Key Takeaways & Executive Findings
- •• • Beta distribution shape parameters for four weather types are empirically fitted as clear-sky sparse-cloud (α=6.5, β=2.3), cloudy (α=β=0.92), overcast (α=3.8, β=4.4), and rain-snow (α=1.5, β=3.5); these parameters directly govern the confidence interval width used for TES reserve sizing, with cloudy conditions exhibiting the highest relative uncertainty (192.10%) and coefficient of variation (0.5934), mandating wider probabilistic reserve margins than deterministic scheduling would allocate. • • Confidence interval sensitivity analysis quantifies relative uncertainty at 76.96% for clear-sky sparse-cloud, 192.10% for cloudy, 132.22% for overcast, and 184.71% for rain-snow, with corresponding variances of 0.0197, 0.0880, 0.0270, and 0.0350; these metrics establish that cloudy and rain-snow regimes require the most conservative TES reservation, directly impacting capital allocation for storage capacity and operational risk exposure. • • The 72 h–24 h bi-level PSO architecture treats the first 48 h as deterministic and the final 24 h as probabilistic interval data, yielding a TES energy reserve interval that is subsequently resolved into a minimum expected cost dispatch; this decomposition avoids the computational intractability of full-horizon stochastic rolling optimization while capturing cross-day state-variable coupling that day-ahead and intra-day scheduling cannot address. • • The proposed strategy achieves coordinated optimization of long-timescale TES energy configuration and dispatch cost across multiple uncertainty scenarios, outperforming conventional scheduling by avoiding both excessive TES reservation (which inflates storage cost) and insufficient reservation (which incurs loss-of-load shutdown risk); the minimum expected cost corresponds to the system optimal irradiance operating point, providing a quantifiable decision threshold for cross-day dispatch.
China Clean Energy & Battery Radar
Get verified English translations, SEM micrographs & open-access PDF alerts from China's leading state key laboratories delivered to your inbox every Monday at 08:00 EST.
Abstract
Cross-day scheduling of photovoltaic-concentrated solar power (PV-CSP) integrated energy systems is constrained by low solar irradiance forecast accuracy and high data volatility over long time horizons. This study proposes a bi-level particle swarm optimization (PSO) scheduling method predicated on a weather probability model to secure system stability and economic performance. A Beta distribution model is constructed to characterize solar irradiance uncertainty, with shape parameters fitted for four weather types: clear-sky sparse-cloud (α=6.5, β=2.3), cloudy (α=β=0.92), overcast (α=3.8, β=4.4), and rain-snow (α=1.5, β=3.5). A 72 h–24 h bi-level PSO architecture is designed: the upper level reserves thermal energy storage (TES) capacity to hedge against weather uncertainty, while the lower level performs economic dispatch based on weather transition probabilities. Confidence interval sensitivity analysis reveals relative uncertainties of 76.96% (clear-sky sparse-cloud), 192.10% (cloudy), 132.22% (overcast), and 184.71% (rain-snow), with coefficients of variation ranging from 0.1901 to 0.6236. Case studies demonstrate that the synergistic mechanism between the probability model and bi-level optimization identifies the optimal irradiance operating point across weather types. Compared with conventional deterministic scheduling, the proposed strategy achieves coordinated optimization of long-timescale TES energy allocation and dispatch cost under multiple uncertainty scenarios, mitigating both over-conservative storage reservation and loss-of-load risk.
1. Introduction
Cross-day scheduling of PV-CSP integrated energy systems is fundamentally bottlenecked by the dual constraints of low solar irradiance forecast accuracy and high data volatility over extended time horizons. Existing commercial approaches—day-ahead, intra-day, and real-time rolling optimization—were designed for short-timescale coordination where forecast updates are frequent and computational complexity is manageable. When extended to cross-day horizons, these methods fail because the thermal energy storage (TES) state variable couples consecutive days: an over-reserved TES level leaves capacity underutilized and inflates storage cost, while an under-reserved level exposes the system to loss-of-load shutdown risk. Prior studies on CSP capacity configuration, CSP power balance capacity, and source-load uncertainty in virtual power plants have not evaluated the impact of TES on future scheduling or its compensatory role against forecast data uncertainty.
The experimental protocol addresses this bottleneck by introducing a weather probability model based on Beta distribution, fitted to historical solar irradiance data across four weather types with shape parameters α=6.5, β=2.3 (clear-sky sparse-cloud); α=β=0.92 (cloudy); α=3.8, β=4.4 (overcast); and α=1.5, β=3.5 (rain-snow). A 72 h–24 h bi-level particle swarm optimization architecture is constructed: the upper level reserves TES energy to hedge against weather uncertainty, while the lower level performs economic dispatch according to weather transition probabilities. The first 48 h are treated as deterministic, and the final 24 h as probabilistic interval data, yielding a TES reserve interval that is resolved into a minimum expected cost dispatch. This decomposition specifically overcomes the computational intractability of full-horizon stochastic rolling optimization while capturing the cross-day state-variable coupling that short-timescale methods cannot address.
Loading authentic research manuscript (Pages 1–5)...
LIU Xinping, MAO Yinghao (2026). Cross-Day Optimal Scheduling of Photovoltaic-Concentrated Solar Power Integrated Energy Systems Considering Weather Variation Probability. Acta Energiae Solaris Sinica. https://doi.org/10.19912/j.0254-0096.tynxb.202608_9687
Research & Educational Purpose Only: The translations, structured abstracts, analytical annotations, and data reports provided by SinoGreenTechare intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoGreenTech claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is the failure mechanism that causes conventional deterministic scheduling to underperform in cross-day PV-CSP dispatch, and how does the Beta distribution model quantify this failure?
Conventional deterministic scheduling treats the TES state variable as a fixed reserve without probabilistic hedging, causing two failure modes: over-reservation leaves TES capacity underutilized and inflates storage cost, while under-reservation exposes the system to loss-of-load shutdown risk. The Beta distribution model quantifies this failure through confidence interval sensitivity analysis, yielding relative uncertainties of 76.96% (clear-sky sparse-cloud), 192.10% (cloudy), 132.22% (overcast), and 184.71% (rain-snow). The cloudy regime, with α=β=0.92 and coefficient of variation 0.5934, exhibits the highest relative uncertainty, meaning deterministic scheduling would systematically mis-size the TES reserve by a factor exceeding 1.9× the mean irradiance variability.
Why is the 72 h–24 h bi-level PSO decomposition necessary instead of full-horizon stochastic optimization, and what computational bottleneck does it resolve?
Full-horizon stochastic optimization over 72 h with probabilistic interval data is computationally intractable because the TES state variable couples consecutive days, creating a high-dimensional decision space that grows exponentially with the number of uncertainty scenarios. The 72 h–24 h bi-level decomposition treats the first 48 h as deterministic and the final 24 h as probabilistic interval data, reducing the stochastic dimension to a single 24 h window while preserving cross-day state-variable coupling. The upper level reserves TES energy to hedge against weather uncertainty, and the lower level performs economic dispatch based on weather transition probabilities, yielding a TES reserve interval that is resolved into a minimum expected cost dispatch. This architecture avoids the computational intractability of full-horizon stochastic rolling optimization while capturing the cross-day coupling that day-ahead and intra-day scheduling cannot address.
What are the scalability bottlenecks when deploying this bi-level PSO scheduling method on a commercial PV-CSP plant with real-time weather data feeds, and how do the Beta distribution parameters affect computational load?
Scalability bottlenecks arise from two sources: the number of weather type transitions within the 24 h probabilistic window and the granularity of the PSO swarm. The Beta distribution shape parameters directly affect computational load because each weather type requires a separate confidence interval calculation—clear-sky sparse-cloud (α=6.5, β=2.3), cloudy (α=β=0.92), overcast (α=3.8, β=4.4), and rain-snow (α=1.5, β=3.5)—and the cloudy regime with α=β=0.92 produces the widest confidence interval (width 0.961) and highest relative uncertainty (192.10%), requiring more PSO iterations to converge on the optimal irradiance operating point. Real-time weather data feeds that update more frequently than the 24 h window would require re-running the lower-level dispatch, increasing computational load proportionally to the update frequency.
How does the proposed strategy achieve cost parity or cost advantage against legacy deterministic scheduling, and what are the quantified trade-offs in TES energy configuration?
The proposed strategy achieves cost advantage by resolving the TES reserve interval into a minimum expected cost dispatch, where the minimum expected cost corresponds to the system optimal irradiance operating point. Legacy deterministic scheduling either over-reserves TES—inflating storage cost because capacity is underutilized—or under-reserves TES—incurring loss-of-load shutdown risk. The Beta distribution confidence interval sensitivity analysis quantifies the trade-off: cloudy conditions require the widest reserve margin (relative uncertainty 192.10%, variance 0.0880), while clear-sky sparse-cloud conditions permit the narrowest margin (relative uncertainty 76.96%, variance 0.0197). By matching the TES reserve to the weather-specific probability distribution, the proposed strategy avoids both failure modes, achieving coordinated optimization of long-timescale TES energy configuration and dispatch cost across multiple uncertainty scenarios.
What are the operational thresholds for switching between deterministic and probabilistic scheduling within the 72 h horizon, and how does the system handle weather type transitions?
The operational threshold is fixed at 48 h: the first 48 h are treated as deterministic scheduling with accurate forecast data, and the final 24 h are treated as probabilistic interval scheduling with Beta-distributed irradiance data. Weather type transitions within the 24 h probabilistic window are handled by the lower-level PSO, which performs economic dispatch according to weather transition probabilities. The upper level reserves TES energy to hedge against weather uncertainty across the transition. The system optimal irradiance operating point is identified as the minimum expected cost solution across the probabilistic interval, with the four weather types—clear-sky sparse-cloud (α=6.5, β=2.3), cloudy (α=β=0.92), overcast (α=3.8, β=4.4), and rain-snow (α=1.5, β=3.5)—providing the discrete probability distributions for the transition matrix.
Related Chinese Research & Cross-Citations
Wind Turbine Gearbox Fault Diagnosis Method Based on Improved CNN-XGBoost Fusion Model Under Gramian Angular Difference Field
Gearbox failures account for 20–30% of total wind turbine faults and incur maintenance costs equivalent to 10–15% of overall turbine value. Conventional vibration diagnostic pipelines—complementary ensemble empirical mode decomposition with singular value energy spectrum, time-varying filtering empirical mode decomposition, and Teager energy spectrum analysis—remain bounded below 90% accuracy and depend on expert-driven feature engineering that is sensitive to non-stationary operating conditions and noise. This study proposes an intelligent diagnostic architecture that converts one-dimensional gearbox vibration signals into two-dimensional images via Gramian angular difference field (GADF) transformation, preserving intrinsic temporal correlation and time-frequency structure while exploiting matrix sparsity to suppress interference. An improved convolutional neural network (CNN) extracts multi-dimensional features: a convolutional block attention module (CBAM) is embedded in the convolutional layers to weight critical channels and focus on fault-sensitive spatial regions, and a modified βc-ACONC activation function replaces ReLU to mitigate neuron necrosis and enable selective activation. The extracted composite features are then fed into an XGBoost network whose hyperparameters are optimized by an improved sparrow search algorithm (ISSA). Validation on a laboratory wind turbine gearbox dataset yields diagnostic accuracy exceeding 99%, demonstrating robust fault identification capability under complex operating conditions.
Joint Forecasting of Wind and Photovoltaic Power Considering Complementarity
The inherent spatiotemporal complementarity between wind and solar resources offers a theoretical basis for improving renewable power forecasting accuracy. This study proposes a joint wind-photovoltaic (PV) power forecasting strategy that explicitly exploits this complementarity. A bidirectional long short-term memory (BiLSTM) neural network serves as the baseline forecasting model, and a novel sorting and comparative optimization (SCO) algorithm is developed to optimize the model's hyperparameters. The SCO algorithm ranks individuals in ascending order and compares adjacent fitness values to escape local optima, a known deficiency in conventional metaheuristics such as genetic algorithms and particle swarm optimization. For wind farms and PV plants exhibiting significant complementarity, the joint forecasting strategy first aggregates their power outputs, normalizes the combined signal, and then feeds it into the optimized BiLSTM model. Experimental results demonstrate that the proposed SCO-BiLSTM model reduces the eMAPE by 10.313% compared with PSO-BiLSTM. Furthermore, joint forecasting under SCO-BiLSTM lowers the eRMSE by 27.443% relative to standalone PV power forecasting. The study also establishes that forecasting accuracy improves with stronger wind-solar complementarity but degrades as the forecasting horizon extends. These findings confirm that exploiting complementarity in joint forecasting substantially enhances predictive performance for renewable energy integration.
Ultra-Short-Term Wind Power Forecasting Based on Fluctuation Continuation Scenario Identification
Existing ultra-short-term wind power forecasting methods exhibit limited performance due to insufficient extraction of fluctuation information and inadequate analysis of evolution patterns. This paper proposes an ultra-short-term wind power forecasting method based on fluctuation continuation scenario identification. First, the coupling mechanism of wind power fluctuations under multiple turbulence processes is investigated, and historical wind power dynamics are decoupled into a combination of nonlinear and linear fluctuation components. A fluctuation continuation concept is introduced, and the future continuation scale of wind power fluctuations is derived from nonlinear and linear decoupling parameters, thereby classifying fluctuation continuation scenarios. A sparse neural network (SNN) oriented to high-dimensional sparse features is constructed to identify historical fluctuation continuation scenarios, and ultra-short-term power forecasting is conducted separately for each scenario. Validation using measured wind speed and power data from three wind farms shows that, compared with baseline models, the proposed model improves root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) by at least 1.46%, 2.44%, and 14.67%, respectively, demonstrating superior accuracy and stability. The method addresses the limitations of signal decomposition techniques that lack physical interpretability and are sensitive to hyperparameters, and overcomes the high-dimensional sparsity challenges faced by traditional scenario identification models.
Multi-Classifier Open Adversarial Network for Rolling Bearing Fault Diagnosis in Wind Turbine Generator Systems
Rolling bearings in wind turbine generator systems operate under variable speed and load conditions that induce significant data distribution shifts between training and field data, while unknown fault modes absent from the source domain are frequently misclassified as known classes. This study proposes a multi-classifier open adversarial network (MCOAN) for open-set fault diagnosis. Within an adversarial domain adaptation framework, a K-way classifier and an additional K+1-way one-vs-all classifier independently estimate target-sample similarity to the source domain. These similarity scores drive a dynamic weighting mechanism that adaptively reweights target samples during open-set adversarial training and supplies per-sample dynamic thresholds for known/unknown discrimination, thereby promoting cross-domain alignment of shared-class features while suppressing negative transfer from unknown samples. A non-adversarial domain classifier is introduced to stabilize dynamic weight estimation. Validation on two datasets demonstrates high-precision shared-class distribution alignment and unknown-class recognition with favorable robustness. The method removes reliance on empirically preset thresholds that plague conventional open-set back-propagation approaches, where a fixed threshold of 0.5 in the binary cross-entropy adversarial loss provides no per-sample adaptivity. By coupling K-way and K+1-way similarity estimates, MCOAN achieves simultaneous known-class alignment and unknown-class separation without prior knowledge of the unknown-class cardinality, addressing a persistent bottleneck in wind turbine drivetrain condition monitoring where unanticipated bearing failure modes emerge under field conditions.
Unsupervised Automated Identification Method for Abnormal States of Wind Turbine Gearboxes
Addressing the scarcity of labeled data for training classification models in wind turbine planetary gearbox anomaly identification, this study proposes an unsupervised automated detection method. Log Mel-band energy features are extracted from raw vibration signals and fed into an unsupervised anomaly recognition model centered on a U-net autoencoder. A health-state threshold is established based on reconstruction error between model input and output, enabling anomaly identification. The method is validated using factory gearbox test data and operational data from a wind farm in Yangtouya, Shanxi. For factory gearboxes, dual validation is performed using a spectrum amplitude modulation-based signal processing method. Results demonstrate that the proposed method achieves 93.34% recognition accuracy on both factory and wind farm test sets, confirming its capability to automatically and correctly separate abnormal wind turbine gearboxes. The approach eliminates reliance on labeled fault data, offering a scalable solution for full-lifecycle health monitoring, from factory acceptance testing to in-service early anomaly detection, adaptable across different operating conditions and turbine models.
Improved Adaptive Super-Twisting Sliding Mode Control for Permanent Magnet Synchronous Motors
Adaptive super-twisting sliding mode control (ASTSMC) for permanent magnet synchronous motors (PMSM) suffers from prolonged convergence and insufficient disturbance rejection under complex operating conditions. This paper proposes an improved ASTSMC incorporating a fixed-time disturbance observer (FTDO). A power term is introduced into the adaptive super-twisting controller to accelerate convergence far from the origin, while the discontinuous sign function is replaced by a continuous h(s) function to mitigate chattering. The FTDO ensures disturbance estimation converges within a fixed time independent of initial states, overcoming the limitations of traditional and finite-time observers. The estimated disturbance is fed forward to the sliding mode controller for compensation, enhancing robustness. The FTDO design is based on an auxiliary state variable z and its derivative, with error dynamics analyzed via Lyapunov stability. Comparative simulations against conventional disturbance observers and sliding mode controllers validate the proposed strategy. The results demonstrate shorter convergence time, improved dynamic performance, and superior disturbance rejection, making the approach suitable for high-performance servo systems. The method addresses the critical need for robust, fast-response control in electric vehicles, rail transit, and aerospace applications where PMSM drives face significant uncertainties and external disturbances.