readtools.py 13 KB
Newer Older
1
2
import numpy as np
import pandas as pd
3
import re
4
from .timeseries import *
5

6

7
def read_timeseries_Modelica(filename, timeseries_names=None, is_regex=False):
8
    from modelicares import SimRes
9
    sim = SimRes(filename)
10
11
12
13
14
    if timeseries_names is None and is_regex is False:
        # No trajectory names or regex specified, thus read in all
        timeseries = []
        for name in sim.names():
            timeseries.append(TimeSeries(name, sim(name).times(), sim(name).values()))
Jan Dinkelbach's avatar
Jan Dinkelbach committed
15
        timeseries_names = sim.names()
16
17
18
19
20
21
22
23
    elif is_regex is True:
        # Read in variables which match with regex
        timeseries = []
        p = re.compile(timeseries_names)
        timeseries_names = [name for name in sim.names() if p.search(name)]
        timeseries_names.sort()
        for name in timeseries_names:
            timeseries.append(TimeSeries(name, sim(name).times(), sim(name).values()))
24
25
    else:
        # Read in specified time series
26
27
28
        if not isinstance(timeseries_names, list):
            timeseries = TimeSeries(timeseries_names, sim(timeseries_names).times(), sim(timeseries_names).values())
        else:
Markus Mirz's avatar
Markus Mirz committed
29
            timeseries = []
30
31
            for name in timeseries_names:
                timeseries.append(TimeSeries(name, sim(name).times(), sim(name).values()))
32
33

    print('Modelica results column names: ' + str(timeseries_names))
34
    print('Modelica results number: ' + str(len(timeseries_names)))
35

36
    return timeseries
37

38

39
def read_timeseries_csv(filename, timeseries_names=None, print_status=True):
40
41
42
43
44
45
46
    """Reads complex time series data from DPsim log file. Real and
    imaginary part are stored in one complex variable.
    :param filename: name of the csv file that has the data
    :param timeseries_names: column name which should be read
    :return: list of Timeseries objects
    """
    pd_df = pd.read_csv(filename)
Markus Mirz's avatar
Markus Mirz committed
47
    timeseries_list = {}
48
49
50
51
52
53
54
55
56
57
58
59
60
    cmpl_result_columns = []
    real_result_columns = []

    if timeseries_names is None:
        # No column names specified, thus read in all and strip off spaces
        pd_df.rename(columns=lambda x: x.strip(), inplace=True)
        column_names = list(pd_df.columns.values)

        # Remove timestamps column name and store separately
        column_names.remove('time')
        timestamps = pd_df.iloc[:, 0]

        # Find real and complex variable names
61
        suffixes = [ ('_re', '_im'), ('.real', '.imag') ]
62
        for column in column_names:
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
            is_complex = False
            for suffix in suffixes:
                real_suffix = suffix[0]
                imag_suffix = suffix[1]

                if column.endswith(imag_suffix):
                    is_complex = True
                    break # Ignore imag columns

                if column.endswith(real_suffix):
                    is_complex = True
                    column_base = column.replace(real_suffix, '')

                    if column_base + imag_suffix not in column_names:
                        continue

                    cmpl_result_columns.append(column_base)
                    timeseries_list[column_base] = TimeSeries(column_base, timestamps,
                        np.vectorize(complex)(
                            pd_df[column_base + real_suffix],
                            pd_df[column_base + imag_suffix]
                        )
                    )
                    break

            if is_complex:
                continue

            real_result_columns.append(column)
Markus Mirz's avatar
Markus Mirz committed
92
            timeseries_list[column] = TimeSeries(column, timestamps, pd_df[column])
93

94
95
96
97
    else:
        # Read in specified time series
        print('cannot read specified columns yet')

Jan Dinkelbach's avatar
Jan Dinkelbach committed
98
    if print_status :
99
100
101
102
        print('column number: ' + str(len(timeseries_list)))
        print('results length: ' + str(len(timestamps)))
        print('real column names: ' + str(real_result_columns))
        print('complex column names: ' + str(cmpl_result_columns))          
103
104

    return timeseries_list
Jan Dinkelbach's avatar
Jan Dinkelbach committed
105

106
107
108
109
110
111
def read_timeseries_dpsim(filename, timeseries_names=None, print_status=True):
    return read_timeseries_csv(filename, timeseries_names, print_status)

def read_timeseries_simulink(filename, timeseries_names=None, print_status=True):
    return read_timeseries_csv(filename, timeseries_names, print_status)

Jan Dinkelbach's avatar
Jan Dinkelbach committed
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
def read_dpsim_log(log_path):
    log_file = open(log_path, "r")
    log_lines = [line for line in log_file]
    log_file.close()

    # Sectionize
    log_sections = {'init':[], 'none':[], 'sysmat_stamp':[], 'sysmat_final':[], 'sourcevec_stamp':[], 'sourcevec_final':[], 'ludecomp':[]}
    section = 'init'
    for line_pos in range(len(log_lines)):
        if re.search('DEBUG: Stamping .+ into system matrix:', log_lines[line_pos]):
            section = 'sysmat_stamp'
        elif re.search('INFO: System matrix:', log_lines[line_pos]):
            section = 'sysmat_final'
        elif re.search('DEBUG: Stamping .+ into source vector:', log_lines[line_pos]):
            section = 'sourcevec_stamp'
        elif re.search('INFO: Right side vector:', log_lines[line_pos]):
            section = 'sourcevec_final'
        elif re.search('INFO: LU decomposition:', log_lines[line_pos]):
            section = 'ludecomp'
131
        elif re.search('INFO: Number of network simulation nodes:', log_lines[line_pos]):
Jan Dinkelbach's avatar
Jan Dinkelbach committed
132
133
134
135
136
137
138
            section = 'none'
        elif re.search('INFO: Added .+ to simulation.', log_lines[line_pos]):
            section = 'none'
        elif re.search('INFO: Initial switch status:', log_lines[line_pos]):
            section = 'none'
        log_sections[section].append(line_pos)

139
    return log_lines, log_sections
Jan Dinkelbach's avatar
Jan Dinkelbach committed
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317

def read_timeseries_PLECS(filename, timeseries_names=None):
    pd_df = pd.read_csv(filename)
    timeseries_list = []
    if timeseries_names is None:
        # No trajectory names specified, thus read in all
        timeseries_names = list(pd_df.columns.values)
        timeseries_names.remove('Time')
        for name in timeseries_names:
            timeseries_list.append(TimeSeries(name, pd_df['Time'].values, pd_df[name].values))
    else:
        # Read in specified time series
        for name in timeseries_names:
            timeseries_list.append(TimeSeries(name, pd_df['Time'].values, pd_df[name].values))

    print('PLECS results column names: ' + str(timeseries_names))
    print('PLECS results number: ' + str(len(timeseries_list)))

    return timeseries_list

def read_timeseries_NEPLAN_loadflow(file_name, timeseries_names=None, is_regex=False):
    """
    Read in NEPLAN loadflow result from result file, the result is in angle notation, amplitude and angle are stored
    separately
    To keep consistent with the names of voltage in most cases, the name of voltage variables are changed into '.V*'
    instead of '.U*' as in the result file

    :param file_name: name of the mat file for the loadflow result from neplan
    :param timeseries_names: column name to be read
    :param is_regex: flag for using regular expression
    :return: list of Timeseries objects
    """
    str_tmp = open(file_name, "r")  # Read in files
    low = 0  # flag for the start of a new data in str_cmp
    high = 0  # flag for the end of this new data in str_cmp
    flag = True  # To judge if this is the first line of the file, which will be the names for the data type

    # Read in data from result file of neplan
    seq = []  # list for data type names
    value = []  # list for data


    namelist = ['U', 'ANGLEU', 'P', 'Q', 'I', 'ANGLEI']  # Suffix of the data name
    timeseries = []
    line_del = []  # a list for the value to be deleted
    isfloat = re.compile(r'^[-+]?[0-9]+\.[0-9]+$')  # regular expression to find float values

    # Transfer ',' in the floats in result file to '.'
    for line in str_tmp.readlines():  # Check the data to find out floats with ','
        line = line.replace(",", ".")
        high -= high
        low -= low
        del value[:]
        # read in different data and start processing
        for letter in line:
            if letter == "	" or letter == "\n":  # different data(separated by '	') or end(/n)
                if low is not high:  # if low is equal to high, no data read in
                    if flag:  # first line of the file, list for data-type name
                        seq.append(line[low:high])
                    else:  # not first line of the file,list for data
                        if isfloat.match(line[low:high]):
                            value.append(float(line[low:high]))
                        else:
                            value.append(line[low:high])
                else:  # no data for this datatype
                    value.append(r'#')  # No value, set as #
                low = high + 1  # refresh low flag
            high += 1

        """
        A typical line current in neplan has two parts from both end, but we doesn't have to calculate them 
        with the assumption that the topology of the gird should be correct with which we can validate the 
        current by comparing the voltage of the nodes connected to the ends of the line 
        """
        if flag is not True:  # flag is true when it's the first line
            if value[3] is not '#':
                for m in range(6):
                    timeseries.append(TimeSeries(value[3] + '.' + namelist[m],
                                                 np.array([0., 1.]), np.array([value[m + 6], value[m + 6]])))
            else:
                for m in range(2):
                    timeseries.append(TimeSeries(value[1] + '.' + namelist[m],
                                                 np.array([0., 1.]), np.array([value[m + 6], value[m + 6]])))
        flag = False
    str_tmp.close()

    # Read in variables which match with regex
    if is_regex is True:
        p = re.compile(timeseries_names)
        length = len(timeseries)
        for rule_check in range(length):
            if p.search(timeseries[rule_check].name):
                pass
            else:
                line_del.append(rule_check)

    # Read in specified time series
    elif timeseries_names is not None:
        length = len(timeseries)
        for rule_check in range(length):
            if timeseries_names == timeseries[rule_check].name:
                pass
            else:
                line_del.append(rule_check)

    # delete those values that are not needed.
    line_del = set(line_del)
    line_del = sorted(line_del)
    for num_to_del in range(len(line_del)):
        del timeseries[line_del[len(line_del) - num_to_del - 1]]

    return timeseries


def read_timeseries_simulink_loadflow(file_name, timeseries_names=None, is_regex=False):
    """
    Read in simulink load-flow result from result file(.rep), the result is in angle notation, amplitude and angle are stored
    separately.
    A suffix is used to tag different data for a component:
        .Arms/.IDegree for current/current angle,
        .Vrms/.VDegree for voltage/voltage angle.

    :param file_name:path of the .rep file for the loadflow result from simulink
    :param timeseries_names: specific values to be read
    :param is_regex: flag for using regular expression
    :return: list of Timeseries objects
    """
    str_tmp = open(file_name, 'r', encoding='latin-1')  # Read in files, using latin-1 to decode /xb0

    # Read in data from result file of neplan
    name = []  # list for data type names
    value = []  # list for data
    timeseries = []
    line_del = []  # a list for the value to be deleted

    for line in str_tmp.readlines():
        line = line.replace("°", "")
        del value[:]
        del name[:]
        # read in different data and start processing
        if len(line) > 37:
            if line[31:35] == '--->':
                if line[13:17] == 'Arms':
                    name = [line[37:len(line)].rstrip() + '.Arms', line[37:len(line)].rstrip() + '.IDegree']
                elif line[13:17] == 'Vrms':
                    name = [line[37:len(line)].rstrip() + '.Vrms', line[37:len(line)].rstrip() + '.VDegree']
                value = [float(line[0:13]), float(line[18:31])]
                timeseries.append(TimeSeries(name[0],
                                             np.array([0., 1.]), np.array([value[0], value[0]])))
                timeseries.append(TimeSeries(name[1],
                                             np.array([0., 1.]), np.array([value[1], value[1]])))

    # Read in variables which match with regex
    if is_regex is True:
        p = re.compile(timeseries_names)
        length = len(timeseries)
        for rule_check in range(length):
            if p.search(timeseries[rule_check].name):
                pass
            else:
                line_del.append(rule_check)

    # Read in specified time series
    elif timeseries_names is not None:
        length = len(timeseries)
        for rule_check in range(length):
            if timeseries_names == timeseries[rule_check].name:
                pass
            else:
                line_del.append(rule_check)

    # delete those values that are not needed.
    line_del = set(line_del)
    line_del = sorted(line_del)
    for num_to_del in range(len(line_del)):
        del timeseries[line_del[len(line_del) - num_to_del - 1]]
    return timeseries