Communication network resource allocation via segmented demand forecasting
A processing system may segregate customers of a communication network into communication network customer segments in accordance with at least one factor, generate predicted customer order weights by customer segment for a first network resource type in accordance with at least a first forecasting model, and calculate inventory demand weights for network resources of the first network resource type in accordance with at least a second forecasting model. The processing system may then obtain a new customer order for the first network resource type from a first customer and configure the communication network to process data traffic of the first customer via one of the network resources of the first network resource type that is selected based upon a customer segment of the first customer and an allocation matching scheme in accordance with the predicted customer order weights by communication network customer segment and the plurality of inventory demand weights.
1 . A method comprising:
segregating, by a processing system including at least one processor deployed in a communication network, a plurality of customers of the communication network into a plurality of communication network customer segments in accordance with at least one factor;
generating, by the processing system, a plurality of predicted customer order weights by communication network customer segment for a first network resource type in accordance with at least a first forecasting model comprising at least a first gradient boosted machine, wherein the first network resource type comprises: a hardware network element type, a network path type, a virtual network element type for a virtual network element hosted via one or more hardware network elements, a service type for a service hosted via the one or more hardware network elements, or an interface port type;
calculating, by the processing system, a plurality of inventory demand weights for a plurality of network resources of the first network resource type in the communication network in accordance with at least a second forecasting model comprising at least a second gradient boosted machine;
obtaining, by the processing system, a new customer order for the first network resource type from a first customer of the communication network; and
configuring, by the processing system, the communication network to process data traffic of the first customer via one of the plurality of network resources of the first network resource type that is selected based upon a customer segment of the first customer and an allocation matching scheme in accordance with the plurality of predicted customer order weights by communication network customer segment and the plurality of inventory demand weights, wherein the configuring comprises configuring a provider edge network component in conjunction with a customer edge network component to process the data traffic of the first customer via the one of the plurality of network resources of the first network resource type that is selected.
2 . The method of claim 1 , wherein the segregating comprises segregating the plurality of customers by customer intensity values.
3 . The method of claim 2 , wherein each customer intensity value of the customer intensity values is calculated based upon counts of a number of network services utilized by a respective customer.
4 . The method of claim 2 , wherein the segregating comprises segregating the plurality of customers into the plurality of communication network customer segments in accordance with a distribution of values of the at least one factor associated with the plurality of customers.
5 . The method of claim 1 , wherein the at least the first forecasting model is trained with a training data set comprising historical order data for at least a portion of the plurality of customers of the plurality of customer segments.
6 . The method of claim 1 , wherein each of the plurality of predicted customer order weights by communication network customer segment is based upon an order count for the first network resource type by a subset of the plurality of customers of a particular customer segment.
7 . The method of claim 6 , wherein the each of the plurality of predicted customer order weights by communication network customer segment is further based upon an order count for a network resource category including a plurality of network resource types including the first network resource type by the subset of the plurality of customers of the particular customer segment.
8 . The method of claim 1 , wherein the at least the first forecasting model further comprises at least a first time series forecasting model.
9 . The method of claim 1 , wherein the at least the second forecasting model further comprises at least a second time series forecasting model.
10 . The method of claim 1 , wherein the at least the second forecasting model is trained with a training data set comprising historical allocations associated with the plurality of network resources.
11 . The method of claim 10 , wherein the historical allocations are across the plurality of communication network customer segments.
12 . The method of claim 1 , wherein the at least the second forecasting model is trained with a training data set comprising historical utilization measures associated with the plurality of network resources.
13 . The method of claim 12 , wherein the historical utilization measures are across the plurality of communication network customer segments.
14 . The method of claim 1 , wherein the at least the second forecasting model includes a respective forecasting model for the one of the plurality of network resources, wherein the respective forecasting model comprises a plurality of input factors for a plurality of network resource types associated with the hardware network element type, the plurality of network resource types including the first network resource type of the one of the plurality of network resources, and wherein the one of the plurality of network resources is associated with a hardware network element of the hardware network element type.
15 . A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor when deployed in a communication network, cause the processing system to perform operations, the operations comprising:
segregating a plurality of customers of the communication network into a plurality of communication network customer segments in accordance with at least one factor;
generating a plurality of predicted customer order weights by communication network customer segment for a first network resource type in accordance with at least a first forecasting model comprising at least a first gradient boosted machine, wherein the first network resource type comprises: a hardware network element type, a network path type, a virtual network element type for a virtual network element hosted via one or more hardware network elements, a service type for a service hosted via the one or more hardware network elements, or an interface port type;
calculating a plurality of inventory demand weights for a plurality of network resources of the first network resource type in the communication network in accordance with at least a second forecasting model comprising at least a second gradient boosted machine;
obtaining a new customer order for the first network resource type from a first customer of the communication network; and
configuring the communication network to process data traffic of the first customer via one of the plurality of network resources of the first network resource type that is selected based upon a customer segment of the first customer and an allocation matching scheme in accordance with the plurality of predicted customer order weights by communication network customer segment and the plurality of inventory demand weights, wherein the configuring comprises configuring a provider edge network component in conjunction with a customer edge network component to process the data traffic of the first customer via the one of the plurality of network resources of the first network resource type that is selected.
16 . An apparatus comprising:
a processing system including at least one processor; and
a computer-readable medium storing instructions which, when executed by the processing system when deployed in a communication network, cause the processing system to perform operations, the operations comprising:
segregating a plurality of customers of the communication network into a plurality of communication network customer segments in accordance with at least one factor;
generating a plurality of predicted customer order weights by communication network customer segment for a first network resource type in accordance with at least a first forecasting model comprising at least a first gradient boosted machine, wherein the first network resource type comprises: a hardware network element type, a network path type, a virtual network element type for a virtual network element hosted via one or more hardware network elements, a service type for a service hosted via the one or more hardware network elements, or an interface port type;
calculating a plurality of inventory demand weights for a plurality of network resources of the first network resource type in the communication network in accordance with at least a second forecasting model comprising at least a second gradient boosted machine;
obtaining a new customer order for the first network resource type from a first customer of the communication network; and
configuring the communication network to process data traffic of the first customer via one of the plurality of network resources of the first network resource type that is selected based upon a customer segment of the first customer and an allocation matching scheme in accordance with the plurality of predicted customer order weights by communication network customer segment and the plurality of inventory demand weights, wherein the configuring comprises configuring a provider edge network component in conjunction with a customer edge network component to process the data traffic of the first customer via the one of the plurality of network resources of the first network resource type that is selected.
17 . The apparatus of claim 16 , wherein the segregating comprises segregating the plurality of customers by customer intensity values.
18 . The apparatus of claim 17 , wherein each customer intensity value of the customer intensity values is calculated based upon counts of a number of network services utilized by a respective customer.
19 . The apparatus of claim 17 , wherein the segregating comprises segregating the plurality of customers into the plurality of communication network customer segments in accordance with a distribution of values of the at least one factor associated with the plurality of customers.
20 . The apparatus of claim 16 , wherein the at least the first forecasting model is trained with a training data set comprising historical order data for at least a portion of the plurality of customers of the plurality of customer segments.