Online Solving Of Economic Dispatch Problem Using Neural Network Approach And Comparing It With Classical Method

Mohammadi, Ali; Varahram, Mohammad Hadi; Kheirizad, Iraj

doi:10.1109/icet.2006.335922

Cited by 24 publications

(4 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus far, researchers have proposed various methods for the optimal resource management in a centralized way. For example, the analytical methods like the Lambda-Iteration method [7] and linear programming method [8], the heuristic optimization methods like genetic algorithm (GA) [9], particle swarm optimization (PSO) [10], and neural network [11]. For centralized methods, a control center is essential for global information collecting.…”

Section: Introductionmentioning

confidence: 99%

A Fully Distributed Economic Dispatch Method in DC Microgrid Based on Consensus Algorithm

Liú

Jiang²,

Yan

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Uncertainties of intermittent renewables and complexities of load demands bring challenges to the optimal operation of the microgrid. This paper proposes a fully distributed method based on consensus algorithm for solving the economic dispatch problem (EDP) of DC microgrid. The proposed distributed method is performed using multiagent system. It only needs information from neighboring agents and does not need a central controller. A two-level control structure is adopted to realize the economic dispatch and voltage regulation simultaneously. The upper level obtains the optimal power reference of dispatchable agents and maintains the power balance of the system. The lower level performs an improved droop control to track the power reference and regulate the average bus voltage for the microgrid. The proposed method's properties and convergence are analyzed using eigenvalue perturbation theory to obtain a faster convergence speed. By designing the adjacency matrix appropriately, the proposed method can ensure the system stable when the communication topology changes. Finally, several simulations are designed to verify the effectiveness of this novel control method.INDEX TERMS DC Microgrid, economic dispatch, consensus algorithm, renewable generation.

show abstract

Section: Introductionmentioning

confidence: 99%

A Fully Distributed Economic Dispatch Method in DC Microgrid Based on Consensus Algorithm

Liú

Jiang²,

Yan

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…R. S. Hartati, and M. E. El-Hawary had given the whole calculation to the HNN by the linearization of the calculation formula of active losses with the use of Taylor series expansions; so they introduced the approximate losses coefficient in the HNN parameter [10]. In reality, for application, these approaches had preferred to handle the ED problem without introducing the power losses of the electrical network [7][8], [11][12][13][14][15][16] in order to avoid the nonlinearity of the equality constraint ; if it wasn't the case, the techniques provided a mismatch in the equality constraint; and not attained the real solution [17][18][19], so, it became weak in fast calculation problem. In [20] for the environment ED, the authors faced great problems in determining the penalty constants introduced at each time for each new objective to treat.…”

Section: Introductionmentioning

confidence: 99%

Economic dispatch by the combination of HNN and the Lagrange method

Bouakacha

Leulmi

2013

2013 8th International Conference on Electrical and Electronics Engineering (ELECO)

View full text Add to dashboard Cite

In this work, we are going to solve the ED (economic dispatch) problem by the use of an HNN (Hopfield neural networks) model combined with the Lagrange method noted LHNN. In contrary to the techniques that use the linear function of the total inputs to neurons, we are going to use it at the non-linear form that allows the parameters of NN to contain all information of the original problem, so the HNN become able to reach exactly the solutions. At the end, simulations will be presented, with promising results, of a multi-objective economic environmental problem.

show abstract

“…It does so by formulating and a multivariable constrained optimization problem [1] that is then solved using such Lagrangian techniques such as lambda iteration [13]. Complex numerical centralized optimization methods such as genetic algorithms, particle swarm optimization or Monte-Carlo Methods [14,15] are often employed to determine the minimum cost allocation of power across generators.…”

Section: Related Workmentioning

confidence: 99%

A Distributed Algorithm for Optimal Dispatch in Smart Power Grids with Piecewise Linear Cost Functions

Yasmeen

Mudumbai

Dasgupta

View full text Add to dashboard Cite

We consider the optimal economic dispatch of power generators in a smart electric grid for allocating power between generators to meet load requirements at minimum total cost. We assume that each generator has a piecewise linear cost function. We first present a polynomial time algorithm that achieves optimal dispatch. We then present a decentralized algorithm where, each generator independently adjusts its power output using only the aggregate power imbalance in the network, which can be observed by each generator through local measurements of the frequency deviation on the grid. The algorithm we propose exponentially erases the power imbalance, while eventually minimizing the generation cost. iii

show abstract

Online Solving Of Economic Dispatch Problem Using Neural Network Approach And Comparing It With Classical Method

Cited by 24 publications

References 2 publications

A Fully Distributed Economic Dispatch Method in DC Microgrid Based on Consensus Algorithm

A Fully Distributed Economic Dispatch Method in DC Microgrid Based on Consensus Algorithm

Economic dispatch by the combination of HNN and the Lagrange method

A Distributed Algorithm for Optimal Dispatch in Smart Power Grids with Piecewise Linear Cost Functions

Contact Info

Product

Resources

About