Search Results (226)

With the widespread adoption of cloud computing technology, modern cloud platforms have become increasingly complex and dynamic, posing significant challenges for efficient resource management. Accurate forecasting of cloud resource loads has therefore become essential for improving service quality, optimizing resource utilization, and reducing operational costs. To address the intrinsic characteristics of cloud load time series, including nonlinear fluctuations, multi-scale temporal dependencies, and redundant high-dimensional features, this paper proposes the MST-iTransformer model, which integrates multi-scale temporal encoding, sparse attention, and adaptive feature selection mechanisms. Specifically, a multi-scale temporal encoding module is developed to capture and fuse temporal dependencies across multiple periodic scales. Furthermore, an adaptive feature selection module is introduced to dynamically assign importance weights to resource features, enhancing informative variables while suppressing redundant ones. Meanwhile, a sparse attention mechanism is incorporated to reduce computational overhead while maintaining forecasting accuracy. The proposed model is evaluated on the Alibaba Cluster Trace dataset. Experimental results demonstrate that MST-iTransformer achieves MSE, RMSE, and MAE values of 0.5559, 0.7456, and 0.4968, respectively. Compared with the original iTransformer, the proposed model achieves simultaneous reductions in prediction errors and inference latency, validating the effectiveness of the multi-scale temporal encoding, sparse attention mechanism, and adaptive feature selection modules in improving forecasting accuracy and computational efficiency. These improvements provide reliable prediction support for resource scheduling and elastic scaling in cloud data centers. Full article

Space Station Operation Mission Planning (SSOMP) requires coordinated decisions across long-term activity allocation, mid-term logistics optimization, and short-term execution scheduling and is a key component of autonomous mission operations for high-precision space missions. Existing optimization methods have achieved substantial progress at individual planning levels, but their dependence on problem-specific models, limited support for semantic review of decision rationale, and computational cost restrict their adaptability to multi-level planning scenarios. This paper proposes a Large Language Model (LLM)-assisted framework for multi-level SSOMP. The framework combines Staged Fine-Tuning (Staged-FT), Reflective Constraint–Repair Prompting (RCRP), and LLM-Guided Evolutionary Variation (LGEV). Staged-FT uses a Cognitive-Load-Theory-informed curriculum with Low-Rank Adaptation to adapt general-purpose LLMs to SSOMP domain knowledge. RCRP couples a Deterministic Rule Engine with LLM-based semantic repair to improve hard constraint satisfaction. LGEV embeds the fine-tuned LLM into NSGA-III as a fitness-aware variation operator for multi-objective activity allocation. Three case studies are conducted on literature-derived benchmark scenarios of logistics optimization, emergency re-planning, and activity allocation with logistics design, corresponding to Flight Increment Planning, Short-Term Execution Planning, and Overall Operation Planning, respectively. Results show that Staged-FT produces solutions close to traditional algorithms, RCRP achieves full hard constraint satisfaction in the emergency re-planning and logistics planning cases, and LGEV reduces the convergence generations of NSGA-III while improving Pareto-front quality. The framework provides a constraint-aware approach with explicit reasoning traces that can support expert review of AI-assisted planning for autonomous space mission operations. Full article

With the rapid penetration of electric vehicles (EVs) and renewable energy generation in distribution networks, the coordinated scheduling of flexible EV loads and uncertain renewable resources has become a critical research focus in modern power systems. This study investigates the collaborative optimal dispatch of thermal units, EVs, and renewable power generation. Different from conventional closed-loop game-based bi-level optimization, this paper constructs a transmission–distribution integrated scheduling framework and proposes a sequential hierarchical progressive optimization strategy for EV charging and discharging dispatch to fully tap the cross-level coordination potential of power grids. The upper transmission layer optimizes the joint operation of thermal units, wind power, and photovoltaic units to minimize the overall power supply cost, where the inequality power balance constraint is reasonably adopted to reserve power regulation margin for renewable fluctuation and meet practical engineering operation requirements. To effectively address the severe uncertainty of renewable power output without relying on accurate probability distribution information, information gap decision theory (IGDT) is employed to realize robust scheduling with risk-averse and opportunity-seeking decision adaptability. In the lower distribution layer, a theoretically grounded nodal electricity price (NEP) model integrating node loss sensitivity (NLS) and node load rate (NLR) is applied to substitute iterative power flow calculation, which realizes the spatial optimal allocation of EV charging and discharging nodes while significantly improving computational efficiency. The proposed framework comprehensively minimizes network power loss and user charging cost. Finally, extensive simulations based on the IEEE 33-node distribution system verify the effectiveness, computational superiority, and robustness of the proposed sequential hierarchical coordinated scheduling strategy. Full article

Background: Faricimab 6 mg and aflibercept 8 mg permit extended treatment intervals in neovascular age-related macular degeneration (nAMD), but their pivotal programmes used different loading and maintenance schedules. This study compared treatment burden under the same loading and treat-and-extend protocol and included an exploratory longitudinal analysis of published aggregate visual and anatomical outcomes. Methods: Treatment-specific Dirichlet distributions represented persistent Q8W, Q12W and Q16W capability. Both treatments received injections at weeks 0, 4, 8 and 16, followed by identical four-week extensions from Q8W to Q16W. The primary analysis comprised 30,000 evidence draws, 100,000 paired virtual eyes, a 1.5-million-pair scenario grid and a nested five-million-pair probabilistic analysis. Exploratory multilevel meta-regressions estimated BCVA and change in retinal thickness through week 52; IRF, SRF and complete retinal dryness were analysed separately. Results: Mean injections with faricimab and aflibercept 8 mg were 7.255 and 7.212 at week 52 and 11.522 and 11.144 at week 104. The nested 104-week difference was −0.393 injection (95% uncertainty interval −0.682 to −0.107), but broad source-weight uncertainty included no difference and credible source analyses changed the direction of the contrast. Exploratory week-52 BCVA gains were 5.65 and 6.29 letters, respectively; the difference was 0.64 letter (95% uncertainty interval −1.41 to 2.70) and should be interpreted in the context of three aflibercept 8 mg study families. The expanded retinal-thickness sensitivity model estimated changes of −171.8 and −147.2 micrometres, while the between-treatment direction varied in the three-dose-only analysis. Complete retinal dryness was projected in 57.0% and 69.0% of eyes, respectively, based on three study families per treatment. Conclusions: Use of the same protocol predicted essentially equal one-year burden and a small two-year fixed-weight difference that varied across source choices. The exploratory longitudinal projections, informed by three independent aflibercept 8 mg study families at one year, provide supportive context for the visual and anatomical findings but should be interpreted as hypothesis-generating rather than confirmatory. Full article

Data centers can provide demand-side flexibility by coordinating computing workloads, cooling systems, and on-site energy resources. However, facility demand varies with information technology (IT) load and cooling operation, making a fixed power usage effectiveness (PUE) or a forecast independent of planned controls inconsistent with dispatch. This paper proposes a control-aware, multi-horizon PUE forecasting framework for coordinated data center demand-side management (DSM) and microgrid dispatch. The key idea of this control-aware approach is to forecast PUE using planned workload and cooling schedules as inputs. A power-consistent Temporal Fusion Transformer (PC-TFT) predicts quantiles of non-IT overhead power and rack inlet temperature from telemetry, weather forecasts, admitted requests, and candidate workload and cooling schedules. Facility power and PUE are derived from the algebraic power balance, ensuring consistency among IT, overhead, and facility power and PUE values no lower than 1. Empirical split conformal calibration and temporally dependent scenarios characterize forecast uncertainty. A trajectory-conditioned piecewise-affine control response map with a recursive thermal state links the forecasts to a risk-informed model predictive controller that coordinates workloads, cooling, photovoltaic generation, battery storage, and grid exchange. The proposed framework is validated through EnergyPlus simulations of a Shenzhen data center, coupled with workload and microgrid simulations. Forecasting performance is compared with persistence and matched-input neural baselines, while dispatch is benchmarked against deterministic and oracle controllers. The results demonstrate improved multi-horizon PUE forecasting accuracy and empirical interval calibration, lower operating cost and peak grid demand, higher renewable energy utilization, and fewer service quality violations. These findings indicate that control-aware, power-balance-constrained probabilistic PUE forecasts can provide a reliable basis for coordinated data center DSM and microgrid dispatch. Full article

The economic scheduling of grid-connected microgrids requires the coordinated dispatch of renewable energy sources, controllable distributed generators, battery energy storage systems, and power exchange with the utility grid while satisfying various operational constraints. Owing to the time-varying nature of renewable generation and load demand, this problem often exhibits strong nonlinearity, temporal coupling, and complex constraint characteristics. To enhance the optimization capability of the original Coati Optimization Algorithm (COA) for such constrained scheduling tasks, this paper proposes an Improved Coati Optimization Algorithm, termed ICOA. Different from the original COA, which mainly depends on random initialization, single-best individual guidance, and simple local perturbation, the proposed ICOA redesigns the search process through several urban-traffic-inspired mechanisms. First, a road-network stratified initialization strategy is employed to improve the spatial coverage and diversity of the initial population. Second, a traffic-signal-guided exploration strategy adaptively adjusts the search direction by considering population congestion and elite information. Third, a lane-changing local exploitation operator is introduced to refine promising solutions with the aid of neighborhood information. Finally, a traffic-rule-based repair mechanism is incorporated to enhance the feasibility of candidate scheduling solutions under operational constraints. The performance of ICOA is first assessed on the CEC2017 benchmark suite with 10-, 30-, 50-, and 100-dimensional test settings. The results obtained from convergence curves, boxplots, Wilcoxon signed-rank tests, and Friedman mean rank tests demonstrate that ICOA achieves competitive performance in terms of convergence accuracy, robustness, and scalability when compared with 11 advanced algorithms. In addition, ICOA is applied to a 24 h grid-connected microgrid economic scheduling case. The simulation results show that ICOA obtains the lowest mean operating cost of 1393.58, which is 13.10% lower than that of the best competing algorithm in terms of mean cost. These results suggest that ICOA is an effective and reliable optimization method for both benchmark function optimization and constrained microgrid scheduling problems. Full article

This paper investigates decentralized demand-side management in renewable energy communities with limited and uncertain renewable energy resources. Consumer interactions are modeled as a Bayesian game in which self-interested consumers schedule flexible loads between daytime and nighttime periods to minimize electricity costs under time-of-use tariffs. Consumer heterogeneity is captured through private information describing both risk preferences and forecasts of renewable energy availability. Analytical conditions under which dominant strategies or mixed-strategy Bayesian Nash equilibria (BNE) exist are derived. Based on this analysis, two distributed algorithms that operate without a central coordinator are developed. The first is an iterative best-reply (BR) algorithm, while the second is a novel Demand Agreement (DA) algorithm that directly exploits the equilibrium conditions to reduce computation and communication requirements. The proposed decentralized mechanisms are compared against a centralized social-cost minimization benchmark. The results further demonstrate that the DA algorithm consistently converges to the minimum-cost equilibrium whenever a BNE exists, while requiring substantially lower communication overhead than BR. In contrast, the BR algorithm may converge even when the BNE conditions are not satisfied. Finally, the analysis quantifies the impact of consumer risk preferences and renewable generation uncertainty on BNE existence, scheduling decisions, and overall system performance. Full article

Renewable-dominated power systems need operational digital twins that do more than mirror assets: they must convert streaming evidence into state awareness and secure control actions. This paper presents DT-Grid, a digital twin (DT) framework for real-time state awareness and operational optimization. DT-Grid treats the twin as an evidential control layer with four coupled functions: a topology and data twin, robust temporal state assimilation, confidence-envelope construction, and rolling optimal power flow (OPF). The state-awareness module solves a Huber-weighted, temporally regularized estimation problem and exposes residual information to the optimization layer. The dispatch layer then uses this evidence as a security margin while scheduling conventional generation, renewable acceptance, and corrective actions. We evaluated the framework on the PGLib IEEE 118-bus benchmark driven by Open Power System Data Germany load, wind, and solar profiles over 365 operating points and three measurement seeds. DT-Grid reduced injection root mean square error (RMSE) from 464.6 MW under static weighted least squares (WLS) to 217.0 MW, improved bad-data F1 from 0.140 to 0.149, and reduced the realized overload proxy by 97.9% compared with persistence-driven OPF. The results indicate that state evidence is most valuable when it is carried into dispatch constraints, while pure temporal smoothing can still produce lower phase-angle error in some operating points. Full article

Foundation models for time series forecasting have recently been applied to energy prediction tasks, where they can produce accurate forecasts without task-specific training. This study investigates the impact of two types of covariates, meteorological variables and calendar-based day type indicators, on the forecasting performance of Chronos-2, a state-of-the-art foundation model, in building energy consumption prediction. Using real-world monitoring data from two non-residential buildings at the ENEA Research Centre in Portici, Italy, we systematically evaluate seven configurations combining past and future covariates across multiple observation window lengths (7–28 days). Future meteorological covariates are derived from historical weather forecasts rather than observed weather data, ensuring that the evaluation reflects realistic operational forecasting conditions. The results show that incorporating day type indicators as both past and future covariates consistently delivers the highest forecasting accuracy, reducing CV-RMSE from 14.58% for the covariate-free baseline to 10.41% with a 28-day observation window. A day-stratified analysis further reveals that these improvements are concentrated on regime transition days, for which recent load history alone provides limited information about the operating conditions of the day being forecast. By contrast, meteorological variables, whether obtained from weather forecasts or historical observations, yield only marginal performance gains, suggesting that calendar-driven operational schedules are the primary determinants of energy demand in the buildings considered. These findings provide practical guidance for deploying foundation models in real-world energy building management systems and show that covariate selection is a key determinant of forecasting performance. Full article

With the rise in small-scale distributed photovoltaic (PV) power generation technology, the behind-the-meter PV problem has greatly increased the difficulty of power system regulation and management and accurate net-load forecasting is of great significance to the economic and stable operation of the power system. The timing features of the net-load sequence are complex due to a variety of factors. In order to improve the extraction effect of the timing model on the timing features of the net-load sequence and to increase the accuracy of the net-load prediction, a net-load prediction method considering multidimensional timing information is proposed. A Mamba module is introduced into the model to filter the input data, retaining some of the effective contextual information while improving the operational efficiency of the model. The structure of Bi-Mamba is used to construct a bidirectional time-series feature extraction model, which fuses the date attributes and the positive and negative time-series features of the net load to improve the stability and accuracy of the model prediction. The results of the validation algorithms show that the proposed method can reduce the normalized Mean Absolute Error (nMAE) by 17.72% and the normalized Root Mean Squared Error (nRMSE) by 21.51% compared with the temporal convolutional network (TCN) baseline. Furthermore, the model exhibits robust stability across different seasons and day types, providing a reliable reference for scheduling decisions in power systems with high PV penetration. Full article

To address the challenges of restricted renewable energy accommodation, high carbon emissions, and elevated operating costs in integrated energy systems (IES), this paper proposes a stochastic optimization scheduling method that incorporates the synergy between carbon–green certificate trading and the multi-use applications of hydrogen energy. First, an integrated “electricity–carbon–hydrogen–methanol” model is constructed, incorporating proton exchange membrane (PEM) electrolyzers (ELs), methanol synthesis reactors, hydrogen storage systems, and hydrogen fuel cells (HFCs). Second, a concentrating solar power (CSP) plant coupled with an electric heater (EH) is integrated based on an “electricity–heat–electricity” mechanism. Concurrently, a joint carbon emission trading (CET) and green certificate trading (GCT) mechanism is incorporated into a low-carbon economic dispatch model to minimize total operational costs. On this basis, Information Gap Decision Theory (IGDT) is applied to address source–load uncertainties via risk-averse (RAS) and opportunity-seeking (OSS) strategies. Simulation results demonstrate that the proposed strategy achieves full accommodation of renewable energy. The EH-coupled CSP plant increases thermal output by 4.96%, reducing system carbon emissions by 8.07% compared with the non-EH scenario and decreasing natural gas procurement costs by 14.1%. Furthermore, the joint CET-GCT mechanism overcomes single-market limitations, increasing carbon trading revenues by 298.01% and lowering total operating costs by 39.6% compared with uncoordinated mechanisms. Finally, under IGDT uncertainty analysis, the opportunity-seeking strategy further reduces operating costs by 9.5% compared with the risk-averse strategy, enhancing the system’s low-carbon economic performance and operational flexibility. From the perspective of sustainable development, this study provides a practical dispatch framework for regional integrated energy systems to balance energy security, low-carbon transition and economic cost, offering methodological support for advancing the sustainable transformation of multi-energy systems amid the dual-carbon drive. Full article

Short-term wastewater flow forecasting is essential for pump-station scheduling, influent-load regulation, and overflow-risk warning in wastewater treatment systems. However, wastewater flow series often exhibit strong nonlinearity, large-amplitude fluctuations, and sensitivity to model hyperparameters, which makes accurate real-time prediction challenging. To address these issues, this study proposes an attention-enhanced hybrid deep learning framework optimized by an Improved Harris Hawks Optimisation algorithm. The prediction target is the wastewater flow value at the next target time step, and the model uses only historical wastewater flow observations as input. The framework integrates a Temporal Convolutional Network to extract local fluctuation and multi-scale temporal features, a Bidirectional Long Short-Term Memory network to capture contextual dependencies within the historical input window, and a Simple Attention Module to recalibrate high-dimensional features and emphasize key information. The improved optimisation algorithm further enhances hyperparameter search through hybrid initialization, early-stage differential evolution mutation, stagnation detection with diversity injection, and late-stage Lévy flight perturbation. Experimental results show that the unoptimized Temporal Convolutional Network (TCN)–Bidirectional Long Short-Term Memory (BiLSTM)–Simple Attention Module (SimAM) model achieved an R² of 0.9697, an RMSE of 231.1821, and an MAE of 177.5324 on the validation set. After Improved Harris Hawks Optimization (IHHO) optimization, these values improved to 0.9728, 218.8228, and 161.8777, respectively. Compared with the unoptimized model, Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) were reduced by approximately 5.35% and 8.82%, respectively, while R² increased by 0.0031. These results indicate that the proposed framework improves prediction accuracy, stability, and robustness under the tested conditions. It provides a feasible technical solution for short-term wastewater flow forecasting and supports intelligent operation management of wastewater treatment systems. Full article

Renewable-rich industrial microgrids require scheduling strategies that convert uncertain renewable generation into reliable and physically feasible decisions. This challenge is particularly significant in oilfield microgrids, where photovoltaic (PV) uncertainty is coupled with crude-oil transportation and temperature requirements. This paper proposes a data-driven stochastic scheduling framework for PV-integrated oilfield microgrids using electric thermal storage boilers (ETSBs) as industrial flexibility resources. A convolutional neural network-gated recurrent unit (CNN-GRU) model is combined with probabilistic scenario generation and reduction to characterize PV uncertainty, while a physics-informed multi-objective model coordinates grid-interaction smoothing, operating cost, PV absorption, ETSB dynamics, and pipeline temperature safety. To improve schedule executability, an oilfield-specific non-dominated sorting genetic algorithm II (NSGA-II) solver is developed with thermo-hydraulic simulation, feasibility projection, ramping correction, and terminal sustainability evaluation. Case studies show that the proposed stochastic strategy reduces net-load variance by 56.82% and increases PV absorption by 17.58 percentage points, while maintaining pipeline temperature within 42.0–42.3 °C. Compared with deterministic scheduling, it limits the real-time cost deviation to 0.11%, indicating stronger day-ahead-to-real-time consistency under PV uncertainty. The proposed framework provides practical decision support for renewable-rich oilfield microgrids balancing renewable accommodation, operating economy, and thermo-hydraulic safety. Full article

The increasing diffusion of Renewable Energy Communities offers new opportunities to support vulnerable households through locally generated renewable energy. However, current Home Energy Management Systems mainly optimize energy efficiency and cost reduction, while providing limited support for protecting critical household loads under constrained energy availability. This paper proposes an AI-based Energy Guardianship framework that combines a commissioning phase, in which a Local Appliance Atlas is created from the electrical signatures of the appliances actually installed in a specific dwelling, with an online phase that identifies operating appliances from aggregated measurements and dynamically allocates available energy according to appliance priority. Appliance identification is performed using rich electrical signatures including transient behavior, dynamic V-I trajectories, harmonic information, power profiles, and conventional electrical features extracted from aggregate voltage and current measurements. Unlike conventional home energy management systems, where appliance identification is mainly used to optimize energy consumption, the proposed framework exploits NILM information to support socially aware decisions that preserve critical services while delaying or limiting non-essential loads. A low-cost monitoring architecture is developed to recognize household appliances through electrical signatures and classify loads according to their criticality. When power thresholds are approached, the system recommends demand-side actions, postpones non-essential consumption, and protects critical devices. Preliminary simulation scenarios demonstrate the feasibility of the proposed framework in protecting vulnerable users under limited energy availability while simultaneously improving photovoltaic self-consumption and reducing dependence on grid energy. Although optimization is not the primary objective, the framework naturally supports renewable-aware energy scheduling and future interaction with energy service providers. Full article

Satellite–terrestrial integrated networks (STINs) can extend remote sensor telemetry, remote Internet of Things (IoT), and emergency communication services beyond terrestrial coverage, but their evaluation is complicated by heterogeneous mobility, channel, resource, and control-plane dynamics. This study presents a software-based modular testbed and performance-emulation framework for STINs. The framework integrates scenario generation, model-driven data processing, replaceable algorithm engines, scheduler-based execution control, and a Kafka-style message interface. It models terrestrial, unmanned aerial vehicle, and low-Earth-orbit satellite entities and provides link-budget abstraction, access control, mobility-aware handover, traffic generation, scheduling, load balancing, adaptive routing, and multi-mode transmission for mixed sensing and communication traffic. The representative strategies are evaluated using a lightweight emulation model parameterized by standards-informed NTN and link-budget assumptions. Representative results reveal tradeoffs between access, handover, routing, and scheduling strategies, together with sensitivity to workload, mobility, outage, demand, and selected model parameters. The proposed framework therefore supports traceable STIN strategy evaluation for remote sensor networks, sensing-data backhaul, and remote-IoT service scenarios under explicit emulation assumptions. Full article