Neuromorphic Edge Server Allocation for Fast Low-Energy EUA

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current techniques for determining edge user allocation (EUA) in cellular networks are suboptimal, slow, and energy-consuming, particularly in dynamic environments with mobile devices, and do not scale well with increased problem sizes.

Innovation Solution

A neuromorphic computing approach using a neural network architecture with winner-take-all neuronal groups and threshold neurons to optimize edge server allocation, employing excitatory and inhibitory signals to efficiently allocate mobile devices to edge servers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If heuristic algorithms are used to solve the EUA problem, then the solution can be found, but the computation is slow and consumes excess energy

Engineering Contradiction:

Improvecomputational throughputVSAvoidenergy consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent replaces traditional computational algorithms (heuristic, quantum, simulated annealing) with a neuromorphic computing system that uses biological-inspired neurons and synapses to solve the EUA problem. This substitution of computational mechanics with neurobiological mechanisms enables parallel processing and energy-efficient optimization, directly addressing the contradiction between computational throughput and energy consumption.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the fundamental parameters of computation by transitioning from digital binary states to continuous neuronal membrane potentials and synaptic weights. This parameter transformation allows the system to process multiple allocation possibilities simultaneously through analog computation, improving productivity while reducing energy consumption compared to traditional discrete algorithms.

Inventive Principle:

Principle #35Parameter changes

2Loss of time

If quantum techniques are used to accelerate solution time, then the time to reaching a solution is reduced, but the approach remains energy expensive

Engineering Contradiction:

Improvesolution timeVSAvoidenergy consumption

Core Design Contradiction:

Loss of timeVSUse of energy by moving object

Solution Approach 1:

The patent substitutes quantum computational mechanics with neuromorphic computational mechanics. Instead of using quantum superposition and entanglement to explore solution spaces, the system uses parallel neuronal activation and inhibition mechanisms that achieve similar optimization results with lower energy requirements, addressing both solution time and energy consumption concerns.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If traditional algorithms are used for EUA, then the allocation can be determined, but the techniques do not scale well with the size of the problem

Engineering Contradiction:

Improveallocation efficiencyVSAvoidproblem size scalability

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the EUA problem into independent neuronal processing units, where each neuron handles a specific allocation decision. This segmentation allows the system to scale horizontally by adding more neurons for larger problems, maintaining allocation efficiency while improving scalability compared to traditional algorithms that must process the entire problem as a single computational task.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces dynamic adaptability through learning mechanisms that adjust synaptic weights based on allocation outcomes. This dynamic behavior allows the system to optimize its performance for different problem sizes and characteristics, improving scalability by adapting to increasing complexity rather than being constrained by fixed algorithmic complexity.

Inventive Principle:

Principle #15Dynamics

4Productivity

If heuristic algorithms are used for EUA, then a solution can be obtained, but the solution is suboptimal

Engineering Contradiction:

Improvecomputational throughputVSAvoidallocation optimization quality

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent implements feedback mechanisms through inhibitory synapses that provide negative feedback when allocation constraints are violated or when better solutions exist. This feedback loop enables the system to iteratively refine allocations and converge to optimal solutions, overcoming the suboptimality of heuristic approaches while maintaining high computational throughput through parallel processing.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20250378316A1Neuromorphic method to optimize user allocation to edge servers

Publication Date: 2025.12.11 TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

AI summary

A method is performed by an electronic device for performing edge user allocation. The method includes selecting a first edge server to connect with a first mobile device. Neurons are arranged as a plurality of winner-take-all neuronal groups, each corresponding to a respective mobile device and comprising a respective first set of neurons representing a plurality of edge servers. Activating a first neuron causes an excitatory signal to be transmitted on a first synapse to a first threshold neuron. Each threshold neuron comprises a plurality of inputs connected by respective first synapses to a respective second set of those neurons of the first sets that correspond to a respective edge server. Each first synapse has a respective weight corresponding to a resource requirement of the mobile device. Activation of the first threshold neuron causes inhibitory signal(s) to be transmitted to at least one other neuron of the respective second set.