We propose a two-stage probabilistic solar power (SP) forecasting algorithm to utilize the solar irradiation (SI) observations measured from different locations. In the first stage, we predict the SI based on the numerical weather prediction (NWP) after interpolating SI observations. Since the SI on the target location is not measured, we interpolate it using the spatio-temporal Kriging technique based on the SI observed from nearby weather stations. In the second stage, we forecast the SP based on the SI predictions after training the SI and SP observations. The model is trained by observations, but it forecasts based on predictions. Furthermore, in the two-stage model, forecasting errors can propagate across stages. We overcome these problems by using probabilistic forecasting. We design distributions of SI predictions through the probabilistic graphical model. Then, we extract SI scenarios from the distributions and predict SP scenarios based on these SI scenarios. We also group the NWP with respect to its prediction time, and we subdivide these groups as subgroups with respect to weather conditions. Furthermore, we propose a changeable ensemble model, where we have different weights for each weather condition. We verify our algorithm based on the data from the Korea power exchange renewable energy forecasting competition 2019. We finished the competition in 2nd place among a few hundred participants.

Restoring missing data holds paramount importance in power system analysis. Traditional recovery methods typically offer only a singular solution, lacking adaptability and depth. To bridge this gap, we introduce BERT-PIN, a pioneering approach harnessing bidirectional encoder representations from transformers for profile inpainting. This innovative technique enables the recovery of multiple segments of missing data by leveraging power system load and temperature profiles. Our findings demonstrate that BERT-PIN enhances accuracy by 5%–30% compared to existing techniques, showcasing its ability to restore numerous missing data segments across extended periods. We have successfully applied BERT-PIN in two critical power system applications: recovering missing data segments and estimating conservation voltage reduction baselines. Serving as a versatile pretrained model, BERT-PIN supports various downstream tasks, including classification and super-resolution, thereby reducing the necessity for extensive training data, and minimizing training time.

This paper presents a novel contextually supervised optimization-based approach for disaggregating heating, ventilation, and air-conditioning (HVAC) loads using smart meter or Supervisory Control and Data Acquisition data. To disaggregate the load into HVAC loads, large and infrequently used loads (LIUL), and base loads, we formulate an optimization problem to minimize a set of five loss terms, consisting of the reconstruction errors of the overall load profile, the ramp rate losses, and three distinct loss functions linked with the HVAC load, base load, and LIUL, respectively. To enhance accuracy, we incorporate two forms of contextual information into the problem formulation. First, we utilize mutual information to estimate HVAC energy consumption. Second, we employ a base load dictionary to constrain HVAC load estimation errors. The obtained HVAC load profiles are fine-tuned by abnormal ramp detection followed by binary hypothesis testing. The proposed method is developed and tested using sub-metered residential and commercial building data. Simulation results show that the proposed method outperforms existing methods across various data resolutions and load aggregation levels, showing excellent transferability and generalizability.

The purpose of this paper is to apply multistage stochastic programming to the transmission line expansion planning problem, especially when uncertain demand scenarios exist. Since the problem of transmission line expansion planning requires an intensive computational load, dual decomposition is used to decompose the problem into smaller problems. Following this, progressive hedging and proximal bundle methods are used to restore the decomposed solutions to the original problems. Mixed-integer linear programming is involved in the problem to decide where new transmission lines should be constructed or reinforced. However, integer variables in multistage stochastic programming (MSSP) are intractable since integer variables are not restored. Therefore, the branch-and-bound algorithm is applied to multistage stochastic programming methods to force convergence of integer variables.In addition, this paper suggests combining progressive hedging and dual decomposition in stochastic integer programming by sharing penalty parameters. The simulation results tested on the IEEE 30-bus system verify that our combined model sped up the computation and achieved higher accuracy by achieving the minimised cost.

This article introduces a neural optimizer-based framework for optimizing battery energy storage system (BESS) control for grid services, including demand charge and energy cost reduction. By leveraging decision-focused learning (DFL), the proposed framework ensures seamless integration and adaptation, significantly enhancing control performance. A patch time-series transformer is employed for peak load forecasting, incorporating aleatoric uncertainty quantification to account for forecasting uncertainties within the decision-making process. The framework utilizes a solver-in-the-loop approach to generate optimal BESS actions, which are then used to train the neural optimizer-based agent. By co-optimizing both BESS operational modes and output power within the NN, the system achieves improved performance and robustness. After initial training, the forecasting and control models are jointly fine-tuned to account for forecasting errors, further improving decision precision and efficiency through DFL. Case studies are performed to validate the performance of the framework using multiple real-world datasets, demonstrating superior performance in monthly peak load forecasting compared to state-of-the-art models. In addition, the results are compared against existing decision-making approaches. The results demonstrate a reduction in monthly peak forecasting error by approximately 15% across various performance measures and achieve an optimization gap for BESS operation that is about three times smaller compared to existing methods.