Improved artificial bee colony algorithm considering harvest season for computing economic dispatch on power system

Afandi, Arif Nur; Miyauchi, Hajime

doi:10.1002/tee.21963

Cited by 23 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, many intelligent methods have been developed to find out the optimal solution for various technical problems [19], [20], [40]- [46]. One of them is the ANN considered the backpropagation.…”

Section: Problem Statementmentioning

confidence: 99%

Demand Forecasting Considering Actual Peak Load Periods Using Artificial Neural Network

Yuan¹,

Afandi²,

Putranto³

2018

EECSI

View full text Add to dashboard Cite

Presently, electrical energy consumption continues to increase from year to year. Therefore, a short-term load forecasting is required that electricity providers can deliver continuous electrical energy to electricity consumers. By considering the estimation of the electrical load, the scheduling plan for operation and allocation of reserves can be managed well by the supply side. This study is focused on a forecasting of electrical loads using Artificial Neural Network (ANN) method considering a backpropagation algorithm model. The advantage of this method is to forecast the electrical load in accordance with patterns of past loads that have been taught. The data used for the learning is Actual Peak Load Period (APLP) data on the 150 kV system during 2017. Results show that the best network architecture is structured for the APLP Day and Night. Moreover, the momentum setting and understanding rate are 0.85 and 0.1 for the APLP Day. In contrast, 0.9 and 0.15 belong to the APLP Night. Based on the best network architecture, the APLP day testing process generates Mean Squared Error (MSE) around 0.04 and Mean Absolute Percentage Error (MAPE) around 4.66%, while the APLP Night generates MSE in 0.16 and MAPE in 16.83%.

show abstract

Section: Problem Statementmentioning

confidence: 99%

Demand Forecasting Considering Actual Peak Load Periods Using Artificial Neural Network

Yuan¹,

Afandi²,

Putranto³

2018

EECSI

View full text Add to dashboard Cite

show abstract

“…An intelligent computation (IC) is more popular than classical approaches to carrying out this problem [7], [9], [15]- [20]. Since an early idea of the IC, many methods have been proposed based on own inspirations [13], [21] and many natural phenomena or biological processes have been also adopted as the inspiration [12], [21], [22]. Currently, many algorithms have also been proposed which are conducted to phenomena or entities in nature [22]- [26].…”

Section: Introductionmentioning

confidence: 99%

Combined Computational Intelligence Approach for the Power System Optimization Problem

Afandi¹,

Fadlika²,

Gumilar³

et al. 2018

EECSI

View full text Add to dashboard Cite

A power system optimization is one of the major problems in the operating performances of the existing system. This problem takes place on the various technical cases to get optimal conditions of the system. Moreover, many approaches have been implemented to carry out the solution under operational constraints. This paper presents Thunderstorm Algorithm (TA) and Artificial Salmon Tracking Algorithm (ASTA) for defining the optimal strategy of the power system optimization based on the unit commitment. Both algorithms are tested on the IEEE-62 bus system, whereas, results show that ASTA and TA can be combined together to solve the power system problem. These algorithms have been applied to predict the power consumption and it has good performances while searching for the optimal solution. These results also show that the economic dispatch problem is conducted to the power production while the algorithm is performed in good characteristics.

show abstract

“…Moreover, this interconnection system is operated continuously to meet the load demand in the sequence of generation, transmission, distribution, and utilization of electric energy [1,2]. These processes are conducted based on the commitment of scheduled generating units at the lowest possible operating cost under the constraint of technical limitations and environmental requirements.…”

Section: Introductionmentioning

confidence: 99%

“…In general, traditional methods are useful and accurate for finding solutions but their performance suffers when applied to large systems and multi-spaces. Such methods also consume a large amount of computation time to complete the task [2,6]. Nowadays, evolutionary methods are often used to replace classical methods [3,7].…”

Section: Introductionmentioning

confidence: 99%

“…Nowadays, evolutionary methods are often used to replace classical methods [3,7]. Studies taking various aspects into account have been conducted in order to increase performance associated with the ELD problem [2,3,6,7]. Several evolutionary methods have been proposed based on natural processes, such as genetic algorithms (GA) and the harvest season artificial bee colony (HSABC) algorithm.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Thunderstorm Algorithm for Determining Unit Commitment in Power System Operation

Afandi

Sulistyorini

2016

J. Eng. Technol. Sci.

View full text Add to dashboard Cite

Abstract. Solving the unit commitment problem is an important task in power system operation for deciding a balanced power production between various types of generating units under technical constraints and environmental limitations. This paper presents a new intelligent computation method, called the Thunderstorm Algorithm (TA), for searching the optimal solution of the integrated economic and emission dispatch (IEED) problem as the operational assessment for determining unit commitment. A simulation using the IEEE-62 bus system showed that TA has smooth convergence and is applicable for solving the IEED problem. The IEED's solution is associated with the total fuel consumption and pollutant emission. The proposed TA method seems to be a viable new approach for finding the optimal solution of the IEED problem.Keywords: economic dispatch; emission dispatch; evolutionary algorithm; power system operation; thunderstorm algorithm; unit commitment. IntroductionPresent-day power systems are complex systems for conveying electric energy from generating sites to load center areas with high reliability and stability in order to guarantee that the system dynamically serves the customers at a good performance level without outages over the whole time period of operation. Nowadays, in view of environmental concerns, power systems are also required to reduce pollutant emissions when burning fossil fuels at thermal power plants. Power systems are monitored regularly and maintained periodically in order to continue normal operation or recover quickly after being struck by a certain disruption. Technically, a power system is constructed as an integrated structure, which acts as an interconnection system for feeding energy under various constraints and conditional limitations. It is set up as a large system of electric networks with several transmission levels and distribution systems joining all sections in order to involve available generating units for maintaining operation in accordance with energy usage.

show abstract

Improved artificial bee colony algorithm considering harvest season for computing economic dispatch on power system

Cited by 23 publications

References 23 publications

Demand Forecasting Considering Actual Peak Load Periods Using Artificial Neural Network

Demand Forecasting Considering Actual Peak Load Periods Using Artificial Neural Network

Combined Computational Intelligence Approach for the Power System Optimization Problem

Thunderstorm Algorithm for Determining Unit Commitment in Power System Operation

Contact Info

Product

Resources

About