添加greedy求解代码

PPO/env.py

@@ -61,7 +61,7 @@ class PartitionMazeEnv(gym.Env):
 
         # 路径规划阶段相关变量
         self.MAX_STEPS = 50         # 迷宫走法步数上限
-        self.BASE_LINE = 2750.0     # 基准时间，通过greedy或者蒙特卡洛计算出来
+        self.BASE_LINE = 3400.0     # 基准时间，通过greedy或者蒙特卡洛计算出来
         self.step_count = 0
         self.rectangles = {}
         self.car_pos = [[0.5, 0.5] for _ in range(self.num_cars)]
@@ -139,6 +139,7 @@ class PartitionMazeEnv(gym.Env):
                         bs_time = self.bs_time_factor * (1 - rho) * d
 
                         self.rectangles[(i, j)] = {
+                            'center': ((h_boundaries[i] + h_boundaries[i+1]) * self.H / 2, (v_boundaries[j+1] - v_boundaries[j]) * self.W / 2),
                             'flight_time': flight_time,
                             'bs_time': bs_time,
                             'is_visited': False
@@ -243,6 +244,8 @@ class PartitionMazeEnv(gym.Env):
                 # 区域覆盖完毕，根据轨迹计算各车队的执行时间
                 T = max([self._compute_motorcade_time(idx)
                         for idx in range(self.num_cars)])
+                print(T)
+                print(self.car_traj)
                 reward += -(T - self.BASE_LINE)
             elif done and self.step_count >= self.MAX_STEPS:
                 reward += -100
@@ -257,21 +260,23 @@ class PartitionMazeEnv(gym.Env):
 
         # 计算车的移动时间，首先在轨迹的首尾添加上大区域中心
         car_time = 0
-        self.car_traj[idx].append([0.5, 0.5])
-        self.car_traj[idx].insert(0, [0.5, 0.5])
+        # self.car_traj[idx].append([0.5, 0.5])
+        # self.car_traj[idx].insert(0, [0.5, 0.5])
         for i in range(len(self.car_traj[idx]) - 1):
             first_point = self.car_traj[idx][i]
             second_point = self.car_traj[idx][i + 1]
-            car_time += math.dist(first_point, second_point) * \
-                self.H * self.W * self.car_time_factor
+            car_time += math.dist(self.rectangles[tuple(first_point)]['center'], self.rectangles[tuple(second_point)]['center']) * \
+                self.car_time_factor
+        car_time + math.dist(self.rectangles[tuple(self.car_traj[idx][0])]['center'], [self.H, self.W])
+        car_time + math.dist(self.rectangles[tuple(self.car_traj[idx][-1])]['center'], [self.H, self.W])
 
         return max(float(car_time) + flight_time, bs_time)
 
     def render(self):
-        if self.phase == 0:
-            print("Phase 0: Partitioning.")
-            print(f"Partition step: {self.partition_step}")
+        if self.phase == 1:
+            print("Phase 1: Initialize maze environment.")
             print(f"Partition values so far: {self.partition_values}")
-        elif self.phase == 1:
-            print("Phase 1: Path planning (maze).")
-            print(f"Step count: {self.step_count}")
+            print(f"Motorcade positon: {self.car_pos}")
+        elif self.phase == 2:
+            print("Phase 2: Play maze.")
+            print(f'Motorcade trajectory: {self.car_traj}')

greedy_solver.py

@@ -0,0 +1,237 @@
+import math
+import yaml
+import matplotlib.pyplot as plt
+import matplotlib.patches as patches
+import numpy as np
+
+def calculate_max_photos_per_flight(params):
+    """计算每次飞行能拍摄的最大照片数量
+    基于以下约束：
+    1. 电池能量约束
+    2. 计算+传输时间 = 飞行时间
+    """
+    # 从参数中提取时间和能量因子
+    flight_time_factor = params['flight_time_factor']
+    comp_time_factor = params['comp_time_factor']
+    trans_time_factor = params['trans_time_factor']
+    battery_energy_capacity = params['battery_energy_capacity']
+    flight_energy_factor = params['flight_energy_factor']
+    comp_energy_factor = params['comp_energy_factor']
+    trans_energy_factor = params['trans_energy_factor']
+
+    # 基于时间约束求解rho：飞行时间 = 计算时间 + 传输时间
+    # flight_time_factor * d = comp_time_factor * rho * d + trans_time_factor * (1-rho) * d
+    rho_time = (flight_time_factor - trans_time_factor) / (comp_time_factor - trans_time_factor)
+
+    # 基于能量约束求解最大照片数d
+    # battery_energy_capacity = flight_energy_factor * d + comp_energy_factor * rho * d + trans_energy_factor * (1-rho) * d
+    energy_per_photo = (flight_energy_factor + 
+                       comp_energy_factor * rho_time + 
+                       trans_energy_factor * (1 - rho_time))
+    
+    max_photos = math.floor(battery_energy_capacity / energy_per_photo)
+    
+    return max_photos, rho_time
+
+def solve_greedy(params):
+    """使用贪心算法求解任务分配问题"""
+    H = params['H']
+    W = params['W']
+    k = params['num_cars']  # 系统数量
+    car_time_factor = params['car_time_factor']
+    bs_time_factor = params['bs_time_factor']
+    flight_time_factor = params['flight_time_factor']
+    
+    # 计算每次飞行能拍摄的最大照片数
+    photos_per_flight, rho = calculate_max_photos_per_flight(params)
+    print(f"贪心无人机计算的情况下，每次飞行能拍摄的最大照片数: {photos_per_flight}")
+    print(f"卸载率 rho: {rho:.3f}")
+    
+    # 用较小的边长来划分网格
+    min_side = min(H, W)
+    next_side = photos_per_flight // min_side
+
+    # 初始化任务分配列表
+    tasks = [[] for _ in range(k)]
+    
+    if min_side == H:
+        grid_h = min_side
+        grid_w = next_side
+        num_rows = 1
+        num_cols = round(W / grid_w)
+
+        current_col = 0
+        for i in range(math.ceil(num_cols / k)):
+            for j in range(k):
+                tasks[j].append((0, current_col))
+                current_col += 1
+                if current_col == num_cols:
+                    break
+    else:
+        grid_w = min_side
+        grid_h = next_side
+        num_cols = 1
+        num_rows = round(H / grid_h)
+        
+        current_row = 0
+        for i in range(math.ceil(num_rows / k)):
+            for j in range(k):
+                tasks[j].append((current_row, 0))
+                current_row += 1
+                if current_row == num_rows:
+                    break
+
+    print(f"网格大小: {grid_w}x{grid_h}")
+    print(f"网格数量: {num_rows}x{num_cols}")
+    print(f"任务分配情况: {tasks}")
+    
+    # 计算区域中心点
+    center_x = W / 2
+    center_y = H / 2
+    
+    # 为每个系统计算完成时间
+    system_times = []
+    for i in range(k):
+        if not tasks[i]:  # 如果该系统没有分配任务
+            system_times.append(0)
+            continue
+            
+        # 生成该系统负责的网格中心坐标
+        grids = []
+        for row, col in tasks[i]:
+            if min_side == H:
+                # 如果H是较小边，那么row=0，col递增
+                # TODO 最后一个网格的中心点不能这么算
+                grid_center_x = (col + 0.5) * grid_w
+                grid_center_y = (row + 0.5) * grid_h
+            else:
+                # 如果W是较小边，那么col=0，row递增
+                grid_center_x = (col + 0.5) * grid_w
+                grid_center_y = (row + 0.5) * grid_h
+            grids.append((grid_center_x, grid_center_y))
+        
+        # 计算车辆路径长度（从中心点出发）
+        car_distance = math.hypot(center_x - grids[0][0], center_y - grids[0][1])  # 从中心到第一个网格
+        for j in range(len(grids)-1):
+            car_distance += math.hypot(grids[j+1][0] - grids[j][0], 
+                                     grids[j+1][1] - grids[j][1])  # 网格间距离
+        car_distance += math.hypot(grids[-1][0] - center_x, 
+                                 grids[-1][1] - center_y)  # 从最后一个网格回到中心
+        
+        # 计算时间
+        num_photos = len(grids) * photos_per_flight  # 该系统需要拍摄的总照片数
+        flight_time = flight_time_factor * num_photos  # 飞行时间
+        car_time = car_time_factor * car_distance  # 车辆移动时间
+        bs_time = bs_time_factor * (1 - rho) * num_photos  # 基站计算时间
+        
+        total_time = max(flight_time + car_time, bs_time)
+        system_times.append(total_time)
+        
+        print(f"\n系统 {i} 详细信息:")
+        print(f"负责的网格数: {len(grids)}")
+        print(f"总照片数: {num_photos}")
+        print(f"车辆移动距离: {car_distance:.2f}")
+        print(f"飞行时间: {flight_time:.2f}")
+        print(f"车辆时间: {car_time:.2f}")
+        print(f"基站时间: {bs_time:.2f}")
+        print(f"总完成时间: {total_time:.2f}")
+    
+    # 找出最大完成时间
+    max_time = max(system_times)
+    print(f"\n最大完成时间: {max_time:.2f}")
+    
+    # 准备返回结果
+    result = {
+        'max_time': max_time,
+        'system_times': system_times,
+        'photos_per_flight': photos_per_flight,
+        'grid_w': grid_w,
+        'grid_h': grid_h,
+        'num_rows': num_rows,
+        'num_cols': num_cols,
+        'tasks': tasks,
+        'rho': rho
+    }
+    
+    return result
+
+def plot_results(params, result):
+    """可视化结果"""
+    H = params['H']
+    W = params['W']
+    k = params['num_cars']
+    
+    plt.rcParams['font.family'] = ['sans-serif']
+    plt.rcParams['font.sans-serif'] = ['SimHei']
+    
+    # 创建图形
+    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(15, 5))
+    
+    # 1. 绘制系统完成时间对比
+    ax1.bar(range(k), result['system_times'])
+    ax1.set_title('各系统完成时间对比')
+    ax1.set_xlabel('系统编号')
+    ax1.set_ylabel('完成时间(秒)')
+    
+    # 2. 绘制网格划分示意图
+    ax2.set_xlim(0, W)
+    ax2.set_ylim(0, H)
+    
+    # 为不同系统的网格使用不同颜色
+    colors = plt.cm.rainbow(np.linspace(0, 1, k))
+    
+    # 绘制网格和系统分配
+    grid_w = result['grid_w']
+    grid_h = result['grid_h']
+    tasks = result['tasks']
+    
+    # 绘制每个系统的网格
+    for system_idx, system_tasks in enumerate(tasks):
+        for row, col in system_tasks:
+            rect = patches.Rectangle(
+                (col * grid_w, row * grid_h),
+                grid_w, grid_h,
+                linewidth=1,
+                edgecolor='black',
+                facecolor=colors[system_idx],
+                alpha=0.3
+            )
+            ax2.add_patch(rect)
+            
+            # 在网格中心添加系统编号
+            center_x = (col + 0.5) * grid_w
+            center_y = (row + 0.5) * grid_h
+            ax2.text(center_x, center_y, str(system_idx), 
+                    ha='center', va='center')
+    
+    # 添加中心点标记
+    ax2.plot(W/2, H/2, 'r*', markersize=15, label='区域中心')
+    ax2.legend()
+    
+    ax2.set_title('网格划分和系统分配示意图')
+    ax2.set_xlabel('宽度')
+    ax2.set_ylabel('高度')
+    
+    plt.tight_layout()
+    plt.show()
+
+def main():
+    # 读取参数
+    with open('params.yml', 'r', encoding='utf-8') as file:
+        params = yaml.safe_load(file)
+    
+    # 求解
+    result = solve_greedy(params)
+    
+    # 输出结果
+    print("\n求解结果:")
+    print(f"最大完成时间: {result['max_time']:.2f} 秒")
+    print("\n各系统完成时间:")
+    for i, time in enumerate(result['system_times']):
+        print(f"系统 {i}: {time:.2f} 秒")
+    
+    # 可视化
+    plot_results(params, result)
+
+if __name__ == "__main__":
+    main()

mtkl_sovler.py

@@ -6,7 +6,7 @@ import yaml
 # 固定随机种子，便于复现
 random.seed(42)
 
-num_iterations = 100000
+num_iterations = 1000000
 
 # ---------------------------
 # 参数设置
@@ -125,6 +125,9 @@ for iteration in range(num_iterations):
                 curr_center = tasks[j]['center']
                 car_time += math.hypot(curr_center[0] - prev_center[0],
                                        curr_center[1] - prev_center[1]) * car_time_factor
+            # 回到区域中心
+            car_time += math.hypot(curr_center[0] - region_center[0],
+                                  curr_center[1] - prev_center[1]) * car_time_factor
         else:
             car_time = 0