WO2023163620A1

WO2023163620A1 - Scheduling transmission of spiking data

Info

Publication number: WO2023163620A1
Application number: PCT/SE2022/050189
Authority: WO
Inventors: András RÁCZ; Robert Baldemair; Tamas Borsos; Stefan Parkvall; András VERES
Original assignee: Telefonaktiebolaget Lm Ericsson (Publ)
Priority date: 2022-02-22
Filing date: 2022-02-22
Publication date: 2023-08-31

Abstract

Embodiments of the present disclosure provide a method (300) for scheduling transmission of spiking data over a communication channel. The method (300) is performed by first neuromorphic transmitter node (102a). The method (300) comprises obtaining (302) the spiking data representing one or more spikes. The method (300) comprises detecting (304) whether the communication channel over which the spiking data is to be transmitted, is being used by one or more second neuromorphic transmitter nodes (102b - 102n). The method (300) comprises assigning (306) a time interval within which the spiking data is to be transmitted based on the maximum delay interval associated with the spiking data and scheduling (308) the transmission of the spiking data over the communication channel based on the assigned time interval. Corresponding first neuromorphic transmitter node, network node and computer program products are disclosed.

Description

SCHEDULING TRANSMISSION OF SPIKING DATA

TECHNICAL FIELD

The present disclosure relates generally to the field of spiking neural network. More particularly, it relates to methods, neuromorphic transmitter node, network node, and computer program products for scheduling transmission of spiking data over a communication channel.

BACKGROUND

In general, spiking neural networks, SNNs are artificial neural networks which closely mimic natural neural networks. A SNN is a collection of many hundreds or thousands of such neurons, which are inter-connected via synapses. In SNNs, all the information carried between neurons are represented by spikes. A spike is considered as a binary data, where the presence of a spike implicitly carries the information. A spike is generated by a change in intensity level detected at the neurons. Some of the examples of devices generating the spikes are neuromorphic or event camera, neuromorphic control system, skin or touch sensors, robotic arms, or the like. Other types of sensors, such as artificial cochlea, skin or touch sensors are directly generating spikes as output signal, or actuators, like robotic arms, which can be controlled via spike signals. There are also chips executing neuromorphic computing as opposed to traditional arithmetic compute, suitable to process e.g., the outputs of neuromorphic sensors.

Figure 1 shows a neuron model having a plurality of inter-connected neurons. As explained above, the SNN is a collection of multiple neurons which are inter-connected via synapses. Each spike received on any of the input synapses 10a - lOd of the neuron 12 (weighted with the synapse weight) (wi - w_n), increases the voltage potential of the neuron. When the increased voltage potential reaches a threshold voltage, the neuron 12 emits an output spike 14.

With the emergence of neuromorphic traffic in wireless networks and in particular with the emergence of neuromorphic data and spiking data, the efficient transmission with short delay and jitter sensitive data over collision based shared medium becomes more important. The existing radio communication and resource sharing solutions have not been designed for the requirements of spiking data such as high delay/jitter sensitivity, good tolerance to loss, high volume, low communication overhead or the like.

SUMMARY

In the wireless communication network, due to the nature of spike-based communication and its communication features, special requirements need to be formulated for the efficient transmission over collision based shared medium. The unique properties altogether create a special situation regarding the communication requirements of spiking data, which none of the existing radio communication and resource sharing solutions can fulfil in an optimal way.

Consequently, there is a need for an improved method and arrangement for for scheduling transmission of spiking data over a communication channel that alleviates at least some of the above cited problems.

It is therefore an object of the present disclosure to provide a method, a neuromorphic transmitter node, a network node and a computer program product for scheduling transmission of spiking data over a communication channel to mitigate, alleviate, or eliminate all or at least some of the above-discussed drawbacks of presently known solutions.

This and other objects are achieved by means of a method, a neuromorphic transmitter node, a network node and a computer program product as defined in the appended claims. The term exemplary is in the present context to be understood as serving as an instance, example or illustration.

According to a first aspect of the present disclosure, a method for scheduling transmission of spiking data over a communication channel is disclosed. The method is performed by a first neuromorphic transmitter node in the wireless communication network. The method comprises obtaining the spiking data representing one or more spikes generated by a neuromorphic application. The spiking data comprises an indicator of a maximum delay interval to be sustained for the spiking data. The method comprises detecting whether the communication channel over which the spiking data is to be transmitted, is being used by one or more second neuromorphic transmitter nodes. The method further comprises upon the detection that the communication channel is being used by the one or more second neuromorphic transmitter nodes, assigning a time interval within which the spiking data is to be transmitted based on the maximum delay interval associated with the spiking data. The coverage map indicates a network condition within a coverage area of the industrial environment. The method further comprises scheduling the transmission of the spiking data over the communication channel based on the assigned time interval.

In some embodiments, the method further comprises converting the spiking data into a digital representation comprising an address of each neuron emitting the spikes.

In some embodiments, the method further comprises transmitting the spiking data over the communication channel to one or more of: the receiver node and a network node in a wireless communication network, in accordance with the scheduled transmission.

In some embodiments, the method further comprises determining that the communication channel is not available for transmission of the spiking data at the assigned time interval and assigning a new time interval for transmission of the spiking data such that the new time interval is within a remaining time interval from the maximum delay interval to be sustained for the spiking data. The method further comprises scheduling the transmission of the spiking data over the communication channel based on the assigned new time interval.

In some embodiments, the method further comprises determining that the communication channel is not available for transmission of the spiking data at the assigned new time interval and determining the expiry of the maximum delay interval to be sustained for the spiking data. The method further comprises upon expiry of the maximum delay interval, aborting the transmission of the spiking data and transmitting an indication to the network node that the spiking data is dropped at the first neuromorphic transmitter node due to expiry of the maximum delay interval.

In some embodiments, the step of detecting whether the communication channel is being used by the one or more second transmitter nodes comprises receiving downlink control information, DCI, from the network node, the DCI comprising information indicating whether the communication channel is being used by the one or more second neuromorphic transmitter nodes from the network node and determining whether the communication channel is being used by the one or more second transmitter nodes based on the received DCL

In some embodiments, the step of assigning the time interval comprises determining whether the transmission of the spiking data is to be delayed by the time interval based on the maximum delay interval associated with the spiking data and selecting a time interval such that the selected time interval is within the maximum delay interval to be sustained for the spiking data. The method further comprises assigning the selected time interval for scheduling transmission of the spiking data.

In some embodiments, the step of assigning the time interval comprises determining that the maximum delay interval associated with one or more spikes is greater than a configurable threshold value. The method further comprises selecting a time interval such that the selected time interval is between a minimum delay interval associated with the one or more spikes and the maximum delay interval to be sustained by the one or more spikes and assigning the selected time interval for transmission of the one or more spikes.

In some embodiment, the step of assigning the time interval comprises determining a priority level associated with each of the one or more spikes and assigning a time interval to each of the spikes based on determined priority level.

In some embodiment, the assigned the time interval of the one or more spikes constantly decreases as time elapses until the one or more spikes are transmitted from the first neuromorphic transmitter node.

In some embodiment, the step of obtaining the spiking data representing one or more spikes further comprises registering an arrival time of the one or more spikes and identifying a maximum delay interval associated with each of the one or more spikes. The method further comprises associating the maximum delay interval and the arrival time of the one or more spikes.

In some embodiment, the step of associating the maximum delay time interval and the arrival time of the one or more spikes comprises establishing a bearer for transmission of the spiking data from the neuromorphic application and defining quality of service, QoS, parameters for the bearer, wherein the QoS parameters comprises a maximum delay interval associated with each of the one or more spikes.

In some embodiment, the step of associating the maximum delay interval and the arrival time of the one or more spikes comprises receiving an indication indicating a delay interval associated with each neuron emitting the one or more spikes, from the neuromorphic application during connection establishment by the first neuromorphic transmitter node and associating the delay interval associated with each neuron and the arrival time of the one or more spikes.

In some embodiment, the step of associating the maximum delay interval and the arrival time of the one or more spikes comprises receiving an indication about a delay interval associated with each spike from an application layer.

According to a second aspect of the present disclosure, a method for scheduling transmission of spiking data from a plurality of neuromorphic transmitter nodes in a wireless communication network is disclosed. The method is performed by a network node in the wireless communication network. The method comprises monitoring transmissions of the spiking data from one or more neuromorphic transmitter nodes in the wireless communication network. The method further comprises detecting that the communication channel is being used by the one or more neuromorphic transmitter nodes based on monitoring of the transmissions of the spiking data from one or more neuromorphic transmitter nodes. The method further comprises transmitting downlink control information, DCI, to one or more neuromorphic transmitter nodes, wherein the DCI comprising information indicating that the communication channel is being used by the one or more neuromorphic transmitter nodes.

In some embodiments, the DCI comprises a BUSY signal and a COLLISION signal.

In some embodiments, the step of transmitting the DCI to one or more neuromorphic transmitter nodes comprises detecting that the communication channel is being used by the one or more neuromorphic transmitter nodes and transmitting the BUSY signal to one or more neuromorphic transmitter nodes indicating that the communication channel is being used.

In some embodiments, the step of transmitting the DCI to one or more neuromorphic transmitter nodes comprises detecting a collision due to transmission of the spiking data by the one or more neuromorphic transmitter nodes and transmitting the COLLISION signal to one or more neuromorphic transmitter nodes indicating the collision.

In some embodiments, the method further comprises receiving an indication from the one or more neuromorphic transmitter nodes indicating that the spiking data is dropped due to expiry of the maximum delay interval at respective neuromorphic transmitter nodes.

In some embodiments, the method further comprises receiving information from the one or more neuromorphic transmitter nodes, the information comprising: spiking events, spiking load information, minimum delay interval associated with the spiking data, and maximum delay interval associated with the spiking data. The method comprises tuning a time interval for the one or more neuromorphic transmitter nodes within which the spiking data is to be transmitted from the one or more neuromorphic transmitter nodes, based on the received information. The method further comprises scheduling radio resources to the one or more neuromorphic transmitter nodes in accordance with the received information.

According to a third aspect of the present disclosure, an apparatus of a first neuromorphic transmitter node for scheduling transmission of spiking data over a communication channel is provided. The apparatus comprising controlling circuitry configured to cause obtaining of the spiking data representing one or more spikes generated by a neuromorphic application, wherein the spiking data comprises an indicator of a maximum delay interval to be sustained for the spiking data. The controlling circuitry is further configured to cause detection of whether the communication channel over which the spiking data is to be transmitted, is being used by one or more second neuromorphic transmitter nodes. The controlling circuitry is further configured to cause upon the detection that the communication channel is being used by the one or more second neuromorphic transmitter nodes, assignment of a time interval within which the spiking data is to be transmitted based on the maximum delay interval associated with the spiking data. The controlling circuitry is further configured to cause scheduling of the transmission of the spiking data over the communication channel based on the assigned time interval.

A fourth aspect is a neuromorphic transmitter node comprising the apparatus of the third aspect.

According to a fifth aspect of the present disclosure, an apparatus of a network node configured to operate in a wireless communication network for scheduling transmission of spiking data from a plurality of neuromorphic transmitter nodes in a wireless communication network is provided. The apparatus comprising controlling circuitry configured to cause monitoring of transmissions of the spiking data from one or more neuromorphic transmitter nodes in the wireless communication network. The controlling circuitry is further configured to cause detection of that the communication channel is being used by the one or more neuromorphic transmitter nodes based on monitoring of the spiking data from the transmissions of one or more neuromorphic transmitter nodes. The controlling circuitry is further configured to cause transmission of downlink control information, DCI, to one or more neuromorphic transmitter nodes, wherein the DCI comprising information indicating that the communication channel is being used by the one or more neuromorphic transmitter nodes.

According to a sixth aspect of the present disclosure, there is provided a computer program product comprising a non-transitory computer readable medium, having thereon a computer program comprising program instructions, the computer program is loadable into a data processing unit and configured to cause execution of the method according to the first and second aspects when the computer program is run by the data processing unit.

In some embodiments, any of the above aspects may additionally have features identical with or corresponding to any of the various features as explained above for any of the other aspects.

An advantage of some embodiments is that alternative and/or improved approaches are provided for scheduling transmission of spiking data over a communication channel.

An advantage of some embodiments is that the unique properties of spikes are considered in the scheduling transmission of spiking data over a communication channel. Thus, the spiking data can be communicated in the wireless communication network more efficiently.

An advantage of some embodiments is that alternative and/or improved approaches are provided for efficiently combining the delay sensitive transmission requirement of spike data traffic with low overhead and fast medium access scheme.

An advantage of some embodiments is that alternative and/or improved approaches are provided for enhancement of the medium access efficiency by utilizing the advantages of a network nodes and the communication infrastructure.

An advantage of some embodiments is that alternative and/or improved approaches are provided for handling the high spike intensity typical in many neuromorphic data communication pattern.

BRIEF DESCRIPTION OF THE DRAWINGS

The foregoing will be apparent from the following more particular description of the example embodiments, as illustrated in the accompanying drawings in which like reference characters refer to the same parts throughout the different views. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating the example embodiments.

Figure 1 discloses an example neuron model;

Figure 2A discloses an example wireless communication network according to some embodiments;

Figure 2B is a protocol stack of a neuromorphic transmitter node according to some embodiments;

Figure 3 is a flowchart illustrating example method steps according to some embodiments;

Figures 4A, 4B, and 4C are block diagrams of transmission of spiking data according to some embodiments;

Figure 5 is a flowchart illustrating example method steps according to some embodiments; Figure 6 is a schematic block diagram illustrating an example apparatus according to some embodiments;

Figure 7 is a schematic block diagram illustrating an example apparatus according to some embodiments; and

Figure 8 discloses an example computing environment according to some embodiments.

DETAILED DESCRIPTION

Aspects of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. The apparatus and methods disclosed herein can, however, be realized in many different forms and should not be construed as being limited to the aspects set forth herein. Like numbers in the drawings refer to like elements throughout.

The terminology used herein is for the purpose of describing particular aspects of the disclosure only and is not intended to limit the invention. It should be emphasized that the term "comprises/comprising" when used in this specification is taken to specify the presence of stated features, integers, steps, or components, but does not preclude the presence or addition of one or more other features, integers, steps, components, or groups thereof. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

Embodiments of the present disclosure will be described and exemplified more fully hereinafter with reference to the accompanying drawings. The solutions disclosed herein can, however, be realized in many different forms and should not be construed as being limited to the embodiments set forth herein.

It will be appreciated that when the present disclosure is described in terms of a method, it may also be embodied in one or more processors and one or more memories coupled to the one or more processors, wherein the one or more memories store one or more programs that perform the steps, services and functions disclosed herein when executed by the one or more processors.

In the present disclosure, receiver nodes, also known as mobile terminals, user equipment (UE) and/or wireless terminals, are enabled to communicate wirelessly with a neuromorphic transmitter node in a wireless communication network. In the present disclosure, it is assumed that connection establishment has already been completed between the receiver node(s) and the neuromorphic transmitter node.

In the following description of exemplary embodiments, the same reference numerals denote the same or similar components.

FIG. 2A discloses an example communication network in the form of a wireless communication network 100. As depicted in FIG. 2A, the wireless communication network 100 includes a plurality of neuromorphic transmitter nodes 102a, 102b, 102c and so on to 102n, a receiver node 104, and a network node 108. The neuromorphic transmitter node 102a - 102n, the receiver node 104, and the network node 108 are connected with each other over a shared communication channel 106.

In some embodiments, the receiver node 104 communicates with the neuromorphic transmitter node 102a - 102n serving the receiver node 104. In another embodiment, the receiver node 104 communicates with the neuromorphic transmitter node 102a - 102n through the network node 108.

Although not shown in FIG. 2A, there may be a plurality of receiver nodes 104a - 104n in the coverage of the neuromorphic transmitter node 102a - 102n.

To facilitate communications, communication channels are established between the neuromorphic transmitter nodes 102a - 102n and the receiver node 104. When the neuromorphic transmitter nodes 102a - 102n has spiking data to be transmitted to the receiver node 104, the neuromorphic transmitter nodes 102a - 102n transmit the data packets using access and resource sharing scheme to the receiver node 104.

In SNNs, the spiking data represents one or more spikes generated by a neuromorphic application. The neuromorphic application is an application which outputs spikes based on a change in intensity detected at the neuron. In scenarios, where components in SNN are wirelessly communicating to each other, the radio technology needs to have some unique capability. The unique capability may comprise low delay and low jitter to preserve the time sensitive aspect of spike information encoding, medium access and resource allocation methods must support unpredictable and bursty traffic patterns, both uni-cast and group- east communication will be needed to effectively support dense, local inter-neuron connectivity, usual loss and Block Error Rate, BLER, mitigation algorithms, like radio retransmission or large transmission buffer sizes may be applied only with significant limitations.

In wireless communication 100, due to the nature of spike-based communication and its communication features, special requirements need to be formulated for the radio technology to effectively support distributed neuromorphic-based applications. As a result, when the data packets to be transmitted by the neuromorphic transmitter nodes 102a - 102n comprises the spiking data, the existing radio communication and resource sharing solutions cannot provide solution for the unique requirements of spiking data.

Therefore, according to some embodiments of the present disclosure, a first neuromorphic transmitter node 102a implements a method for scheduling transmission of spiking data over a communication channel. The first neuromorphic transmitter node may be any of neuromorphic transmitter nodes 102a - 102n.

In at least some implementations, the first neuromorphic transmitter node 102a obtains the spiking data representing one or more spikes generated by the neuromorphic application. The spiking data comprises an indicator of a maximum delay interval to be sustained for the spiking data.

Further, the first neuromorphic transmitter node 102a determines whether the communication channel over which the spiking data is to be transmitted, is being used by one or more second neuromorphic transmitter nodes 102b - 102n. The first neuromorphic transmitter node 102a determines whether the communication channel is being used by the one or more second neuromorphic transmitter nodes 102b - 102n using downlink control information, DCI, received from the network node 108.

The first neuromorphic transmitter node 102a further assigns a time interval within which the spiking data is to be transmitted based on the maximum delay interval associated with the spiking data when it is determined that the communication channel is being used by the one or more second neuromorphic transmitter nodes 102b - 102n. The assigned time interval is selected such that the transmission of the spiking data is to be delayed within the maximum delay interval of the spiking data. Furthermore, the first neuromorphic transmitter node 102a schedules the transmission of the spiking data over the communication channel 106 based on the assigned time interval. For example, the transmission of the spiking data is scheduled such that the spiking data is to be transmitted to the receiver node 104 during the assigned time period. Various embodiments for scheduling transmission of spiking data over a communication channel are explained in conjunction with figures in the later parts of the description.

According to some embodiments of the present disclosure, the network node 108 implements a method for scheduling transmission of spiking data from a plurality of neuromorphic transmitter nodes 102a - 102n in a wireless communication network 100.

In at least some implementations, the network node 108 monitors transmissions of one or more neuromorphic transmitter nodes 102a - 102n in the wireless communication network 100. For example, the network node 108 continuously scans the communication channel 106 to detect the ongoing transmission from the neuromorphic transmitter node 102a - 102n through the communication channel 106.

The network node 108 detects that the communication channel 106 is being used by the one or more neuromorphic transmitter nodes 102a-102n based on monitoring of the transmissions of one or more neuromorphic transmitter nodes 102a - 102n. For example, the network node 108 detects if any of the neuromorphic transmitter node 102a - 102n is transmitting the data packets through the communication channel 106.

Further, the network node 108 transmits DCI to one or more neuromorphic transmitter nodes 102a - 102n. The DCI comprises information indicating that the communication channel is being used by the one or more neuromorphic network nodes 102a - 102n. For example, the network node 108 may transmit one of a BUSY signal or a COLLISION signal to the one or more neuromorphictransmitter nodes 102a - 102n. The BUSY signal indicates that the communication channel is being used and the COLLSION signal indicates the collision between the transmissions from one or more neuromorphic transmitter nodes 102a - 102n.

As discussed in above embodiments, the first neuromorphic transmitter node 102a monitors the communication channel to determine whether the communication channel is being used by one or more neuromorphic transmitter node 102b - 102n and accordingly the neuromorphic transmitter node 102a assigns a time interval within which the spiking data is to be transmitted over the communication channel. Thus, the method provides alternative and/or improved approaches for scheduling transmission of spiking data over a communication channel such that the collision can be avoided.

FIG. 2B discloses the protocol stack of the neuromorphic transmitter node 102. As depicted in FIG. 2B, the neuromorphic transmitter node 102 comprises a plurality of layers for transmission of the spiking data. For example, application layer 204, transport layer 206, Media Access Control (MAC) layer 208, and Physical (PHY) layer 210. The plurality of layers are arranged from top to bottom in layered architecture such that the application layer 204 is on top and the PHY layer 210 is on bottom.

The neuromorphic transmitter node 102 comprises one or more applications executed in the application layer 204. In some examples, the one or more applications are related to neuromorphic applications. The neuromorphic application generates the spikes 202 using the neurons (compare with FIG. 1). Some example of neuromorphic application comprises an application executed in neuromorphic or event camera, neuromorphic control system, skin or touch sensors, robotic arms, or the like. Whenever the voltage generated by change in intensity reaches the threshold voltage, the neuromorphic application generates a spike using corresponding neuron. The one or more generated spikes are represented by the spiking data.

The transport layer 206 of the neuromorphic transmitter node 102 receives the generated spiking data from the application layer 204. The transport layer 206 acts as spiking-aware transport layer. The spiking-aware transport layer acquires capability and preferences of the lower layers (e.g. MAC layer and PHY layer). For example, the capability and preferences of the lower layer comprises latency capability, reliability capability, minimum transport block size, maximum transport block size, orthe like. The spiking-aware transport layer generates spiking protocol data units, PDUs, for the spiking data by using the acquired capability and preferences of the lower layers. In some embodiments, the spiking-aware transport layer may generate a single spiking PDU to include the spiking data based on the capability and preferences of the lower layers. In another embodiments, the spike transport layer may generate multiple spiking PDUs to include the spiking data based on the capability and preferences of the lower layers. Since, the spiking-aware transport layer is aware of capability and preferences of MAC transport block and accordingly generates the spiking PDUs, it avoids creating spiking PDUs which are too large to fit into a single MAC transport block. In addition, details on scheduling, link adaption, and possible PHY optimizations are provided to MAC transport block.

Further, the MAC layer 208 of the neuromorphic transmitter node 102 receives the spiking payload from the transport layer 206. The MAC layer 208 encodes the spiking payload using an address of a neuron emitting the spike. For example, the spiking payload is encoded with the address of the neuron to form one or more spiking PDUs. The encoding of the one or mode spikes may be performed by using one or more of method used for the encoding. For example, binary representation, rate coding, latency encoding, full temporal encoding or the like. In binary representation, the spiking pattern of a neuron is considered in a time interval. For example, if the neuron fires during a time interval then this time interval is represented by one binary value and if the neuron is not active then this time interval is represented by zero binary value. In rate coding, a number of spikes emitted by the neuron in a certain time interval is determined and coded. In latency encoding, the latency between events until a first spike is encoded. In full temporal encoding, the encoding of the one or more spikes depends upon transmission Quality of Service, QoS.

Furthermore, the PHY layer 210 of the neuromorphic transmitter node 102 receives the one or more spiking PDUs from the MAC layer 208. The received one or more spiking PDUs are modulated using one or more selected modulation and coding schemes, MCSs and form one or more data packets. The PHY layer 208 further transmits the one or more data packets to a receiver node.

Figure 3 is a flowchart illustrating example method steps of a method 300 performed by the first neuromorphic transmitter node 102a for scheduling transmission of spiking data over a communication channel.

At step 302, the method 300 comprises obtaining the spiking data representing one or more spikes generated by a neuromorphic application. In some examples, the neuromorphic application can be executed by a neuromorphic transmitter node. The spiking data comprises an indicator of a maximum delay interval to be sustained for the spiking data. The spiking data is generated by the plurality of inter-connected neurons in the SNN.

The first neuromorphic transmitter node registers an arrival time of the one or more spikes. For example, the first neuromorphictransmitter node receives the one or more spikes from the neuromorphic application executing in a spiking neural network, SNN, having a plurality of inter-connected neurons. The first neuromorphic transmitter node detects the arrival time when the each spike is arrived at the first neuromorphic transmitter node. Further the first neuromorphic transmitter node registers the detected arrival time in a buffer. The first neuromorphictransmitter node identifies a maximum delay interval associated each of one or more spikes. Each of the one or more spikes has a corresponding maximum delay interval defined by the neuromorphic application. The maximum delay interval indicates a maximum time interval by which the corresponding spike can be delayed. When a spike is arrived at the first neuromorphic transmitter node, the maximum delay interval associated with that spike is identified by the first neuromorphic transmitter node.

Further, the first neuromorphic transmitter node establishes an association between the maximum delay interval and the arrival time of the one or more spikes. For example, the first neuromorphic transmitter node establishes a bearer for transmission of the spiking data from the neuromorphic application. The first neuromorphic transmitter node further defines quality of service, QoS, parameters for the bearer. The QoS parameters comprises a maximum delay interval associated with each of the one or more spikes. Further, the first neuromorphic transmitter node receives an indication that indicates a delay interval associated with each neuron emitting the one or more spikes. In some embodiments, the indication is received from the neuromorphic application during connection establishment by the first neuromorphic transmitter node. In another embodiments, the indication about a delay interval associated with each spike from an application layer. Furthermore, the first neuromorphic application establishes the association between the delay interval associated with each neuron and the arrival time of one or more spikes.

Further, the first neuromorphic transmitter node converts the spiking data into a digital representation comprising an address of each neuron emitting the spikes as depicted in an optional step 303 of method 300. For example, the first neuromorphic transmitter node encodes the spiking data into a digitalized format e.g. Address Event Representation, AER, format in which the spiking data is composed of the identity of the neuron that has emitted the spike.

At step 304, the method 300 comprises detecting whether the communication channel over which the spiking data is to be transmitted, is being used by one or more second neuromorphic transmitter nodes. The first neuromorphic transmitter node detects whether the one or more second neuromorphic transmitter nodes are using the communication channel over which the spiking data is to be transmitted based on the DCI received from the network node. For example, the first neuromorphic transmitter node receives the DCI from the network node. The DCI comprises information that indicates whether the communication channel is being used by the one or more second neuromorphic transmitter nodes from the network node. Further, the first neuromorphic transmitter node determines whether the communication channel is being used bythe one or more second neuromorphic transmitter nodes by analysis of the received DCI.

At step 306, the method 300 comprises upon the detection that the communication channel is being used by the one or more second neuromorphic transmitter nodes, assigning a time interval within which the spiking data is to be transmitted based on the maximum delay interval associated with the spiking data. The first neuromorphic transmitter node assigns the time interval within the maximum delay interval associated with the spiking data when it is detected that the one or more other neuromorphic transmitter nodes are transmitting the data packets using the communication channel.

The first neuromorphic transmitter node extracts the indicator from the spiking data and identifies the maximum delay interval to be sustained for the spiking data based on the indicator. The first neuromorphic transmitter node determines whether the transmission of the spiking data is to be delayed by the time interval based of the maximum delay interval associated with the spiking data. The first neuromorphic transmitter node further selects a time interval such that the selected time interval is within the maximum delay interval to be sustained for the spiking data. Furthermore, the first neuromorphic transmitter node assigns the selected time interval for scheduling transmission of the spiking data. For example, when the maximum delay interval indicates that the spiking data can be sustained for a time interval of 10 ms, the first neuromorphic transmitter node selects the time interval less than 10 ms to be assigned for the transmission.

In some embodiments, the first neuromorphic transmitter node obtains a configurable threshold value. In some embodiments, the configurable threshold value is received from the network node. The configurable threshold value depends upon a number of transmission through the communication channel. Further, the first neuromorphic transmitter node determines that the maximum delay interval associated with the spiking data is greater than the configurable threshold value. When the maximum delay interval is greater than the configurable threshold value then the first neuromorphic transmitter node selects a time interval such that the selected time interval is between a minimum delay interval associated with the one or more spikes and the maximum delay interval to be sustained by the one or more spikes. Further, the first neuromorphic transmitter node assigns the selected time interval for transmission of the spiking data.

In some embodiments, the first neuromorphic transmitter node obtains a priority level associated with each of the one or more spikes. For example, each spike has its own priority level indicating that which spike is more urgent to be transmitted. The first neuromorphic transmitter node assigns the time interval to each of the spikes based on the determined priority level. For example, the first neuromorphic transmitter node may transmit the spike which more urgent earlier than the spike which is less urgent according to the priority levels of the one or more spikes.

The assigned time interval of the one or more spikes constantly decreases as time elapses until the one or more spikes are transmitted from the first neuromorphic transmitter node. For example, the first neuromorphic transmitter node assigns the time interval for the transmission of the one or more spikes according to one or more embodiments explained above. As time elapses after assignment of the time interval of the one or more spikes, the time interval constantly decreases until the one or more spikes are transmitted from the first neuromorphic transmitter node.

At step 308, the method 300 comprises scheduling the transmission of the spiking data over the communication channel based on the assigned time interval. For example, the first neuromorphic transmitter node schedules the radio resources for the transmission of the spiking data such that each spike is transmitted according to the assigned time interval for the corresponding spike.

In some embodiments, the first neuromorphic transmitter node determines that the communication channel is not available for transmission of the spiking data at the assigned time interval. For example, the first neuromorphic transmitter node determines whether the communication channel being used by one or more second neuromorphic transmitter nodes at the assigned time interval. When it is determined that the communication channel is not available for the transmission of the spiking data, the first neuromorphic transmitter node assigns a new time interval for the transmission of the spiking data. The new time interval is within a remaining time interval from the maximum delay interval to be sustained for the spiking data. Further, the first neuromorphic transmitter node schedules the transmission of the spiking data over the communication channel based on the assigned new time interval.

In some embodiments, the first neuromorphic transmitter node determines that the communication channel is not available for the transmission of the spiking data at the assigned new time interval. For example, the first neuromorphic transmitter node determines whether the communication channel being used by one or more second neuromorphic transmitter nodes at the assigned new time interval. When it is determined that the communication channel is not available for the transmission of the spiking data, the first neuromorphic transmitter node determines the expiry of the maximum delay interval to be sustained for the spiking data. For example, the first neuromorphic transmitter node determines that the spiking data is not transmitted at the expiry of the maximum delay interval. The first neuromorphic transmitter node aborts the transmission of the spiking data upon the expiry of the maximum delay interval. For example, the first neuromorphic transmitter node discards the spiking data when the maximum delay interval has been expired for the spiking data. Further, the first neuromorphic transmitter node transmits an indication to the network node that the spiking data is dropped at the first neuromorphic transmitter node due to the expiry of the maximum delay interval. At step 310, the method 300 comprises transmitting the spiking data over the communication channel to one or more of: a receiver node and a network node in accordance with the scheduled transmission.

In some embodiments, the first neuromorphic transmitter node transmits the spiking data over the communication channel to the receiver node in the wireless communication network. For example, the spiking data is transmitted directly to the receiver node over the communication channel. As depicted in FIG. 4A, the first neuromorphic transmitter node 102a transmits the spiking data to the receiver node 104 over the communication channel. Further, the second neuromorphic transmitter node 102b transmits the spiking data to the receiver node 104 over the communication channel. In absence of the scheduled transmission as described in one or more embodiments of this disclosure, a collision 404 between the spiking data transmitted from the first neuromorphic transmitter node 102a and the spiking data transmitted from the second neuromorphic transmitter node 102b may occurs. Thus, the scheduling of the transmission of the spiking data according to the one or more embodiments explained in this disclosure becomes crucial to avoid the collision 404.

In some embodiments, the first neuromorphic transmitter node transmits the spiking data over the communication channel to receiver node and the network node provides information about the communication channel for scheduling the transmission. The information about the communication channel indicates whether the communication channel is being used by one or more second neuromorphic transmitter nodes. For example, the spiking data is transmitted directly to the receiver node over the communication channel using the information about the communication channel received from the network node. As depicted in FIG. 4B, the first neuromorphic transmitter node 102a transmits the spiking data to the receiver node 104 over the communication channel. The second neuromorphic transmitter node 102b transmits the spiking data to the receiver node 104 over the communication channel. Further, each of the first neuromorphic transmitter node 102a and the second neuromorphic transmitter node 102b transmits indication of the transmitting using the communication channel to the network node 108. The network node 108 monitors the communication channel according to the indication of the transmitting using the communication channel and transmits the information about the communication channel to each of the first neuromorphic transmitter node 102a and the second neuromorphic transmitter node 102b. Further, each of the first neuromorphic transmitter node 102a and the second neuromorphic transmitter node 102b schedules the transmission of the spiking data according to the information about the communication channel according to one or more embodiments explained in this disclosure. In absence of the scheduled transmission as described in one or more embodiments of this disclosure, a collision 404 between the spiking data transmitted from the first neuromorphic transmitter node 102a and the spiking data transmitted from the second neuromorphic transmitter node 102b may occurs. Thus, the scheduling of the transmission of the spiking data according to the one or more embodiments explained in this disclosure becomes crucial to avoid the collision 404.

In some embodiments, the first neuromorphic transmitter node transmits the spiking data over the communication channel to the network node in the wireless communication network. The network node further transmits the spiking data over the communication channel to the receiver node in the wireless communication channel. Further, the network node monitors the communication channel to determine whether the communication channel is being used by one or more second neuromorphic transmitter nodes or not. The network node transmits the spiking data to the receiver node when it is determined that the communication channel is not being used by the one or more second neuromorphic transmitter nodes. Further, the network node schedules the transmission of the spiking data when it is determined that the communication channel is being used by one or more second neuromorphic transmitter nodes. As depicted in FIG. 4C, the first neuromorphic transmitter node 102a transmits the spiking data to the network node 108 over the communication channel. The second neuromorphic transmitter node 102b transmits the spiking data to the network node 108 over the communication channel. Further, the network node 108 monitors the communication channel and transmits the spiking data to the receiver node 104 according to the monitor of the communication channel as explained in one or more embodiments of this disclosure. In absence of the scheduled transmission as described in one or more embodiments of this disclosure, a collision 404 between the spiking data transmitted from the first neuromorphic transmitter node 102a and the spiking data transmitted from the second neuromorphic transmitter node 102b may occurs. Thus, the scheduling of the transmission of the spiking data according to the one or more embodiments explained in this disclosure becomes crucial to avoid the collision 404.

As discussed in above embodiments, the first neuromorphic transmitter node determines whether the communication channel is being used by one or more second neuromorphic transmitter node and accordingly assigns the time interval within which the spiking data is to be transmitted over the communication channel. Thus, the method provides improved approaches for scheduling transmission of spiking data over a communication channel such that the collision can be avoided.

Figure 5 is a flowchart illustrating example method steps of a method 500 performed by the network node in the wireless communication network for scheduling transmission of spiking data from a plurality of neuromorphic transmitter nodes.

At step 502, the method 500 comprises monitoring transmissions of the spiking data from one or more neuromorphic transmitter nodes in the wireless communication network. For example, the network node monitors whether the one or more neuromorphic transmitter nodes are using the communication channel for transmission of the spiking data.

At step 504, the method 500 comprises detecting that the communication channel is being used by the one or more neuromorphic transmitter nodes based on monitoring of the transmissions of the spiking data from one or more neuromorphic transmitter nodes. For example, the network node detects that the one or more neuromorphic transmitter nodes are transmitting the spiking data overthe communication channel based on the monitoring of the transmissions of the one or more neuromorphic transmitter nodes. In some embodiments, the network node determines the information about the time period for which the one or more neuromorphic transmitter node may transmit the spiking data over the communication channel.

At step 506, the method 500 comprises transmitting the DCI to one or more neuromorphic transmitter nodes. The DCI comprises information indicating that the communication channel is being used by the one or more neuromorphic network nodes. For example, the DCI comprises one or more of a BUSY signal and a COLLISION signal. The BUSY signal indicates that the communication channel is being used by the one or more neuromorphic transmitter nodes. The COLLISION signal indicates that a collision has been occurred in the communication channel.

In some embodiments, the network node detects that the communication channel is being used by the one or more neuromorphic network nodes. For example, while monitoring the transmission of the spiking data from one or more neuromorphic transmitter nodes, the network node detects that the communication channel is being used by the one or more neuromorphic network nodes. The network node further transmits the BUSY signal to one or more neuromorphic transmitter nodes. The BUSY signal indicates that the communication channel is being used by one or more neuromorphic transmitter nodes.

In some embodiments, the network node detects a collision due to transmission of the spiking data by the one or more neuromorphic transmitter nodes. For example, while monitoring the transmission of the spiking data from one or more neuromorphic transmitter nodes, the network node detects the collision in the communication channel due to transmission of the spiking data by the one or more neuromorphic network nodes. The network node further transmits the COLLISION signal to one or more neuromorphic transmitter nodes. The COLLISION signal indicates that the communication channel is being used by one or more neuromorphic transmitter nodes.

Further, the network node receives the indication from the one or more neuromorphic network nodes indicating that the spiking data is dropped due to expiry of the maximum delay interval at respective neuromorphic transmitter nodes. For example, when the spiking data has not been transmitted from the respective neuromorphic transmitter node till expiry of the maximum delay interval sustained by the spiking data, the spiking data dropped at the respective neuromorphic transmitter node and the indication is received from the respective neuromorphic transmitter node.

Further, the network node receives information from the one or more neuromorphic transmitter nodes. The information comprises spiking events, spiking load information, minimum delay interval associated with the spiking data, maximum delay interval associated with the spiking data, and the like. The network node tunes a time interval for the one or more neuromorphic transmitter nodes within which the spiking data is to be transmitted from the respective neuromorphic transmitter node based on the received information. For example, the network node determines a time interval which is within the maximum delay interval associated with the spiking data. Further, the network node tunes the time interval that fulfils the requirement according to the received information. The network node further schedules radio resources to the one or more neuromorphic transmitter nodes in accordance with the received information. For example, the network node schedules the radio resources for transmission of the spiking data from the one or more neuromorphic transmitter nodes.

As discussed in above embodiments, the network node monitors the communication channel to determine whether the communication channel is being used by one or more neuromorphic transmitter node and accordingly tunes a time interval within which the spiking data is to be transmitted over the communication channel. Thus, the method provides alternative and improved approaches for scheduling transmission of spiking data from a plurality of neuromorphic transmitter nodes over the communication channel such that the collision can be avoided.

Figure 6 is an example schematic diagram showing an apparatus 102. The apparatus 102 may e.g. be comprised in a first neuromorphic transmitter node. The apparatus 102 is capable of scheduling transmission of spiking data over the communication channel and may be configured to cause performance of the method 300 for scheduling transmission of spiking data over the communication channel.

According to at least some embodiments of the present invention, the apparatus 102 in FIG. 6 comprises one or more modules. These modules may e.g. be a detector 602, a scheduler 604, a controlling circuitry 606, a processor 608, and a transceiver 610. The controlling circuitry 606, may in some embodiments be adapted to control the above mentioned modules.

The detector 602, the scheduler 604, the processor 608, the transceiver 610 as well as the controlling circuitry 606, may be operatively connected to each other.

It can be mentioned that the scheduler 604 may be merged into the processor 608, which may be called a data processor, potentially also covering the controlling circuitry 606. The detector 602 may be adapted to obtain the spiking data representing one or more spikes generated by a neuromorphic application. The controlling circuitry 606 may be adapted to assign the time interval within which the spiking data is to be transmitted. The scheduler 604 may be adapted to schedule the transmission of the spiking data over the communication channel. The transceiver 610 may be adapted to transmit the spiking data to a receiver node.

The controlling circuitry 606 may be adapted to control the steps as executed by the first neuromorphic transmitter node. For example, the controlling circuitry 606 may be adapted to obtain the spiking data representing one or more spikes generated by a neuromorphic application, detect whether the communication channel over which the spiking data is to be transmitted, is being used by one or more second neuromorphic transmitter nodes, assign a time interval within which the spiking data is to be transmitted based on the maximum delay interval associated with the spiking data, schedules the transmission of the spiking data over the communication channel based on the assigned time interval. Thus, the controlling circuitry 606 may be adapted to transmit the spiking data to the receiver node (as described above in conjunction with the method 300 and FIG. 3).

Figure 7 is an example schematic diagram showing an apparatus 108. The apparatus 108 may e.g. be comprised in a network node. The apparatus 108 is capable of monitoring transmissions of the spiking data from one or more neuromorphic transmitter nodes in the wireless communication network and may be configured to cause performance of the method 500 for scheduling transmission of spiking data from a plurality of neuromorphic transmitter nodes in the wireless communication network.

According to at least some embodiments of the present invention, the apparatus 108 in FIG. 7 comprises one or more modules. These modules may e.g. be a transceiver 702, a detector 704, a monitor 706, a controlling circuitry 708, and a processor 710. The controlling circuitry 708, may in some embodiments be adapted to control the above mentioned modules.

The transceiver 702, the detector 704, the monitor 706, the processor 710 as well as the controlling circuitry 708, may be operatively connected to each other. Optionally, the transceiver 702 may be adapted to receive information from the one or more neuromorphic transmitter nodes, from one or more neuromorphic transmitter nodes and transmit the DCI to one or more neuromorphic transmitter nodes.

The detector 704 may be adapted to detect an indication indicating that the spiking data is dropped due to expiry of the maximum delay interval at respective neuromorphic transmitter nodes.

The monitor 706 may be adapted to monitor transmissions of the spiking data from one or more neuromorphic transmitter nodes in the wireless communication network.

The processor 710 may be adapted to detect that the communication channel is being used by the one or more neuromorphic transmitter nodes.

The controlling circuitry 708 may be adapted to control the steps as executed by the network node. For example, the controlling circuitry 708 may be adapted to monitor transmissions of the spiking data from one or more neuromorphic transmitter nodes in the wireless communication network, detect that the communication channel is being used by the one or more neuromorphic transmitter nodes. Thus, the controlling circuitry 708 may be adapted to transmit the DCI to one or more neuromorphic transmitter nodes (as described above in conjunction with the method 500 and FIG. 5).

Any appropriate steps, methods, features, functions, or benefits disclosed herein may be performed through one or more functional units or modules of one or more virtual apparatuses. Each virtual apparatus may comprise a number of these functional units. These functional units may be implemented via processing circuitry, which may include one or more microprocessor or microcontrollers, as well as other digital hardware, which may include digital signal processors, DSPs, special-purpose digital logic, and the like. The processing circuitry may be configured to execute program code stored in memory, which may include one or several types of memory such as read-only memory (ROM), randomaccess memory, RAM, cache memory, flash memory devices, optical storage devices, etc. Program code stored in memory includes program instructions for executing one or more telecommunications and/or data communications protocols as well as instructions for carrying out one or more of the techniques described herein. In some implementations, the processing circuitry may be used to cause the respective functional unit to perform corresponding functions according one or more embodiments of the present disclosure. The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope of the disclosure.

Figure 8 illustrates an example computing environment 800 implementing a method and the network function and the content delivery server as described in FIG. 3 and FIG. 5. As depicted in FIG. 8, the computing environment 800 comprises at least one processing unit 806 that is equipped with a control unit 802 and an Arithmetic Logic Unit, ALU 804, a plurality of networking devices 808 and a plurality Input output, I/O devices 810, a memory 812, a storage 814. The processing unit 806 may be responsible for implementing the method described in FIG. 3 and FIG. 5. For example, the processing unit 806 may in some embodiments be equivalent to the processor of the network node and the first neuromorphic transmitter node described above in conjunction with the FIGS. 1-7. The processing unit 806 is capable of executing software instructions stored in memory 812. The processing unit 806 receives commands from the control unit 802 in order to perform its processing. Further, any logical and arithmetic operations involved in the execution of the instructions are computed with the help of the ALU 804.

The computer program is loadable into the processing unit 806, which may, for example, be comprised in an electronic apparatus (such as a UE or a network node). When loaded into the processing unit 806, the computer program may be stored in the memory 812 associated with or comprised in the data processing module 806. According to some embodiments, the computer program may, when loaded into and run by the processing unit 806, cause execution of method steps according to, for example, any of the methods illustrated in FIGS. 3 and 5 or otherwise described herein.

The overall computing environment 800 may be composed of multiple homogeneous and/or heterogeneous cores, multiple CPUs of different kinds, special media and other accelerators. Further, the plurality of processing units 906 may be located on a single chip or over multiple chips.

The algorithm comprising of instructions and codes required for the implementation are stored in either the memory 812 or the storage 814 or both. At the time of execution, the instructions may be fetched from the corresponding memory 812 and/or storage 814, and executed by the processing unit 806.

In case of any hardware implementations various networking devices 808 or external I/O devices 810 may be connected to the computing environment to support the implementation through the networking devices 808 and the I/O devices 810.

The embodiments disclosed herein can be implemented through at least one software program running on at least one hardware device and performing network management functions to control the elements. The elements shown in FIG. 8 include blocks which can be at least one of a hardware device, or a combination of hardware device and software unit.

Claims

1. A method (300) for scheduling transmission of spiking data over a communication channel, the method being performed by a first neuromorphic transmitter node (102a), the method (300) comprising:

- obtaining (302) the spiking data representing one or more spikes generated by a neuromorphic application, wherein the spiking data comprises an indicator of a maximum delay interval to be sustained for the spiking data;

- detecting (304) whether the communication channel over which the spiking data is to be transmitted, is being used by one or more second neuromorphic transmitter nodes (102b - 102n);

- upon the detection that the communication channel is being used by the one or more second neuromorphic transmitter nodes (102b - 102n), assigning (306) a time interval within which the spiking data is to be transmitted based on the maximum delay interval associated with the spiking data; and

- scheduling (308) the transmission of the spiking data over the communication channel based on the assigned time interval.

2. The method according to claim 1, further comprising:

- converting (303) the spiking data into a digital representation comprising an address of each neuron emitting the spikes.

3. The method according to any of the claims 1 or 2, further comprising:

- transmitting (310) the spiking data over the communication channel to one or more of: the receiver node (104) and a network node (108) in a wireless communication network (100), in accordance with the scheduled transmission.

4. The method according to any of the preceding claims, further comprising:

- determining that the communication channel is not available for transmission of the spiking data at the assigned time interval; - assigning a new time interval for transmission of the spiking data such that the new time interval is within a remaining time interval from the maximum delay interval to be sustained for the spiking data; and

- scheduling the transmission of the spiking data over the communication channel based on the assigned new time interval. The method according to claim 4, further comprising:

- determining that the communication channel is not available for transmission of the spiking data at the assigned new time interval;

- determining the expiry of the maximum delay interval to be sustained for the spiking data;

- upon expiry of the maximum delay interval, aborting the transmission of the spiking data; and

- transmitting an indication to the network node (108) that the spiking data is dropped at the first neuromorphic transmitter node (102a) due to expiry of the maximum delay interval. The method according to any of the preceding claims, wherein the step (304) of detecting whether the communication channel is being used by the one or more second neuromorphic transmitter nodes (102b - 102n) comprises:

- receiving downlink control information, DCI, from the network node (108), the DCI comprising information indicating whether the communication channel is being used by the one or more second neuromorphic transmitter nodes from the network node (108); and

- determining whether the communication channel is being used by the one or more second neuromorphic transmitter nodes (102b - 102n) based on the received DCI. The method according to any of the preceding claims, wherein the step (306) of assigning the time interval comprises: - determining whether the transmission of the spiking data is to be delayed by the time interval based on the maximum delay interval associated with the spiking data;

- selecting a time interval such that the selected time interval is within the maximum delay interval to be sustained for the spiking data; and

- assigning the selected time interval for scheduling transmission of the spiking data. The method according to any of the preceding claims, wherein the step (306) of assigning the time interval comprises:

- determining that the maximum delay interval associated with one or more spikes is greater than a configurable threshold value;

- selecting a time interval such that the selected time interval is between a minimum delay interval associated with the one or more spikes and the maximum delay interval to be sustained by the one or more spikes; and

- assigning the selected time interval for transmission of the one or more spikes. The method according to any of the preceding claims, wherein the step (306) of assigning the time interval comprises:

- determining a priority level associated with each of the one or more spikes; and

- assigning a time interval to each of the spikes in accordance with the determined priority level. The method according to any of the preceding claims, wherein the assigned the time interval of the one or more spikes constantly decreases as time elapses until the one or more spikes are transmitted from the first neuromorphic transmitter node (102a). The method according to any of the preceding claims, wherein the step (302) of obtaining the spiking data representing one or more spikes further comprises:

- registering an arrival time of the one or more spikes; - identifying a maximum delay interval associated with each of the one or more spikes; and

- associating the maximum delay interval and the arrival time of the one or more spikes. The method according to claim 11, wherein the step of associating the maximum delay time interval and the arrival time of the one or more spikes comprises:

- establishing a bearer for transmission of the spiking data from the neuromorphic application; and

- defining quality of service, QoS, parameters for the bearer, wherein the QoS parameters comprises a maximum delay interval associated with each of the one or more spikes. The method according to any of the claims 11 or 12, wherein the step of associating the maximum delay interval and the arrival time of the one or more spikes comprises:

- receiving an indication indicating a delay interval associated with each neuron emitting the one or more spikes, from the neuromorphic application during connection establishment by the first neuromorphic transmitter node (102a); and

- associating the delay interval associated with each neuron and the arrival time of the one or more spikes. The method according to any of the claims 11-13, wherein the step of associating the maximum delay interval and the arrival time of the one or more spikes comprises: receiving an indication about a delay interval associated with each spike from an application layer.

15. A method (500) for scheduling transmission of spiking data from a plurality of neuromorphic transmitter nodes (102a - 102n) in a wireless communication network (100), the method being performed by a network node (108) in the wireless communication network (100), the method (500) comprising:

- monitoring (502) transmissions of the spiking data from one or more neuromorphic transmitter nodes (102a-102n) in the wireless communication network (100);

- detecting (504) that the communication channel is being used by the one or more neuromorphic transmitter nodes (102a-102n) based on monitoring of the transmissions of the spiking data from one or more neuromorphic transmitter nodes (102a-102n); and

- transmitting (506) downlink control information, DCI, to one or more neuromorphic transmitter nodes (102a - 102n), wherein the DCI comprising information indicating that the communication channel is being used by the one or more neuromorphic transmitter nodes (102a-102n).

16. The method according to claim 15, wherein the DCI comprises a BUSY signal and a COLLISION signal.

17. The method according to any of the claims 15 or 16, wherein the step (506) of transmitting the DCI to one or more neuromorphic transmitter nodes (102a-102n) comprises:

- detecting that the communication channel is being used by the one or more neuromorphic transmitter nodes (102a-102n); and

- transmitting the BUSY signal to one or more neuromorphic transmitter nodes (102a-102n) indicating that the communication channel is being used.

18. The method according to any of the claims 15-17, wherein the step (506) of transmitting the DCI to one or more neuromorphic transmitter nodes comprises:

- detecting a collision due to transmission of the spiking data by the one or more neuromorphic transmitter nodes (102a-102n); and transmitting the COLLISION signal to one or more neuromorphic transmitter nodes (102a-102n) indicating the collision. The method according any of the claims 15-18, further comprising:

- receiving an indication from the one or more neuromorphic transmitter nodes (102a-102n) indicating that the spiking data is dropped due to expiry of the maximum delay interval at respective neuromorphic transmitter nodes (102a- 102n). The method according any of the claims 15-19, further comprising: receiving information from the one or more neuromorphic transmitter nodes (102a-102n), the information comprising: spiking events, spiking load information, minimum delay interval associated with the spiking data, and maximum delay interval associated with the spiking data; tuning a time interval for the one or more neuromorphic transmitter nodes (102a-102n) within which the spiking data is to be transmitted from the one or more neuromorphic transmitter nodes (102a-102n), based on the received information; and scheduling radio resources to the one or more neuromorphic transmitter nodes (102a-102n) in accordance with the received information. An apparatus of a first neuromorphic transmitter node (102a) for scheduling transmission of spiking data over a communication channel, the apparatus (102a) comprising controlling circuitry configured to cause:

- obtaining of the spiking data representing one or more spikes generated by a neuromorphic application, wherein the spiking data comprises an indicator of a maximum delay interval to be sustained for the spiking data;

- detection of whether the communication channel over which the spiking data is to be transmitted, is being used by one or more second neuromorphic transmitter nodes (102b - 102n); - upon the detection that the communication channel is being used by the one or more second neuromorphic transmitter nodes (102b - 102n), assignment of a time interval within which the spiking data is to be transmitted based on the maximum delay interval associated with the spiking data; and

- scheduling of the transmission of the spiking data over the communication channel based on the assigned time interval. The apparatus according to claim 2, wherein the controlling circuitry is configured to cause:

- conversion of the spiking data into a digital representation comprising an address of each neuron emitting the spikes. The apparatus according to claims 21 or 22, wherein the controlling circuitry is configured to cause:

- transmission of the spiking data over the communication channel to one or more of: the receiver node (104) and a network node (108) in a wireless communication network (100), in accordance with the scheduled transmission. The apparatus according to claims 21-23, wherein the controlling circuitry is configured to cause:

- determination that the communication channel is not available for transmission of the spiking data at the assigned time interval;

- assignment of a new time interval for transmission of the spiking data such that the new time interval is within a remaining time interval from the maximum delay interval to be sustained for the spiking data; and

- scheduling of the transmission of the spiking data over the communication channel based on the assigned new time interval. The apparatus according to claim 24, wherein the controlling circuitry is configured to cause: - determination that the communication channel is not available for transmission of the spiking data at the assigned new time interval;

- determination of the expiry of the maximum delay interval to be sustained for the spiking data;

- upon expiry of the maximum delay interval, aborting of the transmission of the spiking data; and

- transmission of an indication to the network node that the spiking data is dropped at the first neuromorphic transmitter node (102a) due to expiry of the maximum delay interval. The apparatus according to claims 21-25, wherein the controlling circuitry is configured to cause the step of detecting whether the communication channel is being used by the one or more second neuromorphic transmitter nodes (102b - 102n) by causing:

- reception of downlink control information, DCI, from the network node (104), the DCI comprising information indicating whether the communication channel is being used by the one or more second neuromorphic transmitter nodes from the network node (104); and

- determination of whether the communication channel is being used by the one or more second neuromorphic transmitter nodes (102b - 102n) based on the received DCI. The apparatus according to claims 21-26, wherein controlling circuitry is configured to cause the step of assigning the time interval by causing:

- determination of whether the transmission of the spiking data is to be delayed by the time interval based on the maximum delay interval associated with the spiking data;

- selection of a time interval such that the selected time interval is within the maximum delay interval to be sustained for the spiking data; and

- assignment of the selected time interval for scheduling transmission of the spiking data. The apparatus according to claims 21-27, wherein controlling circuitry is configured to cause the step of assigning the time interval by causing:

- determination that the maximum delay interval associated with one or more spikes is greater than a configurable threshold value;

- selection of a time interval such that the selected time interval is between a minimum delay interval associated with the one or more spikes and the maximum delay interval to be sustained by the one or more spikes; and

- assignment of the selected time interval for transmission of the one or more spikes. The apparatus according to claims 21-28, wherein the controlling circuitry is configured to cause the step of assigning the time interval by causing:

- determination of a priority level associated with each of the one or more spikes; and

- assignment of a time interval to each of the spikes in accordance with the determined priority level. The apparatus according to claims 21-29, wherein the assigned the time interval of the one or more spikes constantly decreases as time elapses until the one or more spikes are transmitted from the first neuromorphic transmitter node (102a). The apparatus according to claims 21-30, wherein the controlling circuitry is configured to cause the step of obtaining the spiking data representing one or more spikes by causing:

- registration of an arrival time of the one or more spikes;

- identification of a maximum delay interval associated with each of the one or more spikes; and

- association of the maximum delay interval and the arrival time of the one or more spikes.

32. The apparatus according to claim 31, wherein the controlling circuitry is configured to cause the step of associating the maximum delay time interval and the arrival time of the one or more spikes by causing:

- establishment of a bearer for transmission of the spiking data from the neuromorphic application; and

- defining of quality of service, QoS, parameters for the bearer, wherein the QoS parameters comprises a maximum delay interval associated with each of the one or more spikes.

33. The apparatus according to claims 31 or 32, wherein the controlling circuitry is configured to cause the step of associating the maximum delay time interval and the arrival time of the one or more spikes by causing:

- reception of an indication indicating a delay interval associated with each neuron emitting the one or more spikes, from the neuromorphic application during connection establishment by the first neuromorphic transmitter node (102a); and

- association of the delay interval associated with each neuron and the arrival time of the one or more spikes.

34. The apparatus according to claims 31-33, wherein the controlling circuitry is configured to cause the step of associating the maximum delay time interval and the arrival time of the one or more spikes by causing:

- reception of an indication about a delay interval associated with each spike from an application layer.

35. A neuromorphic transmitter node comprising the apparatus of any of the claims 21 through 34.

36. An apparatus of a network node (108) configured to operate in a wireless communication network (100) for scheduling transmission of spiking data from a plurality of neuromorphic transmitter nodes (102a - 102n) in the wireless communication network (100), the apparatus (108) comprising controlling circuitry configured to cause:

- monitoring of transmissions of the spiking data from one or more neuromorphic transmitter nodes (102a-102n) in the wireless communication network (100);

- detection of that the communication channel is being used by the one or more neuromorphic transmitter nodes (102a-102n) based on monitoring of the transmissions of the spiking data from one or more neuromorphic transmitter nodes (102a-102n); and

- transmission of downlink control information, DCI, to one or more neuromorphic transmitter nodes (102a - 102n), wherein the DCI comprising information indicating that the communication channel is being used by the one or more neuromorphic transmitter nodes (102a-102n).

37. The apparatus according to claim 36, wherein the DCI comprises a BUSY signal and a COLLISION signal.

38. The apparatus according to claims 36 or 37, wherein the controlling circuitry is configured to cause the step of transmitting the DCI to one or more neuromorphic transmitter nodes (102a-102n) by causing:

- detection that the communication channel is being used by the one or more neuromorphic transmitter nodes (102a-102n); and

- transmission of the BUSY signal to one or more neuromorphic transmitter nodes (102a-102n) indicating that the communication channel is being used.

39. The apparatus according to claims 36-38, wherein the controlling circuitry is configured to cause the step of transmitting the DCI to one or more neuromorphic transmitter nodes by causing:

- detection of a collision due to transmission of the spiking data by the one or more neuromorphic transmitter nodes (102a-102n); and transmission of the COLLISION signal to one or more neuromorphic transmitter nodes (102a-102n) indicating the collision. The apparatus according to claims 36-39, wherein the controlling circuitry is further configured to cause:

- reception of an indication from the one or more neuromorphic transmitter nodes (102a-102n) indicating that the spiking data is dropped due to expiry of the maximum delay interval at respective neuromorphic transmitter nodes (102a-102n). The apparatus according to claims 36-40, wherein the controlling circuitry is further configured to cause: reception of information from the one or more neuromorphic transmitter nodes (102a-102n), the information comprising: spiking events, spiking load information, minimum delay interval associated with the spiking data, and maximum delay interval associated with the spiking data; tuning of a time interval for the one or more neuromorphic transmitter nodes(102a-102n) within which the spiking data is to be transmitted from the one or more neuromorphic transmitter nodes (102a-102n), based on the received information; and scheduling of radio resources to the one or more neuromorphic transmitter nodes (102a-102n) in accordance with the received information. A network node comprising the apparatus of any of the claims 36 through 41. A computer program product comprising a non-transitory computer readable medium, having thereon a computer program comprising program instructions, the computer program is loadable into a data processing unit and configured to cause execution of the method according to any of claims 1 through 20 when the computer program is run by the data processing unit.