WO2021073714A2

WO2021073714A2 - Network node and method for network telemtry

Info

Publication number: WO2021073714A2
Application number: PCT/EP2019/077802
Authority: WO
Inventors: Ben-Shahar BELKAR; Tal Mizrahi
Original assignee: Huawei Technologies Co., Ltd.
Priority date: 2019-10-14
Filing date: 2019-10-14
Publication date: 2021-04-22
Also published as: CN114586320A

Description

NETWORK NODE AND METHOD FOR NETWORK TELEMTRY

TECHNICAL FIELD

The present disclosure relates generally to network telemetry. In particular the disclosure proposes a network node for network telemetry and a corresponding method. The network node is configured to add own telemetry data including performance related data to a data packet and send it to another network node, and may be further configured to expose the telemetry data to a management device.

BACKGROUND Performance measurement and network telemetry are critical capabilities in communication networks. Moreover, performance measurement and telemetry are key capabilities for autonomous networks, which has been a quickly evolving technology over the last few years.

Performance measurement data is typically collected by a central management server, which analyzes the data and takes intelligent decisions (potentially based on artificial intelligence) that affect the network. These decisions include, for example, determining network paths, network resource allocation, and determining network security policies.

One of the challenges in this context is that performance data, which is obtained by the central management server, is often without any context. The management server may receive a performance related measurement result, such as a delay measurement, without knowing how to evaluate the result, e.g., without knowing whether the result is high or low, as it does not have any point of reference.

SUMMARY In view of the above-mentioned disadvantage, embodiments of the invention aim to improve the current implementations of network telemetry. An objective is to allow a management device, e.g. management server, to obtain a point of reference, which allows the management server to evaluate performance data, e.g., to determine whether a performance related measurement is high or low. To this end, the invention intends to provide a network node and a corresponding method for network telemetry.

The objective is achieved by the embodiments of the invention as described in the enclosed independent claims. Advantageous implementations of the embodiments of the invention are further defined in the dependent claims.

In particular, embodiments of the invention propose a network node or a method, which enable exposing network telemetry data, like delay statistics, from a network node to a management server. The telemetry data may be reported in-band, along with data packets, and may include performance data, like an average, minimum and/or maximum delay that have been observed by the network node for a given flow (of data packets) through the network.

A first aspect of the invention provides a network node for network telemetry, the network node configured to: obtain a data packet, add telemetry data of the network node to the data packet or to a special packet, wherein the telemetry data comprises performance data indicating a processing performance of the data packet in the network node, and forward the data packet including the telemetry data to another network node or forward the special packet including the telemetry data to a management device.

That is, if the telemetry data is added to the data packet, this data packet is forwarded to the other network node (e.g., a next hop of the network node). If the telemetry data is added to the special packet, this special packet is forwarded to the management device (e.g., a device for measuring the performance of the network node(s)). In the latter case, the data packet without telemetry data can be forwarded to the other network node. The special packet may be generated by the network node or may be received from the network node, for instance, from another network node or from the management device.

By adding the telemetry data to the data packet or to the special packet, the network node supports another entity, e.g., a management server, to better analyze the telemetry data, particularly the performance data, and take better decisions based on the data. The management server can, for instance, derive a point of reference, e.g. by comparing telemetry data of different network nodes, which allows the management server to better evaluate the telemetry data. For example, the management server can assess whether information included in the telemetry data, like performance data or delay data, is high or low.

In an implementation form of the first aspect, the network node is further configured to: add a telemetry header field to a header of the data packet, and add the telemetry data into the telemetry header field.

In this implementation, the network node may function as a “source node” (of the data packet), which is configured to generate the data packet and prepare the data packet for network telemetry. The network node may also function as a “first node” (for the data packet that is provided by a source node to the network), which is configured to receive the data packet from the source node and prepare the data packet for network telemetry.

In an implementation form of the first aspect, the network node is further configured to: encapsulate the telemetry header field and the telemetry data into a tunnel header, or add the telemetry header field and the telemetry data to an extension field of the header of the data packet.

In an implementation form of the first aspect, the obtained data packet comprises a telemetry header field that includes other telemetry data of one or more other network nodes, and the network node is further configured to: add the telemetry data of the network node to the other telemetry data in the telemetry header field.

That is, the network node may function as a “transit node” (for the data packet belonging to a data packet flow through the network, i.e., is forwarded by multiple network nodes of the network). In this case, another network node (e.g. a network node configured as “first node” or “transit node”) has already created the telemetry header and has already included other telemetry data into the packet header.

In an implementation form of the first aspect, the network node is further configured to: analyze the other telemetry data in the telemetry header field of the data packet, and perform an operation on the data packet based on the analysis of the other telemetry data. That is, the network node may function as an “analyzer node”, which could provide similar functions as the management server.

In an implementation form of the first aspect, the network node is further configured to: expose the other telemetry data to the management device (e.g. management server).

In an implementation form of the first aspect, the network node is further configured to: remove the telemetry header field and the other telemetry data from the header of the data packet.

That is, the network node may function as a “last node”, which is the final node via which the data packet travels in the network.

Notably, the network node according to the first aspect may function as a “source node”, or as a “first node”, or as a “transit node”, or as an “analyzer node”, or as a “last node”. This may depend on its configuration and on the particular data packet flow, to which the packet belongs. In particular, different data packet flows in the network may take different paths/routes. Thus, they may have different “source nodes”, “transit nodes”, or “last nodes”. That means, for one data packet flow the network node may functions as “first node”, for another data packet flow the network node may function as “transit node”, and for yet another data packet flow the network node may function as “last node”.

In an implementation form of the first aspect, the network node is further configured to: expose the telemetry data of the network node to the management device by forwarding one or more special packets to the management device.

The management device may be a management server. The exposed telemetry data includes the performance data and may include delay information, a delay report or other supportive information as described in this disclosure. The exposure of the telemetry data is possible for each node, i.e. regardless of whether the network node is a “first node”, a “transit node”, a “last node”, or an “analyzer node”. Each network node along the path of a packet flow through the network may exposed its telemetry data to the management device, i.e. send a special packet to the management device. In an implementation form of the first aspect, the network node is further configured to expose the other telemetry data and/or the telemetry data of the network node: at predetermined time intervals; and/or upon request of the management device.

The predetermined time interval may be in the order of hours, minutes, seconds, milliseconds, microseconds, or nanoseconds.

In an implementation form of the first aspect, the network node is further configured to reset the telemetry data of the network node: each time the telemetry data is exposed to the management device; and/or upon a reset request of the management device; and/or when the network node is initialized, reset, shut down, or power cycled.

In particular, the performance data and/or delay information and/or delay report, e.g. timers measuring/averaging delay, may be reset.

In an implementation form of the first aspect, the network node is further configured to: add, into the telemetry header field, an indication regarding a type of the telemetry data added into the telemetry header field.

Such an indication may also be added to the special packet forwarded to the management device.

In an implementation form of the first aspect, the performance data includes at least one of: a queue status of a queue, into which the data packet is enqueued in the network node; a duration of processing the data packet in the network node.

In an implementation form of the first aspect, the network node is further configured to: add delay information regarding a delay of the data packet in the network node to the data packet or to the special packet.

In an implementation form of the first aspect, the network node is further configured to add one or more of the following to the data packet or to the special packet: information regarding an average delay of one or more data packets or one or more probe packets in the network node; information regarding a minimum and/or maximum delay of one or more data packets or one or more probe packets in the network node; one or more counter values, wherein each counter value indicates a number of data packets, particularly of one or more data packets belonging to the same data packet flow, marked as congested in the network node.

In an implementation form of the first aspect, the information regarding the average delay, and/or the minimum delay, and/or the maximum delay, is based on one or more measurements of the one or more data packets or the one or more probe packets, which were performed since the network node was initialized or since the delay information was reset.

In an implementation form of the first aspect, the network node is configured to: add one or more of the following to the data packet or to the special packet: one or more Quality of Service, QoS, attributes related to a data packet flow, to which the data packet belongs; a queue ID of a queue, into which the data packet was enqueued in the network node; an entry switch port and/or an exit switch port for the data packet in the network.

A second aspect of the invention provides a method for a network node, the method comprising: obtaining a data packet, adding telemetry data of the network node to the data packet or to the special packet, wherein the telemetry data comprises performance data indicating a processing performance of the data packet in the network node, and forwarding the data packet including the telemetry data to another network node or forwarding the special packet including the telemetry data to a management device.

In an implementation form of the second aspect, the method further comprises: generating the data packet or receiving the data packet, adding a telemetry header field to a header of the data packet, adding the telemetry data into the telemetry header field, and forwarding the data packet including the telemetry data to the other network node.

In an implementation form of the second aspect, the method further comprises: encapsulating the telemetry header field and the telemetry data into a tunnel header, or adding the telemetry header field and the telemetry data to an extension field of the header of the data packet.

In an implementation form of the second aspect, the obtained data packet comprises a telemetry header field that includes other telemetry data of one or more other network nodes, and the network node is further configured to: adding the telemetry data of the network node to the other telemetry data in the telemetry header field, and forwarding the data packet including the telemetry data to the other network node.

In an implementation form of the second aspect, the method further comprises: analyzing the other telemetry data in the telemetry header field of the data packet, and performing an operation on the data packet based on the analysis of the other telemetry data.

In an implementation form of the second aspect, the method further comprises: exposing the other telemetry data to a management device.

In an implementation form of the second aspect, the method further comprises: removing the telemetry header field and the other telemetry data from the header of the data packet.

In an implementation form of the second aspect, the method further comprises: exposing the telemetry data of the network node to the management device by forwarding one or more special packets to the management device.

In an implementation form of the second aspect, the method further comprises exposing the other telemetry data and/or the telemetry data of the network node: at predetermined time intervals; and/or upon request of the management device.

In an implementation form of the second aspect, the method further comprises resetting the telemetry data of the network node: each time the telemetry data is exposed to the management device; and/or upon a reset request of the management device; and/or when the network node is initialized, reset, shut down, or power cycled.

In an implementation form of the second aspect, the method further comprises: adding, into the telemetry header field, an indication regarding a type of the telemetry data added into the telemetry header field.

In an implementation form of the second aspect, the performance data includes at least one of: a queue status of a queue, into which the data packet is enqueued in the network node; a duration of processing the data packet in the network node. In an implementation form of the second aspect, the method further comprises: adding delay information regarding a delay of the data packet in the network node to the data packet or to the special packet.

In an implementation form of the second aspect, the method further comprises adding one or more of the following to the data packet or to the special packet: information regarding an average delay of one or more data packets or one or more probe packets in the network node; information regarding a minimum and/or maximum delay of a one or more data packets or one or more probe packets in the network node; one or more counter values, wherein each counter value indicates a number of data packets, particularly of data packets belonging to the same data packet flow, marked as congested in the network node.

In an implementation form of the second aspect, the information regarding the average delay, and/or the minimum delay, and/or the maximum delay, is based on one or more measurements of the one or more data packets or the plurality of probe packets, which were performed since the network node was initialized or since the delay information was reset.

In an implementation form of the second aspect, the method comprises: adding one or more of the following to the data packet or to the special packet: one or more Quality of Service, QoS, attributes related to a data packet flow, to which the data packet belongs; a queue ID of a queue, into which the data packet was enqueued in the network node.

The method of the second aspect and its implementation forms provide the same advantages and effects as the network node of the first aspect and its respective implementation forms.

A third aspect of the invention provides a computer program which, when executed by a processor, in particular a processor of a network node, causes the method of the second aspect or any of its implementation forms to be performed. Further, the invention also relates to a computer program product comprising a computer program product comprising a computer readable medium and said mentioned computer program, wherein said computer program is included in the computer readable medium, and comprises of one or more from the group: ROM (Read-Only Memory), PROM (Programmable ROM), EPROM (Erasable PROM), Flash memory, EEPROM (Electrically EPROM) and hard disk drive.

A fourth aspect of the invention provides a non-transitory computer readable storage medium comprising computer program code instructions, being executable by a computer, for performing a method according to any one of the embodiments of the second aspect of the invention when the computer program code instructions runs on a computer. The computer readable storage medium, comprises of one or more from the group: ROM, PROM, EPROM, Flash memory, EEPROM and hard disk drive.

A fifth aspect of the invention suggests a network node for network telemetry includes a processor and a memory. The memory is storing instructions that cause the processor to perform the method according to the second aspect of the invention.

Further applications and advantages of the embodiments of the invention will be apparent from the following detailed description.

It has to be noted that all devices, elements, units and means described in the present application could be implemented in the software or hardware elements or any kind of combination thereof. All steps which are performed by the various entities described in the present application as well as the functionalities described to be performed by the various entities are intended to mean that the respective entity is adapted to or configured to perform the respective steps and functionalities.

Even if, in the following description of specific embodiments, a specific functionality or step to be performed by external entities is not reflected in the description of a specific detailed element of that entity which performs that specific step or functionality, it should be clear for a skilled person that these methods and functionalities can be implemented in respective software or hardware elements, or any kind of combination thereof. BRIEF DESCRIPTION OF THE DRAWINGS

The above described aspects and implementation forms of the present invention will be explained in the following description of specific embodiments in relation to the enclosed drawings, in which FIG. 1 shows a network node according to an embodiment of the invention.

FIG. 2 shows an exemplary system including network nodes according to embodiments of the invention.

FIG. 3 shows an exemplary data packet provided by a network node according to an embodiment of the invention. FIG. 4 shows a method according to an embodiment of the invention.

DETAILED DESCRIPTION OF THE EMBODIMENTS

Performance measurement data is typically collected by a central management server, which analyzes the data and takes intelligent decisions (potentially based on artificial intelligence) that affect the network. These decisions include, for example, determining network paths, network resource allocation, and determining network security policies. Two examples of network performance measurement approaches are In-band Network Telemetry (INT), as described e.g. in “C. Kim et al, ‘In-band network telemetry (INT)’, P4 consortium, 2018”, and In situ Operations, Administration and Maintenance (IOAM), as described in “F. Brockners et al, ‘Data Fields for In-situ OAM’, draft-ietf-ippm-ioam- data-05 (work in progress), 2019.

Illustrative embodiments of method, apparatus, and program product for network telemetry are described with reference to the figures. Although this description provides a detailed example of possible implementations, it should be noted that the details are intended to be exemplary and in no way limit the scope of the application.

Moreover, an embodiment/example may refer to other embodiments/examples. For example, any description including but not limited to terminology, element, process, explanation and/or technical advantage mentioned in one embodiment/example is applicative to the other embodiments/examples.

FIG. 1 shows a network node 100 according to an embodiment of the invention. The network node 100 is configured to obtain a data packet 101, to add (own) telemetry data 102 of the network node 100 to the data packet 101, and to forward the data packet 101 to another network node 100, after adding the telemetry data 102 to the data packet 101. The telemetry data 102 comprises performance data 302 (see FIG. 3) indicating a processing performance of the data packet 101 in the network node 100.

The network node 100 may also be configured to expose the (own) telemetry data 102 of the network node 100 to the management device, e.g. a management server 201

(illustrated e.g. in FIG. 2). To this end, the network node 100 is configured to add the telemetry data 102 of the network node 100 to a special packet (instead of the data packet 101), and forward the special packet to the management server 201, after adding the telemetry data 102 to the special packet. In a further embodiment, the network node 100 may be configured to expose the telemetry data 102 to the management server 201 as described, and also add it to the data packet

101 as described. That is, the network node 100 may be configured to obtain a data packet 101, add the telemetry data 102 of the network node 100 to the data packet 101 and to a special packet, and forward the data packet 101 including the telemetry data 102 to another network node 100 and forward the special packet including the telemetry data

102 to a management device.

The data packet 101 may generally be transmitted by a source to a destination (as exemplarily depicted e.g. in FIG. 2), wherein the data packet 101 is transmitted through a network comprising a plurality of network nodes/devices. The data packet 101 may belong to a certain data packet flow, which is forwarded along a certain path/route through the network, in particular, it is forwarded by multiple network nodes 100. Each network node 100 may be or comprise a switch, a router or a network interface card (NIC). A NIC is a hardware component that resides either in the source or destination or both. A network node 100 according to an embodiment of the invention may function as at least one of (and as one of with respect to a certain packet flow of data packets 101):

• A “source node”, i.e. a network node 100 that is the source of the data packet 101 and generates the data packet 101.

• A “first node”, i.e. the first network node 100 in the network that receives the data packet 101 from an external source 202 (see exemplarily FIG. 2), i.e. the first network node along the path that the data packet 101 takes through the network. The “first node” may in some cases be the same as the “source node”.

• A “transit node”, i.e. an intermediate network node 100 in the path that the data packet 101 takes through the network.

• A “last node”, i.e. the last network node 100 in the network that receives the data packet 101, i.e. the last network node 100 in the path that the data packet 101 takes/took through the network.

• A “destination node”, i.e. a network node 100 that is the destination of the data packet 101, which may be the same as the “last node”.

Notably, the other network node 100 (right node) shown in FIG. 1 may function as a “transit node” or as a “last node”. Further, if the network node 100 described with respect to FIG. 1 (middle node) is a “transit node” or a “last node”, it may receive the data packet 101 from yet another network node 100 (left node; shown as the dashed box in FIG. 1). This other network node 100 may function as a “first node” or as a “transit node”.

The network node 100 may comprise processing circuitry (not shown) configured to perform, conduct or initiate the various operations of the network node 100 described herein. The processing circuitry may comprise hardware and software. The hardware may comprise analog circuitry or digital circuitry, or both analog and digital circuitry. The digital circuitry may comprise components such as application-specific integrated circuits (ASICs), field-programmable arrays (FPGAs), digital signal processors (DSPs), or multi purpose processors. In one embodiment, the processing circuitry comprises one or more processors and a non-transitory memory connected to the one or more processors. The non-transitory memory may carry executable program code which, when executed by the one or more processors, causes the network node 100 to perform, conduct or initiate the operations or methods described herein.

FIG. 2 shows an exemplary system 200 including at least a network comprising a plurality of network nodes 100 according to embodiments of the invention. The system 200 may further include a source 202 of the data packet 101, and a destination 203 of the data packet 101. Source 202 and destination 203 may be implemented as network nodes 100 of the network in some embodiments.

In the example shown in FIG. 2, three network nodes 100 are shown. One network node

100 (left node) functions as “first node” and receives the data packet 101 from the source 202. One network node 100 (right node) functions as “last node” and provides the data packet 101 to the destination 203. One network node 100 (middle node) functions as “transit node” and is arranged between “first node” and “last node”. For other data packets

101 of other packet flows, the shown network nodes 100 may take different functions. For instance, another packet flow could be from destination 203 to source 202, and in this case “first node” and “last node” would be exchanged. The system 200 may further include, or may be configured to report to, a management server 201. In FIG. 2, as an example, the “last node” 100 exposes telemetry data 102 (of any one of the network nodes 100) to the management server 201. However, each network node 100 may expose its own telemetry data 102 to the management server 201. Each node may even expose its own telemetry data 102 to the management server 201 without adding it to a data packet 101.

FIG. 3 shows an example of a data packet 101 a provided by a network node 100, according to an embodiment of the invention.

Each network node 100, which is arranged along the path of the data packet 101 through the network, may push its own telemetry data 102, in particular its own performance data 302, into the data packet, and/or may expose it to the management server 201. Each network node 100 along the path may be considered a “hop”. That is, the telemetry data

102 of each network node 100 may be added to a different section of the telemetry header field 301, which sections may be consecutively arranged in the packet header 300 (“Hop 1 Data”, “Hop 2 Data”, “Hop 3 Data”, etc.). Each network node 100 along the path may expose telemetry data 102 of previous hops and/or own telemetry data 102 to the management server 201, e.g., by adding it to a special packet and sending it to the management server 201.

Each network node 100 may also push a node delay 303 into the telemetry header field 301, i.e. delay information regarding a delay of the data packet 101 in the network node 100. The node delay 303 may also be added to the special packet for exposure to the management device 201.

Each network node 100 may also push a delay report 304 into the telemetry header field, which may include an average delay, a minimum delay, or a maximum delay. The average delay may comprise information regarding an average delay of one or more data packets 101 or one or more probe packets in the network node 100. The minimum and maximum delay may comprise information regarding a minimum and/or maximum delay, respectively, of one or more data packets 101 or one or more probe packets in the network node 100. The delay report 304 may also be added to the special packet for exposure to the management device 201.

One or more of the network nodes 100 along the path of the data packet 101 may export or expose some or all of the telemetry data 102, particularly performance data 302, nor delay 303, and/or delay report 303 to a management server 201.

In the following, further detailed implementations of the above embodiments of the invention are described, in particular, for in-band reporting in a network.

A “first node” in the network is a network node 100 that can incorporate a telemetry header field 301 and telemetry data 102 into the packet header 300 of the data packet 101. The “first node” may be the source of the packet, or may be a first switch/router along the path of the data packet 101. The telemetry header 301 and telemetry data 102 may be incorporated in a tunnel header, or as an extension field in the existing header 300 of the data packet 101.

A “transit node” in the network is a network node 100 (e.g., a switch or router) that can receive a data packet 101 with a telemetry header field 301 and telemetry data 102 of another network node 100, and can push its own telemetry data 102 into the telemetry header field 301.

A “last node” in the network is a network node 100 that can remove the telemetry header field 301 and the telemetry data 102 from the data packet 101. This can be done either by removing it along with a tunnel header, which is also removed, or by removing it from an extension field of the packet header 100.

An “analyzer node” in the network is a network node 100 that can analyze the telemetry header field 301 and the telemetry data 102, and can potentially perform an action based on the analyzed telemetry data 102.

The telemetry header field 301 may further indicate the type of telemetry data 102 that is included. In particular, the telemetry header 301 may comprise an indication regarding the type of the telemetry data 102 in the telemetry header field 301. In particular, the network node 100 can add an indication regarding the type of telemetry data 102 it adds to the telemetry header field 301.

The telemetry data 102 may include at least one of:

• Various types of the performance data 302, such as a queue status or a processing duration. In case that a special packet is forwarded to the management device 201, all queues and ports information can be included at once, including the processing duration.

• The node delay 303 reflecting the delay of the data packet 101 through the current network node 100.

• The delay report 304, which may include at least one of:

^■ The average delay, reflecting the average delay in the current node, as measured in the network node 100.

^■ The minimum delay, reflecting the lowest value of delay that was measured in the network node 100.

^■ The maximum delay, reflecting the highest value of delay that was measured in the network node 100. The reporting of the delay can be over data packets 101 (in-band), or can be over probe packets, which are packets sent specifically for checking the delay status.

The average, minimum, and maximum delay values may represent either measurements since the previous data packet 101, or since the network node 100 was initialized, or since the delay parameters were explicitly reset in the network node 100.

In addition to the delay parameters, the delay report 304 may also include a counter value which reflects the number of packets that were marked as congested for Explicit Congestion Notification (ECN). This mechanism may use a per-flow counter that counts the number of marked packets. The delay report 304 may also include additional parameters that help identify, which queue the data packet 101 was enqueued into, for instance at least one of:

• A Queue ID.

• One or more Quality of Service (QoS) attributes, which may include one or more of the following attributes: ■ Differentiated Service Code Point (DSCP) as defined in RFC 791; Traffic

Class (TC), Drop Precedence (DP), User Priority (UP) as per IEEE 802. IQ.

• An entry switch port and/or an exit switch port for the data packet 101 in the network. The entry switch port and the exit switch port may each be a logical or a physical port. The telemetry header field 301 and the telemetry data 102 may be encapsulated in a tunnel header, or as an extension field in an existing header. For instance, the delay report 304 may be incorporated in a Type/Length/V alue (TLV) based field, such as the Opaque State field in IOAM.

FIG. 4 shows a method 400 according to an embodiment of the invention. The method 100 is for network telemetry, and may be performed by a network node 100. The method

400 comprises : a step 401 of obtaining a data packet; a step 402 of adding (own) telemetry data 102 of the network node 100 to the data packet 101 or to a special packet, wherein the telemetry data 102 comprises performance data 302 indicating a processing performance ofthe data packet 101 in the networknode 100; and astep 403 offorwarding the data packet 101 including the telemetry data 102 to another network node 100 or forwarding the special packet including the telemetry data 102 to a management device.

The method 400 may also comprises a step of exposing, by the network node 100, the telemetry data 102 of the network node 100 to a management device, e.g., the management server 201, in addition to or alternatively to adding the telemetry data 102 of the network node 100 to the data packet 101. The method 400 may comprise adding the telemetry data 102 of the network node 100 to one or more special packets, and sending the one or more specials packet to the management device/server 201, for instance, at predetermined time intervals and/or when being actively requested by the management device 201.

Other systems, methods, features, and advantages of the present disclosure will be or become apparent to one with skill in the art upon examination of the following drawings and detailed description. It is intended that all such additional systems, methods, features, and advantages be included within this description, be within the scope of the present disclosure, and be protected by the accompanying claims.

The descriptions of the various embodiments of the present invention have been presented for purposes of illustration, but are not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the embodiments, the practical application or technical improvement over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

It is expected that during the life of a patent maturing from this application many relevant keys will be developed and the scope of the term key is intended to include all such new technologies a priori.

The terms “comprises”, “comprising”, “includes”, “including”, “having” and their conjugates mean “including but not limited to”. This term encompasses the terms “consisting of’ and “consisting essentially of’. The phrase “consisting essentially of’ means that the composition or method may include additional ingredients and/or steps, but only if the additional ingredients and/or steps do not materially alter the basic and novel characteristics of the claimed composition or method. As used herein, the singular form “a”, “an” and “the” include plural references unless the context clearly dictates otherwise. For example, the term “a compound” or “at least one compound” may include a plurality of compounds, including mixtures thereof.

The word “exemplary” and “e.g.” are used herein to mean “serving as an example, instance or illustration”. Any embodiment described as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments and/or to exclude the incorporation of features from other embodiments.

It is appreciated that certain features of the invention, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the invention, which are, for brevity, described in the context of a single embodiment, may also be provided separately or in any suitable sub-combination or as suitable in any other described embodiment of the invention. Certain features described in the context of various embodiments are not to be considered essential features of those embodiments, unless the embodiment is inoperative without those elements. All publications, patents and patent applications mentioned in this specification are herein incorporated in their entirety by reference into the specification, to the same extent as if each individual publication, patent or patent application was specifically and individually indicated to be incorporated herein by reference. In addition, citation or identification of any reference in this application shall not be construed as an admission that such reference is available as prior art to the present invention. To the extent that section headings are used, they should not be construed as necessarily limiting.

The present invention has been described in conjunction with various embodiments as examples as well as implementations. However, other variations can be understood and effected by those persons skilled in the art and practicing the claimed invention, from the studies of the drawings, this disclosure and the independent claims. In the claims as well as in the description the word “comprising” does not exclude other elements or steps and the indefinite article “a” or “an” does not exclude a plurality. A single element or other unit may fulfill the functions of several entities or items recited in the claims. The mere fact that certain measures are recited in the mutual different dependent claims does not indicate that a combination of these measures cannot be used in an advantageous implementation.

Claims

1. A system for predicting flow patterns of traffic and forming outputs dependent thereon in dependence on data received from a plurality of sensors each configured to acquire data at a respective location in a spatial region having a known road layout, wherein the system is configured to: receive data from the sensors; aggregate the received data with historical data from the sensors in the spatial region in dependence on the road layout; and in dependence on the aggregated data, predict traffic flow patterns at the locations and analyse the received data to identify deviations between the received data and the predicted traffic flow patterns and/or analyse the predicted traffic flow patterns to identify vehicle-level features therein; and output the said deviations and/or vehicle level features.

2. The system of claim 1, wherein the system is configured to perform traffic anomaly detection, delay computation, traffic jam detection and/or offset computation in dependence on the output deviations and/or vehicle level features.

3. The system of claim 1 or 2, wherein the vehicle-level features comprise the number of vehicles at a location and/or a queue length of vehicles at a location.

4. The system of any preceding claim, wherein the data received from each of the sensors comprises a dataseries of values.

5. The system as claimed in any preceding claim, wherein the system is configured to predict traffic flow patterns by implementing a learned artificial intelligence model.

6. The system as claimed in any preceding claim, wherein the system is configured to aggregate the received data with historical data from the sensors hierarchically across respective sub-regions of increasing size within the spatial region.

7. The system of any preceding claim, wherein the respective locations are respective traffic intersections.

8. The system as claimed in claim 7, wherein each intersection comprises at least three intersecting vehicle pathways and traffic flow patterns are predicted in further dependence on at least one of: the number of cars entering an intersection in each direction, the stopping probability of vehicles at the intersection, and the probability of vehicles going in each direction at the intersection.

9. The system as claimed in claim 7 or 8, wherein the predicted traffic flow patterns are used to determine traffic lights plans for traffic signals located at the intersections.

10. The system as claimed in claim 9, wherein the system is further configured to determine traffic light plans for traffic signals located at the intersections by optimizing at least one traffic metric at the intersection.

11. The system as claimed in claim 10, wherein the traffic metric is one of traffic throughput, queue length or wasted green time of the traffic signals.

12. The system as claimed in any of claims 9 to 11, wherein the system is further configured to predict the pathways of at least two vehicles in the region and, if these predictions indicate that the vehicles will pass through the same location at the same time, adjust the timings of traffic signals to temporally interleave the pathways.

13. The system of any preceding claim, wherein the system is deployed across more than one cloud-based entity.

14. The system as claimed in any preceding claim, wherein each of the sensors comprises one of a camera, a weather sensor, a pollution sensor, a noise sensor and an induction loop.

15. A method for implementation at a system for predicting flow patterns of traffic and forming outputs dependent thereon in dependence on data received from a plurality of sensors each configured to acquire data at a respective location in a spatial region having a known road layout, wherein the method comprises: receiving data from the sensors; aggregating the received data with historical data from the sensors in the spatial region in dependence on the road layout; and in dependence on the aggregated data, predicting traffic flow patterns at the locations and analysing the received data to identify deviations between the received data and the predicted traffic flow patterns and/or analysing the predicted traffic flow patterns to identify vehicle-level features therein; and outputting the said deviations and/or vehicle level features.