Simulated Annealing Algorithm for Dynamic Economic Dispatch Problem in the Electricity Market Incorporating Wind Energy

Bouddou, Riyadh; Benhamida, Farid; Haba, Mekki; Belgacem, Moussa; Meziane, Mohammed Amine

doi:10.18280/isi.250602

Cited by 3 publications

(1 citation statement)

References 24 publications

(31 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the iteration goes, the value of T is decaying. The algorithm will stop if the value of T reaches Tmin [14], and the most recent w is the final solution containing the set of the importance ranks.…”

Section: Computational Proceduresmentioning

confidence: 99%

Unifying Variable Importance Scores from Different Machine Learning Models Using Simulated Annealing

Rusyana,

Wigena,

Sumertajaya

et al. 2024

ISI

View full text Add to dashboard Cite

Each machine learning algorithm might generate different variable importance even though the identical loss function is used. The difference in the predictor rank order makes it difficult to interpret, so a single predictor rating is required. This paper proposes a method that combines predictor rating from machine learning using simulated annealing algorithms. Simulation and empirical data are used to apply the method and its evaluation. The simulation data contain as many as 24 predictors, 1000 observations, and 100 iterations. Four machine learning algorithms are used: random forest, XGBoost, neural network, and support vector machine. Then, four permutation importance variables were produced with 100 repetitions. Next, a simulated annealing algorithm generates a combined variable importance. This proposed method will be optimal if predictors are independent, and the number of predictors is more than ten. Then, the proposed method was applied to empirical data. Using the proposed method, the machine learning model needs only 14 predictors to reach the accuracy of 74.4% which is similar to the result if the algorithm involves all predictors. The proposed method is possible to be further developed and modified. The change could be employed in the objective value and the solution strategy within the simulated annealing procedure.

show abstract

Section: Computational Proceduresmentioning

confidence: 99%

Unifying Variable Importance Scores from Different Machine Learning Models Using Simulated Annealing

Rusyana,

Wigena,

Sumertajaya

et al. 2024

ISI

View full text Add to dashboard Cite

show abstract

Application of blockchain technology in autonomous electricity transaction and settlement at the end of distribution network

Xing¹,

Liu²

2022

International Journal of Emerging Electric Power Systems

View full text Add to dashboard Cite

With the deepening of the concept of low-carbon environmental protection, the use of renewable energy in social production has become more and more popular. More and more consumers in the distribution network have begun to change their identities to become consumers with the continuous reform of the electricity sales side. Electricity trading and settlement methods in the electricity market directly affect the relevant income of market entities, so a fair and reasonable settlement mechanism is an important factor for the normal operation of the electricity market. Electricity trading refers to the buying and selling of electricity commodities and services, including electricity trading, auxiliary service trading, and transmission rights trading. With the expansion of the electricity market, how to deal with the deviation of electricity is also a difficult problem that requires electricity settlement. This paper aimed to study the application of blockchain technology in the autonomous electricity transaction and settlement at the end of the distribution network. It was expected to use the blockchain technology to set up related transaction mechanisms, provide new solutions for electricity transaction and settlement, and improve the efficiency and fairness of electricity settlement. Blockchain technology does not rely on additional third-party management agencies or hardware facilities, and there is no central control. Except for the self-contained blockchain itself, through distributed accounting and storage, each node realizes information self-verification, transmission and management. On the basis of sorting out the principles of electricity balance and electricity price formation, this paper proposed a contract decomposition method with a higher degree of fit, and revealed the settlement principle of deviation electricity in the electricity market environment. Aiming at the application scenario of blockchain in the energy Internet, an energy trading platform based on blockchain was designed, and the test results showed the feasibility of blockchain in electricity settlement scenarios. The experimental results of this paper showed that in the traditional electricity purchase fee settlement, the average transaction price is stable at 0.6 yuan/KWh. In the blockchain settlement process, the electricity purchase is 25 yuan when the electricity purchase is 50 KWh. Therefore, blockchain settlement is used more frequently in the market, and the profits are higher.

show abstract

Hybrid of Lambda Iteration and Golden Section Ratio to Enhance Local Search of the Bee Colony Optimization Algorithm to Solve an Economic Dispatch Problem

Takeang,

Khamsen,

Aurasopon

2023

Preprint

View full text Add to dashboard Cite

Simulated Annealing Algorithm for Dynamic Economic Dispatch Problem in the Electricity Market Incorporating Wind Energy

Cited by 3 publications

References 24 publications

Unifying Variable Importance Scores from Different Machine Learning Models Using Simulated Annealing

Unifying Variable Importance Scores from Different Machine Learning Models Using Simulated Annealing

Application of blockchain technology in autonomous electricity transaction and settlement at the end of distribution network

Hybrid of Lambda Iteration and Golden Section Ratio to Enhance Local Search of the Bee Colony Optimization Algorithm to Solve an Economic Dispatch Problem

Contact Info

Product

Resources

About