检索结果-内蒙古大学图书馆

30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

作者： Roque, Luis Soares, Carlos Torgo, Luis Univ Porto LIACC Fac Engn Porto Portugal Fraunhofer AICOS Portugal Porto Portugal Dalhousie Univ Halifax NS Canada

ISBN: (纸本)9798400704901

We introduce the Robustness of Hierarchically Organized Time Series (RHiOTS) framework, designed to assess the robustness of hierarchical time series forecasting models and algorithms on real-world datasets. Hierarchical time series, where lower-level forecasts must sum to upper-level ones, are prevalent in various contexts, such as retail sales across countries. Current empirical evaluations of forecasting methods are often limited to a small set of benchmark datasets, offering a narrow view of algorithm behavior. RHiOTS addresses this gap by systematically altering existing datasets and modifying the characteristics of individual series and their interrelations. It uses a set of parameterizable transformations to simulate those changes in the data distribution. Additionally, RHiOTS incorporates an innovative visualization component, turning complex, multidimensional robustness evaluation results into intuitive, easily interpretable visuals. This approach allows an in-depth analysis of algorithm and model behavior under diverse conditions. We illustrate the use of RHiOTS by analyzing the predictive performance of several algorithms. Our findings show that traditional statistical methods are more robust than state-of-the-art deep learning algorithms, except when the transformation effect is highly disruptive. Furthermore, we found no significant differences in the robustness of the algorithms when applying specific reconciliation methods, such as MinT. RHiOTS provides researchers with a comprehensive tool for understanding the nuanced behavior of forecasting algorithms, offering a more reliable basis for selecting the most appropriate method for a given problem.

关键词： Hierarchical time series forecasting algorithms Evaluation methods Time series forecasting

来源：评论

学校读者我要写书评

暂无评论

A post-forecast weighing algorithm to improve wind power forecasting capabilities

引用

IET RENEWABLE POWER GENERATION 2023年第2期17卷 296-304页

作者： Pijnenburg, Petrus Cao, Bo Chang, Liuchen Kilpatrick, Ryan Levy, Thomas Univ New Brunswick Dept Elect & Comp Engn 15 Dineen Dr Fredericton NB E3B 5A3 Canada Nat Resources Canada CanmetENERGY Ottawa Ottawa ON Canada

Wind power generation has had a profound impact on both the green power and traditional power sectors. As a result, wind power forecasting plays an immense role in effectively predicting and providing wind power generated for effective power dispatching for system operators. However, wind power forecasting is a challenging topic with accuracy issues between the predicted power and actual power generation at the point of common coupling. Furthermore, due to the variation of wind, effective dispatching through the utilisation of wind power production forecasting becomes a challenge. This issue is further compounded by the vast amount of data required to train and verify of these forecasting algorithms. This paper presents a fast acting post forecast weighing algorithm designed to evaluate the forecasted power output of a previously developed wind power forecasting package. The developed method is designed to gauge and improve the estimated output forecaster's approach in order to observe performance changes in the algorithm while using minimal data without changing the internal workings of the evaluated forecasting algorithm.

关键词： Wind power plants Power system management, operation and economics effective power dispatching fast acting post forecast actual power generation forecasting algorithms wind power generation forecasted power output predicted power load forecasting Power system planning and layout power generation planning power generation economics power generation dispatch green power wind power production forecasting wind power plants estimated output forecaster developed wind power forecasting package power grids wind power forecasting capabilities wind power post-forecast weighing algorithm evaluated forecasting algorithm

来源：评论

学校读者我要写书评

暂无评论

A Short-Term forecasting Algorithm for Electricity Load Consumption of Energy Generating Plants Under Dual Carbon Goal ConstraintsSubtitle 5

A Short-Term Forecasting Algorithm for Electricity Load Cons...

引用

5th International Conference on Smart Grid and Energy Engineering, SGEE 2024

作者： Chen, Zhijian Ji, Xiaoheng Lu, Xueying Wu, Yongqin China Energy Engineering Group Guangdong Electric Power Design Institute Co. Ltd. Guangdong Guangzhou510000 China

ISBN: (纸本)9798331530686

Conventional short-term forecasting algorithms for power load consumption mainly use the DNN (Deep Neural Network) deep neural network model to generate variable forecasting curves, which is vulnerable to the impact of non-stationary load sequence changes, resulting in poor forecasting performance indicators. Therefore, considering the constraints of dual carbon goals, a short-term forecasting algorithm for power load consumption of energy power plants is proposed. That is to say, the training samples of short-term forecasting of power load are constructed considering the constraints of dual carbon goals, and the optimization process of short-term forecasting algorithm of power load consumption of energy power plants is designed, so as to realize short-term forecasting of power load consumption. The experimental results show that the designed short-term forecasting algorithm for power load consumption of energy power plants considering dual carbon target constraints has better forecasting indicators, better forecasting effect, reliability and certain application value, and has made certain contributions to improving the power supply and distribution efficiency of energy power plants and reducing comprehensive losses. © 2024 IEEE.

关键词： Dual-carbon objective constraints Electricity load consumption Energy power plants forecasting algorithms Short time

来源：评论

学校读者我要写书评

暂无评论

Dynamic line rating forecasting algorithm for a secure power system network

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期219卷

作者： Lawal, Olatunji Ahmed Teh, Jiashen Univ Sains Malaysia USM Sch Elect & Elect Engn Penang Nibong Tebal 14300 Malaysia Kwara State Polytech Inst Technol Dept Elect & Elect Engn Ilorin Nigeria

This research aimed to enhance the capacity of transmission lines by developing an algorithm to predict Dynamic Line Rating (DLR) to avert the curtailment of renewable energy sources. This will help meet electricity demand, prevent power outages, reduce costs, and protect equipment and personnel. The proposed algorithm was trained by analyzing the correlation between sequential hourly DLR calculations derived from historical weather data and line physical parameters. The proposed algorithm used k-means clustering and Monte Carlo simulation to predict hourly DLR, considering the temporal correlation of historical DLR values for each month. The model's accuracy was verified through statistical tests and was compared to other forecasting methods such as ensemble forecasting, quantile regression, and recurrent neural networks. It was found that the proposed model demon-strated performance that is comparable or superior to existing methods, as seen in forecast skill ranging from 91 to 98%, a Continuous Ranked Probability Score (CRPS) between 0.02 and 0.05, and probabilistic ratings that are 48-70% higher than traditional Static Line Rating (SLR).

关键词： Clustering Dynamic line rating forecasting algorithms Monte Carlo simulation Machine learning Probabilistic forecasting

来源：评论

学校读者我要写书评

暂无评论

An analysis of the influence of famous people's posts on social networks on the cryptocurrency exchange rate

引用

BULLETIN OF THE POLISH ACADEMY OF SCIENCES-TECHNICAL SCIENCES 2024年第4期72卷

作者： Telenyk, Sergii Nowakowski, Grzegorz Gavrilenko, Olena Miahkyi, Mykhailo Khalus, Olena Cracow Univ Technol Fac Elect & Comp Engn Warszawska 24 PL-31155 Krakow Poland Natl Tech Univ Ukraine Igor Sikorsky Kyiv Polytech Inst Prosp Peremohy 37 Kyiv Ukraine

In this work, the level of influence of the posts published by famous people on social networks on the formation of the cryptocurrency exchange rate is investigated. Celebrities who are familiar with the financial industry, especially with the cryptocurrency market, or are somehow connected to a certain cryptocurrency, such as Elon Musk with Dogecoin, are chosen as experts whose influence through social media posts on cryptocurrency rates is examined. This research is conducted based on statistical analysis. Real cryptocurrency exchange rate forecasts for the selected time period and predicted ones for the same period, obtained using three algorithms, are utilized as a dataset. This paper uses methods such as statistical hypotheses regarding the significance of Spearman's rank correlation coefficient and Pearson's correlation. It is confirmed that the posts by famous people on social networks significantly affect the exchange rates of cryptocurrencies.

关键词： cryptocurrency exchange rate forecasting algorithms posts on social networks methods of statistical analysis information technology of intellectual analysis

来源：评论

学校读者我要写书评

暂无评论

Overbooking models based on personal data analysis

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GA...

引用

JOURNAL OF THE FACULTY OF ENGINEERING AND ARCHITECTURE OF GAZI UNIVERSITY 2021年第3期36卷 1374-1386页

作者： Yavuz, Tugce Kaya, Onur Eskisehir Tekn Univ Endustri Muhendisligi Bolumu TR-26555 Eskisehir Turkey

Overbooking policy, which is part of revenue management, is applied in many sectors today where unused capacity cannot be stored. The purpose of this application, in which the company receives reservation over the capacity in order to cover the spoilage cost it will encounter because of no-show customers, is to maximize the amount of earnings while reducing spoilage costs. In the classical approach, the show probability of each customer is assumed to be the same. In this study, unlike the classical approach, the show probability of each reservation is estimated on a personal basis. Personal probabilities needed for the suggested approach are obtained from historical booking information using forecasting algorithms. The fact that each customer has different show probability makes it difficult to calculate the total number of no-shows in the classical way. For this reason, Monte Carlo simulation is used to calculate the optimal booking limit when show probability of each customer is taken differently on a personal basis. As a result of the study, it is seen that with the proposed dynamic models, higher gains can be achieved compared to the classical approach.

关键词： Overbooking Monte Carlo simulation data mining forecasting algorithms

来源：评论

学校读者我要写书评

暂无评论

Experimenting forecasting Models for Solar Energy Harvesting Devices for Large Smart Cities Deployments

Experimenting Forecasting Models for Solar Energy Harvesting...

引用

IEEE Symposium on Computers and Communications (ISCC)

作者： Caruso, Antonio Chessa, Stefano Escolar, Soledad del Toro, Xavier Kuzman, Melisa Lopez, Juan C. Univ Salento Dept Math & Phys Ennio de Giorgi Lecce Italy Univ Pisa Comp Sci Dept Pisa Italy Univ Castilla La Mancha Sch Comp Sci Ciudad Real Spain Univ Mar del Plata Mar Del Plata Argentina

ISBN: (纸本)9781728129990

To make sustainable large IoT deployments in smart cities, a promising approach is to develop a new generation of solar energy harvesting IoT devices based on the concept of energy neutrality. Key to this concept are the models for the forecast of energy production, which provide input to the energy neutral schedulers governing the activities of the IoT devices. The development of such models however need to be validated against real-world conditions. To this purpose we propose a testbed aimed at the collection of real-world dataset about the energy parameters of energy harvesting IoT devices, and, on the base of such a dataset, we perform a comparative assessment of state of the art and novel energy production forecast models.

关键词： IoT testbed dataset solar energy harvesting forecasting algorithms

来源：评论

学校读者我要写书评

暂无评论

Online learning with an almost perfect expert

引用

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA 2019年第13期116卷 5949-5954页

作者： Branzei, Simina Peres, Yuval Purdue Univ Dept Comp Sci W Lafayette IN 47907 USA Microsoft Res Redmond WA 98052 USA

We study multiclass online learning, where a forecaster predicts a sequence of elements drawn from a finite set using the advice of n experts. Our main contributions are to analyze the scenario where the best expert makes a bounded number b of mistakes and to show that, in the low-error regime where b = o(log n), the expected number of mistakes made by the optimal forecaster is at most log(4) n + o(log n). We also describe an adversary strategy showing that this bound is tight and that the worst case is attained for binary prediction.

关键词： online learning multiclass decision making expert advice forecasting algorithms lower bounds

来源：评论

学校读者我要写书评

暂无评论

Predicting Grades

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2016年第4期64卷 959-972页

作者： Meier, Yannick Xu, Jie Atan, Onur van der Schaar, Mihaela Univ Calif Los Angeles Dept Elect Engn Los Angeles CA 90095 USA

To increase efficacy in traditional classroom courses as well as in Massive Open Online Courses (MOOCs), automated systems supporting the instructor are needed. One important problem is to automatically detect students that are going to do poorly in a course early enough to be able to take remedial actions. Existing grade prediction systems focus on maximizing the accuracy of the prediction while overseeing the importance of issuing timely and personalized predictions. This paper proposes an algorithm that predicts the final grade of each student in a class. It issues a prediction for each student individually, when the expected accuracy of the prediction is sufficient. The algorithm learns online what is the optimal prediction and time to issue a prediction based on past history of students' performance in a course. We derive a confidence estimate for the prediction accuracy and demonstrate the performance of our algorithm on a dataset obtained based on the performance of approximately 700 UCLA undergraduate students who have taken an introductory digital signal processing over the past seven years. We demonstrate that for 85% of the students we can predict with 76% accuracy whether they are going do well or poorly in the class after the fourth course week. Using data obtained from a pilot course, our methodology suggests that it is effective to perform early in-class assessments such as quizzes, which result in timely performance prediction for each student, thereby enabling timely interventions by the instructor (at the student or class level) when necessary.

关键词： forecasting algorithms online learning grade prediction data mining digital signal processing education

来源：评论

学校读者我要写书评

暂无评论

Personalized Grade Prediction: A Data Mining Approach 15

Personalized Grade Prediction: A Data Mining Approach

引用

IEEE International Conference on Data Mining (ICDM)

作者： Meier, Yannick Xu, Jie Atan, Onur van der Schaar, Mihaela Univ Calif Los Angeles Los Angeles CA 90095 USA

ISBN: (纸本)9781467395038

To increase efficacy in traditional classroom courses as well as in Massive Open Online Courses (MOOCs), automated systems supporting the instructor are needed. One important problem is to automatically detect students that are going to do poorly in a course early enough to be able to take remedial actions. This paper proposes an algorithm that predicts the final grade of each student in a class. It issues a prediction for each student individually, when the expected accuracy of the prediction is sufficient. The algorithm learns online what is the optimal prediction and time to issue a prediction based on past history of students' performance in a course. We derive demonstrate the performance of our algorithm on a dataset obtained based on the performance of approximately 700 undergraduate students who have taken an introductory digital signal processing over the past 7 years. Using data obtained from a pilot course, our methodology suggests that it is effective to perform early in-class assessments such as quizzes, which result in timely performance prediction for each student, thereby enabling timely interventions by the instructor (at the student or class level) when necessary.

关键词： forecasting algorithms online learning grade prediction data mining digital signal processing education

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：