Combining Probabilistic Load Forecasts

GEFCom2014 probabilistic electric load forecasting: An integrated solution with forecast combination and residual simulation

Load probability density forecasting by transforming and combining quantile forecasts

Nonparametric probabilistic load forecasting based on quantile combination in electrical power systems

Probabilistic load forecasting for buildings considering weather forecasting uncertainty and uncertain peak load

Probabilistic load forecasting (PLF) is able to present the uncertainty information of the future loads. It is the basis of stochastic power system planning and operation. Recent works on PLF mainly focus on how to develop and combine forecasting models, while the feature selection issue has not been thoroughly investigated for PLF. This paper fills the gap by proposing a feature selection method for PLF via sparse L_1-norm penalized quantile regression. It can be viewed as an extension from point forecasting-based feature selection to probabilistic forecasting-based feature selection. Since both the number of training samples and the number of features to be selected are very large, the feature selection process is casted as a large-scale convex optimization problem. The alternating direction method of multipliers is applied to solve the problem in an efficient manner. We conduct case studies on the open datasets of ten areas. Numerical results show that the proposed feature selection method can improve the performance of the probabilistic forecasting and outperforms traditional least absolute shrinkage and selection operator method.

In the era of the smart grid, the electrical load on the demand side becomes more dynamic and less predictable than ever before. Differently from deterministic load forecasting, probabilistic load forecasting (PLF) estimates the uncertainty of future loads and has become increasingly important for power system planning and operations. We have previously proposed a deterministic load forecasting method by improving the Informer model in which the periodic property of load profiles is considered. In this paper, a PLF model is designed on the basis of the deterministic load forecasting method. The PLF model estimates the model and data uncertainties through running the deterministic load forecasting model several times with random initial parameters, and determines load intervals by combining the average value of multi runs of the deterministic load forecasting model, the estimated uncertainties and the critical value of the standard normal distribution. The experimental results on GEFCom2014 data set have demonstrated the superior forecasting performance than others.

The extensive deployment of smart meters in millions of households provides a huge amount of individual electricity consumption data for demand side analysis at a fine granularity. Different from traditional aggregated system-level data, smart meter data is more irregular and unpredictable. As a result, probabilistic load forecasting (PLF), which can provide a better understanding of the uncertainty and volatility in future demand, is critical to constructing energy-efficient and reliable smart grids. In this article, a recently developed technique called Bayesian deep learning is employed to solve this challenging problem. In particular, a novel multitask PLF framework based on Bayesian deep learning is proposed to quantify the shared uncertainties across distinct customer groups while accounting for their differences. Further, a clustering-based pooling method is designed to increase the data diversity and volume for the framework. This not only addresses the problem of overfitting but also improves the predictive performance. Numerical results are presented which demonstrate that the proposed framework provides superior probabilistic forecasting accuracy over conventional methods.

Long term load forecasting plays a vital role in power systems planning and utility financial planning. Traditional methods in long term load forecasting rely on monthly data, which offers limited observations to support the comprehensive models with sufficient explanatory variables to capture the salient features in the electricity demand series. The grid modernization efforts undertaken by many utilities over the past decade have made high-resolution data available for many analytical tasks including load forecasting. In this paper, we investigate the effectiveness of using high-resolution data in long term probabilistic load forecasting. The primary error measure we use for forecast evaluation is pinball loss function. Through a case study based on the data from a U.S. utility, we show that high-resolution data is beneficial to the improvement of probabilistic load forecasts.

Short term load forecasting and the effect of temperature at the low voltage level

The integration of renewable energy in modern power systems has increased the stochasticity of load patterns. Probabilistic load forecasting (PLF) acts as a solution to capture the uncertainty of load data. Especially, neural network (NN)-based models can be flexibly adapted for PLF. However, the black-box characteristic of NN makes it difficult for us to understand where the uncertainty comes from, thereby reducing the reliability of the forecast. This paper provides a model-agnostic NN explanation framework for PLF, attributing the uncertainty quantification of the probabilistic forecast to the uncertainty of the input feature to evaluate where the uncertainty in the forecast comes from. Unlike traditional deep learning explanation techniques that examine how the information of the feature affects the result, our explanation focuses on exploring how the uncertainty of the feature affects the result. In this way, we can know the uncertainty and error sources of PLF and further understand its mechanism, which can help reduce the adverse effects of data uncertainty on forecasts. The codes can be found in <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/hkuedl/Explanation-for-Probabilistic-Load-Forecasting</uri>.

Emerging interest in probabilistic load forecasting (PLF) has increased because it can address load uncertainty better than point forecasting. This paper proposed a new strategy to treat the input of PLF as a probability map, which enables an actual pictorial to depict the prediction outcome risk of a load demand profile according to the preferred length of the prediction horizon. The proposed probabilistic method consists of optimal signal decomposition, prediction model construction and an evaluation strategy to obtain the prediction interval risk outcome. Whale optimization algorithm-discrete wavelet transformation (WOA-DWT) is employed to detect optimal input decomposition. The quantile regression random forest (QRRF) is utilized to build a prediction interval from various quantiles. A novel scheme to calculate the prediction outcome risk due to current input, which provides a degree of confidence, is also presented. The efficacy of prediction interval is verified using the Independent System Operator – New England (ISO-NE) set with the Winkler score and proposed risk-severity score.

A novel similar-day based probability density forecasting framework for residential loads

A novel combined probabilistic load forecasting system integrating hybrid quantile regression and knee improved multi-objective optimization strategy

This study uses probabilistic load forecast technique to predict the load demand pattern in Ogun State for year 2018. Energy consumption data for Ogun State for year 2016 and 2017 was obtained from the regional headquarter of the Ibadan Electricity Distribution Company (IBEDC), Abeokuta. The results of the study show that the energy consumption in Ogun State has the probability tendency of rising above 98,469.40 MWHR by 2.68%. Similarly, it was also established that the probability of energy consumed in the state rising below 46,494.68 MWHR within the next few months will be 5.98%. The probability that energy consumption in year 2018 will fall between 98,469.40 MWHR and 46,494.68 MWHR is 91.84%. Energy consumption in year 2018 will mostly fall between 63,500 MWHR – 86,000 MWHR. The result also indicated that energy consumption in 2018, has the highest probability of falling between 72,500 MWHR and 77,000 MWHR by 15.34%. It is unlikely it falls between 45,000 MWHR to 50,000 MWHR and 95,000 MWHR to 99,500 MWHR, with both range having their percentage probabilities at 0.19% and 2.99% respectively. Result of this study is useful to IBEDC for their operational planning and control activities. Keywords: energy consumption forecast, probabilistic load forecast (PLF), deterministic forecast

Researchers have proposed various probabilistic load forecasting models in the form of quantiles, densities, or intervals to describe the uncertainties of future energy demand. Density forecasts can provide more uncertainty information than can be expressed by just the quantile and interval. However, the combining method for density forecasts is seldom investigated. This paper proposes a novel and easily implemented approach to combine density probabilistic load forecasts to further improve the performance of the final probabilistic forecasts. The combination problem is formulated as an optimization problem to minimize the continuous ranked probability score of the combined model by searching the weights of different individual methods. Under the Gaussian mixture distribution assumption of the density forecasts, the problem is cast to a linearly constrained quadratic programming problem and can be solved efficiently. Case studies on the electric load datasets of eight areas verify the effectiveness of the proposed method.