Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs).Its success, however, largely depends on strong base models with rich world knowledge, yielding only modest improvements for small-size language models (SLMs).To address this limitation, we investigate Guided GRPO, which injects ground-truth reasoning steps into roll-out trajectories to compensate for SLMs' inherent weaknesses.Through a comprehensive study of various guidance configurations, we find that naively adding guidance delivers limited gains.These insights motivate G 2 RPO-A, an adaptive algorithm that automatically adjusts guidance strength in response to the model's evolving training dynamics.Experiments on mathematical reasoning and codegeneration benchmarks confirm that G 2 RPO-A substantially outperforms vanilla GRPO.Our code and models are available at https:// github.com/T-Lab-CUHKSZ/G2RPO-A.

Automated prompt optimization is crucial for eliciting reliable reasoning from large language models (LLMs), yet most API-only prompt optimizers iteratively edit monolithic prompts, coupling components and obscuring credit assignment, limiting controllability, and wasting tokens.We propose Adaptive Prompt Structure Factorization (aPSF), an API-only framework (prompt-in/text-out; no access to model internals) that uses an Architect model to discover task-specific prompt structures as semantic factors.aPSF then performs interventional, single-factor updates: interventional factor-level scoring estimates each factor's marginal contribution via validation-performance changes, and errorguided factor selection routes updates to the current dominant failure source for more sample-efficient optimization.Across multiple advanced reasoning benchmarks, aPSF outperforms strong baselines including principleaware optimizers, improving accuracy by up to +2.16 percentage points on average, and reduces optimization cost by 45-87% tokens on MultiArith while reaching peak validation in 1 step.

The operation and scheduling of taxi fleets remain a key application area of Internet of Things (IoT) technologies. However, the operational strategies for new energy taxis—particularly hydrogen-powered and hydrogen-electric hybrid vehicles—are still underexplored. This paper investigates the deployment of plug-in hybrid hydrogen and electric taxis (PH2ETs) in ride-hailing services and proposes a bilevel optimization framework that jointly addresses PH2ETs’ hybrid charging decisions and the pricing strategy of integrated electricity and hydrogen refueling stations (IEHSs). PH2ETs determine charging options based on energy prices and time costs, while IEHSs dynamically adjust pricing in response to aggregate charging behaviors. To reduce the prediction error caused by uncertain behavior of drivers in actual scenarios, the model incorporates algorithm aversion, capturing drivers’ reluctance to follow platform-generated recommendations. An improved whale optimization algorithm (WOA) is developed to solve the multi-objective problem. Simulation results validate the effectiveness of the proposed charging strategy and demonstrate that incorporating algorithm aversion significantly improves the pricing performance of IEHSs over conventional approaches.

The increasing penetration of renewable energy introduces significant uncertainties in power systems, necessitating advanced strategies to maintain economic efficiency and frequency stability. This article addresses the multireserve constrained unit commitment (MRCUC) problem by simultaneously allocating spinning reserve and frequency regulation reserve in systems with high renewable energy penetration. First, spinning reserve requirements are accurately determined by an optimization model addressing imbalances caused by renewable energy volatility and load variations. Second, primary and secondary frequency regulation requirements are quantified through detailed frequency-domain simulations utilizing each unit's frequency-to-active-power-output transfer function, thereby overcoming limitations of traditional first-order frequency approximations applicable mostly to synchronous generators. The proposed comprehensive MRCUC model, characterized by partial observability of load uncertainties and high-ordernonconvexity stemming from precise frequency simulations, cannot be efficiently solved using conventional optimization methods. Therefore, a hybrid optimization framework combining RL with convex optimization techniques is developed to address these complexities, ensuring feasible and effective decision-making. Extensive case studies conducted on IEEE 39-bus and 118-bus test systems confirm the efficacy of the proposed method, highlighting enhanced economic performance, accurate reserve allocation, and robust frequency stability.

Video Temporal Grounding (VTG) strives to accurately pinpoint event timestamps in a specific video using linguistic queries, significantly impacting downstream tasks like video browsing and editing. Unlike traditional task-specific models, Video Large Language Models (video LLMs) can handle multiple tasks concurrently in a zero-shot manner. Consequently, exploring the application of video LLMs for VTG tasks has become a burgeoning research area. However, despite considerable advancements in video content understanding, video LLMs often struggle to accurately pinpoint timestamps within videos, limiting their effectiveness in VTG tasks. To address this, we introduce VTG-LLM, a model designed to enhance video LLMs' timestamp localization abilities. Our approach includes: (1) effectively integrating timestamp knowledge into visual tokens; (2) incorporating absolute-time tokens to manage timestamp knowledge without concept shifts; and (3) introducing a lightweight, high-performance, slot-based token compression technique designed to accommodate the demands of a large number of frames to be sampled for VTG tasks. Additionally, we present VTG-IT-120K, a collection of publicly available VTG datasets that we have re-annotated to improve upon low-quality annotations. Our comprehensive experiments demonstrate the superior performance of VTG-LLM in comparison to other video LLM methods across a variety of VTG tasks.

Federated Learning (FL) has received much attention in recent years. However, although clients are not required to share their data in FL, the global model itself can implicitly remember clients' local data. Therefore, it’s necessary to effectively remove the target client's data from the FL global model to ease the risk of privacy leakage and implement "the right to be forgotten". Federated Unlearning (FU) has been considered a promising solution to remove data without full retraining. But the model utility easily suffers significant reduction during unlearning due to the gradient conflicts. Furthermore, when conducting the post-training to recovery the model utility, it’s prone to move back and revert what have already been unlearned. To address these issues, we propose Federated Unlearning with Orthogonal Steepest Descent (FedOSD). We first design an unlearning cross entropy loss to overcome the convergence issue of the gradient ascent. A steepest descent direction for unlearning is then calculated in the condition of being non-conflicting with other clients’ gradients and closest to the target client's gradient. This benefits to efficiently unlearn and mitigate the model utility reduction. After unlearning, we recover the model utility by maintaining the achievement of unlearning. Finally, extensive experiments in several FL scenarios verify that FedOSD outperforms the SOTA FU algorithms in terms of unlearning and the model utility.

Federated averaging (FedAvg) is the most fundamental algorithm in Federated learning (FL). Previous theoretical results assert that FedAvg convergence and generalization degenerate under heterogeneous clients. However, recent empirical results show that FedAvg can perform well in many real-world heterogeneous tasks. These results reveal an inconsistency between FL theory and practice that is not fully explained. In this paper, we show that common heterogeneity measures contribute to this inconsistency based on rigorous convergence analysis. Furthermore, we introduce a new measure \textit{client consensus dynamics} and prove that \textit{FedAvg can effectively handle client heterogeneity when an appropriate aggregation strategy is used}. Building on this theoretical insight, we present a simple and effective FedAvg variant termed FedAWARE. Extensive experiments on three datasets and two modern neural network architectures demonstrate that FedAWARE ensures faster convergence and better generalization in heterogeneous client settings. Moreover, our results show that FedAWARE can significantly enhance the generalization performance of advanced FL algorithms when used as a plug-in module.

The emergence of vision-language foundation models, such as CLIP, has revolutionized image-text representation, enabling a broad range of applications via prompt learning. Despite its promise, real-world datasets often contain noisy labels that can degrade prompt learning performance. In this paper, we demonstrate that using mean absolute error (MAE) loss in prompt learning, named PromptMAE, significantly enhances robustness against noisy labels while maintaining high accuracy. Though MAE is straightforward and recognized for its robustness, it is rarely used in noisy-label learning due to its slow convergence and poor performance outside prompt learning scenarios. To elucidate the robustness of PromptMAE, we leverage feature learning theory to show that MAE can suppress the influence of noisy samples, thereby improving the signal-to-noise ratio and enhancing overall robustness. Additionally, we introduce PromptOT, a prompt-based optimal transport data purification method to enhance the robustness further. PromptOT employs text features in vision-language models as prototypes to construct an optimal transportation matrix. This matrix effectively partitions datasets into clean and noisy subsets, allowing for the application of cross-entropy loss to the clean subset and MAE loss to the noisy subset. Our Noise-Label Prompt Learning method, named NLPrompt, offers a simple and efficient approach that leverages the expressive representations and precise alignment capabilities of vision-language models for robust prompt learning. We validate NLPrompt through extensive experiments across various noise settings, demonstrating significant performance improvements.

Federated Learning (FL) is a privacy-preserving distributed machine learning paradigm. Nonetheless, the substantial distribution shifts among clients pose a considerable challenge to the performance of current FL algorithms. To mitigate this challenge, various methods have been proposed to enhance the FL training process. This paper endeavors to tackle the issue of data heterogeneity from another perspective -- by improving FL algorithms prior to the actual training stage. Specifically, we introduce the Client2Vec mechanism, which generates a unique client index for each client before the commencement of FL training. Subsequently, we leverage the generated client index to enhance the subsequent FL training process. To demonstrate the effectiveness of the proposed Client2Vec method, we conduct three case studies that assess the impact of the client index on the FL training process. These case studies encompass enhanced client sampling, model aggregation, and local training. Extensive experiments conducted on diverse datasets and model architectures show the efficacy of Client2Vec across all three case studies. Our code is avaliable at \url{https://github.com/LINs-lab/client2vec}.

Federated Learning (FL) is an evolving distributed machine learning approach that safeguards client privacy by keeping data on edge devices. However, the variation in data among clients poses challenges in training models that excel across all local distributions. Recent studies suggest clustering as a solution to address client heterogeneity in FL by grouping clients with distribution shifts into distinct clusters. Nonetheless, the diverse learning frameworks used in current clustered FL methods create difficulties in integrating these methods, leveraging their advantages, and making further enhancements. To this end, this paper conducts a thorough examination of existing clustered FL methods and introduces a four-tier framework, named HCFL, to encompass and extend the existing approaches. Utilizing the HCFL, we identify persistent challenges associated with current clustering methods in each tier and propose an enhanced clustering method called HCFL$^{+}$ to overcome these challenges. Through extensive numerical evaluations, we demonstrate the effectiveness of our clustering framework and the enhanced components. Our code is available at \url{https://github.com/LINs-lab/HCFL}.

The Sparse Mixture of Experts (SMoE) has been widely employed to enhance the efficiency of training and inference for Transformer-based foundational models, yielding promising results. However, the performance of SMoE heavily depends on the choice of hyper-parameters, such as the number of experts and the number of experts to be activated (referred to as top-$k$), resulting in significant computational overhead due to the extensive model training by searching over various hyper-parameter configurations. As a remedy, we introduce the Dynamic Mixture of Experts (DynMoE) technique. DynMoE incorporates (1) a novel gating method that enables each token to automatically determine the number of experts to activate. (2) An adaptive process automatically adjusts the number of experts during training. Extensive numerical results across Vision, Language, and Vision-Language tasks demonstrate the effectiveness of our approach to achieve competitive performance compared to GMoE for vision and language tasks, and MoE-LLaVA for vision-language tasks, while maintaining efficiency by activating fewer parameters. Our code is available at \url{https://github.com/LINs-lab/DynMoE}.

Video Temporal Grounding (VTG) is a crucial capability for video understanding models and plays a vital role in downstream tasks such as video browsing and editing. To effectively handle various tasks simultaneously and enable zero-shot prediction, there is a growing trend in employing video LLMs for VTG tasks. However, current video LLM-based methods rely exclusively on natural language generation, lacking the ability to model the clear structure inherent in videos, which restricts their effectiveness in tackling VTG tasks. To address this issue, this paper first formally introduces causal event modeling framework, which represents video LLM outputs as sequences of events, and predict the current event using previous events, video inputs, and textural instructions. Each event consists of three components: timestamps, salient scores, and textual captions. We then propose a novel task-interleaved video LLM called TRACE to effectively implement the causal event modeling framework in practice. The TRACE process visual frames, timestamps, salient scores, and text as distinct tasks, employing various encoders and decoding heads for each. Task tokens are arranged in an interleaved sequence according to the causal event modeling framework's formulation. Extensive experiments on various VTG tasks and datasets demonstrate the superior performance of TRACE compared to state-of-the-art video LLMs. Our model and code are avaliable at \url{https://github.com/gyxxyg/TRACE}.

This paper introduces the concept of UAV (Unmanned Aerial Vehicle) corridors as structured, wirelessoptimized flight paths to reduce collision risks and enhance safety in urban environments. To address challenges such as signal interference and collisions at shared altitudes, we formulate the UAV trajectory planning and task offloading problem as a continuous-time integer nonlinear programming problem, considering communication constraints, time delay, task offloading, and energy consumption. A novel Signal-Interference Proximal Policy Optimization (SI-PPO) algorithm is proposed, incorporating a reward mechanism based on signal interference to improve UAV coordination in dense urban areas. Simulation results demonstrate that SI-PPO significantly outperforms traditional methods such as Deep Q-Learning (DQN), Simulated Annealing (SA), Greedy Algorithm, and Deep Deterministic Policy Gradient (DDPG) in terms of trajectory optimization, delay reduction, and energy efficiency.

The integration of photovoltaic (PV) systems, electric vehicles (EVs), and charging stations (CSs) faces critical challenges, including PV intermittency, uncertain EV charging demand, and inefficient energy management. Existing strategies often overlook the precision of PV generation forecasts, the economic risks of electricity trading, and the diverse demands of EVs, leading to suboptimal performance. To address these limitations, we propose a two-tier management framework for PV-CS-EV systems, optimizing energy storage charging station (ESCS) operations by balancing profit maximization and risk minimization. The first tier employs accurate PV forecasting and power trading strategies between ESCS, PV farms, and the grid to mitigate economic risks from PV intermittency and market fluctuations. The second tier provides diverse charging strategies to maximize user satisfaction and profit. A key challenge lies in the complex interdependencies between the two tiers, requiring simultaneous optimization of power trading and user-specific charging scheduling under uncertainties. To tackle this, we introduce a hierarchical multi-objective reinforcement learning (MORL) algorithm, which efficiently coordinates decision tasks of both tiers through partial environment information interaction. Experimental results demonstrate the framework’s effectiveness in enhancing the economic performance of PV-CS-EV systems.

Electric vehicles (EVs) represent a critical intelligent terminal within the Internet of Things (IoT). Despite the year-on-year growth in EV penetration, the highway driving experience still requires improvement. Accurate prediction of EV highway charging behavior is crucial to addressing this issue. This article introduces a novel bounded rationality framework to analyze highway charging decisions. Specifically, we utilize the prospect theory to capture the tendency of drivers to reserve more electricity than theoretically necessary. We then propose a Bayesian game in which EV drivers, unaware of others’ decisions, aim to minimize costs, including range anxiety, charging fees, and queuing time. To gain insights into the game, we prove the existence and uniqueness of the Bayesian Nash equilibrium in two practical scenarios. Our numerical experiments, based on real-life data, demonstrate that drivers’ risk aversion tendency significantly influence EV charging decisions, charging demand, queuing lengths at charging stations (CSs), and the departure rate on the highway network. Furthermore, our strategy reduces cumulative EV cost and CSs’ charging costs compared to other benchmarks.

The rapid growth of charging stations (CSs) creates grid challenges, especially with load fluctuations. Optimizing CS management and electricity trading for electricity retailers (ERs) is key for stability. Centralized methods risk privacy leakage, while distributed methods may overfit due to limited electric vehicle (EV) data. To address this, we propose a hierarchical personalized federated reinforcement learning (HPFRL) method for CS management. HPFRL enables CSs to optimize EV pricing and scheduling while balancing load for the ER. It trains local models on private data to ensure personalized decision-making, with a CS aggregator updating models using a similarity-based strategy, protecting privacy and reducing overfitting. The global ER influences CS decisions via real-time electricity pricing, stabilizing the system. We prove the existence of a Nash equilibrium for the ER-CS optimization problem. Experiments show HPFRL achieves high rewards, effectively performing peak shaving and valley filling, demonstrating its practicality.

Cross-domain recommendation (CDR) aims to alleviate the data sparsity problem by leveraging the benefits of modeling two domains. However, existing research often focuses on the recommendation performance while ignores the privacy leakage issue. We find that an attacker can infer user attribute information from the knowledge (e.g., user preferences) transferred between the source and target domains. For example, in our experiments, the average inference accuracies of attack models on gender and age attributes are 0.8323 and 0.3897. The best-performing attack model achieves accuracies of 0.8847 and 0.4634, exceeding a random inference by 25.10% and 64.04%. We can see that the leakage of user attribute information may significantly exceed what would be expected from random inference. In this paper, we propose a novel recommendation framework named CVGAE (short for camouflaged variational graph autoencoder), which effectively models user behaviors and mitigates the risk of user attribute information leakage at the same time. Specifically, our CVGAE combines the strengths of VAEs in capturing latent features and variability with the ability of GCNs in exploiting high-order relational information. Moreover, to ensure against attribute inference attacks without sacrificing the recommendation performance, we design a user attribute protection module that fuses user attribute-camouflaged information with knowledge transfer during cross-domain processes. We then conduct extensive experiments on three real-world datasets, and find our CVGAE is able to achieve strong privacy protection while making little sacrifices in recommendation accuracy.

Fairness has become an important concern in Federated Learning (FL). An unfair model that performs well for some clients while performing poorly for others can reduce the willingness of clients to participate. In this work, we identify a direct cause of unfairness in FL - the use of an unfair direction to update the global model, which favors some clients while conflicting with other clients’ gradients at the model and layer levels. To address these issues, we propose a layer-wise fair Federated Learning algorithm (FedLF). Firstly, we formulate a multi-objective optimization problem with an effective fair-driven objective for FL. A layer-wise fair direction is then calculated to mitigate the model and layer-level gradient conflicts and reduce the improvement bias. We further provide the theoretical analysis on how FedLF can improve fairness and guarantee convergence. Extensive experiments on different learning tasks and models demonstrate that FedLF outperforms the SOTA FL algorithms in terms of accuracy and fairness. The source code is available at https://github.com/zibinpan/FedLF.

Federated Learning (FL) is a machine learning paradigm that safeguards privacy by retaining client data on edge devices. However, optimizing FL in practice can be challenging due to the diverse and heterogeneous nature of the learning system. Though recent research has focused on improving the optimization of FL when distribution shifts occur among clients, ensuring global performance when multiple types of distribution shifts occur simultaneously among clients—such as feature distribution shift, label distribution shift, and concept shift—remain under-explored. In this paper, we identify the learning challenges posed by the simultaneous occurrence of diverse distribution shifts and propose a clustering principle to overcome these challenges. Through our research, we find that existing methods fail to address the clustering principle. Therefore, we propose a novel clustering algorithm framework, dubbed as FedRC, which adheres to our proposed clustering principle by incorporating a bi-level optimization problem and a novel objective function. Extensive experiments demonstrate that FedRC significantly outperforms other SOTA cluster-based FL methods. Our code will be publicly available.

The Internet of Things (IoT) technology connects various aspects of society and enhances human life. Electric vehicles (EVs) and charging stations (CSs) are essential components of the IoT system, offering business opportunities for companies like the aggregator. The aggregator can maximize profit by implementing various CSs management strategies, such as pricing and charging scheduling. However, managing CSs presents challenges due to irrational human behavior, particularly uncertain CS selections by EV users. To address this issue, we propose a cooperative model for CSs that incorporates the cognitive hierarchy quantum response CS selection model. In this model, EV users are considered to possess${k}$-level rationality, and the charging environment is formulated as a Markov decision process (MDP) based on this user model. To make optimal decisions for CSs from the MDP, we propose a denoising autoencoder-based deep reinforcement learning (DEEDRL) method. This method learns from the uncertain environment and effectively denoises the state space using a pretrained autoencoder. In addition, to reduce the computational burden caused by time-varying strategies, we design a discretization strategy for action space based on the current market rule of tiered pricing and CS types. Our experiments with real data demonstrate that our proposed method accurately portrays the CS selection behavior of irrational users in realistic scenarios. Furthermore, our method outperforms noncooperative modes and benchmark cooperative algorithms regarding profitability, such as DDPG and DQN.

This paper presents a novel and practical data-driven approach to sub-optimally allocate charging stations for electric vehicles (EVs) in an early-stage setting. Specifically, we investigate the following problem: For a city with a limited budget for public EV charging infrastructure construction, where should the charging stations be deployed in order to promote the transition of EVs from traditional cars? We develop a$\delta$-nearest model and a$K$-nearest model that can capture people's satisfaction towards a certain design and formulate the early-stage EV charging station placement problem as a monotone submodular maximization problem utilizing fine-grained population, trip, transportation network and POI data. A greedy-based algorithm is proposed to solve the problem efficiently with a provable approximation ratio. A case study of Haikou is provided to demonstrate the effectiveness of our approach.

Battery swapping is a rapid way to recharge electric vehicles (EVs). As more and more entities are involved in building Battery Swapping Stations (BSSs), how non-cooperative BSSs maximize their profit in a competitive market needs further investigation. In this paper, we focus on a practical scenario where competitive BSSs are coordinated by the same aggregator. To study the optimal pricing and battery charging, we formulate a hierarchical game model, where BSSs determine the swapping price in the day-ahead market in the first stage, and then determine the optimal battery charging strategy in the real-time market in the second stage. We rigorously prove the existence and uniqueness of the Subgame Perfect Nash Equilibrium (SPNE). In particular, the uniqueness property provides theoretical support that the strategy under equilibrium is optimal in the competitive environment. Based on the unique SPNE, we propose an optimal pricing and charging strategy for each BSS to maximize profit in the competitive market. A prediction error handling method is also proposed to deal with unexpected fluctuations in swapping demand. Our simulation with a 12-BSS system based on real-life data from Xi’an, China shows that our pricing and charging strategy increases the individual BSS profit by at least 18.1%.

Microservices architecture improves software scalability, resilience, and agility but also poses significant challenges to system reliability due to their complexity and dynamic nature. Identifying and resolving anomalies promptly is crucial because they can quickly propagate to other microservices and cause severe damage to the system. Existing root-cause metric localization approaches rely on metrics or metrics-anomalies correlations but overlook other monitoring data sources (e.g., traces). We are the first to identify and leverage the anomaly-aware monotonic correlation between heterogeneous monitoring data, motivated by which we propose a novel framework, Heterogeneous data sources in Microservice systems for Root Cause Analysis (HeMiRCA) , for hierarchical root cause analysis using Spearman correlation. HeMiRCA is based on the key observation that the microservice responsible for a particular type of fault exhibits a monotonic correlation between the trends of its associated metrics and the trace-based anomaly score of the system. HeMiRCA first calculates time-series anomaly scores using traces and then exploits the correlations between multivariate metrics and the scores to rank the suspicious metrics and microservices. HeMiRCA has been evaluated on two datasets collected from widely used microservice systems. The results show that HeMiRCA outperforms the state-of-the-art approaches by a large margin in identifying root causes at both service level and metric level, achieving a top-1 hit ratio of 82.7% and 74% on average, respectively.

Fairness has been considered as a critical problem in federated learning (FL). In this work, we analyze two direct causes of unfairness in FL - an unfair direction and an improper step size when updating the model. To solve these issues, we introduce an effective way to measure fairness of the model through the cosine similarity, and then propose a federated multiple gradient descent algorithm with fair guidance (FedMDFG) to drive the model fairer. We first convert FL into a multi-objective optimization problem (MOP) and design an advanced multiple gradient descent algorithm to calculate a fair descent direction by adding a fair-driven objective to MOP. A low-communication-cost line search strategy is then designed to find a better step size for the model update. We further show the theoretical analysis on how it can enhance fairness and guarantee the convergence. Finally, extensive experiments in several FL scenarios verify that FedMDFG is robust and outperforms the SOTA FL algorithms in convergence and fairness. The source code is available at https://github.com/zibinpan/FedMDFG.

Federated Learning (FL) is a way for machines to learn from data that is kept locally, in order to protect the privacy of clients. This is typically done using local SGD, which helps to improve communication efficiency. However, such a scheme is currently constrained by slow and unstable convergence due to the variety of data on different clients’ devices. In this work, we identify three under-explored phenomena of biased local learning that may explain these challenges caused by local updates in supervised FL. As a remedy, we propose FedBR, a novel unified algorithm that reduces the local learning bias on features and classifiers to tackle these challenges. FedBR has two components. The first component helps to reduce bias in local classifiers by balancing the output of the models. The second component helps to learn local features that are similar to global features, but different from those learned from other data sources. We conducted several experiments to test FedBR and found that it consistently outperforms other SOTA FL methods. Both of its components also individually show performance gains. Our code is available at https://github.com/lins-lab/fedbr.

The advent of microservice architecture has led to a significant shift in the development of service-oriented software. In particular, the use of Remote Procedure Call (RPC), a mode of Inter-Process Communication (IPC) prevalent in microservices, has noticeably increased. To figure out the relationships between services and obtain a high-level understanding of service-oriented software, a line of recent work focuses on the dynamic construction of service call graphs, which relies on the preliminary deployment of services and only captures the calling relationships within a specific time frame. Meanwhile, static methods avoid the need for pre-deployment and often provide a more stable and complete graph compared to dynamic techniques. However, research and practical applications of static call graph construction remain relatively unexplored. This paper introduces RPCover, a novel gRPC dependency recovery framework that facilitates the interconnection of services across various programming languages using their static gRPC calls. In addition, due to the lack of a multilingual microservice benchmark that uses gRPC, we build the first multilingual benchmark RPCoverBench that contains complex gRPC call relations. RPCover has been evaluated on a single language benchmark (DeathStarBench) and our multilingual benchmark (RPCoverBench). The results show that RPCover effectively recovers 99.33% of the use cases of gRPC calls with less than 200% of the overhead compared with a single-language semantic dependency analyzer.

Partial client participation has been widely adopted in Federated Learning (FL) to reduce the communication burden efficiently. However, an inadequate client sampling scheme can lead to the selection of unrepresentative subsets, resulting in significant variance in model updates and slowed convergence. Existing sampling methods are either biased or can be further optimized for faster convergence. In this paper, we present DELTA, an unbiased sampling scheme designed to alleviate these issues. DELTA characterizes the effects of client diversity and local variance, and samples representative clients with valuable information for global model updates. In addition, DELTA is a proven optimal unbiased sampling scheme that minimizes variance caused by partial client participation and outperforms other unbiased sampling schemes in terms of convergence. Furthermore, to address full-client gradient dependence, we provide a practical version of DELTA depending on the available clients' information, and also analyze its convergence. Our results are validated through experiments on both synthetic and real-world datasets.

In this article, we propose an online datadriven approach that leverages the isolation mechanism for fast event detection with low-quality data measurement. The proposed adaptive and online isolation forest (iForest)based detection (AOIFD) method adopts a hierarchical subspace feature selection scheme to design two levels of detectors. As such, it is capable of differentiating events from low-quality data measurements, preventing false alarms in the presence of low-quality data measurements. We further propose a data augmentation method to address the training data imbalance, which is caused by the rare occurrence of events. Moreover, we propose an adaptive training process to update the AOIFD method so that it can adapt to the time-varying operating conditions of power systems. The proposed AOIFD algorithm is practical in the sense that it is a fast-response method that requires no system modeling information and no global communications. Case studies with both synthetic and realistic PMU data are conducted to validate the effectiveness of the proposed method.

In this paper, we consider an Internet of Electric Vehicles (IoEV) powered by heterogeneous charging facilities in the transportation network. In particular, we take into account the state-of-the-art vehicle-to-grid (V2G) charging and renewable power generation technologies implemented in the charging stations, such that the charging stations differ from each other in their energy capacities, electricity prices, and service types (i.e., with or without V2G capability). In this case, each electric vehicle (EV) user needs to decide which path to take (i.e., the routing problem) and where and how much to charge/discharge its battery at the charging stations in the chosen path (i.e., the charging scheduling problem) such that its journey can be accomplished with the minimum monetary cost and time delay. From the system operator's perspective, we formulate a joint routing and charging scheduling optimization problem for an IoEV network, and show that the problem is NP-hard in general. To tackle the NP-hardness, we propose an approximate algorithm that can achieve affordable computational complexity in large-size IoEV networks. The proposed algorithm allows the routing and charging solution to be calculated in a distributed manner by the system operator and EV users, which can effectively reduce the computational complexity at the system operator and protect the EV users' privacy and autonomy. Besides, a proximal method is introduced to improve the convergence rate of the proposed algorithm. Extensive simulations using real world data show that the proposed distributed algorithm can achieve near-optimal performance with relatively low computational complexity in different system set-ups.

The massive integration of electric vehicles (EVs) will pose great challenges to the stability and efficiency of both the conventional power networks and transportation systems. The recently emerging smart grid technology, which integrates advanced communication, control, and charging infrastructures, provides promising solutions to tackle these challenges. In this paper, we consider a smart-grid enabled EV network with heterogeneous charging facilities of different charging costs and capabilities, e.g., allowing EV to sell energy back to the grid. In this case, an EV user needs to decide which path to take, and where and how much to charge/discharge its battery at charging stations in the chosen path such that its journey can be accomplished with the minimum monetary cost. From the system operator's perspective, we study a joint optimization of the routing selection and charging schedules to maximize the overall consumer surplus of a set of EVs. To reduce the computational complexity of the system operator and signaling exchange, we propose a distributed scheme such that each user can maximize its own profit, and the system operator can also achieve the maximum consumer surplus through limited signaling exchange with the EV users. Our simulation shows that the proposed algorithm could efficiently save energy cost of the users and improve the usage of renewable energy in the power network.