郊狼优化算法python

郊狼优化算法（WLO）是一种基于自然界中狼群捕猎行为的启发式优化算法。它模拟了狼群中的领袖、追随者和孤狼之间的相互作用，通过不断地迭代搜索最优解。以下是一个简单的Python实现：

import random
import numpy as np

def WLO(obj_func, lb, ub, dim, SearchAgents_no, Max_iter):
    Alpha_pos = np.zeros(dim)
    Alpha_score = float("inf")
    Beta_pos = np.zeros(dim)
    Beta_score = float("inf")
    Delta_pos = np.zeros(dim)
    Delta_score = float("inf")
    Positions = np.zeros((SearchAgents_no, dim))
    for i in range(dim):
        Positions[:, i] = np.random.uniform(0, 1, SearchAgents_no) * (ub[i] - lb[i]) + lb[i]
    for l in range(0, Max_iter):
        for i in range(0, SearchAgents_no):
            fitness = obj_func(Positions[i, :])
            if fitness < Alpha_score:
                Alpha_score = fitness
                Alpha_pos = Positions[i, :]
            if fitness > Alpha_score and fitness < Beta_score:
                Beta_score = fitness
                Beta_pos = Positions[i, :]
            if fitness > Alpha_score and fitness > Beta_score and fitness < Delta_score:
                Delta_score = fitness
                Delta_pos = Positions[i, :]
        a = 2 - 2 * l / Max_iter
        for i in range(0, SearchAgents_no):
            r1 = random.random()
            r2 = random.random()
            A = 2 * a * r1 - a
            C = 2 * r2
            b = 1
            l1 = random.random()
            p = random.random()
            if p < 0.5:
                if abs(A) < 1:
                    D_alpha = abs(C * Alpha_pos - Positions[i, :])
                    X1 = Alpha_pos - A * D_alpha
                else:
                    rand_leader_index = np.floor(SearchAgents_no * random.random())
                    X_rand = Positions[int(rand_leader_index), :]
                    D_X_rand = abs(C * X_rand - Positions[i, :])
                    X1 = X_rand - A * D_X_rand
            else:
                distance2Leader = abs(Alpha_pos - Positions[i, :])
                # Eq. (2.5)
                X1 = distance2Leader * np.exp(b * l1) * np.cos(2 * np.pi * l1) + Alpha_pos
            r1 = random.random()
            r2 = random.random()
            A = 2 * a * r1 - a
            C = 2 * r2
            b = 1
            l1 = random.random()
            p = random.random()
            if p < 0.5:
                if abs(A) < 1:
                    D_beta = abs(C * Beta_pos - Positions[i, :])
                    X2 = Beta_pos - A * D_beta
                else:
                    rand_leader_index = np.floor(SearchAgents_no * random.random())
                    X_rand = Positions[int(rand_leader_index), :]
                    D_X_rand = abs(C * X_rand - Positions[i, :])
                    X2 = X_rand - A * D_X_rand
            else:
                distance2Leader = abs(Beta_pos - Positions[i, :])
                # Eq. (2.5)
                X2 = distance2Leader * np.exp(b * l1) * np.cos(2 * np.pi * l1) + Beta_pos
            r1 = random.random()
            r2 = random.random()
            A = 2 * a * r1 - a
            C = 2 * r2
            b = 1
            l1 = random.random()
            p = random.random()
            if p < 0.5:
                if abs(A) < 1:
                    D_delta = abs(C * Delta_pos - Positions[i, :])
                    X3 = Delta_pos - A * D_delta
                else:
                    rand_leader_index = np.floor(SearchAgents_no * random.random())
                    X_rand = Positions[int(rand_leader_index), :]
                    D_X_rand = abs(C * X_rand - Positions[i, :])
                    X3 = X_rand - A * D_X_rand
            else:
                distance2Leader = abs(Delta_pos - Positions[i, :])
                # Eq. (2.5)
                X3 = distance2Leader * np.exp(b * l1) * np.cos(2 * np.pi * l1) + Delta_pos
            Positions[i, :] = (X1 + X2 + X3) / 3
        lb = np.tile(lb, (SearchAgents_no, 1))
        ub = np.tile(ub, (SearchAgents_no, 1))
        Positions = np.clip(Positions, lb, ub)
    return Alpha_pos, Alpha_score

# 示例函数
def sphere(x):
    return sum(x ** 2)

# 测试
lb = [-100] * 30
ub = [100] * 30
WLO(sphere, lb, ub, 30, 50, 500)