def work(modelDir, inputDict):
""" Run the model in its directory."""
outData = {}
rawData = []
actual = []
# write input file to modelDir sans carriage returns
with open(pJoin(modelDir, "demandTemp.csv"), "w") as demandTempFile:
demandTempFile.write(inputDict["demandTemp"].replace("\r", ""))
try:
with open(pJoin(modelDir, 'hist.csv'), 'w') as f:
f.write(inputDict['nn'].replace('\r', ''))
df = pd.read_csv(pJoin(modelDir, 'hist.csv'))
assert df.shape[0] >= 26280 # must be longer than 3 years
if 'dates' not in df.columns:
df['dates'] = df.apply(lambda x: dt(int(x['year']), int(x[
'month']), int(x['day']), int(x['hour'])),
axis=1)
except:
raise Exception("Neural Net CSV file is incorrect format.")
# neural net time
all_X = loadForecast.makeUsefulDf(df)
all_y = df["load"]
nn_pred, nn_accuracy = loadForecast.neural_net_predictions(all_X, all_y)
outData["actual_nn"] = df['load'][-8760:].tolist()
# read it in as a list of lists
try:
with open(pJoin(modelDir, "demandTemp.csv")) as inFile:
df = pd.read_csv(inFile, header=None)
df.columns = ["load", "tempc"]
df["dates"] = pd.date_range(start=inputDict["simStartDate"],
freq="H",
periods=df.shape[0])
print df.shape[0]
except ZeroDivisionError:
errorMessage = "CSV file is incorrect format. Please see valid format definition at <a target='_blank' href = 'https://github.com/dpinney/omf/wiki/Models-~-storagePeakShave#demand-file-csv-format'>\nOMF Wiki storagePeakShave - Demand File CSV Format</a>"
raise Exception(errorMessage)
rawData = df[["load", "tempc"]].fillna(0).values.tolist()
del df
"""
# None -> 0, float-> string
for i in range(len(rawData)):
rawData[i] = [a if a else 0 for a in rawData[i]]
rawData = list(np.float_(rawData))
"""
# populate actual list
for x in range(len(rawData)):
actual.append(float(rawData[x][0]))
(forecasted,
MAPE) = loadForecast.rollingDylanForecast(rawData,
float(inputDict["upBound"]),
float(inputDict["lowBound"]))
(exp, exp_MAPE) = loadForecast.exponentiallySmoothedForecast(
rawData, float(inputDict["alpha"]), float(inputDict["beta"]))
# parse json params for nextDayPeakKatrina
try:
params = json.loads(inputDict.get("katSpec", "{}"))
except ValueError:
params = {}
pred_demand = loadForecast.nextDayPeakKatrinaForecast(
rawData, inputDict["simStartDate"], modelDir, params)
pred_demand = np.transpose(np.array(pred_demand)).tolist()
# zucc it up
prophet_partitions = int(inputDict.get("prophet", 0))
if prophet_partitions > 1:
prophet, prophet_low, prophet_high = loadForecast.prophetForecast(
rawData, inputDict["simStartDate"], modelDir, inputDict["prophet"])
# write our outData
outData["startDate"] = inputDict["simStartDate"]
outData["actual"] = actual
outData["forecasted"] = forecasted
outData["doubleExp"] = exp
outData["neuralNet"] = nn_pred
outData["MAPE"] = "%0.2f%%" % (MAPE * 100)
outData["MAPE_exp"] = "%0.2f%%" % (exp_MAPE * 100)
outData["MAPE_nn"] = "%0.2f%%" % nn_accuracy["test"]
outData["peakDemand"] = pred_demand
if prophet_partitions > 1:
outData["prophet"] = prophet
outData["prophetLow"] = prophet_low
outData["prophetHigh"] = prophet_high
return outData
def forecastWork(modelDir, ind):
''' Run the model in its directory.'''
(cellCapacity, dischargeRate, chargeRate, cellQuantity, cellCost) = \
[float(ind[x]) for x in ('cellCapacity', 'dischargeRate', 'chargeRate', 'cellQuantity', 'cellCost')]
demandCharge = float(ind['demandCharge'])
retailCost = float(ind['retailCost'])
battEff = float(ind.get("batteryEfficiency")) / 100.0
dodFactor = float(ind.get('dodFactor')) / 100.0
projYears = int(ind.get('projYears'))
batteryCycleLife = int(ind.get('batteryCycleLife'))
battCapacity = cellQuantity * float(ind['cellCapacity']) * dodFactor
o = {}
try:
with open(pJoin(modelDir, 'hist.csv'), 'w') as f:
f.write(ind['histCurve'].replace('\r', ''))
df = pd.read_csv(pJoin(modelDir, 'hist.csv'), parse_dates=['dates'])
df['month'] = df['dates'].dt.month
df['dayOfYear'] = df['dates'].dt.dayofyear
assert df.shape[0] >= 26280 # must be longer than 3 years
assert df.shape[1] == 5
except:
raise Exception("CSV file is incorrect format.")
confidence = float(ind['confidence']) / 100
# ---------------------- MAKE PREDICTIONS ------------------------------- #
# train model on previous data
all_X = fc.makeUsefulDf(df)
all_y = df['load']
predictions = fc.neural_net_predictions(all_X, all_y)
dailyLoadPredictions = [
predictions[i:i + 24] for i in range(0, len(predictions), 24)
]
weather = df['tempc'][-8760:]
dailyWeatherPredictions = [
weather[i:i + 24] for i in range(0, len(weather), 24)
]
month = df['month'][-8760:]
dispatched = [False] * 365
# decide to implement VBAT every day for a year
VB_power, VB_energy = [], []
for i, (load24, temp24, m) in enumerate(
zip(dailyLoadPredictions, dailyWeatherPredictions, month)):
peak = max(load24)
if fc.shouldDispatchPS(peak, m, df, confidence):
dispatched[i] = True
vbp, vbe = fc.pulp24hrBattery(load24, dischargeRate * cellQuantity,
cellCapacity * cellQuantity, battEff)
VB_power.extend(vbp)
VB_energy.extend(vbe)
else:
VB_power.extend([0] * 24)
VB_energy.extend([0] * 24)
# -------------------- MODEL ACCURACY ANALYSIS -------------------------- #
o['predictedLoad'] = predictions
o['trainAccuracy'] = 0 #round(model.score(X_train, y_train) * 100, 2)
o['testAccuracy'] = 0 #round(model.score(X_test, y_test) * 100, 2)
# PRECISION AND RECALL
maxDays = []
for month in range(1, 13):
test = df[df['month'] == month]
maxDays.append(test.loc[test['load'].idxmax()]['dayOfYear'])
shouldHaveDispatched = [False] * 365
for day in maxDays:
shouldHaveDispatched[day] = True
truePositive = len([
b
for b in [i and j for (i, j) in zip(dispatched, shouldHaveDispatched)]
if b
])
falsePositive = len([
b for b in
[i and (not j) for (i, j) in zip(dispatched, shouldHaveDispatched)]
if b
])
falseNegative = len([
b for b in [(not i) and j
for (i, j) in zip(dispatched, shouldHaveDispatched)] if b
])
o['precision'] = round(
truePositive / float(truePositive + falsePositive) * 100, 2)
o['recall'] = round(
truePositive / float(truePositive + falseNegative) * 100, 2)
o['number_of_dispatches'] = len([i for i in dispatched if i])
o['MAE'] = round(
sum([
abs(l - m) / m * 100
for l, m in zip(predictions, list(all_y[-8760:]))
]) / 8760., 2)
# ---------------------- FINANCIAL ANALYSIS ----------------------------- #
# Calculate monthHours
year = df[-8760:].copy()
year.reset_index(inplace=True)
year['hour'] = list(year.index)
start = list(year.groupby('month').first()['hour'])
finish = list(year.groupby('month').last()['hour'])
monthHours = [(s, f + 1) for (s, f) in zip(start, finish)]
demand = list(all_y[-8760:])
peakDemand = [max(demand[s:f]) for s, f in monthHours]
demandAdj = [d + p for d, p in zip(demand, VB_power)]
peakDemandAdj = [max(demandAdj[s:f]) for s, f in monthHours]
discharges = [f if f < 0 else 0 for f in VB_power]
# Monthly Cost Comparison Table
o['monthlyDemand'] = peakDemand
o['monthlyDemandRed'] = peakDemandAdj
o['ps'] = [p - s for p, s in zip(peakDemand, peakDemandAdj)]
o['benefitMonthly'] = [x * demandCharge for x in o['ps']]
# Demand Before and After Storage Graph
o['demand'] = demand
o['demandAfterBattery'] = demandAdj
o['batteryDischargekW'] = VB_power
o['batteryDischargekWMax'] = max(VB_power)
batteryCycleLife = float(ind['batteryCycleLife'])
# Battery State of Charge Graph
# Turn dc's SoC into a percentage, with dodFactor considered.
o['batterySoc'] = SoC = [100 - (e / battCapacity * 100) for e in VB_energy]
# Estimate number of cyles the battery went through. Sums the percent of SoC.
cycleEquivalents = sum([
SoC[i] - SoC[i + 1]
for i, x in enumerate(SoC[:-1]) if SoC[i + 1] < SoC[i]
]) / 100.0
o['cycleEquivalents'] = cycleEquivalents
o['batteryLife'] = batteryCycleLife / cycleEquivalents
# Cash Flow Graph
# inserting battery efficiency only into the cashflow calculation
# cashFlowCurve is $ in from peak shaving minus the cost to recharge the battery every day of the year
cashFlowCurve = [sum(o['ps']) * demandCharge for year in range(projYears)]
cashFlowCurve.insert(0, -1 * cellCost *
cellQuantity) # insert initial investment
# simplePayback is also affected by the cost to recharge the battery every day of the year
o['SPP'] = (cellCost * cellQuantity) / (sum(o['ps']) * demandCharge)
o['netCashflow'] = cashFlowCurve
o['cumulativeCashflow'] = [
sum(cashFlowCurve[:i + 1]) for i, d in enumerate(cashFlowCurve)
]
o['NPV'] = npv(float(ind['discountRate']), cashFlowCurve)
battCostPerCycle = cellQuantity * cellCost / batteryCycleLife
lcoeTotCost = cycleEquivalents * retailCost + battCostPerCycle * cycleEquivalents
o['LCOE'] = lcoeTotCost / (cycleEquivalents * battCapacity)
# Other
o['startDate'] = '2011-01-01' # dc[0]['datetime'].isoformat()
o['stderr'] = ''
# Seemingly unimportant. Ask permission to delete.
o['stdout'] = 'Success'
o['months'] = [
"Jan", "Feb", "Mar", "Apr", "May", "Jun", "Jul", "Aug", "Sep", "Oct",
"Nov", "Dec"
]
return o
def forecastWork(modelDir, ind):
import tensorflow as tf
''' Run the model in its directory.'''
(cellCapacity, dischargeRate, chargeRate, cellQuantity, cellCost) = \
[float(ind[x]) for x in ('cellCapacity', 'dischargeRate', 'chargeRate', 'cellQuantity', 'cellCost')]
demandCharge = float(ind['demandCharge'])
retailCost = float(ind['retailCost'])
battEff = float(ind.get("batteryEfficiency")) / 100.0
dodFactor = float(ind.get('dodFactor')) / 100.0
projYears = int(ind.get('projYears'))
batteryCycleLife = int(ind.get('batteryCycleLife'))
battCapacity = cellQuantity * float(ind['cellCapacity']) * dodFactor
o = {}
try:
with open(pJoin(modelDir, 'hist.csv'), 'w') as f:
f.write(ind['histCurve'].replace('\r', ''))
df = pd.read_csv(pJoin(modelDir, 'hist.csv'))
assert df.shape[0] >= 26280 # must be longer than 3 years
if df.shape[1] == 6:
df['dates'] = df.apply(lambda x: dt(int(x['year']), int(x[
'month']), int(x['day']), int(x['hour'])),
axis=1)
else:
df = pd.read_csv(pJoin(modelDir, 'hist.csv'),
parse_dates=['dates'])
df['month'] = df.dates.dt.month
df['dayOfYear'] = df['dates'].dt.dayofyear
except:
raise Exception("CSV file is incorrect format.")
# ---------------------- MAKE PREDICTIONS ------------------------------- #
# train model on previous data
all_X = fc.makeUsefulDf(df)
all_y = df['load']
if ind['newModel'] == 'True':
model = None
else:
with open(pJoin(modelDir, 'neural_net.h5'), 'wb') as f:
f.write(ind['model'].decode('base64'))
model = tf.keras.models.load_model(pJoin(modelDir, 'neural_net.h5'))
# model = tf.keras.models.load_model(ind['model'])
predictions, accuracy = fc.neural_net_predictions(
all_X,
all_y,
epochs=int(ind['epochs']),
model=model,
save_file=pJoin(modelDir, 'neural_net_model.h5'))
dailyLoadPredictions = [
predictions[i:i + 24] for i in range(0, len(predictions), 24)
]
weather = df['tempc'][-8760:]
dailyWeatherPredictions = [
weather[i:i + 24] for i in range(0, len(weather), 24)
]
# decide to implement VBAT every day for a year
VB_power, VB_energy = [], []
for i, (load24, temp24) in enumerate(
zip(dailyLoadPredictions, dailyWeatherPredictions)):
vbp, vbe = pulp24hrBattery(load24, dischargeRate * cellQuantity,
cellCapacity * cellQuantity, battEff)
VB_power.extend(vbp)
VB_energy.extend(vbe)
# -------------------- MODEL ACCURACY ANALYSIS -------------------------- #
o['predictedLoad'] = predictions
o['trainAccuracy'] = 100 - round(accuracy['train'], 1)
o['testAccuracy'] = 100 - round(accuracy['test'], 1)
# ---------------------- FINANCIAL ANALYSIS ----------------------------- #
# Calculate monthHours
year = df[-8760:].copy()
year.reset_index(inplace=True)
year['hour'] = list(year.index)
start = list(year.groupby('month').first()['hour'])
finish = list(year.groupby('month').last()['hour'])
monthHours = [(s, f + 1) for (s, f) in zip(start, finish)]
demand = list(df['load'][-8760:])
peakDemand = [max(demand[s:f]) for s, f in monthHours]
demandAdj = [d + p for d, p in zip(demand, VB_power)]
peakDemandAdj = [max(demandAdj[s:f]) for s, f in monthHours]
# Monthly Cost Comparison Table
o['monthlyDemand'] = peakDemand
o['monthlyDemandRed'] = peakDemandAdj
o['ps'] = [p - s for p, s in zip(peakDemand, peakDemandAdj)]
o['benefitMonthly'] = [x * demandCharge for x in o['ps']]
# Demand Before and After Storage Graph
o['demand'] = demand
o['demandAfterBattery'] = demandAdj
o['batteryDischargekW'] = VB_power
o['batteryDischargekWMax'] = max(VB_power)
batteryCycleLife = float(ind['batteryCycleLife'])
o['batterySoc'] = SoC = [100 - (e / battCapacity * 100) for e in VB_energy]
cycleEquivalents = sum([
SoC[i] - SoC[i + 1]
for i, x in enumerate(SoC[:-1]) if SoC[i + 1] < SoC[i]
]) / 100.0
o['cycleEquivalents'] = cycleEquivalents
o['batteryLife'] = batteryCycleLife / (cycleEquivalents + 10)
# Cash Flow Graph
cashFlowCurve = [sum(o['ps']) * demandCharge for year in range(projYears)]
cashFlowCurve.insert(0, -1 * cellCost *
cellQuantity) # insert initial investment
o['SPP'] = (cellCost * cellQuantity) / (sum(o['ps']) * demandCharge)
o['netCashflow'] = cashFlowCurve
o['cumulativeCashflow'] = [
sum(cashFlowCurve[:i + 1]) for i, d in enumerate(cashFlowCurve)
]
o['NPV'] = npv(float(ind['discountRate']), cashFlowCurve)
battCostPerCycle = cellQuantity * cellCost / batteryCycleLife
lcoeTotCost = cycleEquivalents * retailCost + battCostPerCycle * cycleEquivalents
o['LCOE'] = lcoeTotCost / (cycleEquivalents * battCapacity + 10)
model
# Other
o['startDate'] = '2011-01-01'
o['stderr'] = ''
o['stdout'] = 'Success'
return o