Design and implementation of ACO feature selection algorithm for data stream mining

Harde, Shivani; Sahare, Vaishali

doi:10.1109/icacdot.2016.7877746

Cited by 10 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The BGA finally selects the feature subset which contains the most relevant and nonredundant variables. Predictors 1, 2, 3,4,5,7,8,9,10,13,15,16,17,19,20,21,22,23, and 24, which represent hour of the day, day of the week, month of the year, season of the year, period of the day, holiday/weekend indicator2 (with 0-2 values), ambient air temperature, dew-point temperature, ambient relative humidity, ambient air pressure, wind direction, wind speed, gust speed, global solar radiation, sunshine duration, electricity price, previous 24h average electricity demand, 24h lagged electricity demand, and 168h lagged electricity demand respectively, are selected at least for one of the building types.…”

Section: B Fs Resultsmentioning

confidence: 99%

“…It is soundly revealed in [1] and [2] that the accuracy of prediction models not only relies on the models' configurations and associated learning methods but also on the predictor domain, which is established via the initial predictor space and FS techniques. FS is mostly applied in ML implementations as one of the preprocessing steps where a predictor subset (independent attributes) is found by removing predictors with lower or irrelevant information and highly redundant [3]. However, very few forecasting techniques perform FS before training the prediction models.…”

Section: Introductionmentioning

confidence: 99%

“…Predictors 1,2,3,4,5,7,8,9,10,13,15,16,17,19,20,21,22,23, and 24 are selected for Building A. Similarly, features 1, 2, 3, 4, 5, 7, 8, 9, 10, 13, 15, 17, 19, 20, 21, 23, and 24 are selected for Building B. Variables 1, 2, 3, 4, 5, 7, 8, 13, 17, 19, 20, 21, 22, 23, and 24 are selected for Building C. Attributes 1, 2, 3, 4, 5, 7, 8, 9, 13,16, 17, 21, 22, 23, and 24 are selected for Building D.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems

Eseye¹,

Lehtonen²,

Tukia³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Improved performance electricity demand forecast can provide decentralized energy system operators, aggregators, managers, and other stakeholders with essential information for energy resource scheduling, demand response management, and energy market participation. Most previous methodologies have focused on predicting the aggregate amount of electricity demand at national or regional scale and disregarded the electricity demand for small-scale decentralized energy systems (buildings, energy communities, microgrids, local energy internets, etc.), which are emerging in the smart grid context. Furthermore, few research groups have performed attribute selection before training predictive models. This paper proposes a machine learning (ML)-based integrated feature selection approach to obtain the most relevant and nonredundant predictors for accurate short-term electricity demand forecasting in distributed energy systems. In the proposed approach, one of the ML tools -binary genetic algorithm (BGA) is applied for the feature selection process and Gaussian process regression (GPR) is used for measuring the fitness score of the features. In order to validate the effectiveness of the proposed approach, it is applied to various building energy systems located in the Otaniemi area of Espoo, Finland. The findings are compared with those achieved by other feature selection techniques. The proposed approach enhances the quality and efficiency of the predictor selection, with minimal chosen predictors to achieve improved prediction accuracy. It outperforms the other evaluated feature selection methods. Besides, a feedforward artificial neural network (FFANN) model is implemented to evaluate the forecast performance of the selected predictor subset. The model is trained using two-year hourly dataset and tested with another one-year hourly dataset. The obtained results verify that the FFANN forecast model based on the BGA-GPR FS selected training feature subset has achieved an annual MAPE of 1.96%, which is a very acceptable and promising value for electricity demand forecasting in small-scale decentralized energy systems.INDEX TERMS Binary genetic algorithm, decentralized energy system, electricity demand forecasting, feature selection, feedforward artificial neural network, fitness evaluation measure, Gaussian process regression, machine learning, smart grid.

show abstract

Section: B Fs Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems

Eseye¹,

Lehtonen²,

Tukia³

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…It is soundly revealed in [1] and [2] that the accuracy of prediction models not only relies on the models' configurations and associated learning methods but also on the predictor domain, which is established via the initial predictor space and PSS techniques. PSS is mostly applied in ML implementations as one of the preprocessing steps, where a predictor subset (independent attributes) is found by removing predictors with lower or irrelevant information and highly redundant information [3]. However, very few forecasting techniques perform PSS before training the prediction models.…”

Section: Nomenclature Accmentioning

confidence: 99%

Adaptive Predictor Subset Selection Strategy for Enhanced Forecasting of Distributed PV Power Generation

et al. 2019

View full text Add to dashboard Cite

Distributed photovoltaic (PV) solar power plants are playing an increasing role as a power generation resource in the modern electricity grid. However, PVs pose significant challenges to grid planners, operators, owners, investors, aggregators, and other stakeholders. This is due to the high uncertainty of the PV output power, which is caused by its entire dependence on intermittent environmental factors. This has brought a serious problem to the power industry to integrate and manage power grids containing significant penetration of PVs. Thus, an enhanced PV power forecast is very important to operate these power grids efficiently and reliably. Most previous methodologies have focused on predicting the aggregate amount of potential solar power generation at the national or regional scale and ignored the distributed PVs that are installed primarily for local electric supply. Furthermore, a few research groups have carried out predictor selection before training predictive models. This paper proposes an adaptive hybrid predictor subset selection (PSS) strategy to obtain the most relevant and nonredundant predictors for enhanced short-term forecasting of the power output of distributed PVs. In the proposed strategy, the binary genetic algorithm (BGA) is applied for the feature selection process and support vector regression (SVR) is used for measuring the fitness score of the predictors. In order to validate the effectiveness of the proposed strategy, it is applied to actual distributed PVs located in the Otaniemi area of Espoo, Finland. The findings are compared with those achieved by other PSS techniques. The proposed strategy enhances the quality and efficiency of the predictor subset selection, with minimal chosen predictors to achieve enhanced prediction accuracy. It outperforms the other prediction selection methods. Besides, a configuration of an adaptive forecasting model is introduced and the performance tests are presented to further validate the impact of the PSS results for the PV power prediction accuracy enhancement.

show abstract

“…As thoroughly shown in [1] and [2], the accuracy of forecasting approaches relies on the feature scope that is formed via the initial feature sets and IDIMs. IDI is typically used in ML applications as one of the preprocessing tasks, where a feature subset is established by eradicating variables with inferior or insignificant value and highly repetitive [3]. Nevertheless, only quite few prediction approaches have performed IDI ahead of fitting PV power forecasting models.…”

Section: Introductionmentioning

confidence: 99%

Effective Input Dataset Identification Methodology for Accurate Prediction of Local PV Power Production

Eseye

Lehtonen

Tukia

et al. 2019

2019 IEEE PES Innovative Smart Grid Technologies Europe (ISGT-Europe)

View full text Add to dashboard Cite

Local photovoltaic (PV) systems are playing a considerable role globally as a power resource and constituent element of the smart grid. Nevertheless, PVs may cause significant problems to the electric grid. This is due to the high variability of the PV power that is instigated by intermittent environmental conditions. Accurate prediction of PV power is very important to operate power grids containing high penetration of PVs. Most prior approaches have focused on forecasting the collective quantity of solar power generation at national or regional scale and disregarded the local PVs that are installed mainly for local electric supply. This paper devises an effective input dataset identification methodology (IDIM) to find the most significant and nonrepetitive input variables for accurate prediction of the power production of local PVs. In the devised methodology, the Binary Genetic Algorithm (BGA) is used for the input variable identification and Support Vector Regression (SVR) is employed for evaluating the fitness of the input datasets. The devised methodology is implemented and validated based on actual local PVs (building rooftop PVs) located in the Otaniemi area of Espoo, Finland. The results are compared with those obtained by conventional counterparts and manifest outperformed performances.

show abstract

Design and implementation of ACO feature selection algorithm for data stream mining

Cited by 10 publications

References 6 publications

Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems

Machine Learning Based Integrated Feature Selection Approach for Improved Electricity Demand Forecasting in Decentralized Energy Systems

Adaptive Predictor Subset Selection Strategy for Enhanced Forecasting of Distributed PV Power Generation

Effective Input Dataset Identification Methodology for Accurate Prediction of Local PV Power Production

Contact Info

Product

Resources

About