def rqpso_opt(D, pop_size, max_iter, pop_max, pop_min, fitness_function, alpha=None, beta=None, rec_step=50): swarm = RevisedQuantumParticleSwarm(D, pop_size, pop_max, pop_min) # 种群初始化 opt = Optimizer(max_iter, swarm, evaluator=fitness_function, rec_step=rec_step, is_record=True) # 优化算法初始化 if alpha and beta: opt.fit(alpha, beta) else: opt.fit() # 优化求解 AlgorithmVisual(opt.recoder, evaluator, pop_min_, pop_max_, is_save=True) # 结果可视化
def qpso_opt(D, pop_size, max_iter, pop_max, pop_min, fitness_function, alpha=None, rec_step=50): swarm = QuantumParticleSwarm(D, pop_size, pop_max, pop_min) opt = Optimizer(max_iter, swarm, fitness_function, rec_step=rec_step, is_record=True) if alpha: opt.fit(alpha) else: opt.fit() AlgorithmVisual(opt.recoder, evaluator, pop_min_, pop_max_, is_save=True)
def particle_swarm_opt(D, pop_size, max_iter, pop_max, pop_min, V_max, V_min, fitness_function, weight=None): from swarm.particle import ParticleSwarm swarm = ParticleSwarm(D, pop_size, pop_max, pop_min, V_max, V_min) # 种群初始化 opt = Optimizer(max_iter, swarm, fitness_function) # 优化器初始化 if weight: opt.fit(weight) # 优化迭代 else: opt.fit() return opt.recoder
def revised_quantum_particle_opt(D, pop_size, max_iter, pop_max, pop_min, fitness_function, alpha=None, beta=None): from swarm.particle import RevisedQuantumParticleSwarm swarm = RevisedQuantumParticleSwarm(D, pop_size, pop_max, pop_min) opt = Optimizer(max_iter, swarm, evaluator=fitness_function) if alpha and beta: opt.fit(alpha, beta) else: opt.fit() return opt.recoder
def quantum_particle_swarm_opt(D, pop_size, max_iter, pop_max, pop_min, fitness_function, alpha=None): from swarm.particle import QuantumParticleSwarm swarm = QuantumParticleSwarm(D, pop_size, pop_max, pop_min) opt = Optimizer(max_iter, swarm, fitness_function) if alpha: opt.fit(alpha) else: opt.fit() return opt.recoder
def pso_opt(D, pop_size, max_iter, pop_max, pop_min, V_max, V_min, fitness_function, weight=None, rec_step=50): from swarm.particle import ParticleSwarm swarm = ParticleSwarm(D, pop_size, pop_max, pop_min, V_max, V_min) # 种群初始化 opt = Optimizer(max_iter, swarm, fitness_function, rec_step=rec_step, is_record=True) # 优化器初始化 if weight: opt.fit(weight) # 优化迭代 else: opt.fit() AlgorithmVisual(opt.recoder, evaluator, pop_min_, pop_max_, is_save=True)
def revised_quantum_particle_opt(D, pop_size, max_iter, pop_max, pop_min, fitness_function, alpha=None, beta=None):
from swarm.particle import RevisedQuantumParticleSwarm
swarm = RevisedQuantumParticleSwarm(D, pop_size, pop_max, pop_min)
opt = Optimizer(max_iter, swarm, evaluator=fitness_function)
if alpha and beta:
opt.search(alpha, beta)
else:
opt.search()
plt.figure(figsize=(5, 3))
plt.loglog(range(max_iter), opt.yy)
plt.title('RQPSO')
plt.grid()
def quantum_particle_swarm_opt(D, pop_size, max_iter, pop_max, pop_min, fitness_function, alpha=None):
from swarm.particle import QuantumParticleSwarm
swarm = QuantumParticleSwarm(D, pop_size, pop_max, pop_min)
opt = Optimizer(max_iter, swarm, fitness_function)
if alpha:
opt.search(alpha)
else:
opt.search()
plt.figure(figsize=(5, 3))
plt.loglog(range(max_iter), opt.yy)
plt.title('QPSO')
plt.grid()
def particle_swarm_opt(D, pop_size, max_iter, pop_max, pop_min, V_max, V_min, fitness_function, weight=None):
from swarm.particle import ParticleSwarm
swarm = ParticleSwarm(D, pop_size, pop_max, pop_min, V_max, V_min) # 种群初始化
opt = Optimizer(max_iter, swarm, fitness_function) # 优化器初始化
if weight:
opt.search(weight) # 优化迭代
else:
opt.search()
plt.figure(figsize=(5, 3)) # 结果可视化
plt.loglog(range(max_iter), opt.yy)
plt.title('PSO')
plt.grid()
def rqpso_opt(D,
pop_size,
max_iter,
pop_max,
pop_min,
fitness_function,
alpha=None,
beta=None):
swarm = RevisedQuantumParticleSwarm(D, pop_size, pop_max, pop_min)
opt = Optimizer(max_iter, swarm, evaluator=fitness_function)
if alpha and beta:
opt.fit(alpha, beta)
else:
opt.fit()
plt.figure(figsize=(5, 3))
plt.loglog(range(max_iter // opt.rec_step), opt.recoder.fitness)
plt.title('RQPSO')
plt.grid()
def pso_opt(D,
pop_size,
max_iter,
pop_max,
pop_min,
V_max,
V_min,
fitness_function,
weight=None):
swarm = ParticleSwarm(D, pop_size, pop_max, pop_min, V_max, V_min) # 种群初始化
opt = Optimizer(max_iter, swarm, fitness_function) # 优化器初始化
if weight:
opt.fit(weight) # 优化迭代
else:
opt.fit()
plt.figure(figsize=(5, 3)) # 结果可视化
plt.loglog(range(max_iter // opt.rec_step), opt.recoder.fitness)
plt.title('PSO')
plt.grid()