Research On Multi-Objective Particle Swarm Optimization Algorithm Based On Decomposition In Multi-Energy Scheduling Optimization

With the development of the power system,its scale and complexity are increasing.At the same time,the demand for electricity is becoming more diverse,not only to meet the needs of different industries and regions but also to meet the needs of different time periods.Therefore,how to allocate power resources reasonably and ensure the economic,safe,and reliable operation of the power system has become an important challenge in the development of the power system.The Dynamic Economic Emission Dispatch(DEED)problem is to guide the output of generators based on the predicted load demand within a scheduling period,aiming to minimize the generation cost and pollutant emissions,and achieve a win-win situation of economic and environmental benefits while improving the energy utilization efficiency of the power system.A particle swarm optimization algorithm based on the Cauchy-Lorentz distribution is proposed for the economic dispatch problem in power systems.The algorithm uses an adaptive inertia weight based on the population state to ensure that the algorithm gradually transitions from global search in the early stage to local search in the later stage.In addition,a random trajectory correction strategy based on the Cauchy-Lorentz distribution is used to enable the algorithm to jump out of local optima.After being validated with three standard test functions and compared with the standard particle swarm optimization algorithm,the proposed algorithm can effectively solve the problems of easily falling into local optima and being too dependent on parameters in particle swarm optimization algorithm.Finally,the algorithm is applied to the economic dispatch model of the power system,and simulation results show that the proposed algorithm can significantly improve the economic benefits of power generation.A multi-objective particle swarm optimization algorithm based on decomposition is proposed for the economic environmental dispatch problem in the power system.The algorithm uses a neighborhood reference point combined with a global reference point to improve the distribution of the Pareto Front.It also employs a constraint handling method based on penalty functions to handle complex constraints in multi-objective optimization problems.An external archive set is introduced to store the non-dominated solutions obtained through non-dominated sorting during the algorithm iteration,and the uniform distribution of weight vectors in MOEA/D is used to ensure the distribution of non-dominated solutions in the external archive set.The proposed algorithm is validated with five standard test functions,and it obtains a set of solutions uniformly distributed on the real Pareto Front.Finally,the algorithm is applied to a practical model,and the test results are compared with those obtained with the MOEA/D algorithm.The proposed multi-objective particle swarm optimization algorithm based on decomposition can achieve lower generation costs and higher environmental benefits.