Unmanned aerial vehicle (UAV) has been considered a promising technology for advancing terrestrial mobile computing in the dynamic environment. In this research field, throughput, the number of completed tasks and latency are critical evaluation indicators used to measure the efficiency of UAVs in existing studies. In this paper, we transform these metrics to a single optimization objective, i.e., throughput maximization. To maximize the throughput, we consider realizing this goal in two respects. The first is to adapt the formation of the UAVs to provide cooperative computing service in a dynamic environment, we integrate a policy-based gradient algorithm and the task factorization network as a new reinforcement learning algorithm to improve the cooperation of UAVs. The second is to optimize the association process between UAVs and users, where the heterogeneity of tasks is considered. This algorithm is modified from the Gale-Shapley stability concept to optimize the appropriate association between tasks and UAVs in a dynamic time-varying condition to get the near-optimal association with few iterations. The scheduling of dependent tasks and independent tasks jointly also has to be considered. Finally, simulation results demonstrate the improvement of cooperation performance and the practicability of the association process.

Estimating traffic demand, or origin-destination (OD) matrices, is crucial for transport studies and smart city development. The main objective is to calculate an OD matrix based on available sources (e.g. link traffic counts obtained from traffic sensors) to accurately reproduce field data. A significant complication when using information obtained from traffic sensors, is that such sensors are subject to considerable disruptions impacting data quality and reliability. Despite the extensive study of efficient OD estimation, there is a considerable gap in detecting faulty measurements and identifying faulty sensors within the estimation procedure. This work presents a novel methodology for OD matrix estimation in the presence of faulty measurements. The path-based cell transmission model (CTM) is employed to capture traffic network dynamics within a specified time window, linking link densities with per-path densities and path demand. For the purposes of this work, traffic networks that operate under free-flow conditions are considered and the problem is formulated in an optimisation framework with two distinct variations: 1) no explicit formulation of potential faulty sensors and 2) explicit modelling of potential faulty sensors. Following, a fault-adaptive algorithm is constructed that identifies, isolates and corrects faults to achieve robust demand estimation. The methodology is tested on two realistic literature networks and shows great potential in terms of OD matrix estimation in the presence of faulty measurements. Simulation results underpin the advantage of the proposed approach in terms of performance in estimating quantities of interest as well as identifying the faulty sensors and their fault characteristics.

The Forward-Forward (FF) Algorithm has been recently proposed to alleviate the issues of backpropagation (BP) commonly used to train deep neural networks. However, its current formulation exhibits limitations such as the generation of negative data, slower convergence, and inadequate performance on complex tasks. In this paper we take the main ideas of FF and improve them by leveraging channel-wise competitive learning in the context of convolutional neural networks for image classification tasks. A layer-wise loss function is introduced that promotes competitive learning and eliminates the need for negative data construction. To enhance both the learning of compositional features and feature space partitioning, a channel-wise feature separator and extractor block is proposed that complements the competitive learning process. Our method outperforms recent FF-based models on image classification tasks, achieving testing errors of 0.58%, 7.69%, 21.89%, and 48.77% on MNIST, Fashion-MNIST, CIFAR-10 and CIFAR-100 respectively. Our approach bridges the performance gap between FF learning and BP methods, indicating the potential of our proposed approach to learn useful representations in a layer-wise modular fashion, enabling more efficient and flexible learning. Our source code and supplementary material are available at https://github.com/andreaspapac/CwComp.

The origin-destination (OD) matrix is a crucial requirement for transportation management and planning. Efficient OD matrix estimation is important to enhance the advancement of intelligent transportation systems. We present a novel approach for the estimation of static OD matrices using within-day traffic flow dynamics. The signalised cell transmission model (CTM) is utilised to capture the dynamics of a specific network and associate road segment count observations with path demands. This model is extended to capture per-path densities, yielding a path-based OD matrix problem formulation that results in a nonlinear optimisation problem. Efficient solution methodologies, based on convex and nonconvex optimisation theory, are developed for free-flow and congested conditions, respectively. In contrast with the majority of research for the OD matrix estimation problem, this work offers the following advantages: 1) no prior or target OD matrices are needed to implement the approach outlasting the bias and dependency on such matrices, 2) no historical data are required for accurate estimations, 3) no route choice model or split ratios are needed, 4) no user equilibrium conditions are required for high-quality estimation, and 5) even low partial coverage of the network is sufficient to provide high-quality OD matrix estimation. We illustrate the efficiency of the proposed approach on three literature real-life arterial networks and show that the proposed approach yields accurate results under both free-flow and congested scenarios.

This paper introduces a Channel-wise Goodness Function (CWG) that enhances the Forward-Forward through the use of Convolutional Neural Networks.The CWG function facilitates simultaneous feature extraction and separation, eliminating the requirement for constructing negative data and leading to faster convergence rates.The approach employs a two-component loss function that maximizes positive goodness and minimizes negative goodness.This enables the model to learn class-specific features to outperform recent non-backpropagation approaches on basic image classification datasets and shorten the gap with the well-established backpropagation methods.

Traffic state estimation is a challenging task due to the collection of sparse and noisy measurements from specific points of the traffic network. The emergence of Connected and Automated Vehicles (CAVs) provides new capabilities for traffic state estimation using extended floating car data such as position, speed and spacing information. In this work we propose a Bayesian Traffic State Estimation (BTSE) methodology for estimating the traffic density based on extended floating car data. BTSE utilizes the Bayesian paradigm to express any prior information to derive probability distributions of the traffic density of different road segments of the traffic network. Two variations of the BTSE methodology are developed to handle the offline and online estimation problem. The BTSE methodology is evaluated both using realistic SUMO micro-simulations for M25 Highway, London, U.K., and a real-life vehicle-trajectory dataset from German highways, extracted from videos recorded by drones. The efficiency and accuracy of the BTSE methodology is compared to an existing methodology in the literature. We present results for the estimation performance of the methods showing that the Bayesian methodology consistently results in lower mean absolute percentage error than the compared literature method. The BTSE methodology yields high-quality estimation results even for a low penetration rate of CAVs (e.g. 5%).

Cooperative vehicle management emerges as a promising solution to improve road traffic safety and efficiency. This paper addresses the speed planning problem for connected and autonomous vehicles (CAVs) at an unsignalized intersection with consideration of turning maneuvers. The problem is approached by a hierarchical centralized coordination scheme that successively optimizes the crossing order and velocity trajectories of a group of vehicles so as to minimize their total energy consumption and travel time required to pass the intersection. For an accurate estimate of the energy consumption of each CAV, the vehicle modeling framework in this paper captures 1) friction losses that affect longitudinal vehicle dynamics, and 2) the powertrain of each CAV in line with a battery-electric architecture. It is shown that the underlying optimization problem subject to safety constraints for powertrain operation, cornering and collision avoidance, after convexification and relaxation in some aspects can be formulated as two second-order cone programs, which ensures a rapid solution search and a unique global optimum. Simulation case studies are provided showing the tightness of the convex relaxation bounds, the overall effectiveness of the proposed approach, and its advantages over a benchmark solution invoking the widely used first-in-first-out policy. The investigation of Pareto optimal solutions for the two objectives (travel time and energy consumption) highlights the importance of optimizing their trade-off, as small compromises in travel time could produce significant energy savings.

In this work, we propose a joint route guidance and demand management strategy for multi-region networks with macroscopic traffic dynamics. Route guidance is used to identify the optimal transfer flows between neighbouring regions so that the trip completion rate across all regions is maximized. Demand management is utilized to control the traffic flows entering the network by forcing a portion of the traffic flows to wait at their origin. Towards this direction, we develop a Model Predictive Control (MPC) framework that aims to minimize the total time spent by all vehicles in the network (including the waiting time at the origin) by jointly optimizing the demand flows allowed in the network and the transfer flows between regions. To solve the resulting nonconvex and nonlinear optimization problem, by relaxing the nonconvex constraints, we develop a novel Linear Programming formulation that provides tight lower bounds on the optimal solution, as well as a feasible solution through the proposed MPC framework. Furthermore, (in another formulation) we restrict each region to only operate in the free-flow regime of the macroscopic fundamental diagram, which enables the transformation of the problem to a linear MPC formulation which can be solved in real-time using standard solvers and which provides a feasible solution to the original MPC problem. Extensive simulation results demonstrate that the linear MPC schemes execute in real-time and yield near-optimal results even under heavy traffic scenarios.

Severa1 logistic companies started utilizing electric vehicles (EVs) in their daily operations to reduce greenhouse gas pollution. However, the limited driving range of EVs may require visits to recharging stations during their operation. These potential visits have to be addressed, avoiding unnecessary long detours. We formulate the electric capacitated vehicle routing problem (E-CVRP), which incorporates the possibility of EVs visiting a recharging station while satisfying the delivery demands of customers. The energy consumption of the EVs is proportional to their cargo load which is an important constraint in real-world logistics applications. A new set of benchmark instances is proposed for the E-CVRP. As solution methods to these new benchmarks, we apply the ant colony optimization metaheuristic method and an exact method. Experimental results on the ECVRP demonstrate the high complexity of the problem and the efficiency of the applied metaheuristic solution method.

Efficient traffic monitoring is playing a fundamental role in successfully tackling congestion in transportation networks. Congestion is strongly correlated with two measurable characteristics, the demand and the network density that impact the overall system behavior. At large, this system behavior is characterized through the fundamental diagram of a road segment, a region or the network. In this paper we devise an innovative way to obtain the fundamental diagram through aerial footage obtained from drone platforms. The derived methodology consists of 3 phases: vehicle detection, vehicle tracking and traffic state estimation. We elaborate on the algorithms developed for each of the 3 phases and demonstrate the applicability of the results in a real-world setting.

This paper studies interference exploitation techniques for secure beamforming design in simultaneous wireless information and power transfer in multiple-input single-output systems. In particular, multiuser interference (MUI) and artificially generated noise (AN) signals are designed as constructive to the information receivers (IRs) yet kept disruptive to potential eavesdropping by the energy receivers. The objective is to improve the received signal-to-interference and noise ratio (SINR) at the IRs by exploiting the MUI and AN power in an attempt to minimize the total transmit power. We first propose second-order cone programming-based solutions for the perfect channel state information (CSI) case by defining strong upper and lower bounds on the energy harvesting (EH) constraints. We then provide semidefinite programming-based solutions for the problems. In addition, we also solve the worst case harvested energy maximization problem under the proposed bounds. Finally, robust beamforming approaches based on the above are derived for the case of imperfect CSI. Our results demonstrate that the proposed constructive interference precoding schemes yield huge saving in transmit power over conventional interference management schemes. Most importantly, they show that, while the statistical constraints of conventional approaches may lead to instantaneous SINR as well as EH outages, the instantaneous constraints of our approaches guarantee both constraints at every symbol period.

In this paper, we investigate a problem associated with transferring a set of containers from the storage to the loading area of a warehouse using autonomous robots. In addition to assigning robots to containers, the special topology considered in this paper requires coordinated planning of the robots' movement to avoid conflicts. We formulate the joint problem of robot assignment and movement coordination with the objective of minimizing the time required for all robots to carry their assigned containers to the destination, subject to conflict-free movement of all robots. We use the concept of abstract time windows (ATWs) to represent the movement of robots. The conditions for detecting conflicts in the ATW representation are introduced along with the necessary operations for resolving conflicts. For the solution of the problem, two approaches are developed. The first is a mathematical programming approach that formulates the problem as a mixed-integer linear program that allows optimal solution using appropriate solvers, while the second is a heuristic approach that allows fast, close-to-optimal solutions. Even though the proposed approaches focus on the case where the number of robots is equal to the number of containers, we also discuss how to solve the problem when having unequal number of robots and containers. Simulation results show that the heuristic approach provides a solution within 5% of the optimal solution with the minimum time of completion of all tasks being the performance metric, and executes six orders of magnitude faster than a state-of-the-art mathematical programming solver.

Networks of smart cameras, equipped with on-board processing and communication infrastructure, are increasingly being deployed in a variety of different application fields, such as security and surveillance, traffic monitoring, industrial monitoring, and critical infrastructure protection. The task(s) that a network of smart cameras executes in these applications, e.g., activity monitoring and object identification, can be severely degraded due to errors in the detection module. However, in most cases, higher level tasks and decision making processes in smart camera networks (SCNs) assume ideal detection capabilities for the cameras, which is often not the case due to the probabilistic nature of the detection process, especially for low-cost cameras with limited capabilities. Realizing that it is necessary to introduce robustness in the decision process, this paper presents results toward uncertainty-aware SCNs. Specifically, we introduce a flexible uncertainty model that can be used to characterize the detection behavior in a camera network. We also show how to utilize the model to formulate detection-aware optimization algorithms that can be used to reconfigure the network in order to improve the overall detection efficiency and thus increase the effective number of detected targets. We evaluate our proposed model and algorithms using a network of Raspberry-Pi-based smart cameras that reconfigure in order to improve the detection performance based on the position of targets in the area. The experimental results in the laboratory as well as in a human monitoring application and extensive simulation results indicate that the proposed solutions are able to improve the robustness and reliability of SCNs.

Intelligent buildings are responsible for ensuring the indoor air quality for their occupants under normal operation as well as under possibly harmful contaminant events due to accidental or malicious actions. An emerging environmental control application is monitoring the intelligent buildings against the presence of such events, by incorporating various sensing technologies and distributed detection and isolation algorithms. The needed simplicity, the improved scalability and fault tolerance are some of the main reasons for choosing distributed approaches over centralized ones. Hence, the effective partitioning of buildings into smaller sections for contaminant detection and isolation approaches is of great importance. In this paper, we present an exact Mixed Integer Linear Programming (MILP) formulation for partitioning the building into smaller sections. The building is transformed into a graph which is partitioned into subgraphs indicating the groups of zones in each section while ensuring (i) maximum decoupling between the various subgraphs, (ii) strong connectivity between the zones of a subgraph and (iii) control of the number of allocated zones in each subgraph. The main contribution of this work is the automatic partitioning of the building into sections, which enables the distributed simulation, modeling, analysis and management of the intelligent building in real time, while ensuring the effective detection and isolation of contaminants in the building interior.

In this paper, we propose a power-efficient approach for information and energy transfer in multiple-input single-output downlink systems. By means of data-aided precoding, we exploit the constructive part of interference for both information decoding and wireless power transfer. Rather than suppressing interference as in conventional schemes, we take advantage of constructive interference among users, inherent in the downlink, as a source of both useful information signal energy and electrical wireless energy. Specifically, we propose a new precoding design that minimizes the transmit power while guaranteeing the quality of service (QoS) and energy harvesting constraints for generic phase shift keying modulated signals. The QoS constraints are modified to accommodate constructive interference, based on the constructive regions in the signal constellation. Although the resulting problem is nonconvex, several methods are developed for its solution. First, we derive necessary and sufficient conditions for the feasibility of the considered problem. Then we propose second-order cone programming and semi-definite programming algorithms with polynomial complexity that provide upper and lower bounds to the optimal solution and establish the asymptotic optimality of these algorithms when the modulation order and SINR threshold tend to infinity. A practical iterative algorithm is also proposed based on successive linear approximation of the nonconvex terms yielding excellent results. More complex algorithms are also proposed to provide tight upper and lower bounds for benchmarking purposes. Simulation results show significant power savings with the proposed data-aided precoding approach compared to the conventional precoding scheme.

In this paper we propose a power-efficient transfer of information and energy, where we exploit the constructive part of wireless interference as a source of green useful signal power. Rather than suppressing interference as in conventional schemes, we take advantage of constructive interference among users, inherent in the downlink, as a source of both useful information and wireless energy. Specifically, we propose a new precoding design that minimizes the transmit power while guaranteeing the quality of service (QoS) and energy harvesting constraints for generic phase shift keying modulated signals. The QoS constraints are modified to accommodate constructive interference. We derive a sub-optimal solution and a local optimum solution to the precoding optimization problem. The proposed precoding reduces the transmit power compared to conventional schemes, by adapting the constraints to accommodate constructive interference as a source of useful signal power. Our simulation results show significant power savings with the proposed data-aided precoding compared to the conventional precoding.

In non-orthogonal multiple access (NOMA) downlink, multiple data flows are superimposed in the power domain and user decoding is based on successive interference cancellation. NOMA's performance highly depends on the power split among the data flows and the associated power allocation (PA) problem. In this letter, we study NOMA from a fairness standpoint and we investigate PA techniques that ensure fairness for the downlink users under i) instantaneous channel state information (CSI) at the transmitter, and ii) average CSI. Although the formulated problems are non-convex, we have developed low-complexity polynomial algorithms that yield the optimal solution in both cases considered.

In this paper, we study the problem of resource allocation for a multiuser orthogonal frequency-division multiple access (OFDMA) downlink with eavesdropping. The considered setup consists of a base station, several users, and a single eavesdropper that intends to wiretap the transmitted message within each OFDMA subchannel. By taking into consideration the existence of the eavesdropper, the base station aims to assign subchannels and allocate the available power in order to optimize the max-min fairness criterion over the users' secrecy rate. The considered problem is a mixed integer nonlinear program. For a fixed subchannel assignment, the optimal power allocation is obtained by developing an algorithm of polynomial computational complexity. In the general case, the problem is investigated from two different perspectives due to its combinatorial nature. In the first, the number of users is equal or higher than the number of subchannels, whereas in the second, the number of users is less than the number of subchannels. In the first case, we provide the optimal solution in polynomial time by transforming the original problem into an assignment one for which there are polynomial time algorithms. In the second case, the secrecy rate formula is linearly approximated and the problem is transformed to a mixed integer linear program, which is solved by a branch-and-bound algorithm. Moreover, optimality is discussed for two particular cases where the available power tends to infinity and zero, respectively. Based on the resulting insights, three heuristic schemes of polynomial complexity are proposed, offering a better balance between performance and complexity. Simulation results demonstrate that each one of these schemes achieves its highest performance at a different power regime of the system.

Traffic signal control is a key ingredient in intelligent transportation systems to increase the capacity of existing urban transportation infrastructure. However, to achieve optimal system-wide operation, it is essential to coordinate traffic signals at various intersections. In this paper, we model the multiple-intersection traffic signal control problem using the cell transmission model as a mixed-integer linear program. The solution of the problem is facilitated by its special structure, which allows both temporal and spatial decomposition. Temporal decomposition is employed to reduce the problem size by solving subproblems of a smaller time window compared to the original problem. Temporal subproblems can be further spatially decomposed into subproblems associated with different intersections, which are jointly solved by exchanging messages between neighboring intersections. The proposed distributed solution strategy is comprised of two phases. First, the relaxed linear problem is reformulated and distributedly solved via the alternating direction method of multipliers. Second, two distributed rounding schemes are developed to solve the original problem. Simulation results indicate that the proposed solution strategy is scalable to large transportation topologies, which is suitable for online execution, and provides close-to-optimal results.

In this paper, we theoretically investigate a new technique for simultaneous information and power transfer (SWIPT) in multiple-input multiple-output (MIMO) point-to-point with radio frequency energy harvesting capabilities. The proposed technique exploits the spatial decomposition of the MIMO channel and uses the eigenchannels either to convey information or to transfer energy. In order to generalize our study, we consider channel estimation error in the decomposition process and the interference between the eigenchannels. An optimization problem that minimizes the total transmitted power subject to maximum power per eigenchannel, information and energy constraints is formulated as a mixed-integer nonlinear program and solved to optimality using mixed-integer second-order cone programming. A near-optimal mixed-integer linear programming solution is also developed with robust computational performance. A polynomial complexity algorithm is further proposed for the optimal solution of the problem when no maximum power per eigenchannel constraints are imposed. In addition, a low polynomial complexity algorithm is developed for the power allocation problem with a given eigenchannel assignment, as well as a low-complexity heuristic for solving the eigenchannel assignment problem.

In this paper, we investigate a new technique for simultaneous wireless information and energy transfer in multiple-input multiple-output relay channels. The proposed technique exploits the array configuration at the relay node and uses the antenna elements either for conventional decoding or for rectifying (rectennas). In order to keep the complexity low, a dynamic antenna switching between decoding/rectifying is proposed based on the principles of the generalized selection combiner (GSC); the L strongest paths are allocated for decoding while the remaining channel paths for rectifying (and vice versa). The optimal L as well as the allocation strategy that minimizes the outage probability are investigated via theoretical and numerical results. In addition, two performance bounds that provide the optimal performance without the limitation of GSC are proposed by solving a linear programming and a binary knapsack problem, respectively.

This paper deals with the problem of sum rate maximization for a multiuser orthogonal frequency-division multiple access channel with secrecy rate constraints. We consider the case of a multiple-antenna base station (BS) and several single-antenna downlink receivers; a single secure user, a single eavesdropper and several normal users (without secrecy requirements). The eavesdropper intends to wiretap the message of the secure user and the BS aims to protect its transmission by appropriately scheduling normal users and enforcing spatial multiplexing between them and the secure user. A frequency (subchannel) and power allocation problem that aims to maximize the sum rate of the normal users, while a secrecy rate constraint is ensured for the secure user, is formulated. The resulting resource allocation problem is non-convex. Based on the dual problem and some well-defined transformations, we provide an iterative resource allocation algorithm with linear complexity with respect to the number of normal users and subchannels. In addition, two low-complexity solutions that are based on the decoupling of the subchannel and the power allocation subproblems, are investigated. Numerical results are provided to illustrate the performance of all the proposed solutions.

In this paper, we study the problem of resource allocation for a multiuser orthogonal frequency-division multiple access (OFDMA) downlink with eavesdropping. The considered setup consists of a base station, several users and a single eavesdropper that indents to wiretap the transmitted message within each OFDMA subchannel. By taking into consideration the existence of the eavesdropper, the base station aims to assign subchannels and allocate the available power in order to optimize the max-min fairness criterion over the users' secrecy rate. The investigated problem is hard to be solved because of its combinatorial and nonlinear nature. Thus, optimality is discussed for two particular cases where the available power tends to infinity and zero, respectively. The optimal solution is obtained by formulating a mixed integer linear problem in the first case and a series of linear sum assignment problems in the second. In addition, two low-complexity solutions are presented which are based on decoupling the subchannel and the power allocation subproblems. Numerical results are provided to illustrate the performance of the presented solutions.

In this paper, we investigate a low-complexity technique for simultaneous wireless information and energy transfer in multiple-input multiple-output relay channels. The proposed technique exploits the array configuration at the relay node and uses the antenna elements either for conventional decoding or for rectifying (rectennas). In order to keep the complexity low, a dynamic antenna switching between decoding/rectifying is proposed based on the principles of the generalized selection combiner (GSC); the L strongest paths are allocated for decoding while the remaining channel paths for rectifying (and vice versa). The optimal L as well as the allocation strategy that minimizes the outage probability are investigated via theoretical and numerical results. In addition, two performance bounds that provide the optimal performance without the limitation of GSC are proposed by solving a linear programming and a binary knapsack problem, respectively. The proposed technique is extended to scenarios with multi-user interference, where a zero-forcing receiver is used at the relay node; closed-forms expressions for the outage probability are also derived.

We consider a multiuser multiple-input single-output interference channel where the receivers are characterized by both quality-of-service (QoS) and radio-frequency (RF) energy harvesting (EH) constraints. We consider the power splitting RF-EH technique where each receiver divides the received signal into two parts a) for information decoding and b) for battery charging. The minimum required power that supports both the QoS and the RF-EH constraints is formulated as an optimization problem that incorporates the transmitted power and the beamforming design at each transmitter as well as the power splitting ratio at each receiver. We consider both the cases of fixed beamforming and when the beamforming design is incorporated into the optimization problem. For fixed beamforming we study three standard beamforming schemes, the zero-forcing (ZF), the regularized zero-forcing (RZF) and the maximum ratio transmission (MRT); a hybrid scheme, MRT-ZF, comprised of a linear combination of MRT and ZF beamforming is also examined. The optimal solution for ZF beamforming is derived in closed-form, while optimization algorithms based on second-order cone programming are developed for MRT, RZF and MRT-ZF beamforming to solve the problem. In addition, the joint-optimization of beamforming and power allocation is studied using semidefinite programming (SDP) with the aid of rank relaxation.

This paper deals with a multiple-input single-output (MISO) network where the receivers are characterized by both quality-of-service (QoS) and radio-frequency (RF) energy harvesting (EH) constraints. We consider the power splitting RF-EH technique where each receiver divides the received signal into two parts a) the first part for information decoding and b) the second part for battery charging. The minimum required energy that supports both the QoS and the RF-EH constraints at each receiver is formulated by an optimization problem and is discussed for two standard beamforming designs, the zero-forcing (ZF) and the maximum ratio transmission (MRT). The optimal solution for ZF beamforming is derived in closed-form, while optimization algorithms based on second-order cone programming (SOCP) and Linear Programming (LP) are developed for MRT beamforming to solve the problem. Numerical results indicate that MRT significantly outperforms ZF in terms of transmitted power, as the associated cross-interference becomes beneficial from an EH standpoint, while ZF always ensures the existence of a solution for the optimization problem considered.

We investigate the assignment of assets to tasks where each asset can potentially execute any of the tasks, but assets execute tasks with a probabilistic outcome of success. There is a cost associated with each possible assignment of an asset to a task, and if a task is not executed there is also a cost associated with the non-execution of the task. As we proposed in [Gelenbe, E., Timotheou, S., and Nicholson, D. (2010). Fast distributed near optimum assignment of assets to tasks. Comput. J., doi:10.1093/comjnl/bxq010], we formulate the allocation of assets to tasks in order to minimize the overall expected cost, as a nonlinear combinatorial optimization problem. We propose the use of network flow algorithms which are based on solving a sequence of minimum cost flow problems on appropriately constructed networks with estimated arc costs. We introduce three different schemes for the estimation of the arc costs and we investigate their performance compared with a random neural network algorithm and a greedy algorithm. We also develop an approach for obtaining tight lower bounds to the optimal solution based on a piecewise linear approximation of the considered problem.

We investigate the assignment of assets to tasks where each asset can potentially execute any of the tasks, but assets execute tasks with a probabilistic outcome of success. There is a cost associated with each possible assignment of an asset to a task, and if a task is not executed, there is also a cost associated with the non-execution of the task. Thus, any assignment of assets to tasks will result in an expected overall cost which we wish to minimize. We formulate the allocation of assets to tasks in order to minimize this expected cost, as a nonlinear combinatorial optimization problem. A neural network approach for its approximate solution is proposed based on selecting parameters of a random neural network (RNN), solving the network in equilibrium, and then identifying the assignment by selecting the neurons whose probability of being active is the highest. Evaluations of the proposed approach are conducted by comparison with the optimum (enumerative) solution as well as with a greedy approach over a large number of randomly generated test cases. The evaluation indicates that the proposed RNN-based algorithm is better in terms of performance than the greedy heuristic, consistently achieving on average results within 5% of the cost obtained by the optimal solution for all problem cases considered. The RNN-based approach is fast and is of low polynomial complexity in the size of the problem, while it can be used for decentralized decision making.

The random neural network (RNN) is a recurrent neural network model inspired by the spiking behaviour of biological neuronal networks. Contrary to most artificial neural network models, neurons in the RNN interact by probabilistically exchanging excitatory and inhibitory spiking signals. The model is described by analytical equations, has a low complexity supervised learning algorithm and is a universal approximator for bounded continuous functions. The RNN has been applied in a variety of areas including pattern recognition, classification, image processing, combinatorial optimization and communication systems. It has also inspired research activity in modelling interacting entities in various systems such as queueing and gene regulatory networks. This paper presents a review of the theory, extension models, learning algorithms and applications of the RNN.

The study of artificial neural networks has originally been inspired by neurophysiology and cognitive science. It has resulted in a rich and diverse methodology and in numerous applications to machine intelligence, computer vision, pattern recognition and other applications. The random neural network (RNN) is a probabilistic model which was inspired by the spiking behaviour of neurons, and which has an elegant mathematical treatment that provides both its steady-state behaviour and offers efficient learning algorithms for recurrent networks. Second-order interactions, where more than one neuron jointly act upon other cells, have been observed in nature; they generalize the binary (excitatory–inhibitory) interaction between pairs of cells and give rise to synchronous firing (SF) by many cells. In this paper, we develop an extension of the RNN to the case of synchronous interactions, which are based on two cells that jointly excite a third cell; this local behaviour is in fact sufficient to create SF by large ensembles of cells. We describe the system state and derive its stationary solution as well as a O(N3) gradient descent learning algorithm for a recurrent network with N cells when both standard excitatory–inhibitory interactions, as well as SF, are present.

Large-scale distributed systems, such as natural neuronal and artificial systems, have many local interconnections, but they often also have the ability to propagate information very fast over relatively large distances. Mechanisms that enable such behavior include very long physical signaling paths and possibly saccades of synchronous behavior that may propagate across a network. This letter studies the modeling of such behaviors in neuronal networks and develops a related learning algorithm. This is done in the context of the random neural network (RNN), a probabilistic model with a well-developed mathematical theory, which was inspired by the apparently stochastic spiking behavior of certain natural neuronal systems. Thus, we develop an extension of the RNN to the case when synchronous interactions can occur, leading to synchronous firing by large ensembles of cells. We also present an O(N3) gradient descent learning algorithm for an N-cell recurrent network having both conventional excitatory-inhibitory interactions and synchronous interactions. Finally, the model and its learning algorithm are applied to a resource allocation problem that is NP-hard and requires fast approximate decisions.