To address the challenges of limited Battery Swap Stations datasets, high operational costs, and fluctuating user charging demand, this research proposes a probability estimation model based on charging pile data and constructs nine scenario-specific battery swap demand datasets. In addition, this study combines Least Recently Used strategy with Genetic Algorithm and incorporates a guided search mechanism, which effectively enhances the global optimization capability. Thus, a dual-factor decision-making based charging schedule optimization system is constructed. Experimental results show that the constructed datasets exhibit stable trend characteristics, adhering to 24-hour and 168-hour periodicity patterns, with outlier ratios consistently below 3.26%, confirming data validity. Compared to baseline, the improved algorithm achieves better fitness individuals in 80% of test regions under the same iterations. When benchmarked against immediate swap-and-charge strategy, our algorithm achieves a peak cost reduction of 13.96%. Moreover, peak user satisfaction reaches 98.57%, while the average iteration time remains below 0.6 seconds, demonstrating good computational efficiency. The complete datasets and optimization algorithm are open-sourced at https://github.com/qingshufan/GA-EVLRU.
Predictive maintenance is a key strategy for ensuring the reliability and efficiency of industrial systems. This study investigates the use of supervised learning models to diagnose the condition of electric motors, categorizing them as "Healthy," "Needs Preventive Maintenance (PM)," or "Broken." Key features of motor operation were employed to train various machine learning algorithms, including Naive Bayes, Support Vector Machines (SVM), Regression models, Random Forest, k-Nearest Neighbors (k-NN), and Gradient Boosting techniques. The performance of these models was evaluated to identify the most effective classifier for predicting motor health. Results showed notable differences in accuracy among the models, with one emerging as the best-performing solution. This study underscores the practicality of using supervised learning for electric motor diagnostics, providing a foundation for efficient maintenance scheduling and minimizing unplanned downtimes in industrial applications.
Modular batteries can be aggregated to deliver frequency regulation services for power grids. Although utilizing the idle capacity of battery modules is financially attractive, it remains challenging to consider the heterogeneous module-level characteristics such as dynamic operational efficiencies and battery degradation. In addition, real-time decision making within seconds is required to enable fast frequency response. In order to address these issues, this paper proposes a performance-aware scheduling approach for battery modules to deliver fast frequency response (FFR) support. In particular, the conduction loss and switching loss of battery packs as well as converters are captured within a mix-integer quadratic constrained program (MIQCP). The cycle-based aging model identifies the aging cost of battery modules during frequent cycling by introducing the aging subgradient calculation and linearization. Case studies based on real-world battery data show that the proposed scheduling approach can effectively reduce power loss cost by nearly 28%-57% and battery aging cost by 4%-15% compared to conventional methods, which can also enhance the SoC balance.
The transition to intelligent, low-carbon power systems necessitates advanced optimization strategies for managing renewable energy integration, energy storage, and carbon emissions. Generative Large Models (GLMs) provide a data-driven approach to enhancing forecasting, scheduling, and market operations by processing multi-source data and capturing complex system dynamics. This paper explores the role of GLMs in optimizing load-side management, energy storage utilization, and electricity carbon, with a focus on Smart Wide-area Hybrid Energy Systems with Storage and Carbon (SGLSC). By leveraging spatiotemporal modeling and reinforcement learning, GLMs enable dynamic energy scheduling, improve grid stability, enhance carbon trading strategies, and strengthen resilience against extreme weather events. The proposed framework highlights the transformative potential of GLMs in achieving efficient, adaptive, and low-carbon power system operations.
Reinforcement learning (RL) provides a powerful method to address problems in operations research. However, its real-world application often fails due to a lack of user acceptance and trust. A possible remedy is to provide managers with the possibility of altering the RL policy by incorporating human expert knowledge. In this study, we analyze the benefits and caveats of including human knowledge via action masking. While action masking has so far been used to exclude invalid actions, its ability to integrate human expertise remains underexplored. Human knowledge is often encapsulated in heuristics, which suggest reasonable, near-optimal actions in certain situations. Enforcing such actions should hence increase trust among the human workforce to rely on the model's decisions. Yet, a strict enforcement of heuristic actions may also restrict the policy from exploring superior actions, thereby leading to overall lower performance. We analyze the effects of action masking based on three problems with different characteristics, namely, paint shop scheduling, peak load management, and inventory management. Our findings demonstrate that incorporating human knowledge through action masking can achieve substantial improvements over policies trained without action masking. In addition, we find that action masking is crucial for learning effective policies in constrained action spaces, where certain actions can only be performed a limited number of times. Finally, we highlight the potential for suboptimal outcomes when action masks are overly restrictive.
This paper investigates the secrecy performance of a keyhole-aided multi-user communication network in the presence of multiple eavesdroppers. The communication happens through the same keyhole for legitimate users and eavesdroppers. In this context, the secrecy performance is evaluated for a user scheduling technique by obtaining the exact closed-form expression of secrecy outage probability (SOP). Further, a simplified asymptotic SOP expression is derived assuming high signal-to-noise ratio (SNR) scenario for a better understanding of the impact of system parameters. The effect of the keyhole parameters, number of users, number of eavesdroppers, and threshold secrecy rate on the SOP performance are also investigated for the considered system model. In the high-SNR regime, the asymptotic SOP saturates to a constant value and does not depend on the keyhole parameter and the channel parameter of the source-to-keyhole channel.
Diffusion probabilistic models (DPMs), while effective in generating high-quality samples, often suffer from high computational costs due to their iterative sampling process. To address this, we propose an enhanced ODE-based sampling method for DPMs inspired by Richardson extrapolation, which reduces numerical error and improves convergence rates. Our method, RX-DPM, leverages multiple ODE solutions at intermediate time steps to extrapolate the denoised prediction in DPMs. This significantly enhances the accuracy of estimations for the final sample while maintaining the number of function evaluations (NFEs). Unlike standard Richardson extrapolation, which assumes uniform discretization of the time grid, we develop a more general formulation tailored to arbitrary time step scheduling, guided by local truncation error derived from a baseline sampling method. The simplicity of our approach facilitates accurate estimation of numerical solutions without significant computational overhead, and allows for seamless and convenient integration into various DPMs and solvers. Additionally, RX-DPM provides explicit error estimates, effectively demonstrating the faster convergence as the leading error term's order increases. Through a series of experiments, we show that the proposed method improves the quality of generated samples without requiring additional sampling iterations.
Self-driving labs are transforming drug discovery by enabling automated, AI-guided experimentation, but they face challenges in orchestrating complex workflows, integrating diverse instruments and AI models, and managing data efficiently. Artificial addresses these issues with a comprehensive orchestration and scheduling system that unifies lab operations, automates workflows, and integrates AI-driven decision-making. By incorporating AI/ML models like NVIDIA BioNeMo - which facilitates molecular interaction prediction and biomolecular analysis - Artificial enhances drug discovery and accelerates data-driven research. Through real-time coordination of instruments, robots, and personnel, the platform streamlines experiments, enhances reproducibility, and advances drug discovery.
Quantum generative models offer a promising new direction in machine learning by leveraging quantum circuits to enhance data generation capabilities. In this study, we propose a hybrid quantum-classical image generation framework that integrates variational quantum circuits into a diffusion-based model. To improve training dynamics and generation quality, we introduce two novel noise strategies: intrinsic quantum-generated noise and a tailored noise scheduling mechanism. Our method is built upon a lightweight U-Net architecture, with the quantum layer embedded in the bottleneck module to isolate its effect. We evaluate our model on MNIST and MedMNIST datasets to examine its feasibility and performance. Notably, our results reveal that under limited data conditions (fewer than 100 training images), the quantum-enhanced model generates images with higher perceptual quality and distributional similarity than its classical counterpart using the same architecture. While the quantum model shows advantages on grayscale data such as MNIST, its performance is more nuanced on complex, color-rich datasets like PathMNIST. These findings highlight both the potential and current limitations of quantum generative models and lay the groundwork for future developments in low-resource and biomedical image generation.
The embedding of Large Language Models (LLMs) into autonomous agents is a rapidly developing field which enables dynamic, configurable behaviours without the need for extensive domain-specific training. In our previous work, we introduced SANDMAN, a Deceptive Agent architecture leveraging the Five-Factor OCEAN personality model, demonstrating that personality induction significantly influences agent task planning. Building on these findings, this study presents a novel method for measuring and evaluating how induced personality traits affect task selection processes - specifically planning, scheduling, and decision-making - in LLM-based agents. Our results reveal distinct task-selection patterns aligned with induced OCEAN attributes, underscoring the feasibility of designing highly plausible Deceptive Agents for proactive cyber defense strategies.
Modern sensing and monitoring applications typically consist of sources transmitting updates of different sizes, ranging from a few bytes (position, temperature, etc.) to multiple megabytes (images, video frames, LIDAR point scans, etc.). Existing approaches to wireless scheduling for information freshness typically ignore this mix of large and small updates, leading to suboptimal performance. In this paper, we consider a single-hop wireless broadcast network with sources transmitting updates of different sizes to a base station over unreliable links. Some sources send large updates spanning many time slots while others send small updates spanning only a few time slots. Due to medium access constraints, only one source can transmit to the base station at any given time, thus requiring careful design of scheduling policies that takes the sizes of updates into account. First, we derive a lower bound on the achievable Age of Information (AoI) by any transmission scheduling policy. Second, we develop optimal randomized policies that consider both switching and no-switching during the transmission of large updates. Third, we introduce a novel Lyapunov function and associated analysis to propose an AoI-based Max-Weight policy that has provable constant factor optimality guarantees. Finally, we evaluate and compare the performance of our proposed scheduling policies through simulations, which show that our Max-Weight policy achieves near-optimal AoI performance.
Transformers are the cornerstone of modern large language models, but their quadratic computational complexity limits efficiency in long-sequence processing. Recent advancements in Mamba, a state space model (SSM) with linear complexity, offer promising efficiency gains but suffer from unstable contextual learning and multitask generalization. This paper proposes TransMamba, a novel framework that unifies Transformer and Mamba through shared parameter matrices (e.g., QKV and CBx), and thus could dynamically switch between attention and SSM mechanisms at different token lengths and layers. We design the Memory converter to bridge Transformer and Mamba by converting attention outputs into SSM-compatible states, ensuring seamless information flow at TransPoints where the transformation happens. The TransPoint scheduling is also thoroughly explored for further improvements. We conducted extensive experiments demonstrating that TransMamba achieves superior training efficiency and performance compared to baselines, and validated the deeper consistency between Transformer and Mamba paradigms, offering a scalable solution for next-generation sequence modeling.
Quantum or quantum-inspired Ising machines have recently shown promise in solving combinatorial optimization problems in a short time. Real-world applications, such as time division multiple access (TDMA) scheduling for wireless multi-hop networks and financial trading, require solving those problems sequentially where the size and characteristics change dynamically. However, using Ising machines involves challenges to shorten system-wide latency due to the transfer of large Ising model or the cloud access and to determine the parameters for each problem. Here we show a combinatorial optimization method using embedded Ising machines, which enables solving diverse problems at high speed without runtime parameter tuning. We customize the algorithm and circuit architecture of the simulated bifurcation-based Ising machine to compress the Ising model and accelerate computation and then built a machine learning model to estimate appropriate parameters using extensive training data. In TDMA scheduling for wireless multi-hop networks, our demonstration has shown that the sophisticated system can adapt to changes in the problem and showed that it has a speed advantage over conventional methods.
In this paper, an operating system scheduling algorithm based on Double DQN (Double Deep Q network) is proposed, and its performance under different task types and system loads is verified by experiments. Compared with the traditional scheduling algorithm, the algorithm based on Double DQN can dynamically adjust the task priority and resource allocation strategy, thus improving the task completion efficiency, system throughput, and response speed. The experimental results show that the Double DQN algorithm has high scheduling performance under light load, medium load and heavy load scenarios, especially when dealing with I/O intensive tasks, and can effectively reduce task completion time and system response time. In addition, the algorithm also shows high optimization ability in resource utilization and can intelligently adjust resource allocation according to the system state, avoiding resource waste and excessive load. Future studies will further explore the application of the algorithm in more complex systems, especially scheduling optimization in cloud computing and large-scale distributed environments, combining factors such as network latency and energy efficiency to improve the overall performance and adaptability of the algorithm.
By provisioning inference offloading services, edge inference drives the rapid growth of AI applications at the network edge. However, achieving high task throughput with stringent latency requirements remains a significant challenge. To address this issue, we develop a parameter-sharing AI model loading (PartialLoading) framework for multi-user edge inference, which exploits two key insights: 1) the majority of latency arises from loading AI models into server GPU memory, and 2) different AI models can share a significant number of parameters, for which redundant loading should be avoided. Towards this end, we formulate a joint multi-user scheduling and spectrum bandwidth allocation problem to maximize task throughput by exploiting shared parameter blocks across models. The intuition is to judiciously schedule user requests to reuse the shared parameter blocks between consecutively loaded models, thereby reducing model loading time substantially. To facilitate solution finding, we decouple the problem into two sub-problems, i.e., user scheduling and bandwidth allocation, showing that solving them sequentially is equivalent to solving the original problem. Due to the NP-hardness of the problem, we first study an important special case called the "bottom-layer-sharing" case, where AI models share some bottom layers within clusters, and design a dynamic programming-based algorithm to obtain the optimal solution in polynomial time. For the general case, where shared parameter blocks appear at arbitrary positions within AI models, we propose a greedy heuristic to obtain the sub-optimal solution efficiently. Simulation results demonstrate that the proposed framework significantly improves task throughput under deadline constraints compared with user scheduling without exploiting parameter sharing.
Video Large Language Models (Video LLMs) have achieved significant success by leveraging a two-stage paradigm: pretraining on large-scale video-text data for vision-language alignment, followed by supervised fine-tuning (SFT) for task-specific capabilities. However, existing approaches struggle with temporal reasoning due to weak temporal correspondence in the data and reliance on the next-token prediction paradigm during training. To address these limitations, we propose TEMPLE (TEMporal Preference Learning), a systematic framework that enhances Video LLMs' temporal reasoning capabilities through Direct Preference Optimization (DPO). To facilitate this, we introduce an automated preference data generation pipeline that systematically constructs preference pairs by selecting videos that are rich in temporal information, designing video-specific perturbation strategies, and finally evaluating model responses on clean and perturbed video inputs. Our temporal alignment features two key innovations: curriculum learning which that progressively increases perturbation difficulty to improve model robustness and adaptability; and "Pre-SFT Alignment'', applying preference optimization before instruction tuning to prioritize fine-grained temporal comprehension. Extensive experiments demonstrate that our approach consistently improves Video LLM performance across multiple benchmarks with a relatively small set of self-generated DPO data. We further analyze the transferability of DPO data across architectures and the role of difficulty scheduling in optimization. Our findings highlight our TEMPLE as a scalable and efficient complement to SFT-based methods, paving the way for developing reliable Video LLMs. Code is available at https://github.com/lscpku/TEMPLE.
Scalable and reproducible policy evaluation has been a long-standing challenge in robot learning. Evaluations are critical to assess progress and build better policies, but evaluation in the real world, especially at a scale that would provide statistically reliable results, is costly in terms of human time and hard to obtain. Evaluation of increasingly generalist robot policies requires an increasingly diverse repertoire of evaluation environments, making the evaluation bottleneck even more pronounced. To make real-world evaluation of robotic policies more practical, we propose AutoEval, a system to autonomously evaluate generalist robot policies around the clock with minimal human intervention. Users interact with AutoEval by submitting evaluation jobs to the AutoEval queue, much like how software jobs are submitted with a cluster scheduling system, and AutoEval will schedule the policies for evaluation within a framework supplying automatic success detection and automatic scene resets. We show that AutoEval can nearly fully eliminate human involvement in the evaluation process, permitting around the clock evaluations, and the evaluation results correspond closely to ground truth evaluations conducted by hand. To facilitate the evaluation of generalist policies in the robotics community, we provide public access to multiple AutoEval scenes in the popular BridgeData robot setup with WidowX robot arms. In the future, we hope that AutoEval scenes can be set up across institutions to form a diverse and distributed evaluation network.
We investigate the peak age of information (PAoI) in underwater wireless sensor networks (UWSNs), where Internet of underwater things (IoUT) nodes transmit the latest packets to the sink node, which is in charge of adjusting the sleep-scheduling to match network demands. In order to reduce PAoI, we propose active queue management (AQM) policy of the IoUT node, beneficially compresses the packets having large waiting time. Moreover, we deduce the closed-form expressions of the average PAoI as well as the energy cost relying on probability generating function and matrix-geometric solutions. Numerical results verify that the IoUT node relying on the AQM policy has a lower PAoI and energy cost in comparison to those using non-AQM policy.
The widespread adoption of Large Language Models (LLMs) has enabled diverse applications with very different latency requirements. Existing LLM serving frameworks rely on siloed infrastructure with coarse-grained workload segregation -- interactive and batch -- leading to inefficient resource utilization and limited support for fine-grained Quality-of-Service (QoS) differentiation. This results in operational inefficiencies, over-provisioning and poor load management during traffic surges. We present Niyama, a novel QoS-driven inference serving system that enables efficient co-scheduling of diverse workloads on shared infrastructure. Niyama introduces fine-grained QoS classification allowing applications to specify precise latency requirements, and dynamically adapts scheduling decisions based on real-time system state. Leveraging the predictable execution characteristics of LLM inference, Niyama implements a dynamic chunking mechanism to improve overall throughput while maintaining strict QoS guarantees. Additionally, Niyama employs a hybrid prioritization policy that balances fairness and efficiency, and employs selective request relegation that enables graceful service degradation during overload conditions. Our evaluation demonstrates that Niyama increases serving capacity by 32% compared to current siloed deployments, while maintaining QoS guarantees. Notably, under extreme load, our system reduces SLO violations by an order of magnitude compared to current strategies.
Approximate Nearest Neighbor Search (ANNS) is essential for modern data-driven applications that require efficient retrieval of top-k results from massive vector databases. Although existing graph-based ANNS algorithms achieve a high recall rate on billion-scale datasets, their slow construction speed and limited scalability hinder their applicability to large-scale industrial scenarios. In this paper, we introduce SOGAIC, the first Scalable Overload-Aware Graph-Based ANNS Index Construction system tailored for ultra-large-scale vector databases: 1) We propose a dynamic data partitioning algorithm with overload constraints that adaptively introduces overlaps among subsets; 2) To enable efficient distributed subgraph construction, we employ a load-balancing task scheduling framework combined with an agglomerative merging strategy; 3) Extensive experiments on various datasets demonstrate a reduction of 47.3% in average construction time compared to existing methods. The proposed method has also been successfully deployed in a real-world industrial search engine, managing over 10 billion daily updated vectors and serving hundreds of millions of users.