Date of Award


Degree Name

Doctor of Philosophy


Computer Science

First Advisor

Ala Al-Fuqaha, Ph.D.

Second Advisor

Ajay Gupta, Ph.D.

Third Advisor

Alvis Fong, Ph.D.

Fourth Advisor

Mohammad Salahuddin, Ph.D.


Federated learning, internet of things, security, smart city, topic switching, vehicular data broker


The widespread use of smart devices has led to the Internet of Things (IoT) revolution. Big data generated by billions of devices must be analyzed to make better decisions. However, this introduces security, communication, and processing problems. To solve these problems, we develop algorithms to enhance the work of brokers. We focus our efforts on three problems.

In the first problem, brokers are used in the cloud along with Software Defined Network (SDN) switches. We formulate minimizing brokers’ load difference within a reconfiguration budget with the constraint of indivisible topics as an Integer Linear Programming (ILP) problem. We show that the problem is NP-Hard and propose a heuristic driven by longterm statistics of topics. The proposed heuristic is evaluated with realistic simulation traffic traces and compared against a threshold-based baseline heuristic driven by instantaneous statistics of topics. Results show that the proposed heuristic performs up to 2000% better load distribution than the baseline heuristic and at least 27% less topic switching.

In the second problem, we used vehicles as data brokers for exchanging data between smart devices and service providers in the cloud. We propose an opportunistic algorithm that strives to select vehicles in order to maximize Local Community Broker’s (LCB) service time. The proposed opportunistic algorithm utilizes an ensemble of online selection algorithms by running all of them together in passive mode and selecting the one that has performed the best in recent history. The data set used in the proposed algorithm is evaluated using real taxi traces from the city of Shanghai in China and compared against a baseline of 9 Threshold Based Online (TBO) algorithms. A number of experiments are conducted and results indicate that the proposed algorithm achieves up to 87% more service time with up to 10% fewer vehicle selections compared to the best performing TBO algorithm.

In the third problem, we used a broker (server) to implement a proposed Federated Learning (FL) algorithm that tackle security, communication, and accuracy problems. The proposed algorithm groups clients randomly in many clusters, each with a model selected randomly to explore the performance of different models. The clusters are then trained in a repetitive process where the worst performing cluster is removed in each iteration until one cluster remains. In each iteration, some clients are expelled from clusters either due to using poisoned data or low performance. The surviving clients are exploited in the next iteration. The remaining cluster with surviving clients is then used for training the best FL model (i.e., remaining FL model). Communication cost is reduced since fewer clients are used in the final training of the FL model. To evaluate the performance of the proposed algorithm, we conduct a number of experiments using FMNIST dataset and compare the result against the random FL algorithm. The experimental results show that the proposed algorithm outperforms the baseline algorithm in terms of accuracy, communication cost, and security.

Access Setting

Dissertation-Open Access