Multi-objective optimal reconfiguration and DG (Distributed Generation) power allocation in distribution networks using Big Bang-Big Crunch algorithm considering load uncertainty
In this paper, a multi-objective framework is proposed for simultaneous network reconfiguration and power allocation of DGs (Distributed Generations) in distribution networks. The optimization problem has objective functions of minimizing power losses, operation cost, and pollutant gas emissions as well as maximizing the voltage stability index subject to different power system constraints. The uncertainty of loads is modeled using the TFN (Triangular Fuzzy Number) technique. A novel solution method called MOHBB-BC (Multi-objective Hybrid Big Bang-Big Crunch) is implemented to solve the optimization problem. The MOHBB-BC derives a set of non-dominated Pareto solutions and accumulates them in a retention called Archive. The diversity of Pareto solutions conserved by applying a crowding distance operator and afterwards, the ‘best compromised’ Pareto solution is selected using a fuzzy decision maker. The proposed method is tested on two test systems of 33-bus and 25-bus in different cases including unbalanced three-phase loads. Results obtained from test cases elaborate that the MOHBB-BC results in more diversified Pareto solutions implying a better exploration capability even with a higher fitness. In addition, considering load uncertainty leads to a more realistic solution than deterministic loads but with higher level of power losses.
Application of the hybrid Big Bang-Big Crunch algorithm to optimal reconfiguration and distributed generation power allocation in distribution systems
In this paper, a multi-objective framework is proposed for simultaneous optimal network reconfiguration and DG (distributed generation) power allocation. The proposed method encompasses objective functions of power losses, voltage stability, DG cost, and greenhouse gas emissions and it is optimized subject to power system operational and technical constraints. In order to solve the optimization problem, the HBB-BC (Hybrid Big Bang-Big Crunch) algorithm as one of the most recent heuristic tools is modified and employed here by introducing a mutation operator to enhance its exploration capability. To resolve the scaling problem of differently-scaled objective functions, a fuzzy membership is used to bring them into a same scale and then, the fuzzy fitness of the final objective function is utilized to measure the satisfaction level of the obtained solution. The proposed method is tested on balanced and unbalanced test systems and its results are comprehensively compared with previous methods considering different scenarios. According to results, the proposed method not only offers an enhanced exploration capability but also has a better converge rate compared with previous methods. In addition, the simultaneous network reconfiguration and DG power allocation leads to a more optimal result than separately doing tasks of reconfiguration and DG power allocation.
neural network differential equation deep learning convolutional neural network convolutional neural software development deep neural network feature selection open source deep neural optical network learning approach geographic information system distributed generation geographic information stochastic differential equation power allocation open source software stochastic differential deep convolutional neural source software deep convolutional named entity recognition loss function human action space telescope personal area network mental health feature learning wireless personal area elastic optical multi-task learning personal area elastic optical network network reconfiguration wireless personal learning problem hubble space telescope learning task software developer high rate water pressure hubble space doubly stochastic open source tool source software development free and open capacity allocation low rate source software project group lasso path protection sparse learning backup path rate wireles open source gi spare capacity optimal reconfiguration source gi multi-task deep backward doubly stochastic doubly stochastic differential backward doubly big bang-big crunch low rate wireles survivable routing multi-task deep learning guidance sensor bang-big crunch big bang-big multi-task learning approach source software tool deep multi-task deep multi-task learning pose-invariant face high water pressure fine guidance shared backup fine guidance sensor multi-task convolutional neural multi-task learning model source gis software shared backup path multi-task feature bang-big crunch algorithm backup path protection approximating optimal crunch algorithm multi-task learning method software movement multi-task network spare capacity allocation multi-task convolutional multi-task cnn multi-task sparse multi-task feature learning multi-task regression multi-task allocation feature learning algorithm multiple related task multi-task multi-view multi-task learning algorithm soils contaminated