import numpy as np import pandas as pd import torch import os from datetime import datetime, timedelta import sys import argparse import posixpath import getpass import paramiko weather_utils_path = os.path.abspath( os.path.join(os.path.dirname(__file__), "..") ) if weather_utils_path not in sys.path: sys.path.insert(0, weather_utils_path) from ModelLoading import ModelLoading,SolorFeature _LOCAL_COLS = ("time_shanghai", "time_local", "time_bj", "时间戳") def parse_init_time(init_time) -> pd.Timestamp: """起报时间 -> tz-aware UTC Timestamp。支持 'YYMMDDHH' / 'YYYYMMDDHH' / ISO / datetime / Timestamp""" if isinstance(init_time, pd.Timestamp): ts = init_time elif hasattr(init_time, "year") and not isinstance(init_time, str): ts = pd.Timestamp(init_time) else: s = str(init_time).strip() digits = "".join(ch for ch in s if ch.isdigit()) if len(s) == 8 and s.isdigit(): # YYMMDDHH ts = pd.to_datetime("20" + s, format="%Y%m%d%H") elif len(digits) == 10 and s.isdigit(): # YYYYMMDDHH ts = pd.to_datetime(s, format="%Y%m%d%H") elif "T" in s or " " in s or "-" in s: ts = pd.to_datetime(s, utc=True).tz_localize(None) else: raise ValueError(f"无法识别的 init_time: {init_time!r}") ts = pd.Timestamp(ts) return ts.tz_localize("UTC") if ts.tz is None else ts.tz_convert("UTC") def build_forecast_df(shortTerm_result, init_time, *, freq="15min", tz="Asia/Shanghai", pred_col="power", init_fmt="%y%m%d%H", time_fmt="%Y-%m-%dT%H:%MZ", local_fmt="%Y-%m-%d %H:%M:%S"): """ shortTerm_result : 模型输出, 自动 reshape(-1); 长度 = 预报步数(短期 288 / 中期 960) init_time : 起报时间(UTC) 返回: DataFrame, 列顺序 init_time(YYMMDDHH) | time(UTC) | time_shanghai | 时间从起报时刻起, 共 N 个点, 步长 15min """ pred = np.asarray(shortTerm_result).reshape(-1) n = pred.size if n == 0: raise ValueError("shortTerm_result 为空") t0 = parse_init_time(init_time) utc = pd.date_range(t0, periods=n, freq=freq) return pd.DataFrame({ "init_time": [t0.strftime(init_fmt)] * n, "time": utc.strftime(time_fmt), "time_shanghai": utc.tz_convert(tz).strftime(local_fmt), pred_col: np.asarray(pred, dtype=float), }) def remove_night_power(MediumTerm, lat, lon, *, power_col="power", time_col="time", elev_min=0.0, tz="Asia/Shanghai", clip_negative=True, return_info=False): """ MediumTerm : DataFrame, 含时间列(默认 'time', UTC)与功率列(默认 'power') lat, lon : 场站纬度、经度(度), 正东经/正北纬 power_col : 功率列名, 默认 'power' time_col : 时间列名, 默认 'time'(UTC); 传 'time_shanghai' 按北京时间解释; 指定列不存在而存在 'time_shanghai' 时自动回退 elev_min : 夜间阈值(度), 默认 0(含大气折射修正, 即视地平线) clip_negative : 是否同时把负功率置 0 return_info : True 时返回 (df, info) 返回: 处理后的 DataFrame(副本), 列与原表一致, 仅 power 列被改写 """ if not isinstance(MediumTerm, pd.DataFrame): raise TypeError("MediumTerm 需要是 DataFrame(含时间列); 若只有数值请先自行补上时间列") df = MediumTerm.copy() # 1. 时间列 if time_col not in df.columns: alt = next((c for c in _LOCAL_COLS if c in df.columns), None) if alt is None: raise ValueError(f"时间列 {time_col!r} 不存在, 现有列: {list(df.columns)}") time_col = alt t = pd.to_datetime(df[time_col], errors="coerce") if t.isna().any(): raise ValueError(f"时间列 {time_col!r} 存在无法解析的值({int(t.isna().sum())} 个)") is_local = (time_col in _LOCAL_COLS) or time_col.lower().endswith("_shanghai") if getattr(t.dt, "tz", None) is not None: t_utc = t.dt.tz_convert("UTC") # 已带时区 -> 转 UTC elif is_local: t_utc = t.dt.tz_localize(tz).dt.tz_convert("UTC") # time_shanghai(北京时) -> UTC else: t_utc = t.dt.tz_localize("UTC") # 'time' 列按 UTC 约定 # 2. 功率列 if power_col not in df.columns: raise ValueError(f"功率列 {power_col!r} 不在列中: {list(df.columns)}") # 3. 太阳高度角 -> 夜间掩码 d = pd.DatetimeIndex(t_utc.dt.tz_localize(None)) jd = d.values.astype("datetime64[s]").astype("int64") / 86400.0 + 2440587.5 T = (jd - 2451545.0) / 36525.0 L0 = 280.46646 + T * (36000.76983 + T * 0.0003032) M = 357.52911 + T * (35999.05029 - 0.0001537 * T) e = 0.016708634 - T * (0.000042037 + 0.0000001267 * T) Mr = np.radians(M) C = (np.sin(Mr) * (1.914602 - T * (0.004817 + 0.000014 * T)) + np.sin(2 * Mr) * (0.019993 - 0.000101 * T) + np.sin(3 * Mr) * 0.000289) omega = 125.04 - 1934.136 * T lam = L0 + C - 0.00569 - 0.00478 * np.sin(np.radians(omega)) eps = (23 + (26 + (21.448 - T * (46.815 + T * (0.00059 - T * 0.001813))) / 60) / 60 + 0.00256 * np.cos(np.radians(omega))) decl = np.degrees(np.arcsin(np.sin(np.radians(eps)) * np.sin(np.radians(lam)))) y = np.tan(np.radians(eps / 2)) ** 2 eot = 4 * np.degrees(y * np.sin(2 * np.radians(L0)) - 2 * e * np.sin(Mr) + 4 * e * y * np.sin(Mr) * np.cos(2 * np.radians(L0)) - 0.5 * y * y * np.sin(4 * np.radians(L0)) - 1.25 * e * e * np.sin(2 * Mr)) mins = d.hour.values * 60 + d.minute.values + d.second.values / 60.0 ha = np.radians((mins + eot + 4.0 * lon) / 4.0 - 180.0) # 时角(经度正东) latr, dr = np.radians(lat), np.radians(decl) cosz = np.sin(latr) * np.sin(dr) + np.cos(latr) * np.cos(dr) * np.cos(ha) el = 90.0 - np.degrees(np.arccos(np.clip(cosz, -1, 1))) el = el + np.where(el > -0.575, # 大气折射修正 1.02 / (60 * np.tan(np.radians(el + 10.3 / (el + 5.11)))), 0.0) night = el <= elev_min # 4. 夜间非 0 值置 0 p = pd.to_numeric(df[power_col], errors="coerce") bad = night & p.notna() if clip_negative: bad = bad | (p < 0).fillna(False).to_numpy() changed = bad & p.notna() & (p.to_numpy() != 0) info = {"time_col": time_col, "power_col": power_col, "n_rows": len(df), "n_night": int(night.sum()), "n_night_nonzero": int((night & (p > 0)).sum()), "n_zeroed": int(changed.sum()), "sum_removed": float(p[changed].sum())} df[power_col] = p.mask(bad, 0.0) return (df, info) if return_info else df def mkdir_p(sftp, remote_dir): """递归创建远程目录，已存在则跳过""" dirs = [] current = remote_dir while current not in ("", ".", "/"): dirs.append(current) current = posixpath.dirname(current) for directory in reversed(dirs): try: sftp.stat(directory) except OSError: sftp.mkdir(directory) def upload_files( host, port, username, local_files, remote_files, password=None, ): """ 通过 SFTP 批量上传文件。 参数： host: SFTP 服务器地址 port: 端口 username: 用户名 local_files: 本地文件路径数组 remote_files: 远程文件路径数组 password: 密码，可选；不传则运行时输入 """ if len(local_files) != len(remote_files): raise ValueError("local_files 和 remote_files 数量必须一致") if password is None: password = getpass.getpass("请输入 SFTP 密码: ") transport = paramiko.Transport((host, port)) try: transport.connect( username=username, password=password ) sftp = paramiko.SFTPClient.from_transport(transport) try: for local_file, remote_file in zip(local_files, remote_files): remote_dir = posixpath.dirname(remote_file) # 自动创建远程目录 mkdir_p(sftp, remote_dir) print(f"正在上传:") print(f" 本地: {local_file}") print(f" 远程: {remote_file}") sftp.put( local_file, remote_file, confirm=False ) print("上传成功\n") finally: sftp.close() finally: transport.close() if __name__ == '__main__': # 配置光伏场站信息 parser = argparse.ArgumentParser(description='OuLiPoewev1.0 Prediction') parser.add_argument('--projs', type=str, default='JMJD01', help='场站名') parser.add_argument('--model_name', type=str, default='GRU', help='模型名称') parser.add_argument('--release', type=str, default='v24', help='特征集') parser.add_argument('--lat', type=float, default=22.292, help='场站纬度') parser.add_argument('--lon', type=float, default=120.290, help='场站经度') parser.add_argument('--short_term_seq', type=int, default=288, help='输入序列长度-短期') parser.add_argument('--medium_term_seq', type=int, default=960, help='输入序列长度-中期') parser.add_argument('--capacity', type=int, default=4050, help='装机容量(kw)') parser.add_argument('--saved_model_root', type=str, default='/home/jinhuaiming/OuLiPowerV1.0/saved_model', help='模型权重保存根路径') parser.add_argument('--saved_result_root', type=str, default='/home/jinhuaiming/OuLiPowerV1.0/archive', help='预报结果存档根路径') parser.add_argument('--init_time', type=str, default='2026060200', help='预报时间(UTC)') args = parser.parse_args() #=====读取气象数据--刘博士实现========================================================= # 气象变量特征 # 短期：v24-【'ssrd','tcc','lcc','mcc','hcc','2t','2d','10u','10v'】 # 中期：v24-【'ssrd','tcc','lcc','mcc','hcc','2t','2d','10u','10v'】 # 单位： w/m2, 0-100,0-100,0-100,0-100,°C, °C, m/s, m/s # 模型【输入输出】维度 # 短期：输入 =（1，288，9），输出 =（1，288） # 中期：输出 =（1，960，9），输出 =（1，960） # 注意⚠️：特征顺序不要改变，保持上述描述顺序。 # 根据 某个站点(args.projs)，预报时间(args.init_time)取的气象数据 init_time = args.init_time #YYYYMMDDHH ShortTerm_input = torch.randn(1, 288, 9) MediumTerm_input = torch.randn(1, 960, 9) #=====加载模型======================================================================= # 加载短期功率预测模型 ShortTerm_Modelloader = ModelLoading( trial = 'None', projs = args.projs, model_name = args.model_name, release = args.release, input_seq = args.short_term_seq, saved_model_path = args.saved_model_root, predict_mode = True, capacity = args.capacity ) # 加载中期功率预测模型 MediumTerm_Modelloader = ModelLoading( trial = 'None', projs = args.projs, model_name = args.model_name, release = args.release, input_seq = args.medium_term_seq, saved_model_path = args.saved_model_root, predict_mode = True, capacity = args.capacity ) #=====预测========================================================================== # 短期预测 -输出（288,） shortTerm_result = ShortTerm_Modelloader.predict(ShortTerm_input).detach().numpy().reshape(-1) ShortTerm_df = build_forecast_df(shortTerm_result, args.init_time) # 中期预测 - 输出（960,） MediumTerm_result = MediumTerm_Modelloader.predict(MediumTerm_input).detach().numpy().reshape(-1) MediumTerm_df = build_forecast_df(MediumTerm_result, args.init_time) #=====后处理-消除夜间非0值和可能存在的赋值=============================================== ShortTerm_df = remove_night_power(ShortTerm_df, lat=args.lat, lon=args.lon) MediumTerm_df = remove_night_power(MediumTerm_df, lat=args.lat, lon=args.lon) #=====数据保存与上传================================================================== # 保存本地 os.makedirs(os.path.join(args.saved_result_root, args.projs, 'ShortTerm',args.init_time[0:4],args.init_time[4:6]), exist_ok=True) os.makedirs(os.path.join(args.saved_result_root, args.projs, 'MediumTerm',args.init_time[0:4],args.init_time[4:6]), exist_ok=True) ShortTerm_df.to_csv( os.path.join(args.saved_result_root, args.projs, 'ShortTerm', args.init_time[0:4],args.init_time[4:6], f'{args.init_time}.csv'), index=False ) MediumTerm_df.to_csv( os.path.join(args.saved_result_root, args.projs, 'MediumTerm', args.init_time[0:4],args.init_time[4:6], f'{args.init_time}.csv'), index=False ) # 上传客户服务器 local_files = [ os.path.join(args.saved_result_root, args.projs, 'ShortTerm', args.init_time[0:4], args.init_time[4:6], f'{args.init_time}.csv'), os.path.join(args.saved_result_root, args.projs, 'MediumTerm', args.init_time[0:4], args.init_time[4:6],f'{args.init_time}.csv'), ] remote_files = [ f"./upload/power/{args.projs}/ShortTerm/{args.init_time[0:4]}/{args.init_time[4:6]}/{args.init_time}.csv", f"./upload/power/{args.projs}/MediumTerm/{args.init_time[0:4]}/{args.init_time[4:6]}/{args.init_time}.csv", ] upload_files( host="112.124.19.19", port=22, username="power", password="nv.>d)2M+;u*X$KZ", local_files=local_files, remote_files=remote_files )