检索结果-内蒙古大学图书馆

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

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

Resilience-oriented Operation of Power Distribution Networks with Line Hardening and Comprehensive Reconfiguration Measures 14

学校读者我要写书评

暂无评论

Resilience-oriented Operation of Power Distribution Networks...

14th IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids, SmartGridComm 2023

作者： Li, Zhengmao Shi, Zhao Ruan, Guangchun Lin, Yuzhang Zhao, Jin Aalto University School of Electrical Engineering Espoo Finland Nanyang Technological University School of Electrical and Electronic Engineering Singapore Massachusetts Institute of Technology Laboratory for Information & Decision Systems Boston United States New York University Department of Electrical and Computer Engineering New York United States Trinity College Dublin Department of Electronic and Electrical Engineering Dublin Ireland

ISBN: (纸本)9781665455541

With the frequent occurrence of extreme events like natural disasters and man-made attacks, the resilience concept is attracting worldwide research attention. Thus, this paper proposes a resilient operation model for the power distribution network (PDN) to recover load and limit economic loss to the greatest possible extent. First, the line hardening measure is applied to strengthen the PDN to avoid the serious breakdown of distribution lines. In addition, a comprehensive single commodity flow-based reconfiguration approach is used which not only sets the buses connecting generation sources but also those at the end of broken lines as the slack buses. Then, the radiality of PDNs can still be guaranteed after reconfiguration. The resilience-oriented operation problem can be originally formulated as a nonlinear programming one while efficient linearization methods are applied to reduce computational burdens. Hence, the operation problem is reformulated as a mixed-integer linear programming one which will enjoy favorable solution performances. Finally, case studies on an IEEE 33 PDN including comparison cases with traditional benchmarks are done to show the effectiveness of our method. © 2023 IEEE.

关键词： Hardening

Constructive Function Approximation with Local Models

学校读者我要写书评

暂无评论

Constructive Function Approximation with Local Models

Mediterranean Conference on Control and Automation (MED)

作者： Christos N. Mavridis Karl Henrik Johansson Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm

ISBN: (数字)9798350395440

ISBN: (纸本)9798350395457

We introduce a constructive function approximation approach as a general tool, particularly useful in adaptive and data-driven methods for perception and control. The key idea is to estimate of a collection of simple local models as opposed to a single and complex regression model trained in the entire input space. We use principles from the Online Deterministic Annealing (ODA) optimization framework to construct an adaptive partition of the input space, which enables the introduction of local function approximation models within each subset of the partition. We show that both the partitioning and the local model training algorithms are stochastic approximation algorithms that operate online, and with the same observations, as part of a two-timescale stochastic approximation scheme. This process constitutes a heuristic method to gradually increase the complexity of the function approximation framework in a task-agnostic manner, giving emphasis to regions of the input space where the regression error is high. As a result this framework has inherent explainability properties, and is suitable for continuous learning applications where regression improvement without retraining from scratch is crucial. Simulation results illustrate the properties of the proposed approach.

关键词： Training Adaptation models Simulation Stochastic processes Aerospace electronics Approximation algorithms Partitioning algorithms

An Integrated AI-Based Information System for Energy Forecasting

学校读者我要写书评

暂无评论

An Integrated AI-Based Information System for Energy Forecas...

International Conference on Information, Intelligence, systems and Applications (IISA)

作者： Panagiotis Skaloumpakas Zoi Mylona Sofoklis Strompolas Elissaios Sarmas Haris Doukas HOLISTIC IKE Athens Greece Decision Support Systems Laboratory School of Electrical and Computer Engineering National Technical University of Athens Athens Greece

The aim of reducing carbon emissions through the digitization of the energy sector involves several challenges. One potential solution is the integration of renewable energy sources; however, the volatile and intermittent nature of this type of energy requires precise forecasting. This paper presents a novel, intelligent information system that covers the entire data lifecycle in the energy sector, including data acquisition, processing and storage, model development and training, and a user-friendly web application. The system was tested in three real-life use cases and demonstrated effectiveness and versatility in addressing the intricate data challenges faced by the energy industry. The paper concludes with suggestions for further research in this area.

关键词：

Slow Convergence of Interacting Kalman Filters in Word-of-Mouth Social Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Krishnamurthy, Vikram Rojas, Cristian R. School of Electrical and Computer Engineering Cornell University United States Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

We consider word-of-mouth social learning involving m Kalman filter agents that operate sequentially. The first Kalman filter receives the raw observations, while each subsequent Kalman filter receives a noisy measurement of the conditional mean of the previous Kalman filter. The prior is updated by the m-th Kalman filter. When m = 2, and the observations are noisy measurements of a Gaussian random variable, the covariance goes to zero as k−1/3 for k observations, instead of O(k−1) in the standard Kalman filter. In this paper we prove that for m agents, the covariance decreases to zero as k−(2m−1), i.e, the learning slows down exponentially with the number of agents. We also show that by artificially weighing the prior at each time, the learning rate can be made optimal as k−1. The implication is that in word-of-mouth social learning, artificially re-weighing the prior can yield the optimal learning rate. Copyright © 2024, The Authors. All rights reserved.

关键词： Kalman filters

Energy Sector Digitilisation: A Security Framework Application for Role-Based Access Management

学校读者我要写书评

暂无评论

Energy Sector Digitilisation: A Security Framework Applicati...

International Conference on Information, Intelligence, systems and Applications (IISA)

作者： Georgios Kormpakis Panagiotis Kapsalis Konstantinos Alexakis Zoi Mylona Sotiris Pelekis Vangelis Marinakis Decision Support Systems Laboratory School of Electrical and Computer Engineering National Technical University of Athens Athens Greece HOLISTIC Athens SA Greece

Data security and privacy in the energy sector and especially in buildings' energy management, is an emerging issue which cannot be underestimated, thus, calls for solid and robust solutions. The reliable functioning of energy management data platforms is essential for the efficient operation and performance of buildings, as well as the well-being of occupants. The fast-paced digital advances have aided this direction, but they have also created increased challenges for operation disruption mitigation and immutable services and outcomes. Data obtained from energy management systems frequently comprises highly sensitive and personal information. Consequently, access to such data, whether for reading purposes or for conducting experiments and research, must be strictly restricted and clearly defined. Through security frameworks data protection and information privacy, mitigation of risks and vulnerabilities can be ensured. In this paper, an end-to-end Security Framework is proposed for securing sensitive resources in energy management systems using Keycloak, OAuth2 and UMA 2 protocols as well as an extra security layer on top of the Keycloak, so as to enhance the overall security and avoid immediate interaction with Keycloak, which is the main user storage and access management component. The main concept of this framework is the controlled access of sensitive data and services, such as datasets, databases, functionalities, URLs, APIs, etc., leveraging the OAuth2 access tokens capabilities and the roles of the users. Our proposed architecture ensures that all the functionalities of the involved tools and protocols are properly secured end-to-end. The several existing functionalities of a number of tools and related protocols are properly leveraged and further extended, resulting to a fine-grained architecture with an extra security layer that offers administrative, security and identity access management and orchestration.

关键词：

Bayes and Biased Estimators Without Hyper-parameter Estimation: Comparable Performance to the Empirical-Bayes-Based Regularized Estimator

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ju, Yue Wahlberg, Bo Hjalmarsson, Håkan Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

Regularized system identification has become a significant complement to more classical system identification. It has been numerically shown that kernel-based regularized estimators often perform better than the maximum likelihood estimator in terms of minimizing mean squared error (MSE). However, regularized estimators often require hyper-parameter estimation. This paper focuses on ridge regression and the regularized estimator by employing the empirical Bayes hyperparameter estimator. We utilize the excess MSE to quantify the MSE difference between the empirical-Bayes-based regularized estimator and the maximum likelihood estimator for large sample sizes. We then exploit the excess MSE expressions to develop both a family of generalized Bayes estimators and a family of closed-form biased estimators. They have the same excess MSE as the empirical-Bayes-based regularized estimator but eliminate the need for hyper-parameter estimation. Moreover, we conduct numerical simulations to show that the performance of these new estimators is comparable to the empirical-Bayes-based regularized estimator, while computationally, they are more efficient. Copyright © 2025, The Authors. All rights reserved.

关键词： Mean square error

Real-time Hybrid System Identification with Online Deterministic Annealing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mavridis, Christos N. Johansson, Karl Henrik Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

We introduce a real-time identification method for discrete-time state-dependent switching systems in both the input-output and state-space domains. In particular, we design a system of adaptive algorithms running in two timescales;a stochastic approximation algorithm implements an online deterministic annealing scheme at a slow timescale and estimates the mode-switching signal, and an recursive identification algorithm runs at a faster timescale and updates the parameters of the local models based on the estimate of the switching signal. We first focus on piece-wise affine systems and discuss identifiability conditions and convergence properties based on the theory of two-timescale stochastic approximation. In contrast to standard identification algorithms for switched systems, the proposed approach gradually estimates the number of modes and is appropriate for real-time system identification using sequential data acquisition. The progressive nature of the algorithm improves computational efficiency and provides real-time control over the performance-complexity trade-off. Finally, we address specific challenges that arise in the application of the proposed methodology in identification of more general switching systems. Simulation results validate the efficacy of the proposed methodology. © 2024, CC BY.

关键词： Stochastic systems