The paper compares machine learning models for forecasting residential gas demand, highlighting the impact of temperature forecasts.
problem Forecasting residential gas demand for optimal energy planning.
method Implemented and compared five models: Ridge Regression, GP, k-Nearest Neighbour, ANN, and Torus Model.
result ANN is the best model in terms of RMSE, while GP is the best in terms of MAE.
Improved gas demand forecasting using ensemble methods.
problem Short-term prediction of gas demand components.
method Nine base forecasters (Ridge Regression, GP, NN, ANN, Torus, LASSO, Elastic Net, RF, SVR) and four ensemble predictors (simple, weighted, subset, SVR aggregation) were evaluated.
result Ensemble predictors outperformed individual base forecasters and TSO predictions.
Model forecasts natural gas consumption with Fourier series and feedback.
problem Forecast natural gas consumption for risk minimization.
method Modulated Fourier series with temperature deviations, day-ahead feedback.
result Model outperforms time series methods for long-term projections.
Novel probabilistic models forecast residential heating and electricity demand at hourly resolution.
problem Accurate hourly forecasting of residential heating and electricity demand.
method Probabilistic deep learning models trained on gas-heated region data.
result Significant improvement in forecast accuracy compared to NREL's ResStock model.
Study forecasts Turkish residential NGD using JITL-GPR, reducing errors.
problem Accurately predict future monthly NGD for Turkey's import contracts.
method Used historical NG consumption data, applied various time series models, and introduced JITL-GPR.
result JITL-GPR reduces forecast errors compared to traditional methods.
GAS-Norm improves deep learning time series forecasting in non-stationary settings.
problem Deep learning models struggle with non-stationary time series data.
method Combines GAS model for adaptive normalization with deep neural networks.
result Improves deep learning performance in 21 out of 25 settings.
Improved GAS models using trees and forests for better forecasts.
problem Improving forecasts from GAS models to avoid curse of dimensionality.
method Localized parameters using decision trees and random forests.
result Significantly outperform baseline GAS model in empirical analyses.
GAS models have been recently proposed in time-series econometrics as valuable tools for signal extraction and prediction. This paper details how financial risk managers can use GAS models for Value-at-Risk (VaR) prediction using the novel GAS package for R. Details and code snippets for prediction, comparison and back…
This paper presents the R package GAS for the analysis of time series under the Generalized Autoregressive Score (GAS) framework of Creal et al. (2013) and Harvey (2013). The distinctive feature of the GAS approach is the use of the score function as the driver of time-variation in the parameters of nonlinear models. T…
Demand functions for goods are generally cyclical in nature with characteristics such as trend or stochasticity. Most existing demand forecasting techniques in literature are designed to manage and forecast this type of demand functions. However, if the demand function is lumpy in nature, then the general demand foreca…
Demand variance can result in a mismatch between planned supply and actual demand. Demand shaping strategies such as pricing can be used to shift elastic demand to reduce the imbalance. In this work, we propose to consider elastic demand in the forecasting phase. We present a method to reallocate the historical elastic…
Paper optimizes demand aggregation for low-level electricity markets.
problem Accurate short-term load forecasting at low aggregation levels for market participants.
method Probabilistic portfolio optimization of residential households' demand using ARMA-GARCH models or KDE forecasts.
result Seasonal Residual approach outperforms others in accuracy and efficiency.
The study models and forecasts natural gas prices using skewed, heavy-tailed distributions.
problem Modeling and forecasting natural gas prices with heavy tails and conditional heteroscedasticity.
method State-space time series models under skewed, heavy-tailed distributions.
result The proposed model reduces out-of-sample CRPS by 13% for Day-Ahead and 9% for Month-Ahead forecasts.
Paper develops deep models for forecasting intermittent demand.
problem Forecasting intermittent demand with sporadic occurrences.
method Uses deep neural networks to model conditional interdemand time and size distributions.
result Empirical validation of deep models for intermittent demand forecasting.
A new metric optimizes forecasts for lumpy, intermittent demand.
problem Inaccurate demand forecasts lead to suboptimal logistics and production.
method Developed a novel metric that considers both statistical and business aspects.
result The new metric yields more accurate predictions for lumpy and intermittent demand.
This paper analyzes Ethereum's gas fees and their derivatives, providing a comprehensive model.
problem Understanding and predicting gas fees on the Ethereum blockchain.
method Analyzed Ethereum's gas fee structure and used a fractional Ornstein-Uhlenbeck process to model gas prices.
result A model for pricing and trading gas fee derivatives to hedge against volatility.
Project promoters, forecasters, and managers sometimes object to two things in measuring inaccuracy in travel demand forecasting: (1) using the forecast made at the time of making the decision to build as the basis for measuring inaccuracy and (2) using traffic during the first year of operations as the basis for measu…
Paper proposes a method for predicting any quantile of short-term electricity demand.
problem Uncertainty in power systems due to multiple factors.
method Proposes a novel general approach for distributional forecasting of short-term electricity demand.
result Demonstrates state-of-the-art distributional forecasting results for short-term electricity demand.
SPADE improves demand forecasting accuracy by 4.5% for post-promotion periods.
problem Overreacting to peak events in demand forecasting leads to biased forecasts.
method SPADE splits forecasting into two tasks: one for peak events and another for post-peak events, using masked convolution filters and a specialized Peak Attention module.
result Overall PPE improvement of 4.5%, 30% improvement for most affected forecasts after promotions and holidays, and 3.9% improvement in PE accuracy.
Deep learning improves weather modeling for electricity load forecasting.
problem Accurate load and renewable energy forecasting requires complex spatio-temporal weather modeling.
method Automated spatio-temporal feature extraction using deep neural networks.
result Deep learning outperforms traditional methods in French national load forecasting.
In this work we analyse a stochastic control problem for the valuation of a natural gas power station while taking into account operating characteristics. Both electricity and gas spot price processes exhibit mean-reverting spikes and Markov regime-switches. The Levy regime-switching model incorporates the effects of d…
Graph Neural Networks improve demand forecasting by considering article relationships.
problem Forecasting independent article-level predictions without considering related articles.
method Integrating GNN encoder into DeepAR model and using article attribute similarity to build graphs.
result The proposed approach consistently outperforms non-graph benchmarks and produces useful article embeddings.
New framework forecasts both supply and demand in rental markets.
problem Booking models ignore supply, leading to regime-specific ceilings.
method Three-part coupling framework (behavioral, informational, intervention).
result Booking models learn a regime-specific ceiling and become fragile.
Proposes a new model for more accurate demand forecasting considering dynamic contextual information.
problem Traditional methods fail to capture spatio-temporal and dynamic contextual dependencies in demand forecasting.
method Integrates temporal, relational, spatial, and dynamic contextual dependencies using a Context Integrated Graph Neural Network (CIGNN).
result CIGNN outperforms state-of-the-art baselines in multi-step ahead demand forecasting.
Model forecasts water demand with probabilistic multi-step-ahead approach.
problem Accurate probabilistic forecasts of water demand for operational control.
method Time series model with Lasso for high-dimensional feature space.
result Accurate, interpretable, and fast computable forecasting model.
Tab2vox converts tabular data into 3D images for improved demand forecasting.
problem Forecasting demand influenced by multi-level causes and large volatility.
method Tab2vox neural architecture search (NAS) model to convert tabular data into 3D voxel images for 3D CNN forecasting.
result 3D CNN forecasting model outperforms existing tabular data techniques.
Unified framework for intermittent demand forecasting using renewal processes.
problem Intermittency in demand forecasting.
method Unified framework based on extensions of discrete-time renewal processes.
result Efficacy demonstrated in forecasting practice with favorable predictive accuracy.
New data set and method for BTO supply chain demand forecasting.
problem Lack of demand forecasting methods for BTO supply chains.
method Proposes a novel data transformation technique for BTO products.
result Approach compares well to state-of-the-art methods and is easy to implement.
Quantile regression improves urban water demand forecasting.
problem Improving probabilistic urban water demand forecasting.
method Comparing five quantile regression algorithms and their combinations for one-day ahead forecasting.
result Linear boosting algorithm performs best for probabilistic urban water demand forecasting.
AutoML improves electricity demand forecasting models.
problem Optimizing GAM and state-space model parameters for short-term forecasting.
method Automated online generalized additive model selection using DRAGON package.
result The approach enhances predictive performance of adaptive models.
System uses TDA for user segmentation and demand forecasting.
problem User loyalty and demand forecasting challenges.
method TDA-based clustering of time series data with matrix factorization.
result Significantly higher accuracy in clustering and demand forecasting.
New method for disaggregate electricity demand forecasting at household level.
problem Challenges in forecasting electricity demand at individual household level.
method Additive stacking method for probabilistic disaggregate electricity demand forecasting.
result Improved accuracy in disaggregate electricity demand forecasting.
Study improves retail demand forecasting by integrating macroeconomic data.
problem Lack of accurate demand forecasting due to incomplete data.
method Enriched time series data with macroeconomic variables; compared regression and machine learning models.
result Improved accuracy in predicting retail demand through comprehensive data integration.
DeepPPMNet forecasts EMS demand and performs causal analyses for policy-making.
problem Accurate prediction and causal analysis of EMS demand for effective policy-making.
method DeepPPMNet, a LSTM-based framework, globally forecasts and analyzes causal relationships using Granger causality.
result DeepPPMNet outperforms traditional methods in forecasting EMS demand and policy-making.
Paper proposes a new method for demand forecasting in pricing contexts.
problem Demand forecasting in pricing contexts, especially in a profit optimal manner.
method Combines Double Machine Learning for causal inference and transformer-based forecasting models.
result Our method outperforms other forecasting methods in off-policy settings.
LSTMs improve demand forecasting for e-grocery products.
problem Improving demand forecasting accuracy in e-grocery retail.
method Developed and tested univariate and multivariate LSTM models for 100 fast-moving consumer goods.
result LSTMs outperform traditional models for food products, especially in beverage category.
EGPR method forecasts power grid load and generation with high accuracy.
problem Accurate week-long forecasting of load demand and power generation for efficient power grid operation.
method Gaussian process regression with ensembles of preceding weeks' data.
result EGPR method outperforms traditional methods in forecasting weekly load and generation.
Study forecasts monthly electricity demand using pattern similarity-based methods.
problem Forecasting monthly electricity demand accurately.
method Pattern similarity-based forecasting methods (PSFMs) including k-NN, fuzzy, kernel regression, and GRNN.
result Ensemble models outperform individual PSFMs in forecasting accuracy.
This research improves demand forecasting by predicting complete probability density functions using machine learning.
problem Forecasting complete probability density functions for better operational decision making.
method Supervised machine learning method 'Cyclic Boosting' for explainable predictions.
result Predicted probability density functions are fully explainable and avoid 'black-box' models.
A winning method for day-ahead electricity demand forecasting during and after the COVID-19 pandemic.
problem Day-ahead electricity demand forecasting during and after the COVID-19 pandemic.
method Online forecast combination of multiple point prediction models with a holiday adjustment procedure and smoothed Bernstein Online Aggregation (BOA).
result Excellent forecasting performance, particularly due to the holiday adjustment procedure and fully adaptive smoothed BOA approach.
Less frequent retraining improves forecast accuracy in retail demand forecasting.
problem Balancing forecast accuracy and computational efficiency in global models.
method Analysis of ten machine learning and deep learning models across two large retail datasets with various retraining scenarios.
result Less frequent retraining strategies maintain forecast accuracy while reducing computational costs.
The paper forecasts joint electricity demand across 14 British regions using additive models.
problem Forecasting regional electricity demand with cross-regional dependencies.
method Modified Cholesky parametrisation for multivariate Gaussian model, gradient boosting for model selection.
result The proposed model outperforms non-Gaussian copula-based models in forecasting.
Novel time series forecasting method using sliding window signatures.
problem Challenges in forecasting nonlinear and delayed time series data.
method Ridge regression with signature features calculated on sliding windows.
result Signature features effectively encode temporal and nonlinear dependencies, leading to accurate forecasts.
STG2Seq predicts multi-step passenger demand with graph and hierarchical structure.
problem Predicting passenger demand over multiple time horizons is challenging due to nonlinear and dynamic spatial-temporal dependencies.
method Proposes a graph-based model with a hierarchical graph convolutional structure to capture spatial and temporal correlations.
result Consistently outperforms baseline and state-of-the-art models on real-world datasets.
Foundation AI model outperforms traditional VaR methods in forecasting.
problem Forecasting Value-at-Risk (VaR) for financial returns.
method Time-series foundation AI model, pre-trained on diverse datasets, fine-tuned for specific quantiles.
result Fine-tuned foundation model consistently outperforms traditional methods in actual-over-expected ratios.
The study finds a long-term relationship between Dubai crude oil and US natural gas prices.
problem Examining the relationship between Dubai crude oil and US natural gas prices.
method Used unit root and cointegration tests, ARDL cointegration technique, and Toda-Yamamoto causality test.
result There is a long-run relationship with unidirectional causality from Dubai crude oil to US natural gas.
A new Bayesian model improves forecasting for intermittent demand.
problem Sparse observations, cold-start items, and obsolescence in intermittent demand forecasting.
method Hierarchical Bayesian TSB model with partial pooling and calibrated probabilistic configuration.
result TSB-HB achieves the lowest RMSE and RMSSE on the UCI Online Retail dataset.
Deep-Gap predicts crowdsourcing supply-demand gaps using deep learning.
problem Balancing supply and demand in mobile crowdsourcing.
method Residual learning-based deep neural networks trained on time series data and external factors.
result Deep-Gap achieves lowest forecasting errors compared to state-of-the-art methods.