The recent surge in solar plant installations has notably decreased the reliance on fossil fuels while also presenting significant challenges to power grid. Therefore, the accurate forecasting of centralized and distributed solar power has become critically important. Although site-specific forecasting models typically perform better for utility-scale solar power plants, the model maintenance can be troublesome as the number of solar plants grows. Furthermore, the rapid growth and difficulties in real-time data collection associated with distributed solar systems exacerbate the complexity of regional gross solar power forecasting. To address these issues, we propose SolarMAE, a unified regional solar power forecasting framework enabling end-to-end precise forecasting for both centralized and distributed solar systems. It adopts masked autoencoder (MAE) pre-training strategy for numerical weather prediction (NWP) reconstruction at first, aiming to derive spatiotemporal correlations within meteorological variables, and then fine-tunes a temporal convolutional neural network which predicts future solar power generation. Experiments show that this framework outperforms state-of-the-art centralized or distributed solar power forecasting methods in accuracy, and significantly reduces model maintenance cost. It also demonstrates strong few-shot learning capabilities, which is particularly useful for the cold start problem of newly installed solar plants. The unified solar power forecasting system has been deployed in a province in eastern China, serving solar systems with over 73 GW gross installed capacity and more than 400 centralized solar plants.

Weather forecasting has long posed a significant challenge for humanity. While recent AI-based models have surpassed traditional numerical weather prediction (NWP) methods in global forecasting tasks, overfitting remains a critical issue due to the limited availability of real-world weather data spanning only a few decades. Unlike fields like computer vision or natural language processing, where data abundance can mitigate overfitting, weather forecasting demands innovative strategies to address this challenge with existing data. In this paper, we explore pre-training methods for weather forecasting, finding that selecting an appropriately challenging pre-training task introduces locality bias, effectively mitigating overfitting and enhancing performance. We introduce Baguan, a novel data-driven model for medium-range weather forecasting, built on a Siamese Autoencoder pre-trained in a self-supervised manner and fine-tuned for different lead times. Experimental results show that Baguan outperforms traditional methods, delivering more accurate forecasts. Additionally, the pre-trained Baguan demonstrates robust overfitting control and excels in downstream tasks, such as subseasonal-to-seasonal (S2S) modeling and regional forecasting, after fine-tuning.

Electricity forecasting is crucial in scheduling and planning of future electric load, so as to improve the reliability and safeness of the power grid. Despite recent developments of forecasting algorithms in the machine learning community, there is a lack of general and advanced algorithms specifically considering requirements from the power industry perspective. In this paper, we present eForecaster, a unified AI platform including robust, flexible, and explainable machine learning algorithms for diversified electricity forecasting applications. Since Oct. 2021, multiple commercial bus load, system load, and renewable energy forecasting systems built upon eForecaster have been deployed in seven provinces of China. The deployed systems consistently reduce the average Mean Absolute Error (MAE) by 39.8% to 77.0%, with reduced manual work and explainable guidance. In particular, eForecaster also integrates multiple interpretation methods to uncover the working mechanism of the predictive models, which significantly improves forecasts adoption and user satisfaction.

Although we have witnessed great success of pre-trained models in natural language processing (NLP) and computer vision (CV), limited progress has been made for general time series analysis. Unlike NLP and CV where a unified model can be used to perform different tasks, specially designed approach still dominates in each time series analysis task such as classification, anomaly detection, forecasting, and few-shot learning. The main challenge that blocks the development of pre-trained model for time series analysis is the lack of a large amount of data for training. In this work, we address this challenge by leveraging language or CV models, pre-trained from billions of tokens, for time series analysis. Specifically, we refrain from altering the self-attention and feedforward layers of the residual blocks in the pre-trained language or image model. This model, known as the Frozen Pretrained Transformer (FPT), is evaluated through fine-tuning on all major types of tasks involving time series. Our results demonstrate that pre-trained models on natural language or images can lead to a comparable or state-of-the-art performance in all main time series analysis tasks, as illustrated in Figure1. We also found both theoretically and empirically that the self-attention module behaviors similarly to principle component analysis (PCA), an observation that helps explains how transformer bridges the domain gap and a crucial step towards understanding the universality of a pre-trained transformer. The code is publicly available at https://anonymous.4open.science/r/Pretrained-LM-for-TSForcasting-C561.

Image-based methods for indoor lighting estimation suffer from the problem of intensity-distance ambiguity. This paper introduces a novel setup to help alleviate the ambiguity based on the event camera. We further demonstrate that estimating the distance of a light source becomes a well-posed problem under this setup, based on which an optimization-based method and a learning-based method are proposed. Our experimental results validate that our approaches not only achieve superior performance for indoor lighting estimation (especially for the close light) but also significantly alleviate the intensity-distance ambiguity.