scholarly journals Solar Irradiance Forecasting Using a Data-Driven Algorithm and Contextual Optimisation

2021 ◽  
Vol 12 (1) ◽  
pp. 134
Author(s):  
Paula Bendiek ◽  
Ahmad Taha ◽  
Qammer H. Abbasi ◽  
Basel Barakat
Keyword(s):  
Solar Irradiance ◽  
Contextual Information ◽  
Management Strategies ◽  
Energy Transition ◽  
Data Driven ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Short Term ◽  
Forecast Horizon

Solar forecasting plays a key part in the renewable energy transition. Major challenges, related to load balancing and grid stability, emerge when a high percentage of energy is provided by renewables. These can be tackled by new energy management strategies guided by power forecasts. This paper presents a data-driven and contextual optimisation forecasting (DCF) algorithm for solar irradiance that was comprehensively validated using short- and long-term predictions, in three US cities: Denver, Boston, and Seattle. Moreover, step-by-step implementation guidelines to follow and reproduce the results were proposed. Initially, a comparative study of two machine learning (ML) algorithms, the support vector machine (SVM) and Facebook Prophet (FBP) for solar prediction was conducted. The short-term SVM outperformed the FBP model for the 1- and 2- hour prediction, achieving a coefficient of determination (R2) of 91.2% in Boston. However, FBP displayed sustained performance for increasing the forecast horizon and yielded better results for 3-hour and long-term forecasts. The algorithms were optimised by further contextual model adjustments which resulted in substantially improved performance. Thus, DCF utilised SVM for short-term and FBP for long-term predictions and optimised their performance using contextual information. DCF achieved consistent performance for the three cities and for long- and short-term predictions, with an average R2 of 85%.

Enuresis: Myths, Misunderstandings and Solutions

1995 ◽  
Vol 1 (1) ◽  
pp. 74
Author(s):  
Martin Knapp
Keyword(s):  
Management Strategies ◽  
Short Term ◽  
Treatment Facilities ◽  
Conditioning Therapy ◽  
Treatable Condition ◽  
Term Management

Advice on enuresis has been provided by a range of individuals. Many myths and misunderstandings have been responsible for the confusing range of opinions given to those who seek help. Management should be based on an understanding of the physiology of the condition and the established facts about its treatment. There is still a lack of awareness about how effective are the management strategies now proposed by those who base their practise on the extensive research that is now documented. The best results are obtained with conditioning therapy, when this is supervised and supported. There is an important role for 'wetness' alarms in conditioning. There are now body-worn mini-alarms, established by over a decade of use, that are inexpensive and reliable. There is a decreasing role for tricyclic medication. The recently introduced pharmaceutical Minirin (desmopressin) is useful in short-term management to get dryness on social occasions and, in selected individuals, might have a role in long-term control of enuresis, when conditioning has not been effective. There is an important need to provide advice and treatment facilities for all those with enuresis - a treatable condition.

scholarly journals Artificial Intelligence Techniques for Estimation of Optimum Weibull Parameters for Wind Speed Distribution

2019 ◽  
Vol 8 (4S2) ◽  
pp. 150-156
Keyword(s):  
Wind Speed ◽  
Tamil Nadu ◽  
Optimization Algorithms ◽  
Coefficient Of Determination ◽  
Short Term ◽  
Weibull Parameters ◽  
Wind Speed Data ◽  
Speed Distribution ◽  
Wind Speed Distribution

The main objective of this study is to estimate the optimum Weibull scale and shape parameters for wind speed distribution at three stations of the state of Tamil Nadu, India using Nelder-Mead, Broyden–Fletcher–Goldfarb–Shanno, and Simulated annealing optimization algorithms. An attempt has been made for the first time to apply these optimization algorithms to determine the optimum parameters. The study was conducted for long term wind speed data (38 years), short term wind speed data (5 years) and also with single year’s wind speed data to assess the performance of the algorithm for different quantum of data. The efficiency of these algorithms are analyzed using various statistical indicators like Root mean square error (RMSE), Correlation coefficient (R), Mean absolute error (MAE) and coefficient of determination (R2). The results suggest that the performance of three algorithms is similar irrespective of the quantum of the dataset. The estimated Weibull parameters are almost similar for short term and long term dataset. There is a marginal variation in the obtained parameters when only single year’s wind data is considered for the analysis. The Weibull probability distribution curve fits very well on the wind speed histogram when only single year’s wind speed data is considered and fits marginally well when short term and long term wind speed data is considered

Evolutionary Stable Strategies for Supply Chains: Selfishness, Fairness, and Altruism

2018 ◽  
Vol 6 (6) ◽  
pp. 532-551 ◽  
Author(s):  
Caichun Chai ◽  
Hailong Zhu ◽  
Zhangwei Feng
Keyword(s):  
Supply Chains ◽  
Evolutionary Dynamics ◽  
Replicator Dynamics ◽  
Management Strategies ◽  
Individual Preference ◽  
Short Term ◽  
Evolutionary Stable Strategies ◽  
Pure Strategies ◽  
The Stability

Abstract The management strategies of a firm are inevitable affected by individual behavior preferences. The effect of individual preference on the evolutionary dynamics for supply chains is studied by employing replicator dynamics. Each firm has three behavior preferences: selfishness, fairness, and altruism. Firstly, the case that the strategy set of manufacturers and retailers including two pure strategies is considered and the effect of preference parameter on the equilibrium outcome in the short-term interaction is discussed. Secondly, the equilibrium state in the short-term is always disturbed because the change of the environment, firm’s structure, and so forth. Using the replicator dynamics, the evolutionary stable strategies of manufacturers and retailers in the long-term interaction are analyzed. Finally, the extend case that the strategy set of manufacturers and retailers include three pure strategies is investigated. These results are found that the strategy profile in which both manufacturer and retailer choose fairness or altruism, or one player chooses fair or altruistic strategy and the other player chooses selfish strategy may be evolutionary stable, the stability of these equilibria depends on the the preference parameters.

Long-Term Orientation and Earnings Management Strategies

2019 ◽  
Vol 18 (3) ◽  
pp. 97-119 ◽  
Author(s):  
Jesper Haga ◽  
Fredrik Huhtamäki ◽  
Dennis Sundvik
Keyword(s):  
Earnings Management ◽  
High Precision ◽  
Management Strategy ◽  
Management Strategies ◽  
Real Earnings Management ◽  
Short Term ◽  
Country Level ◽  
Earnings Benchmarks ◽  
Jel Classifications

ABSTRACT In this study, we investigate how country-level long-term orientation affects managers' willingness to engage in earnings management and choice of earnings management strategy. Using a comprehensive dataset of 47 countries for the period from 2003 to 2015, we find that firms in long-term-oriented cultures rely relatively more on earnings management through accruals, while firms in short-term-oriented cultures engage in relatively more real earnings management. Furthermore, we find a larger discontinuity around earnings benchmarks in long-term-oriented cultures suggesting that manipulation of accruals enables benchmark beating with high precision. JEL Classifications: M14; M16; M21; M41.

Determinants of rental strategy: short-term vs long-term rental strategy

2020 ◽  
Vol 13 (12) ◽  
pp. 3873-3894
Author(s):  
Sina Shokoohyar ◽  
Ahmad Sobhani ◽  
Anae Sobhani
Keyword(s):  
Nearest Neighbor ◽  
Performance Metrics ◽  
Sharing Economy ◽  
Real Estate Market ◽  
Support Vector ◽  
Attractive Alternative ◽  
K Nearest Neighbor ◽  
Short Term ◽  
Content Type

Purpose Short-term rental option enabled via accommodation sharing platforms is an attractive alternative to conventional long-term rental. The purpose of this study is to compare rental strategies (short-term vs long-term) and explore the main determinants for strategy selection. Design/methodology/approach Using logistic regression, this study predicts the rental strategy with the highest rate of return for a given property in the City of Philadelphia. The modeling result is then compared with the applied machine learning methods, including random forest, k-nearest neighbor, support vector machine, naïve Bayes and neural networks. The best model is finally selected based on different performance metrics that determine the prediction strength of underlying models. Findings By analyzing 2,163 properties, the results show that properties with more bedrooms, closer to the historic attractions, in neighborhoods with lower minority rates and higher nightlife vibe are more likely to have a higher return if they are rented out through short-term rental contract. Additionally, the property location is found out to have a significant impact on the selection of the rental strategy, which emphasizes the widely known term of “location, location, location” in the real estate market. Originality/value The findings of this study contribute to the literature by determining the neighborhood and property characteristics that make a property more suitable for the short-term rental vs the long-term one. This contribution is extremely important as it facilitates differentiating the short-term rentals from the long-term rentals and would help better understanding the supply-side in the sharing economy-based accommodation market.

scholarly journals Cost Index Predictions for Construction Engineering Based on LSTM Neural Networks

2020 ◽  
Vol 2020 ◽  
pp. 1-14 ◽  
Author(s):  
Jiacheng Dong ◽  
Yuan Chen ◽  
Gang Guan
Keyword(s):  
Neural Network ◽  
Support Vector ◽  
Short Term ◽  
Cost Index ◽  
Long Distance ◽  
Research Knowledge ◽  
Construction Engineering ◽  
Engineering Cost ◽  
Optimization Mechanism

In recent years, the cost index predictions of construction engineering projects are becoming important research topics in the field of construction management. Previous methods have limitations in reasonably reflecting the timeliness of engineering cost indexes. The recurrent neural network (RNN) belongs to a time series network, and the purpose of timeliness transfer calculation is achieved through the weight sharing of time steps. The long-term and short-term memory neural network (LSTM NN) solves the RNN limitations of the gradient vanishing and the inability to address long-term dependence under the premise of having the above advantages. The present study proposed a new framework based on LSTM, so as to explore the applicability and optimization mechanism of the algorithm in the field of cost indexes prediction. A survey was conducted in Shenzhen, China, where a total of 143 data samples were collected based on the index set for the corresponding time interval from May 2007 to March 2019. A prediction framework based on the LSTM model, which was trained by using these collected data, was established for the purpose of cost index predictions and test. The testing results showed that the proposed LSTM framework had obvious advantages in prediction because of the ability of processing high-dimensional feature vectors and the capability of selectively recording historical information. Compared with other advanced cost prediction methods, such as Support Vector Machine (SVM), this framework has advantages such as being able to capture long-distance dependent information and can provide short-term predictions of engineering cost indexes both effectively and accurately. This research extended current algorithm tools that can be used to forecast cost indexes and evaluated the optimization mechanism of the algorithm in order to improve the efficiency and accuracy of prediction, which have not been explored in current research knowledge.

scholarly journals Forecasting of Landslide Displacement Using a Probability-Scheme Combination Ensemble Prediction Technique

2020 ◽  
Vol 17 (13) ◽  
pp. 4788 ◽  
Author(s):  
Junwei Ma ◽  
Xiao Liu ◽  
Xiaoxu Niu ◽  
Yankun Wang ◽  
Tao Wen ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Quantile Regression ◽  
Extreme Learning Machine ◽  
Data Driven ◽  
Ensemble Prediction ◽  
Three Gorges Reservoir Area ◽  
Support Vector ◽  
Landslide Displacement Prediction ◽  
Learning Machine

Data-driven models have been extensively employed in landslide displacement prediction. However, predictive uncertainty, which consists of input uncertainty, parameter uncertainty, and model uncertainty, is usually disregarded in deterministic data-driven modeling, and point estimates are separately presented. In this study, a probability-scheme combination ensemble prediction that employs quantile regression neural networks and kernel density estimation (QRNNs-KDE) is proposed for robust and accurate prediction and uncertainty quantification of landslide displacement. In the ensemble model, QRNNs serve as base learning algorithms to generate multiple base learners. Final ensemble prediction is obtained by integration of all base learners through a probability combination scheme based on KDE. The Fanjiaping landslide in the Three Gorges Reservoir area (TGRA) was selected as a case study to explore the performance of the ensemble prediction. Based on long-term (2006–2018) and near real-time monitoring data, a comprehensive analysis of the deformation characteristics was conducted for fully understanding the triggering factors. The experimental results indicate that the QRNNs-KDE approach can perform predictions with perfect performance and outperform the traditional backpropagation (BP), radial basis function (RBF), extreme learning machine (ELM), support vector machine (SVM) methods, bootstrap-extreme learning machine-artificial neural network (bootstrap-ELM-ANN), and Copula-kernel-based support vector machine quantile regression (Copula-KSVMQR). The proposed QRNNs-KDE approach has significant potential in medium-term to long-term horizon forecasting and quantification of uncertainty.

scholarly journals Control and remediation methods for eutrophic lakes in the past 30 years

2020 ◽  
Vol 81 (6) ◽  
pp. 1099-1113 ◽  
Author(s):  
Yuan Zhang ◽  
Pingping Luo ◽  
Shuangfeng Zhao ◽  
Shuxin Kang ◽  
Pengbo Wang ◽  
...  
Keyword(s):  
New Technologies ◽  
Management Strategies ◽  
Cyanobacterial Blooms ◽  
Small Scale ◽  
Short Term ◽  
Eutrophic Lakes ◽  
Lake Ecosystems ◽  
The Past ◽  
Incomplete Removal

Abstract Accelerated eutrophication, which is harmful and difficult to repair, is one of the most obvious and pervasive water pollution problems in the world. In the past three decades, the management of eutrophication has undergone a transformation from simple directed algal killing, reducing endogenous nutrient concentration to multiple technologies for the restoration of lake ecosystems. This article describes the development and revolution of three remediation methods in application, namely physical, chemical, and biological methods, and it outlines their possible improvements and future directions. Physical and chemical methods have obvious and quick effects to purify water in the short term and are more suitable for small-scale lakes. However, these two methods cannot fundamentally solve the eutrophic water phenomenon due to costly and incomplete removal results. Without a sound treatment system, the chemical method easily produces secondary pollution and residues and is usually used for emergency situations. The biological method is cost-effective and sustainable, but needs a long-term period. A combination of these three management techniques can be used to synthesize short-term and long-term management strategies that control current cyanobacterial blooms and restore the ecosystem. In addition, the development and application of new technologies, such as big data and machine learning, are promising approaches.

scholarly journals Multi-step streamflow forecasting using data-driven non-linear methods in contrasting climate regimes

2013 ◽  
Vol 16 (3) ◽  
pp. 671-689 ◽  
Author(s):  
Daniel J. Karran ◽  
Efrat Morin ◽  
Jan Adamowski
Keyword(s):  
Wavelet Transforms ◽  
Model Performance ◽  
Probability Of Detection ◽  
Data Driven ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Lead Times ◽  
Streamflow Forecasting ◽  
Non Linear ◽  
Using Data

Considering the popularity of using data-driven non-linear methods for forecasting streamflow, there has been no exploration of how well such models perform in climate regimes with differing hydrological characteristics, nor has the performance of these models, coupled with wavelet transforms, been compared for lead times of less than 1 month. This study compares the use of four different models, namely artificial neural networks (ANNs), support vector regression (SVR), wavelet-ANN, and wavelet-SVR in a Mediterranean, Oceanic, and Hemiboreal watershed. Model performance was tested for 1, 2 and 3 day forecasting lead times, measured by fractional standard error, the coefficient of determination, Nash–Sutcliffe model efficiency, multiplicative bias, probability of detection and false alarm rate. SVR based models performed best overall, but no one model outperformed the others in more than one watershed, suggesting that some models may be more suitable for certain types of data. Overall model performance varied greatly between climate regimes, suggesting that higher persistence and slower hydrological processes (i.e. snowmelt, glacial runoff, and subsurface flow) support reliable forecasting using daily and multi-day lead times.

Explaining Bureaucratic Optimism: Theory and Evidence from U.S. Executive Agency Macroeconomic Forecasts

2007 ◽  
Vol 101 (1) ◽  
pp. 129-142 ◽  
Author(s):  
GEORGE A. KRAUSE ◽  
J. KEVIN CORDER
Keyword(s):  
Institutional Design ◽  
Executive Branch ◽  
Social Security Administration ◽  
Short Term ◽  
Forecast Horizon ◽  
Distant Future ◽  
The Social ◽  
Executive Agencies ◽  
Executive Agency

We offer a theory of intertemporal bureaucratic decision making which proposes that an agency's forecast optimism is related to the extent to which it discounts future reputation costs associated with bureaucratic incompetence. Agency forecasts of the distant future are more likely to be optimistic than short-term forecasts. We claim that unstable organizations will discount reputation costs at a steeper rate than stable organizations, and therefore will produce more optimistic forecasts. We test our theory using macroeconomic forecasts produced by the Office of Management and Budget (OMB) and the Social Security Administration (SSA) across six forecast horizons from 1979 to 2003. The statistical results are generally consistent with our theory: OMB generates more optimistic long-term forecasts than SSA. Further, differences in forecast optimism between these executive branch agencies widen as the forecast horizon increases. Our evidence suggests that more stable agencies place a premium on minimizing reputation costs. Conversely, less stable agencies are more likely to accommodate political pressures for forecast optimism. These findings underscore the importance of institutional design for understanding how executive agencies balance the conflicting goals of political responsiveness and bureaucratic competence within the administrative state.

Sign in / Sign up

Export Citation Format

Share Document