pop_size=200
max_gen=300
solution=
company = [0,118.719989,32.208781]
for n in range(pop_size):
location = [[1, 118.77089, 32.242341], [2, 118.77116, 32.242325], [3, 118.758009, 32.236431],
[4, 118.753302, 32.25167],
[5, 118.743133, 32.24938], [6, 118.756796, 32.251199], [7, 118.745644, 32.21866],
[8, 118.747782, 32.222601], [9, 118.754213, 32.230573], [10, 118.756172, 32.234696],
[11, 118.751653, 32.211145], [12, 118.724399, 32.181262], [13, 118.732268, 32.168273],
[14, 118.741251, 32.154059], [15, 118.739814, 32.149382], [16, 118.741502, 32.144766],
[17, 118.753899, 32.156138], [18, 118.75663, 32.151614], [19, 118.722315, 32.136388],
[20, 118.705346, 32.182783], [21, 118.640739, 32.082919], [22, 118.766203, 32.236144],
[23, 118.82427, 32.339209], [24, 118.711883, 32.100773], [25, 118.624981, 32.078503],
[26, 118.791455, 32.120714], [27, 118.77255, 32.113826], [28, 118.7786, 32.108053],
[29, 118.806232, 32.115148], [30, 118.780361, 32.099122], [31, 118.772132, 32.113803],
[32, 118.826143, 32.119479], [33, 118.770969, 32.104218]]
random.shuffle(location)
#迭代gen_now=0
while (gen_now <= max_gen):
function1_values = [function1(solution[i]) for i in range(0, pop_size)]
function2_values = [function2(solution[i]) for i in range(0, pop_size)]
# 生成兩個函式值列表，構成乙個種群
non_dominated_sorted_solution = fast_non_dominated_sort(function1_values[:], function2_values[:])
# 種群之間進行快速非支配性排序,得到非支配性排序集合0-200
#print(non_dominated_sorted_solution)
# print("the best front for generation number ", gen_now, " is")
#print( non_dominated_sorted_solution[0])
# for valuez in non_dominated_sorted_solution[0]:
# print((solution[valuez]))
# print(function1(solution[valuez]))
# print(function2(solution[valuez]))
# print("\n")
crowding_distance_values =
# 計算非支配集合中每個個體的擁擠度
for i in range(0, len(non_dominated_sorted_solution)):
crowding_distance(function1_values[:], function2_values[:], non_dominated_sorted_solution[i][:]))
solution2 = solution[:]
#沒問題
# print( crowding_distance_values)
# print(len(crowding_distance_values))
while (len(solution2) < 2 * pop_size):
a1 = random.randint(0, pop_size - 1)
b1 = random.randint(0, pop_size - 1)
# 選擇
# 隨機選擇，將種群中的個體進行交配，得到子代種群2*pop_size
# 隨機選擇，將種群中的個體進行交配，得到子代種群2*pop_size
# print(solution2)
# print(len(solution2))
if len(solution2)==2*pop_size+1:
del(solution2[-1])
if len(solution2)==2*pop_size+2:
del (solution2[-1])
del (solution2[-1])
function1_values2 = [function1(solution2[i]) for i in range(0, 2 * pop_size)]
function2_values2 = [function2(solution2[i]) for i in range(0, 2 * pop_size)]
non_dominated_sorted_solution2 = fast_non_dominated_sort(function1_values2[:], function2_values2[:])
# 將兩個目標函式得到的兩個種群值value,再進行排序 得到2*pop_size解
crowding_distance_values2 =
for i in range(0, len(non_dominated_sorted_solution2)):
crowding_distance(function1_values2[:], function2_values2[:], non_dominated_sorted_solution2[i][:]))
# 計算子代的個體間的距離值
new_solution =
for i in range(0, len(non_dominated_sorted_solution2)):
non_dominated_sorted_solution2_1 = [
index_of(non_dominated_sorted_solution2[i][j], non_dominated_sorted_solution2[i]) for j in
range(0, len(non_dominated_sorted_solution2[i]))]
# 排序
front22 = sort_by_values(non_dominated_sorted_solution2_1[:], crowding_distance_values2[i][:])
front = [non_dominated_sorted_solution2[i][front22[j]] for j in
range(0, len(non_dominated_sorted_solution2[i]))]
front.reverse()
for value in front:
if (len(new_solution) == pop_size):
break
if (len(new_solution) == pop_size):
break
solution = [solution2[i] for i in new_solution]
if gen_now % 50==0:
print(solution)
gen_now = gen_now + 1
# lets plot the final front now
functionx = [i * 1 for i in function1_values]
functiony = [j * 1 for j in function2_values]
plt.xlabel('function 1', fontsize=15)
plt.ylabel('function 2', fontsize=15)
plt.scatter(functionx, functiony)
# plt.xlim((0.002, 0.006))
# plt.ylim((100, 300))
plt.pause(0.1)
plt.pause(0)
nsga2演算法 NSGA2 遺傳演算法解決多目標優化
進行多目標優化時，通常面臨多個目標函式無法同時達到最優的情況，為了解決這一矛盾，引入pareto optimality的概念 通常，多目標優化的一般形式為 經過處理，可以化為以下形式 其中f1 x f2 x fn x 為目標函式，其全部都是求最小值的形式 以下針對兩個目標函式進行討論 有幾個目標函式...
NSGA 2學習筆記
分類 演算法 2010 04 17 21 05 341人閱讀收藏 舉報 nsga2主要是對nsga演算法的改進。nsga是n.srinivas 和 k.deb在1995年發表的一篇名為 multiobjective function optimization using nondominated s...
NSGA 2學習筆記
nsga2主要是對nsga演算法的改進。nsga是n.srinivas 和 k.deb在1995年發表的一篇名為 multiobjective function optimization using nondominated sorting genetic algorithms 的 中提出的。該演算...