Opportunity
The rapid growth of mobile communication demands, particularly with the advent of 5G technology, has led to an explosion in the number of connected devices and data transmission volumes. A significant challenge arises in indoor environments, where approximately 80% of data traffic occurs. High-frequency 5G signals suffer from severe attenuation over distance and poor penetration through building materials, making it difficult for outdoor base station antennas to provide high-quality, comprehensive coverage indoors. Signal coverage varies drastically between scenarios; while it can reach 90% on outdoor urban roads, it often falls below 60% in many indoor settings and can drop to less than 50% in confined spaces like underground parking lots and elevators. Consequently, ensuring reliable wireless signal coverage indoors is a critical step toward achieving ubiquitous 5G connectivity. Existing network planning tools primarily focus on outdoor base station distribution and lack specialized solutions for optimizing the complex topology of Indoor Distributed Antenna Systems (IB-DAS), which are essential for effective indoor signal distribution.
Technology
This patent presents a novel topology design method for Indoor Distributed Antenna Systems (IB-DAS) to address multi-objective optimization challenges, such as simultaneously minimizing construction cost and average power loss. The core innovation is a Tree-Encoded Evolutionary Algorithm (TEA). The method encodes the inter-floor network structure of an IB-DAS as a spanning tree, where the root connects to the signal source, non-leaf nodes represent power devices (e.g., splitters, couplers), and leaf nodes represent building floors. This tree encoding ensures locality and facilitates the generation of valid network structures. The process begins by acquiring building parameters, device parameters, and signal source information. An initial parent population of N network structures (individuals) is generated. N weight vectors and their neighborhoods are established, with each vector associated with a parent individual. Specialized crossover and mutation operators, designed specifically for the tree encoding, are then applied to the parent population based on these weight vectors and neighborhoods to produce a child population. The performance of each individual (both parent and child) is evaluated using selection indicators, typically based on objectives like construction cost and average power loss. An environmental selection strategy updates the parent population by replacing individuals in a weight vector's neighborhood with superior child individuals. This iterative process of crossover, mutation, and selection continues until a set of Pareto-optimal target inter-floor network structures is obtained, providing multiple optimal trade-off solutions for decision-makers.
Advantages
- Provides a set of Pareto-optimal solutions, offering multiple optimal trade-off plans between conflicting objectives like cost and performance in a single algorithm run.
- Employs a novel tree encoding for network representation, which ensures good locality (small changes in code lead to small changes in the network) and guarantees the generation of valid network structures.
- Introduces problem-specific crossover and mutation operators capable of effectively generating and evolving tree-encoded solutions, which standard evolutionary operators cannot handle.
- Enables efficient multi-objective optimization for the NP-hard problem of IB-DAS topology design, finding high-quality solutions within reasonable computational budgets.
- Outperforms existing methods like Prufer-string or binary-string encoded evolutionary algorithms in terms of solution quality (e.g., lower cost and power loss).
- Better meets practical engineering requirements by allowing planners and contractors to choose from a variety of optimized network blueprints.
Applications
- Planning and deployment of 5G Indoor Distributed Antenna Systems (IB-DAS) in office buildings, shopping malls, hospitals, airports, and stadiums.
- Network infrastructure optimization for mobile network operators and telecommunications equipment providers.
- Design tools for engineering firms specializing in in-building wireless coverage solutions.
- Retrofitting existing buildings with enhanced indoor mobile connectivity for 4G/LTE and future 6G networks.
- Research and development in the field of multi-objective optimization for communication network design.
