Distributed Artificial Intelligence Research Articles

Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance

Emerging Distributed AI systems are revolutionizing big data computing and data processing capabilities with growing economic and societal impact. However, recent studies have identified new attack surfaces and risks caused by security, privacy, and fairness issues in AI systems. In this paper, we review representative techniques, algorithms, and theoretical foundations for trustworthy distributed AI through robustness guarantee, privacy protection, and fairness awareness in distributed learning. We first provide a brief overview of alternative architectures for distributed learning, discuss inherent vulnerabilities for security, privacy, and fairness of AI algorithms in distributed learning, and analyze why these problems are present in distributed learning regardless of specific architectures. Then we provide a unique taxonomy of countermeasures for trustworthy distributed AI, covering (1) robustness to evasion attacks and irregular queries at inference, and robustness to poisoning attacks, Byzantine attacks, and irregular data distribution during training; (2) privacy protection during distributed learning and model inference at deployment; and (3) AI fairness and governance with respect to both data and models. We conclude with a discussion on open challenges and future research directions toward trustworthy distributed AI, such as the need for trustworthy AI policy guidelines, the AI responsibility-utility co-design, and incentives and compliance.

RevAP: A bankruptcy-based algorithm to solve the multi-agent credit assignment problem in task start threshold-based multi-agent systems

Multi-Agent Systems (MASs) are the prominent symbol of Distributed Artificial Intelligence (DAI). Learning in MAS, which is commonly based on Reinforcement Learning (RL), is one of the problems that play an essential role in unknown environments. In this study aimed at solving the Multi-agent Credit Assignment (MCA) problem, we introduce the Task Start Threshold (TST) of agents as a new constraint in a multi-score operational environment, transforming the MCA into a bankruptcy problem. In the following, considering the bankruptcy concept, a new base algorithm, which is called Reverse Adjusted Proportional (RevAP), is introduced. Based on this algorithm, three methods PTST, T-MAS, and T-KAg, were presented to solve the MCA with different strategies. The proposed methods were evaluated in terms of group learning rate, confidence, expertness, certainty, efficiency, correctness, and density in comparison to the state-of-the-art methods such as ranking methods, dynamic, history-based as knowledge-based methods, Counterfactual Multi-Agent Policy Gradient (COMA) as an example of policy-based methods, Value-Decomposition Network (VDN) as an example of value-based methods, and Shapley Q- value Deep Deterministic Policy Gradient (SQDDPG) as a game theory-based method. The results reveal the better performance of the proposed approach compared to the existing methods based on the majority of the parameters.

Driving into the future: a cross-cutting analysis of distributed artificial intelligence, CCAM and the platform economy

The future of driving is autonomous. It requires a comprehensive stack of embedded software components, enabled by open-source and proprietary platforms at different abstraction layers, and then operating within a larger ecosystem. Autonomous driving demands connectivity, cooperation and automation to form the cornerstone of autonomous mobility solutions. Platform economy principles have revolutionized the way we produce, deliver and consume products and services worldwide. More and more businesses in the field of mobility and transport appear to implement transaction, innovation, and integration platforms as core enablers for Mobility-as-a-Service and transport applications. Artificial intelligence approaches, especially those dealing with distributed systems, enable new mobility solutions, such as autonomous driving. This paper contributes to understanding the intertwining role between distributed artificial intelligence, autonomous mobility and the resulting platform ecosystem. A systematic literature review is applied, in order to identify the intersection between those aspects. Furthermore, the research project BeIntelli is considered as a hands-on application of our findings. Taking into account our analysis and the aforementioned research project, we pose a blueprint architecture for autonomous mobility. This architecture is the subject of further research. Our conclusions facilitate the development and implementation of future urban transportation systems and resulting mobility ecosystems in practice.

Distributed Artificial Intelligence Application in Agri-food Supply Chains 4.0

Supply Chain 4.0 is characterized by various factors, including seamless integration and connectivity, the Internet of Things (IoT), Big Data, AI participation, Cyber-Physical Systems (CPSs), flexibility, adaptability, and customer-centricity across different parts of the supply chain. The application of Distributed AI (DAI) systems like Multi-Agent Systems (MAS) opens new horizons to enhance the efficiency, responsiveness, and intelligence of these supply chains. DAI facilitates advanced autonomous decision-making and real-time optimization at different stages of the agri-food supply chain, such as demand forecasting, inventory management, production planning, logistics optimization, and quality assurance and control. This article, by focusing on the case of scheduling through the entire supply chain, examines how DAI initiatives, including Multi-Agent Systems (MASs) enhanced with Case-Based Reasoning (CBR), enable the distribution of intelligence across smart, interconnected elements of the supply chain network. It is shown that through the use of DAI in SCM, the performance of the entire supply chain optimizes consistently and adaptively through the use of MAS, in which different parts of SCM collaborate as agents. Supply Chain 4.0 can gain autonomy, self-organization, self-optimization, self-adaptation, robustness, and flexibility, and its knowledge base can be enriched over time by using CBR to learn from past situations. It also discusses the opportunities and challenges associated with the adoption of DAI in Supply Chain 4.0, including operational efficiency, cost reduction, agility enhancement, and improved customer satisfaction. However, several concerns, such as data security, privacy issues, and interoperability, must be addressed.

DISTRIBUTED ARTIFICIAL INTELLIGENCE MODELS IN PERSPECTIVE COMMUNICATION NETWORKS

6G technology will create an intelligent, highly scalable, dynamic and programmable wireless network capable of serving a variety of heterogeneous wireless devices. Various 6G modules and devices will generate colossal amounts of distributed data, so post-NGN (New Generation Networks) will need to implement a number of machine learning methods that will solve significantly complicated network problems. To overcome these problems, distributed learning methods can be used, allowing devices to train models jointly, without exchanging raw data, which reduces communication costs, delays, and increases data privacy level as well. Distributed machine learning models will play an important role in 6G networks, since they have a number of advantages over centralized methods, however, the implementation of distributed algorithms in resource-constrained wireless environments can be challenging. It is important to take into account the wireless environment uncertainty associated with various disturbing factors and limited wireless (transmission power, radio frequency spectrum) and hardware resources (computing power). Consequently, it is important to choose the suitable machine learning algorithm based on the wireless environment characteristics and the resource requirements of the learning process. The article reviews the application of distributed artificial intelligence models in new generation communication networks for resource management and data processing purposes. The general algorithms and approaches of distributed machine learning, applications, methods and models are described. The article analyzes the ways in which distributed artificial intelligence models can solve various problems in communication networks, including optimizing resource use and ensuring high performance and availability of network services.

Self-Organizing Democratized Learning: Toward Large-Scale Distributed Learning Systems.

Emerging cross-device artificial intelligence (AI) applications require a transition from conventional centralized learning systems toward large-scale distributed AI systems that can collaboratively perform complex learning tasks. In this regard, democratized learning (Dem-AI) lays out a holistic philosophy with underlying principles for building large-scale distributed and democratized machine learning systems. The outlined principles are meant to study a generalization in distributed learning systems that go beyond existing mechanisms such as federated learning (FL). Moreover, such learning systems rely on hierarchical self-organization of well-connected distributed learning agents who have limited and highly personalized data and can evolve and regulate themselves based on the underlying duality of specialized and generalized processes. Inspired by Dem-AI philosophy, a novel distributed learning approach is proposed in this article. The approach consists of a self-organizing hierarchical structuring mechanism based on agglomerative clustering, hierarchical generalization, and corresponding learning mechanism. Subsequently, hierarchical generalized learning problems in recursive forms are formulated and shown to be approximately solved using the solutions of distributed personalized learning problems and hierarchical update mechanisms. To that end, a distributed learning algorithm, namely DemLearn, is proposed. Extensive experiments on benchmark MNIST, Fashion-MNIST, FE-MNIST, and CIFAR-10 datasets show that the proposed algorithm demonstrates better results in the generalization performance of learning models in agents compared to the conventional FL algorithms. The detailed analysis provides useful observations to further handle both the generalization and specialization performance of the learning models in Dem-AI systems.

Distributed artificial intelligence: Taxonomy, review, framework, and reference architecture

Artificial intelligence (AI) research and market have grown rapidly in the last few years, and this trend is expected to continue with many potential advancements and innovations in this field. One of the emerging AI research directions is Distributed Artificial Intelligence (DAI). It has been motivated by technological advances in communication, networking, and hardware, together with the nature of data being generated from connected, distributed, and diverse objects. DAI is expected to create a fertile environment for innovative, advanced, robust, and scalable approaches for AI supporting the vision of smart societies. In this paper, we explore state of the art on DAI and identify the opportunities and challenges of provisioning distributed AI as a service (DAIaaS). We provide a taxonomy and a comprehensive review covering the literature from 2016 to 2022. It comprises various aspects of DAI, including AI workflow, distribution paradigms, supporting infrastructure, management techniques, and applications. Based on the gained insights from the conducted review, we propose Imtidad, a framework for provisioning DAIaaS over the cloud, fog, and edge layers. We refine this framework and propose the Imtidad software Reference Architecture (RA) for designing and deploying DAI services. In addition, we extended the framework and developed a future networking infrastructure transformation framework, as it is one of the main enablers for DAI. This framework and RA can be used as guidance facilitating the transition to the future DAI, where DAI is decoupled from the design and development of smart applications. This paper, including the proposed framework, RA, taxonomy, and detailed review, is expected to have an extensive impact on DAI research and accelerate innovations in this area.

DAIS Project - Distributed Artificial Intelligence Systems

DAIS is a step forward in the area of artificial intelligence and edge computing. DAIS intends to create a complete framework for self-organizing, energy efficient and private-by-design distributed AI. DAIS is a European project with a consortium of 47 partners from 11 countries coordinated by RISE Research Institute of Sweden.

Distributed Artificial Intelligence Empowered by End-Edge-Cloud Computing: A Survey

As the computing paradigm shifts from cloud computing to end-edge-cloud computing, it also supports artificial intelligence evolving from a centralized manner to a distributed one. In this paper, we provide a comprehensive survey on the distributed artificial intelligence (DAI) empowered by end-edge-cloud computing (EECC), where the heterogeneous capabilities of on-device computing, edge computing, and cloud computing are orchestrated to satisfy the diverse requirements raised by resource-intensive and distributed AI computation. Particularly, we first introduce several mainstream computing paradigms and the benefits of the EECC paradigm in supporting distributed AI, as well as the fundamental technologies for distributed AI. We then derive a holistic taxonomy for the state-of-the-art optimization technologies that are empowered by EECC to boost distributed training and inference, respectively. After that, we point out security and privacy threats in DAI-EECC architecture and review the benefits and shortcomings of each enabling defense technology in accordance with the threats. Finally, we present some promising applications enabled by DAI-EECC and highlight several research challenges and open issues toward immersive performance acquisition.

SmartVM: A Smart Contract Virtual Machine for Fast On-Chain DNN Computations

Blockchain-based artificial intelligence (BC-AI) has been applied for protecting deep neural network (DNN) data from being tampered with, which is expected to further boost trusted distributed AI applications in many fields. However, due to smart contract execution environment architectural defects, it is challenging for previous BC-AI systems to support computing-intensive tasks on-chain performing such as DNN convolution operations. They have to offload computations and a large amount of data from blockchain to off-chain platforms to execute smart contracts as native code. This failure to take advantage of data locality has become one of the major critical performance bottlenecks in BC-AI system. To this end, in this article, we propose SmartVM with optimization methods to support on-chain DNN inference for BC-AI system. The key idea is to design and optimize the computing mechanism and storage structure of smart contract execution environment according to the characteristics of DNN such as high computational parallelism and large data volume. We decompose SmartVM into three components: 1) a compact DNN-oriented instruction set to describe computations in a short number of instructions to reduce interpretation time. 2) a memory management mechanism to make SmartVM memory dynamic free/allocated according to the size of DNN feature maps. 3) a block-based weight prefetching and parallel computing method to organize each layer's computing and weights prefetching in a pipelined manner. We perform the typical image classification in a private Ethereum blockchain testbed to evaluate SmartVM performance. Experimental results highlight that SmartVM can support DNN inference on-chain with roughly the same efficiency against the native code execution. Compared with the traditional off-chain computing, SmartVM can speed up the overall execution by <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">70×</b> , <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">16×</b> , <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11×</b> , and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">12×</b> over LeNet5, AlexNet, ResNet18, and MobileNet, respectively. The memory footprint can be reduced by <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">84%</b> , <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">90.8%</b> , <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">94.3%</b> , and <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">93.7%</b> over the above four models, while offering the same level model accuracy. This article sheds light on the design space of the smart contract virtual machine for DNN computation and is promising to further boost BC-AI applications.

Boundary consensus control strategies for fractional-order multi-agent systems with reaction-diffusion terms

Multi-agent systems (MASs), as an essential research topic of distributed artificial intelligence, mainly refer to the coordination behavior among the agents to achieve a global goal. The issue dealing with the security threats of the oil and gas industry has always attracted the attention of numerous researchers. Meanwhile, MASs play a significant role in the security and defense of oil pipelines. This paper mainly studies the spatial boundary control for consensus of fractional-order MASs with reaction–diffusion term. First of all, two kinds of consensus boundary control methods are studied in fractional-order MASs, both based on Neumann boundary conditions. Furthermore, by employing fractional-order inequalities, consensus criteria of the MASs are presented in terms of LMIs. Finally, two numerical examples in the multi-agent simulation environment indicate the effectiveness of the proposed theoretical results.

Reasoning and interaction for social artificial intelligence

Current work on multi-agent systems at King’s College London is extensive, though largely based in two research groups within the Department of Informatics: the Distributed Artificial Intelligence (DAI) thematic group and the Reasoning &amp; Planning (RAP) thematic group. DAI combines AI expertise with political and economic theories and data, to explore social and technological contexts of interacting intelligent entities. It develops computational models for analysing social, political and economic phenomena to improve the effectiveness and fairness of policies and regulations, and combines intelligent agent systems, software engineering, norms, trust and reputation, agent-based simulation, communication and provenance of data, knowledge engineering, crowd computing and semantic technologies, and algorithmic game theory and computational social choice, to address problems arising in autonomous systems, financial markets, privacy and security, urban living and health. RAP conducts research in symbolic models for reasoning involving argumentation, knowledge representation, planning, and other related areas, including development of logical models of argumentation-based reasoning and decision-making, and their usage for explainable AI and integration of machine and human reasoning, as well as combining planning and argumentation methodologies for strategic argumentation.

A novel Distributed AI framework with ML for D2D communication in 5G/6G networks

Inspired by the adoption of Artificial Intelligence (AI) and Machine Learning (ML) approaches in 5G and 6G networks, in this paper we propose a novel ML based Distributed AI (DAI) framework able to attain the ambitious goals set for emerging 5G/6G networks. The novelty of the DAI framework is that it is implemented in an autonomous, dynamic and flexible fashion, utilising Belief Desire Intention (BDI) agents, extended with ML capabilities, which reside on the mobile devices (User Equipment). We refer to these as BDIx agents. This provides a component-based framework (likened to LEGO-based building blocks), which can build on and utilise execution plans, by composing and arranging ML techniques in flexible ways within the framework, in order to achieve the desired goals. More specifically, we form a modular BDIx agent at a multi-agent system (MAS), integrated with Fuzzy Logic for the perception/cognitive part of the agents. By exploiting the capabilities of the BDIx agents in our DAI framework, we allow mobile devices to intercommunicate and cooperate in an autonomous manner, thus offering a number of attractive features, including improved performance in terms of network control execution time and message exchange, fast response in handling dynamic aspects in the network, self-organising network functionalities, and a framework that can act as the glue platform in employing one or more intelligent approaches to tackle the diverse 5G/6G technical requirements. To demonstrate the potential of the DAI framework we focus on Device to Device (D2D) communication and illustrate its flexibility in addressing diverse D2D challenges. Through example Plan Libraries and enhanced metrics, we outline DAI implementation specifics to achieve a number of identified 5G/6G D2D requirements. To embed the concept further, the specific problem of D2D transmission mode selection is expanded upon, from problem description to solution approach (DAIS) and implementation specifics, and hence comparatively evaluate over other approaches (i.e., Unsupervised learning ML techniques, centralised control techniques, random techniques). The results demonstrated that DAIS provides, among other performance metrics, improved mobile network Spectral Efficiency (SE) and Power Consumption (PC), better and more efficient cluster formation and reduced control decision delay.

Swarm learning for decentralized artificial intelligence in cancer histopathology

Artificial intelligence (AI) can predict the presence of molecular alterations directly from routine histopathology slides. However, training robust AI systems requires large datasets for which data collection faces practical, ethical and legal obstacles. These obstacles could be overcome with swarm learning (SL), in which partners jointly train AI models while avoiding data transfer and monopolistic data governance. Here, we demonstrate the successful use of SL in large, multicentric datasets of gigapixel histopathology images from over 5,000 patients. We show that AI models trained using SL can predict BRAF mutational status and microsatellite instability directly from hematoxylin and eosin (H&E)-stained pathology slides of colorectal cancer. We trained AI models on three patient cohorts from Northern Ireland, Germany and the United States, and validated the prediction performance in two independent datasets from the United Kingdom. Our data show that SL-trained AI models outperform most locally trained models, and perform on par with models that are trained on the merged datasets. In addition, we show that SL-based AI models are data efficient. In the future, SL can be used to train distributed AI models for any histopathology image analysis task, eliminating the need for data transfer.

A distributed AI/ML framework for D2D Transmission Mode Selection in 5G and beyond

In this paper we build on the Distributed Artificial Intelligence (DAI) Framework, which makes use of Belief-Desire-Intention extended (BDIx) agents residing on Device-to-Device (D2D) Mobile Devices in order to establish D2D communication in an efficient, distributed, autonomous and flexible way. To demonstrate the potentials of this framework, in this work we focus on D2D Transmission Mode Selection in 5G. Specifically, we build on our previous work and develop an enhanced version of DAIS, a specific plan executed by the BDIx agents, for selecting the D2D Transmission mode that the D2D Devices will operate, aiming to offer improved Spectral Efficiency (SE) and Power Consumption (PC). To set a benchmark and allow for a fairer comparison we also enhance the Distributed Sum Rate (DSR), a distributed algorithmic approach that focuses on maximising the aggregated data rate of all the links established in the network, with similar functionality as DAIS. Furthermore, an extensive comparative evaluation of the enhanced DAIS and DSR with a number of unsupervised ML clustering approaches adapted for D2D Communication(i.e., GMEANS, Fuzzy ART, MEC, and DBSCAN) is provided. Specifically, for each approach the following have been collected and compared: QoE and QoS Fairness, SE and PC achieved, efficiency of clusters created, signalling overhead caused (i.e., volume of messages exchanged), time execution delay, D2D Effectiveness, D2D Stability and D2D Productivity. Based on the insight gained into the performance of the enhanced DAIS, DSR and the unsupervised ML techniques, we discuss performance gain trade-offs in terms of SE and PC versus signalling overhead and control delay in responding to changes.

Coordinate-based efficient indexing mechanism for intelligent IoT systems in heterogeneous edge computing

Powered by edge servers (also called as edge nodes) which are close to the data source, distributed edge AI processes the huge amounts of data generated by Internet of Things (IoT) devices, extracting value for users. In edge computing, massive data are stored in several distributed edge nodes with heterogeneous capabilities. Intelligent applications running on one edge node may need data from other edge nodes. An efficient data indexing mechanism can rapidly locate the edge node where the data is kept, supporting latency-sensitive intelligent applications. The existing indexing methods in edge computing assume that all edge nodes are the same in capability and the number of edge nodes is constant. This paper proposes CREIM, a coordinate-based efficient indexing mechanism for intelligent IoT systems in heterogeneous edge computing. CREIM achieves fair load balancing on edge nodes with heterogeneous capabilities. The indexing mechanism deals well with the horizontal scaling of edge nodes. Besides, CREIM addresses a fast lookup with one overlay hop, providing low latency data retrieval for edge intelligent applications. In the experiments, CREIM is applied in a realistic network simulated by the mininet and the routing forwarding is supported by the P4 switch. The experiments are constructed by combining real location datasets of Shanghai Telecoms base stations with the real-collected requests of end-devices. The experimental results demonstrate that CREIM achieves a near-optimal latency of index-lookup, adapts the heterogeneous capabilities among edge nodes and reduces the cost of increasing/decreasing edge nodes by 56.36% compared with the state-of-the-art method.

AI Based Energy Efficient Routing Protocol for Intelligent Transportation System

The future advancement of technology in Internet of Things (IoT) paradigm, Wireless Sensor Networks (WSNs) provide sensing services to connect all the devices. In the upper layer of OSI model designing an energy efficient routing protocol in WSN is a challenge, which can ease the work of Multi-access edge computing (MEC) in IoT applications. The advent of 6G is also playing key role for reliable communication between the sensing elements for IoT applications. These two phenomena are significantly influencing for the progress of next generation Intelligent Transportation System (ITS). Therefore, the proposed work presents a novel method of implementing Distributed Artificial Intelligence (DAI) with neural networks for energy efficient routing as well as a fast response for intra-cluster communication of the nodes to overcome the challenges for ITS. Although there exist several works on the inter-cluster energy-efficient network, our work proposes a new way of implementing the hybrid approach of DAI and Self Organizing Map (SOM). The proposed approach proves to be a better solution in terms of overall energy consumption by the network, along with the computational challenges. Further, the work presents mathematical analysis, simulation results and comparison with the conventional techniques for justification.

Paving the Way for Distributed Artificial Intelligence Over the Air

Distributed Artificial Intelligence (DAI) is one of the most promising techniques to provide intelligent services under strict privacy protection regulations for multiple clients. By applying DAI, training on raw data is carried out locally. At the same time, the trained outputs, e.g., model parameters from multiple local clients, are sent back to a central server for aggregation. DAI is recently studied in conjunction with wireless communication networks to achieve better practicality, incorporating various random effects brought by wireless channels. However, because of wireless channels&#x2019; complex and case-dependent nature, a generic simulator for applying DAI in wireless communication networks is still lacking. To accelerate the development of DAI in wireless communication networks, we propose a generic system design in this paper and an associated simulator that can be set according to wireless channels and system-level configurations. Details of the system design and analysis of the impacts of wireless environments are provided to facilitate further implementations and updates. We employ a series of experiments to verify the effectiveness and efficiency of the proposed system design and reveal its superior scalability.

A Survey on Trusted Distributed Artificial Intelligence

Emerging Artificial Intelligence (AI) systems are revolutionizing computing and data processing approaches with their strong impact on society. Data is processed with automated labelling pipelines rather than providing it as input to the system. The innovative nature increases the overall performance of monitoring/detection/reaction mechanisms for efficient system resource management. However, due to hardware-driven design limitations, networking and trust mechanisms are not flexible and adaptive enough to be able to interact and control the resources dynamically. Novel adaptive software-driven design approaches can enable us to build growing intelligent mechanisms with software-defined networking (SDN) features by virtualizing network functionalities with maximized features. These challenges and critical feature sets have been identified and introduced into this survey with their scientific background for AI systems and growing intelligent mechanisms. Furthermore, obstacles and research challenges between 1950-2021 are explored and discussed with a focus on recent years. The challenges are categorized according to three defined architectural perspectives (central, decentral/autonomous, distributed/hybrid) for emerging trusted distributed AI mechanisms. Therefore, resiliency and robustness can be assured in a dynamic context with an end-to-end Trusted Execution Environment (TEE) for growing intelligent mechanisms and systems. Furthermore, as presented in the paper, the trust measurement, quantification, and justification methodologies on top of Trusted Distributed AI (TDAI) can be applied in emerging distributed systems and their underlying diverse application domains, which will be explored and experimented in our future related works.

Distributed Artificial Intelligence Empowered Sustainable Cognitive Radio Sensor Networks: A Smart City on-demand Perspective

Smart cities are claimed to be smart if the new technologies are capable of providing desired sustainable outcome. The sustainable properties of smart city applications require less energy consumption and efficient resource allocation. The Internet-of-Things (IoT), 5G, and fog networks have emerged as the most crucial researched areas due to their numerous applications for smart cities to provide the desired sustainable outcome. The sustainable properties of Wireless Sensor Networks (WSNs) play a vital role in the deployment of these technologies into the physical world and efficient utilization of the available spectrum is a major problem faced here. As a potential solution of this, Cognitive Radio (CR) merged with WSN as Cognitive Radio Sensor Networks (CRSNs) make the smart perspective with high resource management through cooperative communication. The proposed work establishes a dynamic correlation between Secondary Users/nodes (SUs) in a single cluster according to their statistical behavior at the time of performing smart cooperative communication in CRSNs to improve sustainability of smart world IoT applications. Distributed Artificial Intelligence (DAI) is used to calculate the real-time resource allocation to these clusters using their respective Coordinator Agent (CoA) based on the dynamic behaviors. To improve sustainability in the smart city applications, the time delay in the prediction of vacant channels is reduced which results in making these applications become more energy efficient. The effectiveness of the proposed work is illustrated with mathematical analysis and simulation results confirm its better sustainable performance compared to the existing techniques.