as much as possible. Extensive experimental results show that our proposed method achieves significant improvements over the state-of-the-art in terms of FLOPs and parameters reduction with similar accuracies. For example, with VGG-16-baseline, our proposed method reduces parameters by 83.3% and FLOPs by 66.3%, with only a loss of 0.13% in top-5 accuracy. Furthermore, it effectively balances pruning efficiency and prediction accuracy.

Demand response (DR) of power grids services an increasing key component of smart grids. This article is devoted to the DR active power control for smart buildings based on a cloud platform for security interconnection with power grids. The objective of the DR control is to cope with the intermittent renewable power injection and power fluctuation of the tie-line between the building and the distribution grid. The renewable energy power includes photovoltaic panel and on-site wind power generators on the building roof, and the flexible loads includes electric vehicles (EVs) connected to the building, and thermostatically controlled loads (TCLs) in the building. We propose two fair and flexible indexes, comfortable levels for TCLs and the charging priority for EVs, and design two kinds of DR control algorithm, i.e., centralized load reduction control algorithm and distributed load following control algorithm, to coordinate the power balance of the building while maintain the grid exchange power is distributed in a probabilistic security controllable interval such that the building turns out to be a grid-friendly building. The case study is tested on a smart building with random renewable power injection and flowing EVs, civil electric water heaters (EWHs) thermostatically controlled loads and the simulations results shows the effectiveness of the proposed DR control algorithms.

Distortion risk measure, defined by an integral of a distorted tail probability, has been widely used in behavioral economics and risk management as an alternative to expected utility. The sensitivity of the distortion risk measure is a functional of certain distribution sensitivities. We propose a new sensitivity estimator for the distortion risk measure that uses generalized likelihood ratio estimators for distribution sensitivities as input and establish a central limit theorem for the new estimator. The proposed estimator can handle discontinuous sample paths and distortion functions.

We propose a dynamic sampling allocation and selection paradigm for finding the alternative with the optimal quantile in a Bayesian framework. Myopic allocation policies (MAPs), analogous to existing methods in classic ranking and selection for selecting the alternative with the optimal mean, and computationally efficient selection policies are derived for selecting the alternative with the optimal quantile. Under certain conditions, we prove that the proposed MAPs and selection procedures are consistent, which means that the best quantile would be eventually correctly selected as the sample size goes to infinity. Numerical experiments demonstrate that the proposed schemes can significantly improve the performance.

At present, abnormal rise of rail potential in DC traction power supply system of urban rail transit has become a difficult problem in line safety. The mechanism and distribution of abnormal rail potential need to be clarified. In the traditional analysis method, the mode that single train operating in single power supply section is far from the mode that multitrain run in multi-power supply sections in the actual line. The power allocation of multitrain and traction substations is complex, which will affect the rail potential. In this paper, the parallel multiconductor model of traction power supply system under multitrain parallel operation is established. A new power distribution calculation method for urban rail power supply system is analyzed. Dynamic simulation of the system is carried out based on the parameters of actual line, and the effect of power allocation on rail potential is analyzed. Results show that, rail potential is greatly affected by the power allocation of the system. Optimizing the power distribution of the system can effectively control the abnormal increase of rail potential.

A new generation of home healthcare monitoring system strives to have such characteristics as low-cost, low-power and low-volume etc., and furthermore, it needs to quickly adapt to the development of national medical information based Cloud computing in China. In response to this trend, a Cloud-assisted home health monitoring system was designed in this paper. Sensors can be selectively configured to monitor the respective physiological signal depending on the diagnostic demands of a patient's disease. This system uses smart phones to receive physiological signals and cloud platforms (such as Xiamen Health Cloud) to storage physiological monitoring data. Combined with these data, health cloud provides risk assessment of chronic disease. Clinical application of the system shows that it has positive significance for patients with hypertension and diabetes who can enjoy health monitoring and the services of health could at home.

This paper deals with a consensus tracking problem for multiagent systems (MASs) with Lipschitz-type nonlinear dynamics and directed switching topology. Unlike most existing works where the relative full state measurements of neighboring agents are utilized, it is assumed that only the relative output measurements of neighboring agents are available for coordination. To achieve consensus tracking in the considered MASs, a new class of observer-based protocols is proposed. By appropriately constructing some topology-dependent multiple Lyapunov functions, it is theoretically shown that distributed consensus tracking in the closed-loop MASs equipped with the designed protocols can be ensured if each possible topology contains a directed spanning tree rooted at the leader and the dwell time for the switchings among different topology is less than a derived positive quantity. Interestingly, it is found that the communication topology for observers' states may be independent with that of the feedback signals. The derived results are further extended to the case of directed switching topology with only average dwell time constraints. Finally, the effectiveness of the analytical results is demonstrated via numerical simulations.

In the above paper[1], there are errors regarding the description of(4), and misquotes in Algorithm 1 and 2. In Algorithm 1, the first equation referenced should be (5) and not (40). In Algorithm 2, the first equation referenced should be (40) and not (5). The correction for(4)is as follows:\begin{equation*} \mathcal {L}^{(\sigma (t))}=\left [{\begin{array}{cc} \widetilde {\mathcal {L}}^{(\sigma (t))}& \mathrm {a}^{(\sigma (t))}\\ \mathrm {0}_{N}^{T}& 0 \end{array}}\right ] \tag{4}\end{equation*}where$\widetilde {\mathcal {L}}^{(\sigma (t))}\in \mathbb {R}^{N\times N}$,$\mathrm {a}^{(\sigma (t))}=-[a_{1(N+1)}^{(\sigma (t))},a_{2(N+1)}^{(\sigma (t))},\cdots ,~a_{N(N+1)}^{(\sigma (t))}]^{T}\in \mathbb {R}^{N}$, and$\mathcal {A}^{(\sigma (t))} = [a_{ij}^{(\sigma (t))}]_{(N+1) \times (N+1)}$is the adjacency matrix of$\mathcal {G}^{(\sigma (t))}$.

Most inventory models in the literature assume that demands are independent among different time periods. However, a number of recent studies suggest that demands are often correlated over different time periods, which motivates our work here. In this paper, we study a class of periodic review (s, S) inventory systems in which demands are correlated and modeled as a Markov-modulated process. Using a Maclaurin series analysis and a Pade approximation, as well as an infinite system of linear equations, we develop algorithms to calculate the moments of the inventory level based on which various performance measures of the system can also be evaluated. Numerical experiments show that our approach is quite efficient and provides accurate estimates for the moments of the inventory level and other related performance measures.

We formulate the statistical selection problem in a general dynamic framework comprising fully sequential sampling allocation and optimal design selection. Because the traditional probability of correct selection measure is not sufficient to capture both aspects in this more general framework, we introduce the integrated probability of correct selection to better characterize the objective. As a result, the usual selection policy of choosing the design with the largest sample mean as the estimate of the best is no longer necessarily optimal. Rather, the optimal selection policy is to choose the design that maximizes the posterior integrated probability of correct selection, which is a function of the posterior mean and the correlation structure induced by the posterior variance. Because determining the optimal selection policy is generally intractable, we also devise an approximation scheme to efficiently approximate the optimal selection policy. For the allocation policy, we study an asymptotic policy called general Bayesian budget allocation, which is comprised of a sampling statistic and a sequential rule. The optimal computing budget allocation algorithm can be interpreted as a special case of the asymptotical sampling statistics. Numerical examples are provided to illustrate the potential performance improvements, especially in small sample behavior.

A compound control strategy is proposed for frequency regulation of source-grid-load systems in which power sources, power grids, and loads are all participating in the process. Here, power sources are conventional thermal generators, including new energy power generations, and loads are composed of energy storage units (ESUs) and grid-friendly appliances (GFAs). The proposed control scheme includes two levels of operations, with the upper level to be a model predictive control (MPC) for generators and the lower level to be a distributed leader-following consensus control strategy for multiple ESUs. For new energy power generations, the power outputs are restricted on a constant value during a sampling period based on a predicted generating curve. GFAs respond to the system frequency by regulating their active power consumption. Simulations on a single power system and three interconnected area power systems are provided to verify the effectiveness of the proposed compound control strategy.

The hierarchical cooperative control problem is concerned for a two-layer networked multiagent system under switching directed topologies. The group cooperative objective is to achieve finite-time formation control for the upper layer of leaders and containment control for the lower layer of followers. Two kinds of cooperative strategies, including centralized-distributed control and distributed-distributed control, are proposed for two types of switching laws: 1) random switching law with the dwell time and 2) Markov switching law with stationary distribution. Utilizing the state transition matrix methods and matrix measure techniques, some sufficient conditions are derived for asymptotical containment control and exponential almost sure containment control, respectively. Finally, some numerical examples are provided to demonstrate the effectiveness of the proposed control schemes.

This paper is concerned with the problem of synchronization control for the delayed hybrid-coupled heterogeneous network with stochastic disturbances. To begin with, the open-loop control is imposed on the whole network, based on which the pinning adaptive control and the impulsive control are introduced to synchronize the whole network to an arbitrary objective trajectory. Furthermore, by employing stochastic analysis techniques and the improved Halanay inequality, some easy-to-verify sufficient conditions are derived to guarantee the asymptotic/exponential synchronization in the mean square of the complex network under study. Numerical example of a directed network is illustrated to demonstrate the applicability and efficiency of the proposed theoretical results.

In order to manage the increasing amount of RDF data, an RDF repository should provide not only necessary scalability and efficiency, but also sufficient inference capabilities. Though existing RDF repositories have made progress towards this goal, there is still ample space for improving the overall performance. In this paper, we propose a native RDF repository, System II, to pursue a better tradeoff among the system scalability, the query efficiency, and the inference capabilities. System II takes the hypergraph representation for RDF as the data model for its persistent storage, which effectively avoids the costs of data model transformation when accessing RDF data. Based on this native storage scheme, a set of efficient semantic query processing techniques are designed. First, several indices are built to accelerate RDF data access including a value index, a labeling scheme for transitive closure computation, and three triple indices. Second, we propose a hybrid inference strategy under the pD* semantics to support inference for OWL-Lite with a relatively low computational complexity. Finally, we extend the SPARQL algebra to explicitly express inference semantics in logical query plan by defining new algebra operators. The results of performance evaluation on the LUBM benchmark show that System II has a better combined metric value than the other comparable systems.

We consider the problem of efficiently allocating simulation replications in order to maximize the probability of selecting the best design under the scenario in which system performances are sampled in the presence of correlation. In the case of two designs, we are able to derive the optimal allocation exactly, and find that in the presence of positive correlation, unless the variance of one design is significantly larger than that of the other, the number of simulation replications should be identical. In extending to a general number of competing designs, an approximation for the asymptotically optimal allocation is obtained. The approximation coincides with the independent case derived previously in the limit as the correlation vanishes and also agrees with the two-design exact solution. Furthermore, the allocations prescribed by the results seem to match intuition, in terms of the relationship to correlations and relative variances between designs, again suggesting that equal allocation is optimal for sufficiently high positive correlation. An allocation algorithm based on the approximation is proposed and tested on several numerical examples.

Web service is an Internet-based software component that can shield all sorts of resources on basis of standard protocol stack. It helps to raise the level of abstraction and simplify conventional COTS middleware for resource sharing and cooperation across organization. In this paper, a Web service container framework (WSCF) is presented to offer an effective systematic solution for Web service-based application supporting environment, referencing from CORBA and J2EE system managing architecture and using SOAP interoperation protocol. The proposed framework focuses on addressing problems in two aspects: 1) Web service runtime supporting technologies: unified resource mapping strategy, flexible service adaptation mechanism, and SOAP engine scheduling algorithm; 2) several application supporting services: publication and discovery service, Web service composition service, and security service, etc. In particular, it describes ongoing project StarWebService that has followed WSCF. Finally, some open issues about WSCF are introduced and the future direction of WSCF is pointed out.

In this paper, we consider the traffic grooming, routing, and wavelength assignment (GRWA) problem for optical mesh networks. In most previous studies on optical mesh networks, traffic demands are usually assumed to be wavelength demands, in which case no traffic grooming is needed. In practice, optical networks are typically required to carry a large number of lower rate (sub-wavelength) traffic demands. Hence, the issue of traffic grooming becomes very important since it can significantly impact the overall network cost. In our study, we consider traffic grooming in combination with traffic routing and wavelength assignment. Our objective is to minimize the total number of transponders required in the network. We first formulate the GRWA problem as an integer linear programming (ILP) problem. Unfortunately, for large networks it is computationally infeasible to solve the ILP problem. Therefore, we propose a decomposition method that divides the GRWA problem into two smaller problems: the traffic grooming and routing problem and the wavelength assignment problem, which can then be solved much more efficiently. In general, the decomposition method only produces an approximate solution for the GRWA problem. However, we also provide some sufficient condition under which the decomposition method gives an optimal solution. Finally, some numerical results are provided to demonstrate the efficiency of our method.

We study the diverse routing problem in optical mesh networks. We use a general framework based on shared risk link groups to model the problem. We prove that the diverse routing problem is indeed NP-complete, a result that has been conjectured by several researchers previously. In fact, we show that even the fiber-span-disjoint paths problem, a special case of the diverse routing problem, is also NP-complete. We then develop an integer linear programming formulation and show through numerical results that it is a very viable method to solve the diverse routing problem for most optical networks found in many applications which typically have no more than a few hundred nodes and fiber spans.

The growth of the Internet has fuelled the development of new technologies that enable IP backbone networks to be engineered efficiently. One such prominent technology, multiprotocol label switching (MPLS) enables IP networks with quality of service to be traffic engineered well. We mathematically formulate the traffic engineering problem's in MPLS based IP networks including constraint based routing, connection admission control, rerouting and capacity planning problems. Unfortunately, obtaining the optimal solution of the traffic engineering problems has undesirable computational complexity since they can be shown to be NP-complete. It is intended that this work will articulate the details and provide insights into the inherent structure of the problems as well as motivate the development of efficient solution techniques.