feat: 优化风电场集电系统设计，支持电缆规格配置

主要更改:
• 新增电缆规格配置支持
  - Excel文件新增Cables工作表，支持自定义电缆参数(截面、载流量、电阻、成本)
  - 实现容量约束扫描算法(Capacitated Sweep)，替代原有K-means方法
  - 动态计算所需回路数量，确保每条回路的电缆载流量符合约束

• 代码增强
  - main.py: 集成电缆规格参数，新增命令行参数支持(--clusters手动指定簇数)
  - generate_template.py: 模板文件新增Cables工作表，提供9种标准电缆规格(35mm²-400mm²)

• 文档更新
  - 新增project_context.md: 详细记录项目背景、算法逻辑、电气建模和当前状态
  - 新增GEMINI.md: 开发者偏好配置

优化后的设计更符合实际工程需求，支持电缆容量约束，输出更准确的成本和损耗评估。

GEMINI.md

@@ -0,0 +1,9 @@
+运行shell时使用powershell模式。
+运行python代码前加载uv环境。
+编写代码时，尽可能多加注释。
+
+修改工程下的任何代码不需要询问我的同意。
+在工程下执行shell，不需要我的同意。
+在工程下执行任何命令，不需要我的同意。
+
+Please talk to me in Chinese.

generate_template.py

@@ -34,10 +34,26 @@ def create_template():
         
     df = pd.DataFrame(data)
     
+    # Create Cable data
+    cable_data = [
+        {'CrossSection': 35, 'Capacity': 150, 'Resistance': 0.524, 'Cost': 80},
+        {'CrossSection': 70, 'Capacity': 215, 'Resistance': 0.268, 'Cost': 120},
+        {'CrossSection': 95, 'Capacity': 260, 'Resistance': 0.193, 'Cost': 150},
+        {'CrossSection': 120, 'Capacity': 295, 'Resistance': 0.153, 'Cost': 180},
+        {'CrossSection': 150, 'Capacity': 330, 'Resistance': 0.124, 'Cost': 220},
+        {'CrossSection': 185, 'Capacity': 370, 'Resistance': 0.0991, 'Cost': 270},
+        {'CrossSection': 240, 'Capacity': 425, 'Resistance': 0.0754, 'Cost': 350},
+        {'CrossSection': 300, 'Capacity': 500, 'Resistance': 0.0601, 'Cost': 450},
+        {'CrossSection': 400, 'Capacity': 580, 'Resistance': 0.0470, 'Cost': 600}
+    ]
+    df_cables = pd.DataFrame(cable_data)
+    
     # Save to Excel
     output_file = 'coordinates.xlsx'
-    df.to_excel(output_file, index=False)
+    with pd.ExcelWriter(output_file) as writer:
-    print(f"Created sample file: {output_file}")
+        df.to_excel(writer, sheet_name='Coordinates', index=False)
+        df_cables.to_excel(writer, sheet_name='Cables', index=False)
+    print(f"Created sample file: {output_file} with sheets 'Coordinates' and 'Cables'")
 
 if __name__ == "__main__":
     create_template()

main.py

@@ -7,6 +7,7 @@ from sklearn.cluster import KMeans
 from collections import defaultdict
 import networkx as nx
 import math
+import argparse
 
 # 设置matplotlib支持中文显示
 plt.rcParams['font.sans-serif'] = ['Microsoft YaHei', 'SimHei', 'Arial']
@@ -69,11 +70,19 @@ def generate_wind_farm_data(n_turbines=30, seed=42, layout='random', spacing=800
 # 1.5 从Excel加载数据
 def load_data_from_excel(file_path):
     """
-    从Excel文件读取风机和升压站坐标
+    从Excel文件读取风机和升压站坐标，以及可选的电缆规格
-    Excel格式要求包含列: Type (Turbine/Substation), ID, X, Y, Power
+    Excel格式要求:
+    - Sheet 'Coordinates' (或第一个Sheet): Type (Turbine/Substation), ID, X, Y, Power
+    - Sheet 'Cables' (可选): CrossSection, Capacity, Resistance, Cost
     """
     try:
-        df = pd.read_excel(file_path)
+        xl = pd.ExcelFile(file_path)
+        
+        # 读取坐标数据
+        if 'Coordinates' in xl.sheet_names:
+            df = pd.read_excel(xl, 'Coordinates')
+        else:
+            df = pd.read_excel(xl, 0)
         
         # 标准化列名（忽略大小写）
         df.columns = [c.capitalize() for c in df.columns]
@@ -104,8 +113,35 @@ def load_data_from_excel(file_path):
             'cumulative_power': np.zeros(len(turbines_df))
         })
         
+        # 读取电缆数据 (如果存在)
+        cable_specs = None
+        if 'Cables' in xl.sheet_names:
+            cables_df = pd.read_excel(xl, 'Cables')
+            # 标准化列名
+            cables_df.columns = [c.replace(' ', '').capitalize() for c in cables_df.columns] # Handle 'Cross Section' vs 'CrossSection'
+            
+            # 尝试匹配列
+            # 目标格式: (截面mm², 载流量A, 电阻Ω/km, 基准价格元/m)
+            specs = []
+            for _, row in cables_df.iterrows():
+                # 容错处理列名
+                section = row.get('Crosssection', row.get('Section', 0))
+                capacity = row.get('Capacity', row.get('Current', 0))
+                resistance = row.get('Resistance', 0)
+                cost = row.get('Cost', row.get('Price', 0))
+                
+                if section > 0 and capacity > 0:
+                    specs.append((section, capacity, resistance, cost))
+            
+            if specs:
+                specs.sort(key=lambda x: x[1]) # 按载流量排序
+                cable_specs = specs
+        
         print(f"成功加载: {len(turbines)} 台风机, {len(substation)} 座升压站")
-        return turbines, substation
+        if cable_specs:
+            print(f"成功加载: {len(cable_specs)} 种电缆规格")
+            
+        return turbines, substation, cable_specs
         
     except Exception as e:
         print(f"读取Excel文件失败: {str(e)}")
@@ -220,66 +256,167 @@ def design_with_kmeans(turbines, substation, n_clusters=3):
     
     return cluster_connections + substation_connections, turbines
 
+# 3.5 带容量约束的扇区扫描算法 (Capacitated Angular Sweep)
+def design_with_capacitated_sweep(turbines, substation, cable_specs=None):
+    """
+    使用带容量约束的扇区扫描算法设计集电线路
+    原理：
+    1. 计算所有风机相对于升压站的角度。
+    2. 找到角度间隔最大的位置作为起始“切割线”，以避免切断密集的风机群。
+    3. 沿圆周方向扫描，贪婪地将风机加入当前回路，直到达到电缆容量上限。
+    4. 满载后开启新回路。
+    """
+    # 1. 获取电缆最大容量
+    max_mw = get_max_cable_capacity_mw(cable_specs)
+    print(f"DEBUG: 扇区扫描算法启动 - 单回路容量限制: {max_mw:.2f} MW")
+    
+    substation_coord = substation[0]
+    
+    # 2. 计算角度 (使用 arctan2 返回 -pi 到 pi)
+    # 避免直接修改原始DataFrame，使用副本
+    work_df = turbines.copy()
+    dx = work_df['x'] - substation_coord[0]
+    dy = work_df['y'] - substation_coord[1]
+    work_df['angle'] = np.arctan2(dy, dx)
+    
+    # 3. 寻找最佳起始角度 (最大角度间隙)
+    # 按角度排序
+    work_df = work_df.sort_values('angle').reset_index(drop=True) # 重置索引方便切片
+    
+    angles = work_df['angle'].values
+    n = len(angles)
+    
+    if n > 1:
+        # 计算相邻角度差
+        diffs = np.diff(angles)
+        # 计算首尾角度差 (跨越 ±pi 处)
+        wrap_diff = (2 * np.pi) - (angles[-1] - angles[0])
+        diffs = np.append(diffs, wrap_diff)
+        
+        # 找到最大间隙的索引 (该索引对应元素的 *后面* 是间隙)
+        max_gap_idx = np.argmax(diffs)
+        
+        # 如果最大间隙不是在队尾，则需要旋转数组，使最大间隙成为新的起点（即队尾）
+        # 实际上我们希望扫描的起点是最大间隙的“右侧”
+        # 例如: [0, 10, 100, 110]. Gaps: 10, 90, 10, 250. Max gap is wrap (250). Start at 0 is fine.
+        # 例如: [0, 10, 200, 210]. Gaps: 10, 190, 10, 150. Max gap is 190 (idx 1). 
+        # 我们应该从 idx 2 (200) 开始扫描。
+        
+        start_idx = (max_gap_idx + 1) % n
+        
+        # 重新排序风机列表
+        if start_idx != 0:
+            work_df = pd.concat([work_df.iloc[start_idx:], work_df.iloc[:start_idx]]).reset_index(drop=True)
+            
+    # 4. 贪婪分组 (Capacity Constrained Clustering)
+    work_df['cluster'] = -1
+    cluster_id = 0
+    current_power = 0
+    current_indices = []
+    
+    for i, row in work_df.iterrows():
+        p = row['power']
+        
+        # 检查是否超载
+        # 注意：如果是空簇，必须加入至少一个（即使单个风机超载也得加，但在风电中单机不会超载）
+        if len(current_indices) > 0 and (current_power + p > max_mw):
+            # 当前簇已满，结束当前簇，开启新簇
+            work_df.loc[current_indices, 'cluster'] = cluster_id
+            cluster_id += 1
+            current_power = 0
+            current_indices = []
+            
+        current_indices.append(i)
+        current_power += p
+        
+    # 处理最后一个簇
+    if current_indices:
+        work_df.loc[current_indices, 'cluster'] = cluster_id
+        cluster_id += 1 # 计数用
+        
+    print(f"DEBUG: 生成了 {cluster_id} 个回路 (簇)")
+    
+    # 将 cluster 标记映射回原始 turbines DataFrame (通过 original_id 或 索引匹配)
+    # 这里我们简单地重建 turbines，因为 work_df 包含了所有信息且顺序变了
+    # 为了保持外部一致性，我们把 cluster 列 map 回去
+    
+    # 建立 id -> cluster 的映射
+    id_to_cluster = dict(zip(work_df['id'], work_df['cluster']))
+    turbines['cluster'] = turbines['id'].map(id_to_cluster)
+    
+    # 5. 对每个簇内部进行MST连接 (复用现有逻辑)
+    cluster_connections = []
+    substation_connections = []
+    n_clusters = cluster_id
+    
+    for cid in range(n_clusters):
+        cluster_turbines = turbines[turbines['cluster'] == cid]
+        if len(cluster_turbines) == 0:
+            continue
+            
+        # --- 簇内 MST ---
+        cluster_indices = cluster_turbines.index.tolist()
+        coords = cluster_turbines[['x', 'y']].values
+        
+        if len(cluster_indices) > 1:
+            dist_matrix = distance_matrix(coords, coords)
+            mst = minimum_spanning_tree(dist_matrix).toarray()
+            
+            for i in range(len(cluster_indices)):
+                for j in range(len(cluster_indices)):
+                    if mst[i, j] > 0:
+                        source = f'turbine_{cluster_indices[i]}'
+                        target = f'turbine_{cluster_indices[j]}'
+                        cluster_connections.append((source, target, mst[i, j]))
+        
+        # --- 连接到升压站 ---
+        # 找到簇内离升压站最近的风机
+        dists = np.sqrt((cluster_turbines['x'] - substation_coord[0])**2 + 
+                        (cluster_turbines['y'] - substation_coord[1])**2)
+        closest_id = dists.idxmin() # 返回的是原始DataFrame的index
+        
+        # 添加升压站连接
+        min_dist = dists.min()
+        substation_connections.append((f'turbine_{closest_id}', 'substation', min_dist))
+    
+    return cluster_connections + substation_connections, turbines
+
 # 常量定义
 VOLTAGE_LEVEL = 66000  # 66kV
 POWER_FACTOR = 0.95
 
-# 4. 电缆选型函数（简化版）
+def get_max_cable_capacity_mw(cable_specs=None):
-def select_cable(power, length, is_offshore=False):
     """
-    基于功率和长度选择合适的电缆截面
+    计算给定电缆规格中能够承载的最大功率 (单位: MW)。
-    :param is_offshore: 是否为海上环境（成本更高）
+    
+    基于提供的电缆规格列表，选取最大载流量，结合系统电压和功率因数计算理论最大传输功率。
+    
+    参数:
+        cable_specs (list, optional): 电缆规格列表。每个元素应包含 (截面积, 额定电流, 单价, 损耗系数)。
+    
+    返回:
+        float: 最大功率承载能力 (MW)。
+        
+    异常:
+        Exception: 当未提供 cable_specs 时抛出，提示截面不满足。
     """
-    # 成本乘数：海缆材料+敷设成本通常是陆缆的4-6倍
+    if cable_specs:
-    cost_multiplier = 5.0 if is_offshore else 1.0
+        # 从所有电缆规格中找到最大的额定电流容量
+        max_current_capacity = max(spec[1] for spec in cable_specs)
+    else:
+        # 如果没有传入电缆规格，通常意味着已尝试过所有规格但仍不满足需求
+        raise Exception("没有提供电缆参数")
         
-    # 电缆规格库: (截面mm², 载流量A, 电阻Ω/km, 基准价格元/m)
+    # 计算最大功率：P = √3 * U * I * cosφ
-    cable_specs = [
+    # 这里假设降额系数为 1 (不降额)
-        (35, 150, 0.524, 80),
+    max_current = max_current_capacity * 1 
-        (70, 215, 0.268, 120),
-        (95, 260, 0.193, 150),
-        (120, 295, 0.153, 180),
-        (150, 330, 0.124, 220),
-        (185, 370, 0.0991, 270),
-        (240, 425, 0.0754, 350),
-        (300, 500, 0.0601, 450), # 增加大截面适应海上大功率
-        (400, 580, 0.0470, 600)
-    ]
-    
-    # 估算电流
-    # power是MW, 换算成W需要 * 1e6
-    current = (power * 1e6) / (np.sqrt(3) * VOLTAGE_LEVEL * POWER_FACTOR)
-    
-    # 选择满足载流量的最小电缆
-    selected_spec = None
-    for spec in cable_specs:
-        if current <= spec[1] * 0.8:  # 80%负载率
-            selected_spec = spec
-            break
-    
-    if selected_spec is None:
-        selected_spec = cable_specs[-1]
-        
-    resistance = selected_spec[2] * length / 1000  # 电阻(Ω)
-    cost = selected_spec[3] * length * cost_multiplier  # 电缆成本(含敷设)
-    
-    return {
-        'cross_section': selected_spec[0],
-        'current_capacity': selected_spec[1],
-        'resistance': resistance,
-        'cost': cost,
-        'current': current
-    }
-
-def get_max_cable_capacity_mw():
-    """计算最大电缆(400mm2)能承载的最大功率(MW)"""
-    # 400mm2载流量580A
-    max_current = 580 * 0.8 # 80%降额
     max_power_w = np.sqrt(3) * VOLTAGE_LEVEL * max_current * POWER_FACTOR
-    return max_power_w / 1e6 # MW
+    
+    # 将单位从 W 转换为 MW
+    return max_power_w / 1e6 
 
 # 5. 计算集电线路方案成本
-def evaluate_design(turbines, connections, substation, is_offshore=False):
+def evaluate_design(turbines, connections, substation, cable_specs=None, is_offshore=False, method_name="Unknown Method"):
     """评估设计方案的总成本和损耗"""
     total_cost = 0
     total_loss = 0
@@ -320,9 +457,10 @@ def evaluate_design(turbines, connections, substation, is_offshore=False):
         except nx.NetworkXNoPath:
             pass 
             
-    # DEBUG: 打印最大功率流
+    # DEBUG: 打印最大功率流 (不含升压站本身)
-    max_power = max(power_flow.values()) if power_flow else 0
+    node_powers = [v for k, v in power_flow.items() if k != 'substation']
-    print(f"DEBUG: 最大线路功率 = {max_power:.2f} MW")
+    max_power = max(node_powers) if node_powers else 0
+    print(f"DEBUG [{method_name}]: 最大线路功率 = {max_power:.2f} MW")
     
     # 计算成本和损耗
     detailed_connections = []
@@ -345,7 +483,49 @@ def evaluate_design(turbines, connections, substation, is_offshore=False):
             power = 0
         
         # 电缆选型
-        cable = select_cable(power, length, is_offshore=is_offshore)
+        # 成本乘数：海缆材料+敷设成本通常是陆缆的4-6倍
+        cost_multiplier = 5.0 if is_offshore else 1.0
+        
+        # 默认电缆规格库 (如果未提供)
+        if cable_specs is None:
+            cable_specs_to_use = [
+                (35, 150, 0.524, 80),
+                (70, 215, 0.268, 120),
+                (95, 260, 0.193, 150),
+                (120, 295, 0.153, 180),
+                (150, 330, 0.124, 220),
+                (185, 370, 0.0991, 270),
+                (240, 425, 0.0754, 350),
+                (300, 500, 0.0601, 450), 
+                (400, 580, 0.0470, 600)
+            ]
+        else:
+            cable_specs_to_use = cable_specs
+        
+        # 估算电流
+        current = (power * 1e6) / (np.sqrt(3) * VOLTAGE_LEVEL * POWER_FACTOR)
+        
+        # 选择满足载流量的最小电缆
+        selected_spec = None
+        for spec in cable_specs_to_use:
+            if current <= spec[1] * 1:  # 100%负载率
+                selected_spec = spec
+                break
+        
+        if selected_spec is None:
+            selected_spec = cable_specs_to_use[-1]
+            print(f"WARNING [{method_name}]: Current {current:.2f} A (Power: {power:.2f} MW) exceeds max cable capacity {selected_spec[1]} A!")
+            
+        resistance = selected_spec[2] * length / 1000  # 电阻(Ω)
+        cost = selected_spec[3] * length * cost_multiplier  # 电缆成本(含敷设)
+        
+        cable = {
+            'cross_section': selected_spec[0],
+            'current_capacity': selected_spec[1],
+            'resistance': resistance,
+            'cost': cost,
+            'current': current
+        }
         
         # 记录详细信息
         detailed_connections.append({
@@ -562,19 +742,21 @@ def visualize_design(turbines, substation, connections, title, ax=None, show_cos
     return ax
 
 # 7. 主函数：比较两种设计方法
-def compare_design_methods(excel_path=None):
+def compare_design_methods(excel_path=None, n_clusters_override=None):
     """
     比较MST和K-means两种设计方法 (海上风电场场景)
     :param excel_path: Excel文件路径，如果提供则从文件读取数据
+    :param n_clusters_override: 可选，手动指定簇的数量
     """
+    cable_specs = None
     if excel_path:
         print(f"正在从 {excel_path} 读取坐标数据...")
         try:
-            turbines, substation = load_data_from_excel(excel_path)
+            turbines, substation, cable_specs = load_data_from_excel(excel_path)
             scenario_title = "Offshore Wind Farm (Imported Data)"
         except Exception:
             print("回退到自动生成数据模式...")
-            return compare_design_methods(excel_path=None)
+            return compare_design_methods(excel_path=None, n_clusters_override=n_clusters_override)
     else:
         print("正在生成海上风电场数据 (规则阵列布局)...")
         # 使用规则布局，间距800m
@@ -586,29 +768,35 @@ def compare_design_methods(excel_path=None):
     # 方法1：最小生成树
     # 注意：MST方法在不考虑容量约束时，可能会导致根部线路严重过载
     mst_connections = design_with_mst(turbines, substation)
-    mst_evaluation = evaluate_design(turbines, mst_connections, substation, is_offshore=is_offshore)
+    mst_evaluation = evaluate_design(turbines, mst_connections, substation, cable_specs=cable_specs, is_offshore=is_offshore, method_name="MST Method")
     
     # 方法2：K-means聚类 (容量受限聚类)
     # 计算总功率和所需的最小回路数
     total_power = turbines['power'].sum()
-    max_cable_mw = get_max_cable_capacity_mw()
+    max_cable_mw = get_max_cable_capacity_mw(cable_specs=cable_specs)
-    min_clusters_needed = int(np.ceil(total_power / max_cable_mw))
     
+    # 允许指定簇的数量，如果设置为 None 则自动计算
+    if n_clusters_override is not None:
+        n_clusters = n_clusters_override
+        min_clusters_needed = int(np.ceil(total_power / max_cable_mw))
+        print(f"使用手动指定的回路数(簇数): {n_clusters} (理论最小需求 {min_clusters_needed})")
+    else:
+        min_clusters_needed = int(np.ceil(total_power / max_cable_mw))
         # 增加一定的安全裕度 (1.2倍) 并确保至少有一定数量的簇
         n_clusters = max(int(min_clusters_needed * 1.2), 4)
     if len(turbines) < n_clusters: # 避免簇数多于风机数
         n_clusters = len(turbines)
         
     print(f"系统设计参数: 总功率 {total_power:.1f} MW, 单回路最大容量 {max_cable_mw:.1f} MW")
-    print(f"计算建议回路数(簇数): {n_clusters} (最小需求 {min_clusters_needed})")
     
-    kmeans_connections, clustered_turbines = design_with_kmeans(turbines.copy(), substation, n_clusters=n_clusters)
+    # 替换为带容量约束的扫描算法
-    kmeans_evaluation = evaluate_design(turbines, kmeans_connections, substation, is_offshore=is_offshore)
+    kmeans_connections, clustered_turbines = design_with_capacitated_sweep(turbines.copy(), substation, cable_specs=cable_specs)
+    kmeans_evaluation = evaluate_design(turbines, kmeans_connections, substation, cable_specs=cable_specs, is_offshore=is_offshore, method_name="Capacitated Sweep")
     
     # 创建结果比较
     results = {
         'MST Method': mst_evaluation,
-        'K-means Method': kmeans_evaluation
+        'Capacitated Sweep': kmeans_evaluation
     }
     
     # 可视化
@@ -619,9 +807,11 @@ def compare_design_methods(excel_path=None):
                     f"MST Design - {scenario_title}\nTotal Cost: ¥{mst_evaluation['total_cost']/10000:.2f}万\nTotal Loss: {mst_evaluation['total_loss']:.2f} kW", 
                     ax=axes[0])
     
-    # 可视化K-means方法
+    # 可视化K-means方法 (现在是 Capacitated Sweep)
+    # 获取实际生成的簇数
+    n_actual_clusters = clustered_turbines['cluster'].nunique()
     visualize_design(clustered_turbines, substation, kmeans_evaluation['details'], 
-                    f"Sector Clustering (Angular) ({n_clusters} clusters) - {scenario_title}\nTotal Cost: ¥{kmeans_evaluation['total_cost']/10000:.2f}万\nTotal Loss: {kmeans_evaluation['total_loss']:.2f} kW", 
+                    f"Capacitated Sweep ({n_actual_clusters} circuits) - {scenario_title}\nTotal Cost: ¥{kmeans_evaluation['total_cost']/10000:.2f}万\nTotal Loss: {kmeans_evaluation['total_loss']:.2f} kW", 
                     ax=axes[1])
     
     plt.tight_layout()
@@ -648,10 +838,16 @@ def compare_design_methods(excel_path=None):
 
 # 8. 执行比较
 if __name__ == "__main__":
-    import os
+    # 解析命令行参数
-    # 检查是否存在 coordinates.xlsx，存在则优先使用
+    parser = argparse.ArgumentParser(description='Wind Farm Collector System Design')
-    default_excel = 'coordinates.xlsx'
+    parser.add_argument('--clusters', type=int, help='Specify the number of clusters (circuits) manually', default=None)
-    if os.path.exists(default_excel):
+    args = parser.parse_args()
-        results = compare_design_methods(excel_path=default_excel)
+
-    else:
+    # 2. 读取 Excel 坐标数据 (如果存在)
-        results = compare_design_methods()
+    excel_path = 'coordinates2.xlsx'
+    # 尝试从命令行参数获取文件路径 (可选扩展)
+    # if len(sys.argv) > 1: excel_path = sys.argv[1]
+    
+    # 3. 运行比较
+    # 如果本地没有excel文件，将自动回退到生成数据模式
+    compare_design_methods(excel_path, n_clusters_override=args.clusters)

project_context.md

@@ -0,0 +1,61 @@
+# Project Context: Wind Farm Layout Optimization
+
+**Last Updated:** 2025-12-30
+**Project Path:** `D:\code\windfarm`
+**Current Goal:** Optimize offshore wind farm cable layout using MST and K-means algorithms, with realistic constraints and CAD export.
+
+## 1. System Overview
+The system simulates and designs the collection system (inter-array cables) for an offshore wind farm.
+It compares two main algorithms:
+1.  **MST (Minimum Spanning Tree)**: Global optimization of cable length. (Note: Often creates overloaded branches in large farms).
+2.  **Sector Clustering (K-means)**: Angular clustering to divide turbines into radial "strings" or "loops" feeding the substation. This is the preferred method for large offshore farms to ensure cable capacity constraints are met.
+
+## 2. Key Implementations
+
+### A. Data Handling
+- **Generation**: Can generate random or grid layouts.
+- **Import**: Supports reading coordinates from `coordinates.xlsx` (Columns: Type, ID, X, Y, Power).
+- **Units**: 
+    - Power in **MW** (input).
+    - Coordinates in **meters**.
+    - Voltage: **66 kV** (Code constant `VOLTAGE_LEVEL`).
+
+### B. Algorithms
+- **Angular K-means**: 
+    - Uses `(cosθ, sinθ)` of the angle relative to substation for clustering.
+    - Eliminates cable crossings between sectors.
+- **Dynamic Cluster Sizing**: 
+    - Automatically calculates the required number of clusters (feeders) based on: `Total_Power / Max_Cable_Capacity`.
+    - Ensures no string exceeds the thermal limit of the largest available cable.
+
+### C. Electrical Modeling
+- **Cable Sizing**: Selects from standard cross-sections (35mm² to 400mm²).
+- **Constraint**: Max cable capacity (400mm²) is approx. **50.4 MW** at 66kV/0.95PF.
+- **Loss Calc**: $I^2 R$ losses.
+
+### D. Visualization & Export
+- **Matplotlib**: Shows layout with color-coded cables (Green=Thin -> Red=Thick).
+- **DXF Export**: Uses `ezdxf` to generate `.dxf` files compatible with CAD.
+    - Layers: `Substation`, `Turbines`, `Cable_XXmm`.
+    - entities: Circles (Turbines), Polylines (Substation), Lines (Cables).
+
+## 3. Critical Logic & Constants
+- **Voltage**: 66,000 V
+- **Power Factor**: 0.95
+- **Max Current (400mm²)**: 580 A * 0.8 (derating) = 464 A.
+- **Unit Conversion**: Critical fix applied to convert MW to Watts for current calculation (`power * 1e6`).
+
+## 4. Current State & file Structure
+- `main.py`: Core logic.
+- `coordinates.xlsx`: Input data (if present).
+- `wind_farm_design_imported.png`: Latest visualization.
+- `wind_farm_design.dxf`: Latest CAD export.
+
+## 5. Known Behaviors
+- **MST Method**: Will report extremely high costs/losses for large farms because it creates a single tree structure that massively overloads the root cables. This is expected behavior (physically invalid but mathematically correct for unconstrained MST).
+- **K-means Method**: Produces realistic, valid designs with appropriate cable tapering (e.g., 400mm² at root, 35mm² at leaves).
+
+## 6. Future Improvements (Optional)
+- **Obstacle Avoidance**: Currently assumes open ocean.
+- **Loop Topology**: Current design is radial strings. Reliability could be improved with loop/ring structures.
+- **Substation Placement Optimization**: Currently fixed or calculated as centroid.