Network

This section describes two network models used in Soundcast:

• Network Assignment
• Network Skimming
• Bike Model

Network Assignment

A network assignment model estimates volume on each link in the transportation system for both highway and transit modes. In addition, the model generates performance measures such as congested speed or travel time on a highway link or the boardings and alightings on a transit route.

Network assignment is performed separately for each mode (auto and transit) and time period. The model system has four assignment periods, which are listed below:

Assignment Time Periods

Period	Description	Start Time	End Time	Label in Emme	Highway Duration (hour)	Transit Duration (hour)
AM	AM Peak	6:00 a.m.	9:00 a.m.	6to9	3	3
MD	Mid Day	9:00 a.m.	3:30 p.m.	9to1530	6.5	6.5
PM	PM Peak	3:30 p.m.	6:30 p.m.	1530to1830	3	3
NI	Night	6:30 p.m.	6:00 a.m.	1830to6	11.5	3.5

*The night period has only 3.5 hours of transit service (until 10:00 p.m.)

Highway Assignment

The highway assignment uses an equilibrium procedure to assign vehicle trips to the roadway network for different time periods. This is a user-optimal procedure that is based on the assumption that each traveler chooses a route that is the shortest time path. The highway assignment is performed in the Emme software and utilizes the gradient-based path analysis.

The multiclass assignment is performed for 21 vehicle classes, which are developed based on mode and income group:

Highway Vehicle Classes

Name	Description	Value-of-Time (unit?)
svtl1	SOV Toll Income Level 1	1200
svtl2	SOV Toll Income Level 2	2400
svtl3	SOV Toll Income Level 3	4000
svnt1	SOV No Toll Income Level 1	1200
svnt2	SOV No Toll Income Level 2	2400
svnt3	SOV No Toll Income Level 3	4000
h2tl1	HOV 2 Toll Income Level 1	2000
h2tl2	HOV 2 Toll Income Level 2	3000
h2tl3	HOV 2 Toll Income Level 3	5000
h2nt1	HOV 2 No Toll Income Level 1	2000
h2nt2	HOV 2 No Toll Income Level 2	3000
h2nt3	HOV 2 No Toll Income Level 3	5000
h3tl1	HOV 3 Toll Income Level 1	2400
h3tl2	HOV 3 Toll Income Level 2	3500
h3tl3	HOV 3 Toll Income Level 3	5500
h3nt1	HOV 3 No Toll Income Level 1	2400
h3nt2	HOV 3 No Toll Income Level 2	3500
h3nt3	HOV 3 No Toll Income Level 3	5500
lttrk	Light Trucks	4000
metrk	Medium Trucks	4500
hvtrk	Heavy Trucks	5000

The highway assignment procedure is applied iteratively; travel times are updated after each iteration to reflect congestion occurring on the network. These updates to travel time are based on a volume-delay function for each link. The majority of roads use a derivative of the volume-delay function originally developed by the Bureau of Public Roads (BPR). The free-flow time is based initially on the network data provided for each link and then updated in each iteration to represent the travel time from the last iteration. This process continues until “equilibrium" is reached, which is based on achieving one of the following criteria:

• The best relative gap is less than 0.01% (0.001). This is the difference between the current assignment and a perfect equilibrium assignment.
• The normalized gap or trip time difference is less than 0.001. This is the difference between the mean trip time of the current assignment and the mean minimal trip time.

All volume-delay functions use a time period factor (TPF) to convert daily volume-to-capacity ratios to time-period-specific ratios. The time period factors used for all modes are as follows:

Time Period Factors for Highway Assignment

AM	MD	PM	NI
0.350	0.184	0.350	0.354

Turn penalties are included in the trip assignment model to either prohibit certain turn movements or to penalize certain turn movements. These are included in the model by identifying specific turn movements by their node numbers, and then coding the penalty function that will apply to these turn movements. The current model includes turn penalty functions to prohibit turns that cannot be made under “real world” conditions and to prohibit direct access from interchanges to HOV lanes where direct access ramps do not exist. Examples of different types of turn penalty functions are listed in the following table:

Turn Penalty Functions

Penalty Function	Definition	Function	Range of Delay
tp 1	Fixed Delay	Turn Delay = Delay/100	0.1-1.5
tp 2	Prohibited Turns	Turn Delay = 0	0

Transit Assignment

The model system uses Emme to perform a frequency-based transit assignment using optimal strategies and variants. The assignment results are saved in Emme database. The following network results are available:

• Transit times on segments (timtr), in minutes; the transit time is the sum of the travel time (given by the transit time function) plus the dwell time at the J-node
• Transit boardings (board) and alightings (alight) at I-node of segments
• Transit volumes on segments (voltr)
• Initial boardings (inboaj) and final alightings (fialij) at nodes
• Auxiliary transit volumes on links (volax)

The transit mode contains five transit submodes:

Transit Submodes

Sub-mode	Description
b	Local Bus
p	Express Bus
r	Light Rail
c	Commuter Rail
f	Passenger Ferry

Network Skimming

Network skims are produced by time period in HDF5 format and are stored here. The files contain both highway and transit skims.

Highway

Four travel attributes are skimmed for every highway vehicle class: travel time (t), distance (d), cost (c), and generalized cost (g). The following table presents highway skims produced by the model. In the table, an x represents availability of the attribute for the vehicle class. For example, three skims are available for svtl1: travel time (svtl1t), travel distance (svtl1d), and travel cost (svtl1c).

Mode	Description	Time(t)	Distance(d)	Cost(c)	Generalized Cost(g)
svtl1	SOV Toll Income Level 1	x	x	x
svtl2	SOV Toll Income Level 2	x	x	x	x
svtl3	SOV Toll Income Level 3	x	x	x
svnt1	SOV No Toll Income Level 1	x	x	x
svnt2	SOV No Toll Income Level 2	x	x	x
svnt3	SOV No Toll Income Level 3	x	x	x
h2tl1	HOV 2 Toll Income Level 1	x	x	x
h2tl2	HOV 2 Toll Income Level 2	x	x	x
h2tl3	HOV 2 Toll Income Level 3	x	x	x
h2nt1	HOV 2 No Toll Income Level 1	x	x	x
h2nt2	HOV 2 No Toll Income Level 2	x	x	x
h2nt3	HOV 2 No Toll Income Level 3	x	x	x
h3tl1	HOV 3 Toll Income Level 1	x	x	x
h3tl2	HOV 3 Toll Income Level 2	x	x	x
h3tl3	HOV 3 Toll Income Level 3	x	x	x
h3nt1	HOV 3 No Toll Income Level 1	x	x	x
h3nt2	HOV 3 No Toll Income Level 2	x	x	x
h3nt3	HOV 3 No Toll Income Level 3	x	x	x
lttrk	Light Trucks	x	x	x	x
metrk	Medium Trucks	x	x	x	x
hvtrk	Heavy Trucks	x	x	x	x

Note:

• Travel time (t) and cost (c) skims are produced for all four time periods
• Distance (d) and generalized cost (g) skims are produced only for the AM and PM time periods

Transit

Transit skims are produced for all four time periods (except transit fare which is generated only for AM period). The following table presents a list of transit skims produced by the model:

Skim	Description
ivtwa[sub-mode]*	In-vehicle time by mode
xfrwa	Transfer wait time
ndbwa	Avg. boardings all mode
iwtwa	First wait time all modes
twtwa	Total wait time all modes
ivtwa	Actual IVTs all modes
mfafarbx	Transit fare (generated only for AM period)

*Transit sub-modes: local bus (b), express bus (p), commuter rail (c), light rail (r), and passenger ferry (f)

Other

The model also produces travel time skims for bike and walk modes. The skims are produced only for the AM period and are shown in the following table.

Skim	Description
biket	Bike travel time
walkt	Walk travel time
mfbkat	Actual auxiliary transit times
mfbkpt

Bike Model

BKRCast has a separate bike assignment model that uses generalized cost based on multiple attributes that affect likelihood of biking on a roadway. Three important attributes are used in the calculation of bike cost (bike weight):

1. Total vehicles on the roadway
2. Bike facility - premium (Trail/Separated bike lane), standard (bike lane striped, Bike shoulder, and Wider lane/shared shoulder), or none
3. Elevation gain (up slope) on the roadway

The weights (perception factor) for the above attributes are provided by a user in input_configuration.py. Based on the weights for the three attributes, a total weight for biking on a link is calculated. This total weight is then used to assign bike trips on the network. After the assignment , bike skims are also generated based on the total weight.