The increasing energy demand in multifunctional buildings, like university buildings, hinders sustainability and cost efficiency. This study addresses this issue by designing and optimizing a multi-generation solar farm using Machine Learning to enhance system performance and reduce costs. By framing Response Surface Methodology (RSM) as an interpretable supervised machine learning technique, this study combines it with the Building Energy Optimization Tool (BEopt) and Engineering Equation Solver (EES) for data modeling and optimization. The integration leverages RSM's computational efficiency to optimize exergy efficiency and cost. The novelty lies in enhancing renewable energy integration in large-scale educational facilities, an underexplored domain, using Machine Learning-driven Multi-Objective Optimization. A university building in a cooling-dominant extreme climate was selected, with annual energy demands of 18.24 Gigawatt hours (GWh) for electricity, 6.57 GWh for heating, and 7.52 GWh for cooling. A multi-generation solar farm is proposed and optimized to meet this demand and provide surplus energy, which can be stored, utilized for additional applications, or exported to the grid. The optimized solar farm generates 22.8 GWh of electricity, 17.9 GWh of heating, and 12.9 GWh of cooling, achieving an exergy efficiency of 25.69 % with an operational cost of $10.15 per hour, and a CO 2 emissions reduction of 7395 metric tons per year. This study provides a scalable and modular framework for optimizing energy management in high-demand environments, contributing to sustainability goals and energy-efficient buildings. Future studies may explore dynamic climate variations, real-time demand forecasting, and hybrid renewable energy sources to improve system resilience, adaptability, and sustainability. • Machine learning optimizes solar systems to improve energy efficiency in campuses. • Response Surface Methodology enhances efficiency and reduces operational costs. • Optimized solar farm generates surplus energy for cooling, heating, and power. • Achieved 25.69 % exergy efficiency with an operational cost of $10.15/hour. • Scalable Machine-Learning solutions advance sustainability in university buildings.

Packet classification is a core function in network and security systems; hence, hardware-based solutions, such as packet classification accelerator chips or Ternary Content Addressable Memory (T-CAM), have been widely adopted for high-performance systems. With the rapid improvement of general hardware architectures and growing popularity of multi-core multi-threaded processors, software-based packet classification algorithms are attracting considerable attention, owing to their high flexibility in satisfying various industrial requirements for security and network systems. For high classification speed, these algorithms internally use large tables, whose size increases exponentially with the ruleset size; consequently, they cannot be used with a large rulesets. To overcome this problem, we propose a new software-based packet classification algorithm that simultaneously supports high scalability and fast classification performance by merging partition decision trees in a search table. While most partitioning-based packet classification algorithms show good scalability at the cost of low classification speed, our algorithm shows very high classification speed, irrespective of the number of rules, with small tables and short table building time. Our test results confirm that the proposed algorithm enables network and security systems to support heavy traffic in the most effective manner.

In cognitive radio networks, spectrum sensing is critical to the discovery of spectrum opportunities for secondary systems. To enhance the accuracy of spectrum sensing, cooperative sensing has been considered, but it incurs communication overhead as well as more energy consumption of secondary users. To alleviate these problems while taking advantage of cooperative sensing, the authors propose a two‐step spectrum sensing scheme, where only one or a few selected sensors are involved in the first step, but the second step occurs for cooperative sensing when the outcome of the first step is uncertain to make a decision in the presence of primary users. For this, there are two thresholds for measured energy in the first step; if the sensed energy by the designated sensor in the first step is between these thresholds, the second step incurs cooperative sensing of all the other sensors; otherwise, the second step is not triggered. This way, they can enhance the probability of detection and reduce consumed energy as well as communication overhead while maintaining a reasonable sensing time. The authors’ analysis and simulation results confirm that their proposed selectively triggered cooperative sensing with two steps outperforms the conventional schemes.

In wireless sensor networks, the routing control overhead could be large because multiple relays are involved in the routing operation. In order to mitigate this problem, a promising solution is to use tier-based anycast protocols. The main shortcoming of these protocols is that they can consume a much greater amount of energy as compared with other competing protocols using deterministic routing. In this paper, we analyze, in depth, a tier-based anycast protocol and develop a new technique of improving network lifetime. Our solution is guided by our analytic framework that consists of subtiering and a new forwarding protocol called 'scheduling controlled anycast protocol'. We formulate the problem for finding an optimal duty cycle for each tier with a delay constraint as a minimax optimization problem and find its solution, which we show is unique. From the analytical results, we find that the network lifetime can be significantly extended by allocating a different duty cycle adaptively for each tier under a delay constraint. Through simulations, we verify that our duty cycle control algorithm enhances the network lifetime by approximately 70% in comparison with an optimal homogeneous duty cycle allocation. Copyright © 2012 John Wiley & Sons, Ltd.

In a cognitive radio (CR) network, cooperative spectrum sensing is a viable sensing technique to enhance spectral utilisation efficiency of secondary users (SUs) while ensuring the quality of service (QoS) of primary users (PUs). Intuitively, the more SUs are involved in sensing, the more sensing accuracy the CR can achieve, whereas the more sensing overhead the SUs consume, the less throughput the CR network can achieve. In this study, the authors investigate overhead-throughput trade-off over Rayleigh-fading channels in a cooperative CR network that consists of a number of the SUs employing energy detectors and a single decision fusion centre. Considering the trade-off, the authors prove that there is an optimal set of the sensing length and the number of SUs that maximise the throughput of an SU network. They further extend their analysis to a two-stage cooperative sensing mechanism where the second-stage fine sensing is triggered whenever any SU reports the presence of a PU after the first-stage detection. Numerical results showed that compared with the single-stage sensing, the two-stage sensing scheme achieves higher throughput via a reduction of the false alarm probability.

In this paper, we propose a new centralized routing protocol named WRP that aims at maximizing the network lifetime. In WRP, the sink node is assumed to be with more capabilities and basically collects each node's estimated wakeup time. This enables the sink node to estimate the wakeup times of all sensor nodes even if some of them are multi-hops away from the sink node. The estimated information is used to find a new route without flooding when some links are broken. Owing to these features, WRP solves the problem of high energy consumption mainly caused by the clock drift in ultra low duty cycled environments. It achieves longer network lifetime independently of the node density because the amount of control traffic does not increase with the node density. We investigate the performance of WRP through extensive simulations and show that WRP increases the network lifetime by more than 10 times against existing routing protocols. WRP can be a very promising routing protocol applicable to the monitoring case like AMR (Automatic Metering Reading) and AMI (Advanced Metering Infrastructure).

The duty cycle of a wireless sensor node is a key factor that determines the life time of a wireless sensor network. In general, sensor medium access control protocols reduce the duty cycle to achieve longer lifetime. However, we found out that their performance improvements substantially decrease under extremely low duty cycles (0.1%). It is with estimation of the relative clock speed between the sender and the receiver, and uses it to minimize energy consumption. It saves energy significantly well compared to the existing schemes in an order of ten times, and the performance gap increases with lowering the duty cycle.

To support various services in the current Internet, QoS routing was proposed. QoS routing finds a path to meet the requested QoS specification for a user, reserves network resource, thereby guaranteeing the QoS for the user. Much work has been done for QoS routing in an autonomous system (AS) to make it feasible in large networks. For a large network, hierarchical QoS routing is promising candidate because it is scalable. It divides the network into several levels and routing is performed at each level. The most important factor in hierarchical QoS routing is topology aggregation, which makes lower level nodes send simplified and aggregated network topology information to upper level nodes. Therefore the topology aggregation enables QoS routing to be run in large networks while it causes some errors during the aggregation process. In this paper, we introduce a way to optimize the topology aggregation to improve the performance of QoS routing in terms of exactness. Our scheme uses the partial optimization technique instead of whole topology optimization, which is general enough to be used with other existing schemes.

We introduce a fast IP table lookup algorithm that improves the table updating time as well as the IP address searching time. Because routers with Patricia trie can not support giga-bit performance, many algorithms to support giga-bit routing performance by reducing the searching time have been introduced. Most of them, however, did not considerably count the importance of the updating time. As a network often falls into unstable states, a router may generate and receive hundreds of update request messages per second. So the router should be able to update its routing table at least 1000 times per second to appropriately run in real networks. We consider the updating time as much an important factor as the searching time in proposing a flexible and fast IP lookup algorithm (FFILA). Our scheme searches the table about 3 times faster than Patricia trie. It also shows improved performance in updating time by at least 30% when compared with Patricia trie. Also as many backbone routers today have over 100,000 routing table entries and its number is still increasing due to the growth in the network size, the memory requirement for the lookup algorithm becomes more important. An additional advantage of our algorithm is in its small memory requirement, which is good to overcome the scalability problem.