Search Results (2,209)

Electricity price uncertainty directly affects the economy and reliability of scheduling, especially when flexible loads are scheduled only according to point forecasts. To improve the coupling between price forecasting uncertainty and load scheduling, this paper proposes a two-stage affine adjustable robust optimization method for flexible loads based on the confidence level of electricity price prediction via an improved hybrid convolutional neural network temporal convolutional network (CNN-TCN) model. An attention-enhanced CNN-TCN model is used to obtain day-ahead electricity price forecasts, and conformalized quantile regression (CQR) is introduced to construct calibrated asymmetric prediction intervals under different confidence levels. The interval bounds are then converted into a budgeted price uncertainty set and embedded in a two-stage affine adjustable robust optimization model for industrial, commercial, and residential loads. The model considers power limits, ramping constraints, total energy requirements, baseline deviation limits, and smoothing penalties, enabling load transfer from high-price periods to low-price periods while preserving operational feasibility. Case studies based on Spanish electricity market data show that the proposed method reduces operating costs under forecast, worst-case, and abnormal disturbance scenarios compared with the original load plan. The results also show that the 90% confidence level provides a suitable balance among cost reduction, risk coverage, and scheduling conservatism in the studied case. Full article

Electricity load forecasting is essential for balancing energy supply and demand, reducing energy waste, and maintaining power grid stability. Accurate forecasts enable power utilities to optimize energy dispatch and mitigate the risk of supply shortages or outages. However, conventional forecasting methods often struggle to capture highly nonlinear local fluctuations in electricity consumption and long-term temporal dependencies. To address these challenges, this study proposes MSCNN-ResLSTM, a hybrid model for multi-step electricity load forecasting. The proposed model integrates Multi-Scale Convolutional Neural Networks (MSCNNs) to extract local time-series features at multiple temporal scales, residual blocks (ResBlocks) to enhance feature representation through residual connections, and Long Short-Term Memory (LSTM) networks to model long-range temporal dependencies. To comprehensively evaluate its effectiveness, a cross-paradigm experimental framework is established in which MSCNN-ResLSTM is compared with seven representative benchmark models from three methodological categories: traditional machine learning (Extreme Gradient Boosting-XGBoost), classical recurrent and convolutional neural networks (LSTM, Temporal Convolutional Network-TCN, CNN-LSTM, MSCNN-LSTM, and Direct LSTM (Seq2Seq)), and self-attention-based architectures (Transformer). Experimental results show that MSCNN-ResLSTM achieves higher forecasting accuracy and greater stability across the full 24-step prediction horizon, consistently outperforming all competing baselines while effectively suppressing recursive error propagation. Full article

Data centers are facing rapidly increasing electricity demand and carbon emissions, while the intermittency of renewable energy creates a significant temporal mismatch between renewable generation and data center load demand. To bridge this temporal mismatch, we propose a coordinated optimization strategy that integrates shared hydrogen energy storage facilities with load scheduling mechanisms. A multi-objective MILP model is formulated to minimize annualized cost, renewable energy curtailment, and carbon emissions. Simulation results show that, compared with the no-shared-station case, the proposed electricity–hydrogen coordination strategy with load shifting yields significant benefits: the annualized total cost decreases from 13.65 to 4.74 million yuan; annual carbon emissions are reduced from 6297 to 1432 tons; and peak-period electricity purchases are reduced from 5373 to 906 MWh. Under the representative daily forecast condition, Scenario S4 achieves zero renewable curtailment when grid export is permitted; therefore, the renewable-electricity utilization rate reaches 100.00% within the model boundary. When grid export is prohibited, the utilization rate decreases to 98.59%, with 179,100 kWh of annualized renewable curtailment. The research findings indicate that integrating shared hydrogen energy storage with the load flexibility of data centers can effectively reduce the system’s overall operating costs, promote the integration of renewable energy, and achieve low-carbon operation. Full article

High photovoltaic (PV) penetration introduces rapid variability, voltage deviations, and increased real-power losses in distribution networks, necessitating control strategies that remain effective under forecast uncertainty. This paper presents a unified Particle Swarm Optimization-based Receding-Horizon Control (PSO-RHC) framework for optimal coordination of multiple Battery Energy Storage Systems (BESSs) in a PV-rich distribution feeder. The controller employs a receding-horizon structure—using horizon-based forecasts, constraint enforcement, and stepwise decision updates—while PSO serves as the optimization engine that computes BESS power setpoints at each prediction step. Deterministic PV and load forecasts are perturbed with stochastic noise to emulate realistic uncertainty, and each candidate solution is evaluated using a forward–backward sweep load-flow model. Simulation results on the IEEE-69 bus system show that the proposed PSO-RHC scheme reduces total daily energy losses from 1467.50 kWh to 1310.19 kWh (10.72% reduction), improves weakest-bus voltages by 1–4%, and maintains all BESS units within operational limits. The normalized objective components remain small (below 0.5%), indicating balanced operation without excessive cycling. These findings demonstrate the effectiveness and simulation-level effectiveness of PSO-based receding-horizon control for enhancing distribution-network performance under uncertain and dynamic PV conditions. Full article

Cloud central processing unit (CPU) utilization forecasting is fundamental to capacity planning, overload warning, elastic scaling, and resource provisioning in cloud computing systems. Conventional forecasting models usually optimize average point-error accuracy, whereas provisioning decisions are often more sensitive to high-load underestimation and upper-bound failures that indicate potential under-provisioning risk. This paper proposes Risk-Aware TimeMixer (RA-TimeMixer), a provisioning-oriented adaptation of Original TimeMixer for machine-level multi-step CPU utilization forecasting. RA-TimeMixer preserves the multiscale forecasting backbone and introduces two targeted risk-oriented components: batch-wise high-load weighted training and residual-based asymmetric upper-bound calibration. Experiments are conducted on a preprocessing-audited 50-machine subset of Alibaba Cluster Trace 2018 with 1 min sampling, input length 96, and prediction lengths 6, 12, and 24. At prediction length 12, RA-TimeMixer reduces High-load MAE, Under-rate high, Under-magnitude high, and Under-MAE when under by 2.72%, 1.89%, 4.06%, and 1.98%, respectively, compared with Original TimeMixer. Machine-level paired analyses, horizon and threshold studies, three-seed stability, persistence-baseline diagnostics, and fully observed-window retraining support the robustness of the observed accuracy–risk trade-off. The results indicate that RA-TimeMixer offers a transparent, risk-sensitive extension of TimeMixer for provisioning-oriented cloud CPU forecasting, while asymmetric calibration reduces empirical upper-bound violations at the cost of wider intervals and margins. Full article

The rapid growth of electric vehicle (EV) adoption has increased the importance of understanding charging behavior and improving the operational sustainability of charging infrastructure. Although existing studies have extensively investigated charging demand forecasting, charging load prediction, and charging behavior analysis, limited attention has been given to evaluating the sustainability of individual charging sessions. To address this gap, this study proposes a Sustainable Charging Session Index (SCSI) framework for assessing and classifying real-world EV charging behaviors based on operational charging characteristics. The proposed framework integrates the Entropy Weight Method (EWM), K-Means clustering, Principal Component Analysis (PCA), Random Forest feature importance analysis, and statistical validation techniques. A real-world dataset comprising 1929 EV charging sessions was analyzed, from which 1795 valid charging records were retained after preprocessing. Charging energy usage, average output power, and charging duration were selected as complementary indicators representing energy delivery effectiveness, charging efficiency, and temporal efficiency, respectively. The EWM assigned the highest weights to charging energy usage (0.5119) and average output power (0.4340), reflecting their greater discriminatory capability within the analyzed dataset. Clustering analysis identified three charging behavior archetypes, namely High-Sustainability Charging Sessions, Low-Sustainability Charging Sessions, and Efficient Charging Sessions. PCA demonstrated clear cluster separation, with the first two principal components explaining 97.9% of the total variance. Statistical analyses confirmed significant differences among the identified charging behavior groups (p < 0.001), while one-way ANOVA demonstrated strong internal consistency between the charging behavior clusters and SCSI scores (η² = 0.730). Furthermore, Random Forest analysis identified charging power as the most influential factor in differentiating charging behaviors. The proposed SCSI framework provides an objective and data-driven approach for charging session sustainability assessment, charging behavior characterization, and sustainable charging infrastructure management. Full article

Machine learning (ML) is increasingly shifting toward data-centric artificial intelligence approaches. In building energy prediction, a data-centric ML approach is essential for achieving reliable and accurate load forecasting. Despite significant advances in algorithmic approaches, data quality remains underexplored, particularly in interdisciplinary research integrating computer science and building energy studies. Unlike generic universal data quality frameworks, this review systematically examines data quality issues in ML-based building energy prediction and refines intrinsic data quality attributes customized for building energy forecasting and AI modeling. Through bibliometric analysis and a structured literature review, this study establishes two conceptual frameworks that distinguish the core dimensions of high- and poor-quality data. Further, a proprietary paired dual framework implements closed-loop data quality benchmarking and defect diagnosis, a key limitation of existing evaluation architectures. Additionally, a three-stage data processing paradigm provides conceptual insights for data handling in building energy applications. The findings reveal a significant research gap concerning data quality in building energy prediction and highlight the need for more integrated, domain-aware approaches to data curation and model training. This review provides researchers and practitioners with methodological references for selecting appropriate strategies to improve data quality, thereby enhancing the robustness and accuracy of ML-based building energy forecasting. Full article

Electric vehicle (EV) charging has a large, spatially clustered, schedulable load whose vehicle-to-grid flexibility can be sold back to the power system. That flexibility has grid value only when the committed quantity can be reliably delivered under uncertainty. Open forecasting benchmarks operators rely on report-only point predictions. The dispatch models that turn forecasts into firm commitments assume a constant round-trip efficiency, so the committed flexibility is systematically over-scheduled. This study contributes two complementary modules, validated separately on public data. The first is a calibrated probabilistic charging forecaster that provides, to our knowledge, the first prediction intervals with reported empirical coverage on the UrbanEV benchmark. It is a gradient-boosted quantile-regression model that combines each zone’s own-history lags with adjacency-weighted neighbor-mean features and exogenous price and calendar inputs. It is calibrated by conformalized quantile regression and scored over thirty zones across a 120-day hourly window. The second is a deliverable-flexibility envelope whose returnable-energy bounds are set by measured, state-of-charge- and rate-dependent vehicle-to-grid (V2G) discharge efficiency rather than a constant round-trip number. These bounds are fit to the measured discharge traces of three V2G-capable vehicles in the Esser bidirectional-charging dataset. Chosen as a lightweight, reproducible baseline, the forecaster keeps its prediction intervals within a five-percentage-point coverage tolerance at both the 80% and 90% nominal levels. Measured coverage is 0.823 and 0.911. It also improves on the continuous ranked probability score of its conformalized-point counterpart at matched point accuracy. This calibration holds across the hyperparameter neighborhood and under data deficiency. On the delivery side, a leave-one-vehicle oracle shows the efficiency-aware envelope short-delivers less than the constant-average-efficiency aggregator on held-out vehicles. Its residual shortfall is 1.21% against the aggregator’s 2.03% at the conservative operating point. The margin widens as commitments grow more aggressive and discharges reach the lowest states of charge. Each of these two measured properties, calibrated demand-side uncertainty and state-dependent discharge physics, imposes a material, separately validated constraint on how much contracted EV flexibility can be delivered, a constraint the point-forecasting frontier leaves unaddressed. Full article

The optimal control of complex energy systems via Bellman’s principle of optimality quickly becomes difficult for high-dimensional, path-dependent dynamics because the state space grows exponentially with each time step. We propose a computationally tractable framework based on hierarchical path-dependency decomposition: (i) graph compression that reduces multi-layer topologies to a single directed flow network; (ii) a diffusion convolutional recurrent neural network (DCRNN) that maps historical trajectories into a finite-dimensional hidden state, approximating the transport of past states without storing full trajectories; and (iii) multi-agent reinforcement learning (MARL) for decentralized local control. By restricting full-path online optimization to a rolling one-step horizon and using temperature and flow rate as sufficient statistics for thermal dynamics, the framework preserves physical fidelity while enabling real-time execution. This reduction is justified because thermal constraints constitute the primary active failure mode in energy systems. We provide a proof sketch showing that the diffusion convolution operation in the DCRNN approximates the Green’s function of the underlying transport equation. Using weather data from Palm Springs, California (a region with moderate path dependency), initial numerical experiments achieve 98.4% correlation with reference solutions, a temperature forecasting mean absolute error (MAE) of 1.23 °C, and mostly subsecond (<1 s) inference times using consumer-grade hardware. Despite the thermodynamic advantages of concentrated solar thermal (CST) systems over conventional photovoltaic panels—higher conversion efficiency and integrated thermal storage—their deployment on factory rooftops remains elusive due to the continuous, real-time control burden they impose. The proposed framework directly addresses this barrier by delivering accuracy comparable to classical controllers (MPC, PID) with latency sufficient for real-time intervention, positioning CST for transition from remote desert locations to distributed industrial sites. Beyond solar-thermal generation, the same hierarchical architecture is applicable to integrated HVAC system control (e.g., using movable mirrors to both produce renewable energy and reduce cooling loads in data centers), energy storage management, desalination plant control, and chemical production optimization—any domain where thermal-hydraulic transport must be regulated under tight safety and latency constraints. The framework demonstrates that trading exact Bellman optimality for data-driven approximations enables a shift from offline simulation to sensor-driven real-time regulation across this broader class of energy systems. Full article

With the advancement of global energy conservation and emission reduction, hydrogen-powered ships (HPSs) have received great attention. However, the current drainage volume of HPSs is generally small, and its operating load fluctuates greatly due to the influence of hydrological and meteorological conditions in the waterway. Therefore, a reasonable energy management strategy (EMS) is needed to allocate the output of hydrogen fuel cells (HFCs) and lithium batteries (LBs). This article proposes a two-stage EMS framework for HPSs based on dynamic empirical modeling and model predictive control (DEM-MPC) to achieve optimal operational energy efficiency of the HFC-LB energy supply system. Firstly, a DEM probabilistic load forecasting (PLF) model was established by combining the operational status data of an HPS system with the meteorological data of waterway water level. The DEM model was constructed using delay coordinate embedding (DCE) and nearest neighbor prediction (NNP) methods to obtain future multi-step PLF sequences as important reference information for the EMS. Subsequently, the PLF sequence is used as input for MPC to optimize the output allocation of the EMS. In the first stage of MPC, the efficiency of HFCs and LBs is optimized, and in the second stage, the comprehensive cost is optimized. Finally, the method was validated using actual data from an HPS in the Yangtze River waterway. The results indicate that the proposed DEM-MPC framework significantly improves the overall operational energy efficiency of HPSs. Full article

Scrap-based electric arc furnace (EAF) steelmaking powered by on-site variable renewable energy is a key decarbonisation route, but the heteroscedastic, non-Gaussian nature of joint wind–photovoltaic forecast errors makes the EAF—a large, metallurgically constrained load—hard to coordinate with on-site generation under feeder limits. We develop a unified stochastic dispatch and adaptive setpoint-control framework. A chance-constrained dispatch over a zone-wise Beta uncertainty model is propagated through a degree-two polynomial chaos expansion (PCE) and reformulated as a second-order cone programme via the Cantelli inequality, with EAF-specific metallurgical constraints (electrode slew, short-circuit-ratio-tied flicker, stage-dependent melt-power floor, multi-stage tap-to-tap profile) embedded by the same procedure. The EAF setpoint gain is then extracted in closed form—without Jacobian inversion—as a ratio of first-order PCE coefficients, so it inherits the dispatch’s 95% feeder-security guarantee. Calibrated on 24 months of real wind/PV data for a Qingdao site (ERA5 reanalysis vs. archived ECMWF-IFS forecast), which confirms the heteroscedastic premise and a measured wind–PV error correlation of 0.015, the extracted gain scales across the Low–Mid–High zones (medians 6.07, 11.91, 17.22 p.u.) following the operating regime rather than the disturbance magnitude. The scheme bounds worst-case tracking below 1.18 MW per zone (vs. up to 3.34 MW for no droop), satisfies the feeder limit in 100% of realisations, matches model-predictive control without online optimisation, and lowers within-EAF specific CO₂ emissions by 4.4% versus no droop. An out-of-sample test on real records confirms a decisive advantage in the data-rich zones and, candidly, a shortfall in the data-limited high-wind zone. Full article

Accurate short-term load forecasting is essential for power system operations, including unit commitment, economic dispatch, and reserve scheduling. Regional load series exhibit temporal variation and horizon-dependent dynamics that make multi-horizon forecasting challenging. This paper proposes a bidirectional gated recurrent unit-based multi-head joint forecasting framework (EA-BiGRU-Multi) for one-step, six-step, and 24-step-ahead electricity load prediction. A shared recurrent encoder captures temporal dependencies from historical observations, while horizon-specific forecasting heads produce separate predictions for each lead time. A terminal-anchor injection strategy incorporates day-ahead demand information only at the forecast origin, preserving the distinction between historical observations and known-future priors. Feature-channel recalibration adjusts heterogeneous input contributions before temporal encoding. Experiments on three regional load zones from a regional independent system operator in the northeastern United States show that the proposed model achieves competitive multi-horizon performance. In the Southeast Massachusetts six-step-ahead case, the proposed model increases the mean coefficient of determination from 0.7604 to 0.8346 and reduces the mean absolute error from 100.44 MW to 79.07 MW compared with the linear baseline. Ablation analysis confirms that the terminal-anchor prior is essential for medium- and long-horizon accuracy. The results indicate that model suitability depends jointly on forecast horizon, regional load characteristics, and availability of forecast-origin demand information. Full article

The large-scale integration of wind and solar power has significantly intensified peak-shaving pressure and operational risk in provincial power grids. Effectively leveraging the flexible regulation capability of hydropower to mitigate the uncertainty of wind and solar output is a promising approach to enhancing grid security and stability. To simultaneously improve the peak-shaving performance and risk resilience of hydro-wind-solar systems for a provincial power grid, this paper proposes a multi-objective short-term scheduling model that jointly minimizes the peak value of net load and the Conditional Value-at-Risk (CVaR) of flexibility shortage. Specifically, the residual peak load is used to quantify the system’s peak-shaving burden, while the average CVaR of upward/downward ramping deficits across all time periods characterizes the tail risk associated with insufficient flexibility. Historical wind and solar forecast error data are employed to generate representative uncertainty scenarios via Gaussian mixture model, and the Rockafellar–Uryasev formulation is adopted to accurately embed CVaR into a mixed-integer linear programming (MILP) framework. Furthermore, the normalized normal constraint (NNC) method is introduced to compute a well-distributed Pareto front. Numerical simulations based on a real-world hydro-wind-solar system in a provincial grid in Southwest China demonstrate that the proposed model can significantly reduce the peak load while effectively mitigating flexibility shortfall risk. The resulting Pareto front clearly reveals the trade-off between peak-shaving effectiveness and risk control, providing a scientific basis for day-ahead generation scheduling and coordinated dispatch of flexible resources. Full article

Short-term electricity demand forecasting is a critical enabler of the secure and efficient operation of modern power systems, particularly amid increasing renewable energy integration, smart grid expansion, and the broader energy transition. This paper presents a rigorous comparative analysis of electricity demand forecasting models, encompassing statistical methods, Machine Learning (ML), Deep Learning (DL), and hybrid architectures. A structured taxonomy is proposed to classify models according to their methodological family, application horizon, and data requirements, thereby providing a unified reference framework for researchers and energy-sector practitioners. Models are evaluated using a multi-criteria framework comprising accuracy, robustness, scalability, interpretability, computational cost, and the capacity to handle exogenous variables. The analysis identifies critical research gaps, including the limited integration of probabilistic forecasting into operational contexts and the absence of standardized evaluation protocols under real-world conditions. Future research directions are outlined, with particular emphasis on uncertainty quantification, adaptive learning strategies, and hierarchical forecast coherence in systems with high penetration of distributed energy resources. Full article

Short-term power load forecasting is fundamental to the secure operation and optimal dispatch of modern power systems. This study proposes an Improved Pied Kingfisher Optimization–Temporal Convolutional Network–Bidirectional Gated Recurrent Unit (IPKO-TCN-BiGRU) model to address the challenges of strong non-stationarity, high randomness, and multi-factor coupling in load time series. The model employs a multi-scale TCN for simultaneous extraction of local and global temporal features, a BiGRU enhanced with an Improved Self-Attention (ISA) mechanism for bidirectional dependency modeling, and an Autoregressive (AR) module combined with an election mechanism to jointly capture linear and nonlinear load components. The Improved Pied Kingfisher Optimization (IPKO) algorithm—incorporating SPM chaotic initialization, a planetary optimization strategy, and adaptive t-distribution perturbation—is applied to globally optimize key hyperparameters, demonstrating superior convergence accuracy and global search capability over the original PKO and other benchmark optimizers. To ensure evaluation integrity, dataset splitting precedes all normalization operations, with StandardScaler fitted exclusively on the training set and applied to the test set without leakage. Validation is conducted on two benchmark datasets: a U.S. residential electricity load dataset (hourly, 2012, 13-dimensional features including HVAC and lighting systems) and a China Electrical Engineering Mathematical Modeling Competition dataset (15 min intervals, three years, enriched with five meteorological variables). The U.S. dataset exhibits a clear annual double-peak seasonal pattern, while the Chinese dataset shows strong intraday fluctuations significantly coupled with temperature and humidity, both posing substantial forecasting challenges. On the U.S. dataset, the proposed model achieves MAE = 0.0190 kW, RMSE = 0.0301 kW, MAPE = 1.7673%, and R² = 0.9947; on the China dataset, MAE = 79.8125 MW, RMSE = 109.4154 MW, MAPE = 1.1124%, and R² = 0.9955. The proposed model consistently outperforms six mainstream baseline models—including Transformer, Autoformer, and FEDformer—reducing RMSE by up to 34.4% and 18.9% on the two datasets, respectively, while maintaining a compact architecture of 15.2 MB and 74.6–78.9 MFLOPs. Ablation experiments confirm the significant and synergistic contribution of each module, and the direct comparison between PKO-TCN-BiGRU and IPKO-TCN-BiGRU validates that the algorithmic improvements translate into measurable forecasting gains beyond benchmark function optimization. The proposed model is most suitable for ultra-short-term to short-term single-step-ahead forecasting within a horizon of 15 min to 24 h, with an inference latency of 2.3–2.7 ms per sample, fully meeting the real-time requirements of practical power dispatching systems. Full article