|
@@ -0,0 +1,639 @@
|
|
|
+# # Day-ahead load forecasting
|
|
|
+#
|
|
|
+# DB : MS SQL
|
|
|
+#
|
|
|
+# Program Language : Python
|
|
|
+#
|
|
|
+# kgpark@hdc-icontrols.com
|
|
|
+# April 10, 2020
|
|
|
+
|
|
|
+# ### BEMS 데이터 수집 메카니즘
|
|
|
+# #### 데이터 별로 수집 타입에 따라 다르지만, Raw 테이블에 적산 값으로 저장이 되고 15min 테이블에서 해당 시간대와 그 전 시간대의 차이 값을 입력한다.
|
|
|
+# #### DGW 혹은 시스템에 이상이 생겼을 때, 데이터가 들어오지 않거나 0으로 입력된다.
|
|
|
+# #### 1시간 테이블은 15분 테이블에서 각 15분, 30분, 45분, 60분의 데이터 합산 값이 나왔다.
|
|
|
+# #### 합산 값으로 저장되다보니 4개 포인트 중 적어도 하나만 있어도 1시간 데이터로 저장이 된다.
|
|
|
+# #### 따라서, 15분 데이터를 전처리하는 것이 주효하고 데이터가 없거나 0값을 검출하여 비정상 데이터로 추정하는 것을 추천한다.
|
|
|
+# #### 또한, 1시간 단위로 데이터 주기를 변환한다면 15분 테이블의 4개 포인트 중 하나라도 값을 모른다면 그 시간의 데이터가 비정상이라고 가정하는 것을 추천한다.
|
|
|
+
|
|
|
+
|
|
|
+import matplotlib.pyplot as plt
|
|
|
+import pymssql
|
|
|
+import datetime
|
|
|
+import numpy as np
|
|
|
+import math
|
|
|
+from korean_lunar_calendar import KoreanLunarCalendar
|
|
|
+import calendar
|
|
|
+import configparser
|
|
|
+import sys
|
|
|
+import time
|
|
|
+
|
|
|
+
|
|
|
+# ## Define functions
|
|
|
+### Define day-type
|
|
|
+def getDayName(year, month, day):
|
|
|
+ return ['MON','TUE','WED','THU','FRI','SAT','SUN'][datetime.date(year, month, day).weekday()]
|
|
|
+def getDayType(DateinDay, Period, SpecialHoliday):
|
|
|
+ DoW=[]; # Day of Week
|
|
|
+ for i in range(Period):
|
|
|
+ if DateinDay[i].year==2019 and DateinDay[i].month==5 and DateinDay[i].day==18:
|
|
|
+ DoW.append([5, DateinDay[i]])
|
|
|
+ elif getDayName(DateinDay[i].year,DateinDay[i].month,DateinDay[i].day) == 'MON':
|
|
|
+ DoW.append([1, DateinDay[i]])
|
|
|
+ elif getDayName(DateinDay[i].year,DateinDay[i].month,DateinDay[i].day) == 'TUE':
|
|
|
+ DoW.append([2, DateinDay[i]])
|
|
|
+ elif getDayName(DateinDay[i].year,DateinDay[i].month,DateinDay[i].day) == 'WED':
|
|
|
+ DoW.append([3, DateinDay[i]])
|
|
|
+ elif getDayName(DateinDay[i].year,DateinDay[i].month,DateinDay[i].day) == 'THU':
|
|
|
+ DoW.append([4, DateinDay[i]])
|
|
|
+ elif getDayName(DateinDay[i].year,DateinDay[i].month,DateinDay[i].day) == 'FRI':
|
|
|
+ DoW.append([5, DateinDay[i]])
|
|
|
+ elif getDayName(DateinDay[i].year,DateinDay[i].month,DateinDay[i].day) == 'SAT':
|
|
|
+ DoW.append([6, DateinDay[i]])
|
|
|
+ elif getDayName(DateinDay[i].year,DateinDay[i].month,DateinDay[i].day) == 'SUN':
|
|
|
+ DoW.append([7, DateinDay[i]])
|
|
|
+
|
|
|
+ for j in range(len(SpecialHoliday)):
|
|
|
+ if SpecialHoliday[j] == datetime.date(DateinDay[i].year,DateinDay[i].month,DateinDay[i].day):
|
|
|
+ DoW[-1][0] = 8
|
|
|
+ break
|
|
|
+ ### W:1, N:2, ### W: Workday, N: Non-workday
|
|
|
+ DayType=[]
|
|
|
+ for i in range(Period):
|
|
|
+ if DoW[i][0] <= 5:
|
|
|
+ DayType.append([1, DateinDay[i]])
|
|
|
+ elif DoW[i][0] > 5:
|
|
|
+ DayType.append([2, DateinDay[i]])
|
|
|
+ return DoW, DayType
|
|
|
+
|
|
|
+
|
|
|
+def Reconstruction(DayType, DatainHour, mark, DataRes, isRecent):
|
|
|
+ ReconstructedData=[]
|
|
|
+ DayType1h=[]
|
|
|
+ Day_len = len(DayType)
|
|
|
+
|
|
|
+ # Rearrange data in hour unit
|
|
|
+ for i in range(Day_len):
|
|
|
+ if i == Day_len-1 and isRecent:
|
|
|
+ Time_len = len(DatainHour) - i*DataRes
|
|
|
+ else:
|
|
|
+ Time_len=DataRes
|
|
|
+ for j in range(Time_len):
|
|
|
+ DayType1h.append([DatainHour[i*DataRes + j], DayType[i][0], datetime.datetime(DayType[i][1].year, DayType[i][1].month, DayType[i][1].day, j, 0)]) ## data, daytype, time
|
|
|
+
|
|
|
+ # 비정상 데이터보다 앞선 시간의 데이터 중 DayType이 같고 시간이 같은 5개 날 데이터의 평균으로 복원함
|
|
|
+ for i in reversed(range(len(DayType1h))):
|
|
|
+ AccData=[]
|
|
|
+ cnt=0
|
|
|
+ if math.isnan(DayType1h[i][0]):
|
|
|
+ for j in range(len(DayType1h)):
|
|
|
+ if cnt > 5:
|
|
|
+ break
|
|
|
+ if i < j and DayType1h[j][1] == DayType1h[i][1] and DayType1h[j][2].hour == DayType1h[i][2].hour and (not math.isnan(DayType1h[j][0])):
|
|
|
+ AccData.append(DayType1h[j][0])
|
|
|
+ cnt += 1
|
|
|
+ DayType1h[i][0] = np.mean(AccData)
|
|
|
+ ReconstructedData.append(DayType1h[i][0])
|
|
|
+ ReconstructedData.reverse()
|
|
|
+
|
|
|
+ ### Double-checking for the data which is not reconstructed, especially in front
|
|
|
+ for i in range(len(DayType1h)):
|
|
|
+ AccData=[]
|
|
|
+ cnt=0
|
|
|
+ if math.isnan(DayType1h[i][0]):
|
|
|
+ #print('Here is NaN!!',ReconstructedData[i],i,DayType1h[i][2].hour, DayType1h[i][1])
|
|
|
+ for j in reversed(range(len(DayType1h))):
|
|
|
+ if cnt > 5:
|
|
|
+ break
|
|
|
+ if i > j and DayType1h[j][1] == DayType1h[i][1] and DayType1h[j][2].hour == DayType1h[i][2].hour and (not math.isnan(DayType1h[j][0])):
|
|
|
+ AccData.append(DayType1h[j][0])
|
|
|
+ cnt += 1
|
|
|
+ ReconstructedData[i] = np.mean(AccData)
|
|
|
+ return ReconstructedData, DayType1h
|
|
|
+
|
|
|
+## For day-ahead linear prediction
|
|
|
+def lpc_pred_DayAhead(Data_trn, DayType_trn, cov_lth, DayType_tst, DataRes):
|
|
|
+ # Calculating the filter bank for each hour and day-type using traing set
|
|
|
+ for c_w in range(1,3):
|
|
|
+ DayType_trn[0,0]=0
|
|
|
+ CP_pred_fb=np.zeros(Data_trn.shape)
|
|
|
+ lpc_fb=np.zeros([cov_lth[c_w-1],DataRes])
|
|
|
+ Prv_A=[]
|
|
|
+ Prv_A=np.transpose(Data_trn[DataRes-cov_lth[c_w-1]:DataRes,np.where(DayType_trn == c_w)[0]-1])
|
|
|
+ for hr_i in range(24):
|
|
|
+ lpc_fb[:,hr_i]=np.dot(np.linalg.pinv(Prv_A), np.transpose(Data_trn[hr_i,np.where(DayType_trn == c_w)[0]]))
|
|
|
+
|
|
|
+ if c_w == 1:
|
|
|
+ lpc_fb1=lpc_fb
|
|
|
+ elif c_w == 2:
|
|
|
+ lpc_fb2=lpc_fb
|
|
|
+
|
|
|
+ ## For testing
|
|
|
+ if DayType_tst[0,0] == 1:
|
|
|
+ lpc_t=lpc_fb1
|
|
|
+ elif DayType_tst[0,0] == 2:
|
|
|
+ lpc_t=lpc_fb2
|
|
|
+
|
|
|
+ Data_tt=Data_trn[:,-1]
|
|
|
+ # Load prediction for test day based on the filter bank
|
|
|
+ CP_pred=np.transpose(np.dot(np.transpose(Data_tt[DataRes-cov_lth[DayType_tst[0,0]-1]:DataRes+1]),lpc_t))
|
|
|
+ return CP_pred
|
|
|
+
|
|
|
+## For step-ahead linear prediction
|
|
|
+def lpc_pred_OneStepAhead(Data_trn, DayType_trn, cov_lth, DayType_tst, DataRes):
|
|
|
+ for c_w in range(1,3):
|
|
|
+ DayType_trn[0,0]=0
|
|
|
+ lpc_fb=np.zeros([cov_lth[c_w-1],DataRes])
|
|
|
+ Prv_A=[]
|
|
|
+ Prv_A=np.transpose(Data_trn[DataRes-cov_lth[c_w-1]:DataRes,np.where(DayType_trn == c_w)[0]-1])
|
|
|
+ lpc_fb=np.dot(np.linalg.pinv(Prv_A), np.transpose(Data_trn[0,np.where(DayType_trn == c_w)[0]]))
|
|
|
+
|
|
|
+ if c_w == 1:
|
|
|
+ lpc_fb1=lpc_fb
|
|
|
+ elif c_w == 2:
|
|
|
+ lpc_fb2=lpc_fb
|
|
|
+ ## Testing
|
|
|
+ if DayType_tst[0,0] == 1:
|
|
|
+ lpc_t=lpc_fb1
|
|
|
+ elif DayType_tst[0,0] == 2:
|
|
|
+ lpc_t=lpc_fb2
|
|
|
+
|
|
|
+ Data_tt=Data_trn[:,-1]
|
|
|
+ CP_pred=np.transpose(np.dot(np.transpose(Data_tt[DataRes-cov_lth[DayType_tst[0,0]-1]:DataRes+1]),lpc_t))
|
|
|
+ return CP_pred
|
|
|
+
|
|
|
+## Measure
|
|
|
+def MAPE(y_observed, y_pred):
|
|
|
+ return np.mean(np.abs((y_observed - y_pred) / y_observed)) * 100
|
|
|
+def MAE(y_observed, y_pred):
|
|
|
+ return np.mean(np.abs(y_observed - y_pred))
|
|
|
+def MBE(y_observed, y_pred):
|
|
|
+ return (np.sum((y_observed - y_pred))/(len(y_observed)*np.mean(y_observed)))*100
|
|
|
+def CVRMSE(y_observed, y_pred):
|
|
|
+ return (np.sqrt(np.mean((y_observed - y_pred)*(y_observed - y_pred)))/np.mean(y_observed))*100
|
|
|
+
|
|
|
+## Check for normal time stamp
|
|
|
+def Check_AlivedTimeStamp(RawData, ComparedData, idx_raw, idx_comp):
|
|
|
+ if datetime.date(RawData[idx_raw][4].year,RawData[idx_raw][4].month,RawData[idx_raw][4].day) == datetime.date(ComparedData[idx_comp].year, ComparedData[idx_comp].month, ComparedData[idx_comp].day) and datetime.time(RawData[idx_raw][4].hour,RawData[idx_raw][4].minute) == datetime.time(ComparedData[idx_comp].hour, ComparedData[idx_comp].minute):
|
|
|
+ isAlived = True
|
|
|
+ else:
|
|
|
+ isAlived = False
|
|
|
+ return isAlived
|
|
|
+
|
|
|
+if __name__ == "__main__" :
|
|
|
+
|
|
|
+ ## Check every hour on the hour operating infinite loop
|
|
|
+ while True:
|
|
|
+ now = datetime.datetime.now().now()
|
|
|
+
|
|
|
+ ## distinguish real time update and specific day
|
|
|
+ ## 자정에 생기는 인덱싱 문제로 0시에는 16분에 업데이트
|
|
|
+ if (now.hour != 0 and now.minute == 1) or (now.hour == 0 and now.minute == 16):
|
|
|
+ PredctionActive = True
|
|
|
+ else:
|
|
|
+ PredctionActive = False
|
|
|
+ if now.second > 55:
|
|
|
+ print("[ Current Time -", now.hour,":", now.minute,":", now.second,"], " "Sleeping for 30 seconds... Prediction starts every hour")
|
|
|
+ time.sleep(30)
|
|
|
+ else:
|
|
|
+ print("[ Current Time -", now.hour,":", now.minute,":", now.second,"], " "Sleeping for 60 seconds... Prediction starts every hour")
|
|
|
+ time.sleep(60)
|
|
|
+
|
|
|
+ if PredctionActive:
|
|
|
+
|
|
|
+ ## Loading .ini file
|
|
|
+ myINI = configparser.ConfigParser()
|
|
|
+ myINI.read("Config.ini", "utf-8" )
|
|
|
+ # MSSQL Access
|
|
|
+ conn = pymssql.connect(host=myINI.get('LocalDB_Info','ip_address'), user=myINI.get('LocalDB_Info','user_id'), password=myINI.get('LocalDB_Info','user_password'), database=myINI.get('LocalDB_Info','db_name'))
|
|
|
+ # Create Cursor from Connection
|
|
|
+ cursor = conn.cursor()
|
|
|
+
|
|
|
+ # Execute SQL (Electric consumption)
|
|
|
+ cursor.execute('SELECT * FROM BemsConfigData where SiteId = 1')
|
|
|
+ rowDB_info = cursor.fetchone()
|
|
|
+
|
|
|
+ conn.close()
|
|
|
+
|
|
|
+ loadDBIP = rowDB_info[1]
|
|
|
+ loadDBUserID = rowDB_info[2]
|
|
|
+ loadDBUserPW = rowDB_info[3]
|
|
|
+ loadDBName = rowDB_info[4]
|
|
|
+ targetDBIP = rowDB_info[5]
|
|
|
+ targetDBUserID = rowDB_info[6]
|
|
|
+ targetDBUserPW = rowDB_info[7]
|
|
|
+ targetDBName = rowDB_info[8]
|
|
|
+ linearFilterLength = rowDB_info[10]
|
|
|
+
|
|
|
+ print("=================== Prediction start! ===================")
|
|
|
+
|
|
|
+ startday = datetime.date(int(rowDB_info[9].year), int(rowDB_info[9].month), int(rowDB_info[9].day))
|
|
|
+
|
|
|
+ # ## Data accumulation
|
|
|
+ isRecent = True
|
|
|
+ lastday = datetime.date(now.year, now.month, now.day)
|
|
|
+ if startday < datetime.date(2017,1,1):
|
|
|
+ print('[ERROR] 데이터 최소 시작 시점은 2017.01.01 입니다')
|
|
|
+ elif startday > lastday:
|
|
|
+ print('[ERROR] 예측 타깃 시작시점이 데이터 시작 시점보다 작을 수 없습니다')
|
|
|
+
|
|
|
+ now_ = datetime.date(now.year, now.month, now.day)
|
|
|
+ # 학습데이터의 기간은 최대 2년으로 한정
|
|
|
+ if (startday-now_).days > 730:
|
|
|
+ Ago_2year = now_ + timedelta(days=-730)
|
|
|
+ startday = datetime.date(Ago_2year.year, Ago_2year.month, Ago_2year.day)
|
|
|
+
|
|
|
+ # MSSQL Access
|
|
|
+ conn = pymssql.connect(host = loadDBIP, user = loadDBUserID, password = loadDBUserPW, database = loadDBName)
|
|
|
+
|
|
|
+ # Create Cursor from Connection
|
|
|
+ cursor = conn.cursor()
|
|
|
+
|
|
|
+ # Execute SQL (Electric consumption)
|
|
|
+ cursor.execute('SELECT * FROM BemsMonitoringPointHistory15min where SiteId = 1 and FacilityTypeId = 99 and FacilityCode = 4863 and PropertyId = 1 order by CreatedDateTime desc')
|
|
|
+
|
|
|
+ # 데이타 하나씩 Fetch하여 출력
|
|
|
+ row = cursor.fetchone()
|
|
|
+ DataRes_org=96
|
|
|
+ DataRes_24=24
|
|
|
+
|
|
|
+ rawData=[]
|
|
|
+ while row:
|
|
|
+ row = cursor.fetchone()
|
|
|
+ if datetime.date(row[4].year,row[4].month,row[4].day) < startday:
|
|
|
+ break
|
|
|
+ rawData.append(row)
|
|
|
+ rawData.reverse() # 오름차순 정렬
|
|
|
+
|
|
|
+ # 연결 끊기
|
|
|
+ conn.close()
|
|
|
+ print('rawData',rawData[0],rawData[-1])
|
|
|
+ # 현장 데이터가 없을 경우 예외처리
|
|
|
+ if now.hour == 0:
|
|
|
+ hour_calib = 0
|
|
|
+ else:
|
|
|
+ hour_calib = 1
|
|
|
+ if datetime.datetime(now.year, now.month, now.day, now.hour, 0, 0) - datetime.timedelta(hours=hour_calib) == datetime.datetime(rawData[-1][4].year, rawData[-1][4].month, rawData[-1][4].day, rawData[-1][4].hour, 0, 0):
|
|
|
+
|
|
|
+ # MSSQL Access
|
|
|
+ conn = pymssql.connect(host = loadDBIP, user = loadDBUserID, password = loadDBUserPW, database = loadDBName)
|
|
|
+ # Create Cursor from Connection
|
|
|
+ cursor = conn.cursor()
|
|
|
+ # SQL문 실행 (정기휴일)
|
|
|
+ cursor.execute('SELECT * FROM CmHoliday where SiteId = 1 and IsUse = 1')
|
|
|
+
|
|
|
+ # 데이타 하나씩 Fetch하여 출력
|
|
|
+ row = cursor.fetchone()
|
|
|
+ regularHolidayData = [row]
|
|
|
+ while row:
|
|
|
+ row = cursor.fetchone()
|
|
|
+ regularHolidayData.append(row)
|
|
|
+ regularHolidayData = regularHolidayData[0:-1]
|
|
|
+
|
|
|
+ # SQL문 실행 (비정기휴일)
|
|
|
+ cursor.execute('SELECT * FROM CmHolidayCustom where SiteId = 1 and IsUse = 1')
|
|
|
+
|
|
|
+ # 데이타 하나씩 Fetch하여 출력
|
|
|
+ row = cursor.fetchone()
|
|
|
+ suddenHolidayData = [row]
|
|
|
+ while row:
|
|
|
+ row = cursor.fetchone()
|
|
|
+ suddenHolidayData.append(row)
|
|
|
+ suddenHolidayData = suddenHolidayData[0:-1]
|
|
|
+
|
|
|
+ # 연결 끊기
|
|
|
+ conn.close()
|
|
|
+
|
|
|
+ # 공휴일의 음력 계산
|
|
|
+ calendar_convert = KoreanLunarCalendar()
|
|
|
+ SpecialHoliday = []
|
|
|
+ for i in range(lastday.year-startday.year+1):
|
|
|
+ for j in range(len(regularHolidayData)):
|
|
|
+ if regularHolidayData[j][3] == 1:
|
|
|
+ if regularHolidayData[j][1] == 12 and regularHolidayData[j][2] == 30: ## 설 하루 전 연휴 계산을 위함
|
|
|
+ calendar_convert.setLunarDate(startday.year+i-1, regularHolidayData[j][1], regularHolidayData[j][2], False)
|
|
|
+ SpecialHoliday.append(datetime.date(int(calendar_convert.SolarIsoFormat().split(' ')[0].split('-')[0]), int(calendar_convert.SolarIsoFormat().split(' ')[0].split('-')[1]), int(calendar_convert.SolarIsoFormat().split(' ')[0].split('-')[2])))
|
|
|
+ else:
|
|
|
+ calendar_convert.setLunarDate(startday.year+i, regularHolidayData[j][1], regularHolidayData[j][2], False)
|
|
|
+ SpecialHoliday.append(datetime.date(int(calendar_convert.SolarIsoFormat().split(' ')[0].split('-')[0]), int(calendar_convert.SolarIsoFormat().split(' ')[0].split('-')[1]), int(calendar_convert.SolarIsoFormat().split(' ')[0].split('-')[2])))
|
|
|
+ else:
|
|
|
+ SpecialHoliday.append(datetime.date(startday.year+i,regularHolidayData[j][1],regularHolidayData[j][2]))
|
|
|
+
|
|
|
+ for i in range(len(suddenHolidayData)):
|
|
|
+ if suddenHolidayData[i][1].year >= startday.year:
|
|
|
+ SpecialHoliday.append(datetime.date(suddenHolidayData[i][1].year, suddenHolidayData[i][1].month, suddenHolidayData[i][1].day))
|
|
|
+
|
|
|
+ SpecialHoliday=list(set(SpecialHoliday))
|
|
|
+ DayPeriod = (lastday - startday).days + 1
|
|
|
+ print('First day:',startday,',', 'Last Day:', lastday,',','Current Time:', now)
|
|
|
+ print('Day period :', DayPeriod)
|
|
|
+
|
|
|
+ # ## Find unkown/zero data (Bad data)
|
|
|
+
|
|
|
+ StartTime = datetime.datetime(int(startday.strftime('%Y')), int(startday.strftime('%m')), int(startday.strftime('%d')), 0, 0, 0)
|
|
|
+ TimeStamp_DayUnit = []
|
|
|
+ StandardTimeStamp = []
|
|
|
+ # Create normal time stamp
|
|
|
+ for idx_day in range(DayPeriod):
|
|
|
+ TimeStamp_DayUnit.append(startday + datetime.timedelta(days=idx_day))
|
|
|
+ if isRecent and idx_day == DayPeriod-1:
|
|
|
+ if now.hour == 0: # 예외처리용 (자정에 Day count가 안되는 현상)
|
|
|
+ tmp_len = 1
|
|
|
+ else:
|
|
|
+ tmp_len = now.hour*4 + int(now.minute/15)
|
|
|
+ for idx_time in range(tmp_len):
|
|
|
+ StandardTimeStamp.append(StartTime)
|
|
|
+ StartTime += datetime.timedelta(minutes = 15)
|
|
|
+ else:
|
|
|
+ for idx_time in range(DataRes_org):
|
|
|
+ StandardTimeStamp.append(StartTime)
|
|
|
+ StartTime += datetime.timedelta(minutes = 15)
|
|
|
+
|
|
|
+ RawDate=[] # raw data (date)
|
|
|
+ RawElectricLoad=[] # raw data (electric load)
|
|
|
+ for i in range(len(rawData)):
|
|
|
+ if datetime.date(rawData[i][4].year,rawData[i][4].month,rawData[i][4].day) >= startday:
|
|
|
+ if datetime.date(rawData[i][4].year,rawData[i][4].month,rawData[i][4].day) <= lastday:
|
|
|
+ RawDate.append(rawData[i][4])
|
|
|
+ RawElectricLoad.append(rawData[i][5])
|
|
|
+ if datetime.date(rawData[i][4].year,rawData[i][4].month,rawData[i][4].day) > lastday:
|
|
|
+ break
|
|
|
+
|
|
|
+ Data_len=len(RawDate)
|
|
|
+ if isRecent:
|
|
|
+ DataAct_len = (DayPeriod-1)*DataRes_org + now.hour*4 + int(now.minute/15)
|
|
|
+ else:
|
|
|
+ DataAct_len = DayPeriod*DataRes_org
|
|
|
+ ### Unknown/zero data counts
|
|
|
+ DataCount=[]
|
|
|
+ for i in range(len(TimeStamp_DayUnit)):
|
|
|
+ cnt_unk=0 # For Unknown data count
|
|
|
+ cnt_zero=0 # zero data count
|
|
|
+ for j in range(Data_len):
|
|
|
+ if TimeStamp_DayUnit[i] == datetime.date(RawDate[j].year,RawDate[j].month,RawDate[j].day):
|
|
|
+ cnt_unk += 1
|
|
|
+ if RawElectricLoad[j] == 0:
|
|
|
+ cnt_zero += 1
|
|
|
+ if isRecent and i==len(TimeStamp_DayUnit)-1:
|
|
|
+ DataCount.append([TimeStamp_DayUnit[i], now.hour*4 + int(now.minute/15) - cnt_unk, cnt_zero])
|
|
|
+ else:
|
|
|
+ DataCount.append([TimeStamp_DayUnit[i], DataRes_org-cnt_unk, cnt_zero])
|
|
|
+
|
|
|
+ ## Visualization
|
|
|
+ ## 월 인덱스 설정 ##
|
|
|
+ idxCal=[]
|
|
|
+ idxCalName=[]
|
|
|
+ idxCal.append(0)
|
|
|
+ for y_idx in range(lastday.year - startday.year + 1):
|
|
|
+ if startday.year == lastday.year:
|
|
|
+ for m_idx in range(lastday.month - startday.month + 1):
|
|
|
+ month = startday.month + m_idx
|
|
|
+ idxCal.append(idxCal[-1] + calendar.monthrange(startday.year, month)[1])
|
|
|
+ idxCalName.append(calendar.month_name[month])
|
|
|
+ else:
|
|
|
+ if y_idx == 0: ## 첫번째 해
|
|
|
+ for m_idx in range(13-startday.month):
|
|
|
+ month = startday.month + m_idx
|
|
|
+ idxCal.append(idxCal[-1] + calendar.monthrange(startday.year, month)[1])
|
|
|
+ idxCalName.append(calendar.month_name[month])
|
|
|
+ elif y_idx !=0 and y_idx == lastday.year - startday.year: ## 마지막 해
|
|
|
+ for m_idx in range(lastday.month):
|
|
|
+ month = m_idx + 1
|
|
|
+ idxCal.append(idxCal[-1] + calendar.monthrange(lastday.year, month)[1])
|
|
|
+ idxCalName.append(calendar.month_name[month])
|
|
|
+ else:
|
|
|
+ for m_idx in range(12):
|
|
|
+ month = m_idx + 1
|
|
|
+ idxCal.append(idxCal[-1] + calendar.monthrange(startday.year+y_idx, month)[1])
|
|
|
+ idxCalName.append(calendar.month_name[month])
|
|
|
+
|
|
|
+ DataCountMat=np.matrix(DataCount)
|
|
|
+
|
|
|
+ print("The number of unknown data:",sum(DataCountMat[:,1]), ", The number of zero data:", sum(DataCountMat[:,2]))
|
|
|
+
|
|
|
+ plt.figure(figsize=(16,9))
|
|
|
+ plt.subplot(311)
|
|
|
+ plt.plot(DataCountMat[:,1],label='Unknown data', linewidth = 2)
|
|
|
+ plt.plot(DataCountMat[:,2],label='Zero data', linewidth = 2)
|
|
|
+ # plt.xlabel('Months', fontsize = 16)
|
|
|
+ plt.ylabel('Data counts', fontsize = 14)
|
|
|
+ plt.legend(loc='upper left', fontsize = 14)
|
|
|
+ plt.title("Unknown/zero electric load data per 15min. unit ("+str(startday.year)+"."+str(startday.month)+"."+str(startday.day)+" - "+str(lastday.year)+"."+str(lastday.month)+"."+str(lastday.day)+")", fontsize = 14)
|
|
|
+ plt.xlim(idxCal[0], idxCal[-1])
|
|
|
+ plt.xticks(idxCal, idxCalName, fontsize=6.5)
|
|
|
+ plt.yticks(fontsize=14)
|
|
|
+
|
|
|
+ print("Bad data detection complete!")
|
|
|
+
|
|
|
+ ### NaN-padding after finding unknown data
|
|
|
+ ######## 현재 DB 특성상 값이 0으로 찍히거나 시간테이블의 행 자체가 없는 경우가 있고, 이 데이터 1 step 앞뒤로 데이터가 비정상일 확률이 높으므로 비정상데이터 뿐만 아니라 앞뒤 1 step까지 nan으로 처리함
|
|
|
+
|
|
|
+ ElectricLoad_Un_ZP=[]
|
|
|
+ RawDate=[]
|
|
|
+ idx=0
|
|
|
+ idx2=0
|
|
|
+ isBadData = False
|
|
|
+
|
|
|
+ for i in range(DataAct_len):
|
|
|
+ if datetime.date(rawData[idx][4].year,rawData[idx][4].month,rawData[idx][4].day) >= startday and datetime.date(rawData[idx][4].year,rawData[idx][4].month,rawData[idx][4].day) <= lastday:
|
|
|
+ RawDate.append(StandardTimeStamp[idx2])
|
|
|
+ if isBadData == True:
|
|
|
+ ElectricLoad_Un_ZP.append(np.nan)
|
|
|
+ isBadData=False
|
|
|
+ elif rawData[idx][5]==0:
|
|
|
+ ElectricLoad_Un_ZP[-1]=np.nan
|
|
|
+ ElectricLoad_Un_ZP.append(np.nan)
|
|
|
+ if rawData[idx+1][5] > 0 and Check_AlivedTimeStamp(rawData, StandardTimeStamp, idx+1, idx2+1):
|
|
|
+ isBadData = True
|
|
|
+ elif Check_AlivedTimeStamp(rawData, StandardTimeStamp, idx, idx2):
|
|
|
+ ElectricLoad_Un_ZP.append(rawData[idx][5])
|
|
|
+ else:
|
|
|
+ ElectricLoad_Un_ZP[-1]=np.nan
|
|
|
+ ElectricLoad_Un_ZP.append(np.nan)
|
|
|
+ if rawData[idx+1][5] > 0 and Check_AlivedTimeStamp(rawData, StandardTimeStamp, idx+1, idx2+1):
|
|
|
+ isBadData = True
|
|
|
+ idx -= 1
|
|
|
+ idx2 += 1
|
|
|
+ idx += 1
|
|
|
+
|
|
|
+ print('NaN-padding complete!')
|
|
|
+
|
|
|
+
|
|
|
+ # ## Decimation to 1-hour period
|
|
|
+ ElectricLoad_1h = []
|
|
|
+ for i in range(DayPeriod):
|
|
|
+ if i == DayPeriod-1 and isRecent:
|
|
|
+ Time_len = DataAct_len - i*DataRes_org + 1
|
|
|
+ else:
|
|
|
+ Time_len = DataRes_org
|
|
|
+ isNaN=False
|
|
|
+ for j in range(Time_len):
|
|
|
+ if ElectricLoad_Un_ZP[i*4 + j] == np.nan:
|
|
|
+ isNaN=True
|
|
|
+ if j%4==3:
|
|
|
+ if isNaN:
|
|
|
+ ElectricLoad_1h.append(np.nan)
|
|
|
+ else:
|
|
|
+ ElectricLoad_1h.append(sum(ElectricLoad_Un_ZP[i*DataRes_org + j-3:i*DataRes_org + j+1]))
|
|
|
+
|
|
|
+ print('Decimation to 1hour complete!')
|
|
|
+
|
|
|
+ # ## Data reconstruction using similar-day approach
|
|
|
+ DateinDay=[]
|
|
|
+ for k in range(DayPeriod):
|
|
|
+ DateinDay.append(RawDate[k*DataRes_org])
|
|
|
+
|
|
|
+ DoW, DayType = getDayType(DateinDay, DayPeriod, SpecialHoliday)
|
|
|
+
|
|
|
+ # Find the similar-day and reconstructed data
|
|
|
+ marking=np.nan
|
|
|
+ ReconstructedData, DayType1h = Reconstruction(DayType, ElectricLoad_1h, marking, DataRes_24, isRecent)
|
|
|
+
|
|
|
+ plt.subplot(312)
|
|
|
+ plt.plot(ReconstructedData, '*-', label='Reconstructed data',linewidth=3)
|
|
|
+ plt.plot(ElectricLoad_1h, '--', label='Raw data',linewidth=3)
|
|
|
+ plt.legend(loc='upper right', fontsize = 14)
|
|
|
+ plt.ylabel('Power [kW]', fontsize = 14)
|
|
|
+ plt.yticks(fontsize=14)
|
|
|
+ plt.xticks([0],fontsize=14)
|
|
|
+ plt.xlim((DayPeriod-10)*24, DayPeriod*24)
|
|
|
+ plt.title('Raw & reconstructed data in the latest 10 days',fontsize=14)
|
|
|
+
|
|
|
+ print('Reconstruct complete!')
|
|
|
+
|
|
|
+
|
|
|
+ # ## Day-ahead load forecasting
|
|
|
+ ####### Convert to matrix
|
|
|
+ ReconstructedData_Arr=np.zeros((DataRes_24, DayPeriod))
|
|
|
+ for i in range(DayPeriod):
|
|
|
+ if isRecent and i==DayPeriod-1:
|
|
|
+ for j in range(len(ReconstructedData)%DataRes_24):
|
|
|
+ ReconstructedData_Arr[j,i]=ReconstructedData[i*DataRes_24+j]
|
|
|
+ else:
|
|
|
+ for j in range(DataRes_24):
|
|
|
+ ReconstructedData_Arr[j,i]=ReconstructedData[i*DataRes_24+j]
|
|
|
+
|
|
|
+ trn_period=DayPeriod - 1
|
|
|
+ DayType_m=np.matrix(DayType)
|
|
|
+ Data_trn=ReconstructedData_Arr[:,0:trn_period]
|
|
|
+ Data_tst=ReconstructedData_Arr[:,trn_period]
|
|
|
+ DayType_trn=DayType_m[0:trn_period,:]
|
|
|
+ DayType_tst=DayType_m[trn_period,:]
|
|
|
+ cov_lth=np.array([int(linearFilterLength.split(',')[0]),int(linearFilterLength.split(',')[1])])
|
|
|
+ y_pred_dayAhead = lpc_pred_DayAhead(Data_trn, DayType_trn, cov_lth, DayType_tst, DataRes_24)
|
|
|
+ print('-------------------------Day-ahead prediction result-------------------------')
|
|
|
+ if isRecent:
|
|
|
+ if now.hour == 0:
|
|
|
+ print('MAPE :', MAPE(Data_tst[0],y_pred_dayAhead[0]), 'MAE :', MAE(Data_tst[0],y_pred_dayAhead[0]))
|
|
|
+ else:
|
|
|
+ print('MAPE :', MAPE(Data_tst[0:now.hour],y_pred_dayAhead[0:now.hour]), 'MAE :', MAE(Data_tst[0:now.hour],y_pred_dayAhead[0:now.hour]))
|
|
|
+ else:
|
|
|
+ print('MAPE :', MAPE(Data_tst,y_pred_dayAhead),'MAE :', MAE(Data_tst,y_pred_dayAhead))
|
|
|
+ print('MBE :', MBE(Data_tst,y_pred_dayAhead), 'CVRMSE :', CVRMSE(Data_tst,y_pred_dayAhead))
|
|
|
+ print('-------------------------------------------------------------------------------')
|
|
|
+
|
|
|
+ # ## One-step-ahead load forecasting
|
|
|
+ y_pred_oneStep=[]
|
|
|
+ Data_tst_oneStep=[]
|
|
|
+ if isRecent:
|
|
|
+ dayHour = now.hour + 1
|
|
|
+ else:
|
|
|
+ dayHour = DataRes_24
|
|
|
+ for i in range(dayHour):
|
|
|
+ ####### Convert to matrix
|
|
|
+ ReconstructedData_tmp=ReconstructedData[i:]
|
|
|
+ if isRecent:
|
|
|
+ for ii in range(DataRes_24-i):
|
|
|
+ ReconstructedData_tmp.append(np.nan)
|
|
|
+ for ii in range(i):
|
|
|
+ ReconstructedData_tmp.append(np.nan)
|
|
|
+ ReconstructedData_Arr_oneStep=np.zeros((DataRes_24, DayPeriod))
|
|
|
+ for j in range(DayPeriod):
|
|
|
+ for k in range(DataRes_24):
|
|
|
+ ReconstructedData_Arr_oneStep[k,j]=ReconstructedData_tmp[j*DataRes_24+k]
|
|
|
+ Data_trn=ReconstructedData_Arr_oneStep[:,0:trn_period]
|
|
|
+ if isRecent:
|
|
|
+ Data_tst_oneStep.append(ReconstructedData_Arr_oneStep[i,trn_period])
|
|
|
+ else:
|
|
|
+ Data_tst_oneStep=ReconstructedData_Arr[:,trn_period]
|
|
|
+ y_pred_oneStep.append(lpc_pred_OneStepAhead(Data_trn, DayType_trn, cov_lth, DayType_tst, DataRes_24))
|
|
|
+
|
|
|
+ print('-------------------------OneStep-ahead prediction result-------------------------')
|
|
|
+ if isRecent:
|
|
|
+ if now.hour == 0:
|
|
|
+ print('MAPE :', MAPE(Data_tst[0],y_pred_oneStep[0]), 'MAE :', MAE(Data_tst[0],y_pred_oneStep[0]))
|
|
|
+ else:
|
|
|
+ print('MAPE :', MAPE(Data_tst[0:now.hour],y_pred_oneStep[0:now.hour]), 'MAE :', MAE(Data_tst[0:now.hour],y_pred_oneStep[0:now.hour]))
|
|
|
+ else:
|
|
|
+ print('MAPE :', MAPE(Data_tst_oneStep,y_pred_oneStep),'MAE :', MAE(Data_tst_oneStep,y_pred_oneStep))
|
|
|
+ print('-------------------------------------------------------------------------------')
|
|
|
+
|
|
|
+ plt.subplot(313)
|
|
|
+ plt.grid(b=True, which='both',axis='y')
|
|
|
+ if isRecent:
|
|
|
+ plt.plot(ReconstructedData_Arr[0:now.hour,trn_period], label='Observed data', linewidth=3)
|
|
|
+ else:
|
|
|
+ plt.plot(ReconstructedData_Arr[:,trn_period], label='Observed data', linewidth=3)
|
|
|
+ plt.plot(y_pred_dayAhead, '--', label='Day-ahead Prediction', linewidth=3)
|
|
|
+ plt.plot(y_pred_oneStep, '*-.', label='OneStep-ahead Prediction', MarkerSize=10, linewidth=3)
|
|
|
+ plt.xlabel('Time [hour]', fontsize = 14)
|
|
|
+ plt.ylabel('Power [kW]', fontsize = 14)
|
|
|
+ plt.legend(loc='upper right', fontsize = 14)
|
|
|
+ plt.xticks([6,12,18,24],['6','12','18','24'], fontsize = 14)
|
|
|
+ plt.yticks(fontsize = 14)
|
|
|
+ plt.ylim(min(ReconstructedData)*0.9,max(ReconstructedData)*1.1)
|
|
|
+ if isRecent:
|
|
|
+ plt.title("Electric load forecasting on "+str(now.year)+"."+str(now.month)+"."+str(now.day)+" (Updated every hour) - DGB 2nd branch", fontsize=14)
|
|
|
+ else:
|
|
|
+ plt.title("Electric load forecasting on "+str(lastday.year)+"."+str(lastday.month)+"."+str(lastday.day)+" (Updated every hour) - DGB 2nd branch", fontsize=14)
|
|
|
+ #plt.show()
|
|
|
+ print("=================== Prediction was successfully finished! ===================")
|
|
|
+ fig = plt.gcf()
|
|
|
+ if isRecent:
|
|
|
+ # Save the figure file of result
|
|
|
+ # fig.savefig("Result of electric load forecasting on "+str(now.year)+"."+str(now.month)+"."+str(now.day)+" "+str(now.hour)+"h"+str(now.minute)+"m - DGB 2nd branch.png", dpi=fig.dpi)
|
|
|
+
|
|
|
+ ### One-hour-ahead load forecasting updated every 1 minute
|
|
|
+ # MSSQL Access
|
|
|
+ conn = pymssql.connect(host = targetDBIP, user = targetDBUserID, password = targetDBUserPW, database = targetDBName)
|
|
|
+ # Create Cursor from Connection
|
|
|
+ cursor = conn.cursor()
|
|
|
+ cursor.execute("INSERT INTO " + targetDBName + ".dbo.BemsMonitoringPointForecastingHourAhead (SiteId,FacilityTypeId,FacilityCode,PropertyId,CreatedDateTime,TargetDateTime,ForecastedValue) VALUES(1,99,4863,1,'" + datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S') + "','"+ datetime.datetime(now.year,now.month,now.day,now.hour,0,0).strftime('%Y-%m-%d %H:00:00') + "',"+str(y_pred_oneStep[-1])+")")
|
|
|
+
|
|
|
+ ## Insert data temporary
|
|
|
+ if now.hour==0:
|
|
|
+ try:
|
|
|
+ cursor.execute("INSERT INTO " + targetDBName + ".dbo.BemsMonitoringPointHistoryHourly (SiteId,FacilityTypeId,FacilityCode,PropertyId,CreatedDateTime,CurrentValue) VALUES(1,99,4863,1,'" + (datetime.datetime(now.year,now.month,now.day,now.hour,0,0) - datetime.timedelta(hours=1)).strftime('%Y-%m-%d %H:00:00') + "',"+str(ReconstructedData_Arr[23,trn_period-1])+")")
|
|
|
+ conn.commit()
|
|
|
+ except:
|
|
|
+ print('Hour-ahead forecasted data already exists! (' + (datetime.datetime(now.year,now.month,now.day,now.hour,0,0) - datetime.timedelta(hours=1)).strftime('%Y-%m-%d %H:00:00') + ')')
|
|
|
+
|
|
|
+ else:
|
|
|
+ try:
|
|
|
+ cursor.execute("INSERT INTO " + targetDBName + ".dbo.BemsMonitoringPointHistoryHourly (SiteId,FacilityTypeId,FacilityCode,PropertyId,CreatedDateTime,CurrentValue) VALUES(1,99,4863,1,'" + (datetime.datetime(now.year,now.month,now.day,now.hour,0,0) - datetime.timedelta(hours=1)).strftime('%Y-%m-%d %H:00:00') + "',"+str(ReconstructedData_Arr[now.hour-1,trn_period])+")")
|
|
|
+ conn.commit()
|
|
|
+ except:
|
|
|
+ print('Hour-ahead forecasted data already exists! (' + (datetime.datetime(now.year,now.month,now.day,now.hour,0,0) - datetime.timedelta(hours=1)).strftime('%Y-%m-%d %H:00:00') + ')')
|
|
|
+
|
|
|
+ ### Day-ahead load forecasting updated every midnight
|
|
|
+ if now.hour == 0:
|
|
|
+ # Create Cursor from Connection
|
|
|
+ cursor = conn.cursor()
|
|
|
+ for i in range(len(y_pred_dayAhead)):
|
|
|
+ try:
|
|
|
+ cursor.execute("INSERT INTO " + targetDBName + ".dbo.BemsMonitoringPointForecastingDayAhead (SiteId,FacilityTypeId,FacilityCode,PropertyId,CreatedDateTime,TargetDateTime,ForecastedValue) VALUES(1,99,4863,1,'" + datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S') + "','" + (datetime.datetime(now.year,now.month,now.day,0,0,0) + datetime.timedelta(hours=i)).strftime('%Y-%m-%d %H:00:00') + "'," + str(y_pred_dayAhead[i]) + ")")
|
|
|
+ conn.commit()
|
|
|
+ except:
|
|
|
+ print('Day-ahead forecasted data already exists! ('+(datetime.datetime(now.year,now.month,now.day,0,0,0) + datetime.timedelta(hours=i)).strftime('%Y-%m-%d %H:00:00')+')')
|
|
|
+
|
|
|
+ conn.close()
|
|
|
+ print("The result was saved!")
|
|
|
+ else:
|
|
|
+ fig.savefig("Result of electric load forecasting on "+str(lastday.year)+"."+str(lastday.month)+"."+str(lastday.day)+ "- DGB 2nd branch.png", dpi=fig.dpi)
|
|
|
+ plt.show()
|
|
|
+
|
|
|
+ print("Sleeping for 60 seconds ...")
|
|
|
+
|
|
|
+ else:
|
|
|
+ print("No data ... Sleeping for 60 seconds ...")
|
|
|
+
|
|
|
+ time.sleep(60)
|