修改超参数设置

GA/main.py

@@ -14,7 +14,15 @@ best_solution = None
 best_row_boundaries = None
 best_col_boundaries = None
 
+
+# ---------------------------
+# 需要修改的超参数
+# ---------------------------
+R = 3
+C = 3
 params_file = 'params3'
+
+
 with open(params_file + '.yml', 'r', encoding='utf-8') as file:
     params = yaml.safe_load(file)
 
@@ -37,13 +45,13 @@ battery_energy_capacity = params['battery_energy_capacity']
 numbers = [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
 
 # 生成所有的排列情况（取三次，每次都可以从10个数中选）
-row_product = list(product(numbers, repeat=1))
+row_product = list(product(numbers, repeat=R))
 # 对每种情况从小到大排序，并剔除重复的情况
 row_cuts_set = set(
     tuple(sorted(set(item for item in prod if item > 0))) for prod in row_product)
 row_cuts_set = sorted(row_cuts_set)
 
-col_product = list(product(numbers, repeat=1))
+col_product = list(product(numbers, repeat=C))
 col_cuts_set = set(
     tuple(sorted(set(item for item in prod if item > 0))) for prod in col_product)
 col_cuts_set = sorted(col_cuts_set)
@@ -95,6 +103,7 @@ print("Best solution:", best_solution)
 print("Time:", best_T)
 print("Row boundaries:", best_row_boundaries)
 print("Col boundaries:", best_col_boundaries)
+print("Car Paths:", car_paths)
 
 output_data = {
     'row_boundaries': best_row_boundaries,

GA/main_parallel.py

@@ -27,7 +27,14 @@ if __name__ == "__main__":  # 重要：在 Windows 上必须加这一行
     np.random.seed(42)
     random.seed(42)
 
-    params_file = 'params3'
+    # ---------------------------
+    # 需要修改的超参数
+    # ---------------------------
+    R = 3
+    C = 1
+    params_file = 'params2'
+    batch_size = 60  # 控制一次最多并行多少个任务
+
     with open(params_file + '.yml', 'r', encoding='utf-8') as file:
         params = yaml.safe_load(file)
 
@@ -50,13 +57,13 @@ if __name__ == "__main__":  # 重要：在 Windows 上必须加这一行
     numbers = [0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
 
     # 生成所有的排列情况（取三次，每次都可以从10个数中选）
-    row_product = list(product(numbers, repeat=1))
+    row_product = list(product(numbers, repeat=R))
     # 对每种情况从小到大排序，并剔除重复的情况
     row_cuts_set = set(
         tuple(sorted(set(item for item in prod if item > 0))) for prod in row_product)
     row_cuts_set = sorted(row_cuts_set)
 
-    col_product = list(product(numbers, repeat=1))
+    col_product = list(product(numbers, repeat=C))
     col_cuts_set = set(
         tuple(sorted(set(item for item in prod if item > 0))) for prod in col_product)
     col_cuts_set = sorted(col_cuts_set)
@@ -65,7 +72,6 @@ if __name__ == "__main__":  # 重要：在 Windows 上必须加这一行
     best_solution = None
     best_row_boundaries = None
     best_col_boundaries = None
-    batch_size = 60  # 控制一次最多并行多少个任务
 
     all_tasks = [(row_cuts, col_cuts)
                  for row_cuts in row_cuts_set for col_cuts in col_cuts_set]
@@ -123,6 +129,7 @@ if __name__ == "__main__":  # 重要：在 Windows 上必须加这一行
     print("Time:", best_T)
     print("Row boundaries:", best_row_boundaries)
     print("Col boundaries:", best_col_boundaries)
+    print("Car Paths:", car_paths)
 
     output_data = {
         'row_boundaries': best_row_boundaries,

GA/sa_finetune.py

@@ -203,12 +203,18 @@ def load_initial_solution(file_path):
 if __name__ == "__main__":
     random.seed(42)
 
-    # 从 JSON 文件加载初始解
+    # ---------------------------
-    file_path = r"e:\studio2\HPCC_code\solutions\trav_ga_params3_parallel.json"
+    # 需要修改的超参数
+    # ---------------------------
+    file_path = r"solutions\trav_ga_params2_parallel.json"
+    max_iterations=10000
+    initial_temp=100
+    cooling_rate=0.95
+
     initial_row_cuts, initial_col_cuts, car_paths = load_initial_solution(
         file_path)
 
-    sa = SA_FineTuner(initial_row_cuts, initial_col_cuts, car_paths)
+    sa = SA_FineTuner(initial_row_cuts, initial_col_cuts, car_paths, max_iterations, initial_temp, cooling_rate)
     best_row_cuts, best_col_cuts, best_T = sa.run()
 
     # 输出结果

mtkl_sovler.py

@@ -7,12 +7,20 @@ import numpy as np
 # 固定随机种子，便于复现
 random.seed(42)
 
-num_iterations = 10000
 
 # ---------------------------
-# 参数设置
+# 需要修改的超参数
 # ---------------------------
-params_file = 'params3'
+num_iterations = 10000
+# 随机生成分区的行分段数与列分段数
+# R = random.randint(0, 3)  # 行分段数
+# C = random.randint(0, 3)  # 列分段数
+R = 3
+C = 1
+
+params_file = 'params2'
+
+
 with open(params_file + '.yml', 'r', encoding='utf-8') as file:
     params = yaml.safe_load(file)
 
@@ -38,12 +46,6 @@ best_T = float('inf')
 best_solution = None
 
 for iteration in range(num_iterations):
-    # 随机生成分区的行分段数与列分段数
-    # R = random.randint(0, 3)  # 行分段数
-    # C = random.randint(0, 3)  # 列分段数
-    R = 1
-    C = 1
-
     # 生成随机的行、列分割边界
     horiz = [np.clip(np.floor(random.random() * 10) / 10, 0.0, 0.9)
              for _ in range(R)]
@@ -174,6 +176,8 @@ for iteration in range(num_iterations):
 # ---------------------------
 if best_solution is not None:
     print("最佳 T:", best_solution['T_max'])
+    print("Row boundaries:", best_solution['row_boundaries'])
+    print("Col boundaries:", best_solution['col_boundaries'])
     print("最佳路径:", best_solution['car_paths'])
 
     # 保存分区边界和车辆轨迹到JSON文件

solutions/mtkl_params2.json

@@ -0,0 +1,30 @@
+{
+    "row_boundaries": [
+        0.0,
+        0.3,
+        0.4,
+        0.7,
+        1.0
+    ],
+    "col_boundaries": [
+        0.0,
+        0.5,
+        1.0
+    ],
+    "car_paths": [
+        [
+            2,
+            0
+        ],
+        [
+            4,
+            5,
+            3,
+            1
+        ],
+        [
+            6,
+            7
+        ]
+    ]
+}

solutions/trav_ga_params2_parallel.json

@@ -0,0 +1,30 @@
+{
+    "row_boundaries": [
+        0.0,
+        0.2,
+        0.4,
+        0.7,
+        1.0
+    ],
+    "col_boundaries": [
+        0.0,
+        0.5,
+        1.0
+    ],
+    "car_paths": [
+        [
+            7,
+            6
+        ],
+        [
+            4,
+            2,
+            0
+        ],
+        [
+            1,
+            3,
+            5
+        ]
+    ]
+}

visualization.py

@@ -2,7 +2,8 @@ import matplotlib.pyplot as plt
 import matplotlib.patches as patches
 import json
 
-def visualize_solution(row_boundaries, col_boundaries, car_paths, W, H):
+
+def visualize_solution(row_boundaries, col_boundaries, car_paths_coords, W, H):
     plt.rcParams['font.family'] = ['sans-serif']
     plt.rcParams['font.sans-serif'] = ['SimHei']
     fig, ax = plt.subplots()
@@ -28,32 +29,68 @@ def visualize_solution(row_boundaries, col_boundaries, car_paths, W, H):
     for col in col_boundaries:
         ax.axvline(x=col * W, color='black', linestyle='--')
 
-    # 绘制每辆车的轨迹
+    # 绘制每辆车的轨迹并标注区域序号
-    for system_id, path in enumerate(car_paths):
+    for system_id, path in enumerate(car_paths_coords):
-        path = [(region_center[0], region_center[1])] + path + [(region_center[0], region_center[1])]
+        path = [(region_center[0], region_center[1])] + \
+            path + [(region_center[0], region_center[1])]
         y, x = zip(*path)
-        ax.plot(x, y, marker='o', color=colors[int(system_id) % len(colors)], label=f"系统 {system_id}")
+        ax.plot(x, y, marker='o', color=colors[int(
+            system_id) % len(colors)], label=f"系统 {system_id}")
+
+        # 标注每个区域的序号
+        for idx, (px, py) in enumerate(zip(x[1:-1], y[1:-1])):  # 跳过起点和终点
+            ax.text(px, py, str(idx), color='black', fontsize=8, ha='center', va='center')
 
     # 添加图例
     ax.legend()
     plt.show()
 
+
 if __name__ == "__main__":
     import yaml
 
-    # 读取参数
+    # ---------------------------
-    with open('params3.yml', 'r', encoding='utf-8') as file:
+    # 需要修改的超参数
+    # ---------------------------
+    params_file = 'params2'
+    solution_file = r'solutions\trav_ga_params2_parallel.json'
+
+    with open(params_file + '.yml', 'r', encoding='utf-8') as file:
         params = yaml.safe_load(file)
 
     H = params['H']
     W = params['W']
+    k = params['num_cars']
 
     # 读取最佳方案的JSON文件
-    with open(r'solutions\trav_ga_params3_parallel.json', 'r', encoding='utf-8') as f:
+    with open(solution_file, 'r', encoding='utf-8') as f:
         best_solution = json.load(f)
 
     row_boundaries = best_solution['row_boundaries']
     col_boundaries = best_solution['col_boundaries']
     car_paths = best_solution['car_paths']
 
-    visualize_solution(row_boundaries, col_boundaries, car_paths, W, H)
+    # 计算分块区域的中心点坐标
+    rectangle_centers = []
+    for i in range(len(row_boundaries) - 1):
+        for j in range(len(col_boundaries) - 1):
+            r1 = row_boundaries[i]
+            r2 = row_boundaries[i + 1]
+            c1 = col_boundaries[j]
+            c2 = col_boundaries[j + 1]
+            d = (r2 - r1) * H * (c2 - c1) * W  # 任务的照片数量（矩形面积）
+
+            # 计算任务矩形中心，用于后续车辆移动时间计算
+            center_r = (r1 + r2) / 2.0 * H
+            center_c = (c1 + c2) / 2.0 * W
+
+            rectangle_centers.append((center_r, center_c))
+    
+    # 将car_paths里的index换成坐标
+    car_paths_coords = [[] for _ in range(k)]
+    for car_idx in range(k):
+        car_path = car_paths[car_idx]
+        for point in car_path:
+            car_paths_coords[car_idx].append(rectangle_centers[point])
+
+    visualize_solution(row_boundaries, col_boundaries, car_paths_coords, W, H)