检索结果-内蒙古大学图书馆

TRANSFER LEARNING FOR DAY-AHEAD LOAD forecasting: A CASE STUDY ON EUROPEAN NATIONAL ELECTRICITY DEMAND TIME SERIES

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Tzortzis, Alexandros-Menelaos Pelekis, Sotiris Spiliotis, Evangelos Karakolis, Evangelos Mouzakitis, Spiros Psarras, John Askounis, Dimitris Decision Support Systems Laboratory School of Electrical and Computer Engineering National Technical University of Athens Greece Forecasting and Strategy Unit School of Electrical and Computer Engineering National Technical University of Athens Greece

Short-term load forecasting (STLF) is crucial for the daily operation of power grids. However, the non-linearity, non-stationarity, and randomness characterizing electricity demand time series renders STLF a challenging task. Various forecasting approaches have been proposed for improving STLF, including neural network (NN) models which are trained using data from multiple electricity demand series that may not necessary include the target series. In the present study, we investigate the performance of this special case of STLF, called transfer learning (TL), by considering a set of 27 time series that represent the national day-ahead electricity demand of indicative European countries. We employ a popular and easy-to-implement NN model and perform a clustering analysis to identify similar patterns among the series and assist TL. In this context, two different TL approaches, with and without the clustering step, are compiled and compared against each other as well as a typical NN training setup. Our results demonstrate that TL can outperform the conventional approach, especially when clustering techniques are considered. © 2023, CC BY.

关键词： Time series

A COMPARATIVE ASSESSMENT OF DEEP LEARNING MODELS FOR DAY-AHEAD LOAD forecasting: INVESTIGATING KEY ACCURACY DRIVERS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pelekis, Sotiris Seisopoulos, Ioannis-Konstantinos Spiliotis, Evangelos Pountridis, Theodosios Karakolis, Evangelos Mouzakitis, Spiros Askounis, Dimitris Decision Support Systems Laboratory School of Electrical and Computer Engineering National Technical University of Athens Greece Forecasting and Strategy Unit School of Electrical and Computer Engineering National Technical University of Athens Greece

Short-term load forecasting (STLF) is vital for the effective and economic operation of power grids and energy markets. However, the non-linearity and non-stationarity of electricity demand as well as its dependency on various external factors renders STLF a challenging task. To that end, several deep learning models have been proposed in the literature for STLF, reporting promising results. In order to evaluate the accuracy of said models in day-ahead forecasting settings, in this paper we focus on the national net aggregated STLF of Portugal and conduct a comparative study considering a set of indicative, well-established deep autoregressive models, namely multi-layer perceptrons (MLP), long short-term memory networks (LSTM), neural basis expansion coefficient analysis (N-BEATS), temporal convolutional networks (TCN), and temporal fusion transformers (TFT). Moreover, we identify factors that significantly affect the demand and investigate their impact on the accuracy of each model. Our results suggest that N-BEATS consistently outperforms the rest of the examined models. MLP follows, providing further evidence towards the use of feed-forward networks over relatively more sophisticated architectures. Finally, certain calendar and weather features like the hour of the day and the temperature are identified as key accuracy drivers, providing insights regarding the forecasting approach that should be used per case. © 2023, CC BY.

关键词： Convolution

A User-Friendly Electric Vehicle Reallocation Solution for Uniformly Utilized Charging Stations

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Skaloumpakas, Panagiotis Spiliotis, Evangelos Stoian, Daniela Stravodimos, George Makarouni, Ioanna Marinakis, Vangelis Psarras, Ioannis Psarras, John HOLISTIC S.A. Athens Greece Forecasting and Strategy Unit School of Electrical & Computer Engineering National Technical University of Athens Greece Decision Support Systems Laboratory School of Electrical & Computer Engineering National Technical University of Athens Greece National Technical University of Athens Greece

Electric vehicle (EV) users often struggle to identify charging stations (EVCSs) that are both available at the time of interest and placed in convenient locations. At the same time, EVCSs in nearby locations may systematically be underutilized. This variance in the utilization of the EVCSs can have negative implications, both for the EV users (e.g. higher anxiety, waiting time, and discomfort) and the owners/operators of the EVCSs (e.g. lower income and longer payback period of investment). The present work aims to mitigate said implications by introducing a solution that efficiently allocates EV users to stations based on their expected utilization and their proximity to the charging locations of preference. To do so, a forecasting model is first used to predict the arrivals at the EVCSs. Then, the utilization rates of the EVCSs are computed and a heuristic algorithm is employed to dynamically reallocate the EV users from overutilized stations to nearby, underutilized stations. The proposed approach, which has been implemented in a web-based application, is evaluated through simulation experiments and compared with the traditional ``first-come, first-served'' approach. The results indicate that our approach can achieve more uniformly distributed utilization rates with a minimal deterioration on the convenience of the EV users, thus offering a practical solution to the examined problem. © 2023, The Authors. All rights reserved.

关键词： forecasting

Unraveling the effect of engagement and consistency in the results of the M6 forecasting competition

学校读者我要写书评

暂无评论

International Journal of forecasting 2025年

作者： Kaltsounis, Anastasios Theodorou, Evangelos Spiliotis, Evangelos Assimakopoulos, Vassilios Forecasting and Strategy Unit School of Electrical and Computer Engineering National Technical University of Athens Greece

The M6 competition evaluated investment performance over a period of one year, contributing to the efficient market hypothesis debate. This paper provides further insights into the outcomes of the competition by unraveling the effect that team engagement and performance consistency had on the final results. First, we identify three different types of engagement and investigate their relationship with portfolio efficiency, also making useful observations about the learning effect implied by a re-submission process. Then, we analyze the monthly performance of the teams and determine whether it aligned with their global performance or was affected significantly by extreme instances. Our results suggest that consistency is more important than engagement for making profitable investments. Nevertheless, we identify many cases where both regular portfolio updates and luck provided an advantage. © 2025 The Authors

关键词： Forecast performance forecasting competitions Investment decisions M6 Trading

The M6 forecasting competition: Bridging the gap between forecasting and investment decisions

学校读者我要写书评

暂无评论

International Journal of forecasting 2024年

作者： Makridakis, Spyros Spiliotis, Evangelos Hollyman, Ross Petropoulos, Fotios Swanson, Norman Gaba, Anil Makridakis Open Forecasting Center Institute For the Future University of Nicosia Cyprus Forecasting and Strategy Unit School of Electrical and Computer Engineering National Technical University of Athens Greece School of Management University of Bath United Kingdom Business School University of Exeter Exeter United Kingdom Department of Economics Rutgers University NJ United States INSEAD Singapore

The M6 forecasting competition, the sixth in the Makridakis competition sequence, focused on financial forecasting. A key objective of the M6 competition was to contribute to the debate surrounding the Efficient Market Hypothesis by examining how and why market participants make investment decisions. To address these objectives, the M6 competition investigated forecasting accuracy and investment performance in a universe of 100 publicly traded assets. The competition employed live evaluation on real data across multiple periods, a cross-sectional setting where participants predicted asset performance relative to that of other assets, and a direct evaluation of the utility of forecasts. In this way, we were able to measure the benefits of accurate forecasting and assess the importance of forecasting when making investment decisions. Our findings highlight the challenges that participants faced when attempting to accurately forecast the relative performance of assets, the great difficulty associated with trying to consistently outperform the market, the limited connection between submitted forecasts and investment decisions, the value added by information exchange and the “wisdom of crowds”, and the value of utilizing risk models when attempting to connect prediction and investing decisions. © 2024 The Author(s)

关键词： Assets Forecast accuracy forecasting competitions Investment decisions M competitions

The M6 forecasting competition: Bridging the gap between forecasting and investment decisions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Makridakis, Spyros Spiliotis, Evangelos Hollyman, Ross Petropoulos, Fotios Swanson, Norman Gaba, Anil Makridakis Open Forecasting Center Institute For the Future University of Nicosia Cyprus Forecasting and Strategy Unit School of Electrical and Computer Engineering National Technical University of Athens Greece Business School University of Exeter Exeter United Kingdom School of Management University of Bath United Kingdom Department of Economics Rutgers University NJ United States INSEAD Singapore

The M6 forecasting competition, the sixth in the Makridakis’ competition sequence, is focused on financial forecasting. A key objective of the M6 competition was to contribute to the debate surrounding the Efficient Market Hypothesis (EMH) by examining how and why market participants make investment decisions. To address these objectives, the M6 competition investigated forecasting accuracy and investment performance on a universe of 100 publicly traded assets. The competition employed live evaluation on real data across multiple periods, a cross-sectional setting where participants predicted asset performance relative to that of other assets, and a direct evaluation of the utility of forecasts. In this way, we were able to measure the benefits of accurate forecasting and assess the importance of forecasting when making investment decisions. Our findings highlight the challenges that participants faced when attempting to accurately forecast the relative performance of assets, the great difficulty associated with trying to consistently outperform the market, the limited connection between submitted forecasts and investment decisions, the value added by information exchange and the "wisdom of crowds", and the value of utilizing risk models when attempting to connect prediction and investing decisions. © 2023, CC BY.

关键词： forecasting

Time Series and Regression Methods for Univariate Environmental forecasting: An Empirical Evaluation

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Effrosynidis, Dimitrios Spiliotis, Evangelos Sylaios, Georgios Arampatzis, Avi Database & Information Retrieval research unit Department of Electrical & Computer Engineering Democritus University of Thrace Xanthi67100 Greece Forecasting and Strategy Unit School of Electrical and Computer Engineering National Technical University of Athens Athens Greece Lab of Ecological Engineering & Technology Department of Environmental Engineering Democritus University of Thrace Xanthi67100 Greece

One of the most common and valuable applications of science to the environment is to forecast the future, as it affects human lives in many aspects. However, it is not yet clear which methods –conventional time series or regression– deliver the highest performance in univariate time series forecasting. This study attempts to answer that question with a large-scale comparative evaluation that includes 68 environmental variables over three frequencies (hourly, daily, monthly), forecasted in one to twelve steps into the future, and evaluated over six statistical time series and fourteen regression methods. Results suggest that the strongest representatives of the time series modes (ARIMA, Theta) exhibit high accuracies, but certain regression models (Huber, Extra Trees, Random Forest, Light Gradient Boosting Machines, Gradient Boosting Machines, Ridge, Bayesian Ridge) deliver even more promising results for all forecasting horizons. Finally, depending on the specific use case, the suitable method should be employed, as certain methods are more appropriate for different frequencies and some have an advantageous trade-off between computational time and performance. © 2022, The Authors. All rights reserved.

关键词： forecasting

Exploring the representativeness of the M5 competition data

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Theodorou, Evangelos Wang, Shengjie Kang, Yanfei Spiliotis, Evangelos Makridakis, Spyros Assimakopoulos, Vassilios Forecasting and Strategy Unit School of Electrical and Computer Engineering National Technical University of Athens Greece School of Economics and Management Beihang University China Institute For the Future University of Nicosia Cyprus

The main objective of the M5 competition, which focused on forecasting the hierarchical unit sales of Walmart, was to evaluate the accuracy and uncertainty of forecasting methods in the field in order to identify best practices and highlight their practical implications. However, whether the findings of the M5 competition can be generalized and exploited by retail firms to better support their decisions and operation depends on the extent to which the M5 data is sufficiently similar to unit sales data of retailers that operate in different regions, sell different types of products, and consider different marketing strategies. To answer this question, we analyze the characteristics of the M5 time series and compare them with those of two grocery retailers, namely Corporación Favorita and a major Greek supermarket chain, using feature spaces. Our results suggest that there are only small discrepancies between the examined data sets, supporting the representativeness of the M5 data. Copyright © 2021, The Authors. All rights reserved.

关键词： Sales

Model combinations through revised base-rates

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Petropoulos, Fotios Spiliotis, Evangelos Panagiotelis, Anastasios School of Management University of Bath United Kingdom Forecasting and Strategy Unit School of Electrical and Computer Engineering National Technical University of Athens Greece Discipline of Business Analytics University of Sydney Australia

Standard selection criteria for forecasting models focus on information that is calculated for each series independently, disregarding the general tendencies and performances of the candidate models. In this paper, we propose a new way to statistical model selection and model combination that incorporates the base-rates of the candidate forecastingmodels, which are then revised so that the per-series information is taken into account. We examine two schemes that are based on the precision and sensitivity information from the contingency table of the base rates. We apply our approach on pools of exponential smoothing models and a large number of real time series and we show that our schemes work better than standard statistical benchmarks. We discuss the connection of our approach to other cross-learning approaches and offer insights regarding implications for theory and practice. © 2021, CC BY.

关键词：