With the exponential growth of cloud computing, data centres (DCs) have come under scrutiny for their energy use.

AI and machine-learning algorithms are extremely good at spotting patterns in datasets. This can be embraced to improve and streamline the function of day-to-day operations, enabling real-time improvements using predictive analysis.

Specifically, AI applications for energy optimisation, early fault detection and predictive maintenance are gaining traction. In this context, two studies exemplify how AI technologies are transforming practices.

Data-centre cooling

The first study, by Zhichu Wang at the University of Hull, focuses on enhancing the performance of DC cooling systems through advanced time series machine learning.

In 2022, data centres accounted for 1% of global electricity consumption, with up to 40% of this driven by their cooling systems.

Wang developed a novel time series machine-learning model for hourly performance forecasting in an operational DC’s advanced dew-point cooling system.

The dataset used to train the model was collected over four months from a live DC. This model effectively forecasts hourly cooling system performance, enabling precise short-term and long-term energy consumption predictions.

The findings encompass a wide array of parameters relevant to managing DC cooling operations. Wang anticipates that the research could herald a new era of energy-efficient
DC operations.

The paper will be presented at CIBSE’s Technical Symposium in Cardiff from April 11-12 www.cibse.org/symposium.

Chiller plant optimisation

In Hong Kong, a second research study looked at Chiller Energy Optimisation using Artificial Intelligence. Air conditioning in Hong Kong contributes to around 30% of total electricity consumption. In line with the government’s climate action plan, which is aiming for carbon neutrality by 2050, researchers Lai Kam-Fai, Yow Kin-Fai, Wong Tat-Tong and Li Kin-Pong implemented AI-driven chiller optimisation strategies in government and public buildings. Leveraging artificial neural networks and particle swarm optimisation computational methods, the study saw energy savings of 5-10% in revitalised chiller plants.

To enhance the energy efficiency of air cooled chiller plants, a hybrid predictive operational control strategy was employed, using variable speed drive components for optimal efficiency. This approach optimised the number, sequencing, water supply and pump speeds of the chillers.

With these promising results, a rolling schedule to extend the application of AI optimisation control to the ‘AI-ready’ chiller plants in a wide spectrum of in-service government buildings and healthcare facilities is under way. The paper was presented at the ASHRAE Winter 2024 conference.

These studies indicate how AI can harness the power of data and advanced algorithms for a more sustainable future. DCs and chiller plants embracing AI-driven optimisation may be another step towards achieving carbon neutrality.  

The post Decarbonising data centres: optimising operation with artificial intelligence appeared first on CIBSE Journal.

NCSC’s seventh annual report was published in November 2023, highlighting key milestones in the year ending August 2023. The report also looks ahead to future challenges.

In 2023, we witnessed growing interest in artificial intelligence (AI) and the rise of ChatGPT (other AI tools are available). Such systems have the potential to bring many benefits to society, but there are also some broad, dystopian predictions of how AI will affect almost every aspect of our future lives.

The field of AI is much broader than large language models (LLMs) such as ChatGPT, presenting a range of cyber threats. The NCSC has focused on understanding the cyber-security challenges and opportunities of AI for many years. 

While much debate around AI focuses on broader existential risks, its rapid development also brings many immediate security concerns. As this technology develops further, ongoing cyber research aims to understand its vulnerabilities and keep track of how our adversaries are seeking to exploit AI irresponsibly and unethically, often for malign ends. The NCSC is working with industry, academics and international partners to provide clear guidance to help us all understand and manage these risks. 

While the risks of AI are significant, it is basically a type of software – and while it creates new challenges, we have learned many lessons from previous generations of cyber-security practice that can be used to secure this rapidly developing technology. 

AI also presents the cyber-security sector with significant opportunities to develop new and innovative defences against hostile actors.

On 1 and 2 November 2023, the UK hosted the first AI Safety Summit at Bletchley Park, with governments, leading technology organisations, academia and civil society coming together to consider rapid national and international action in response to AI development. The resulting ‘Bletchley Declaration’ acknowledges the need for inclusive and collaborative action to address risks around the most advanced and cutting-edge ‘frontier’ AI.

The summit emphasised the importance of a ‘secure by design’ approach to cyber security in AI development. This is the key principle behind the new Guidelines for secure AI system development, published by the NCSC, the US Cybersecurity and Infrastructure Security Agency, and 21 other international agencies at the end of November. 

The guidelines are primarily for providers of AI systems, but are also relevant to stakeholders who are using AI within systems to enable informed decisions to be made about their design, development, deployment and operation. They make recommendations about the considerations and mitigations that will reduce risk in organisational AI-based systems development.

AI is not the only consideration, however. Last month, the NCSC met representatives of the UK cultural sector to discuss protection of institutions’ online collections, which pool millions of digital records and increase public accessibility to materials with unique social and cultural value. This makes the cultural sector an attractive target for opportunistic threat actors looking to exploit and disrupt these assets through ransomware, causing a loss of income not only for the organisation concerned, but also for society at large.

Even closer to our sector, the NCSC and US recently issued guidance to address active and malicious exploitation of Unitronics programmable logic controllers in the water, energy, food and healthcare sectors. Key messages include the need for multifactor authentication and use of unique strong passwords, and not defaults. This is but one example of the threat to UK national infrastructure posed by cyber operations.

I wish readers a secure new year and encourage you all to check in with the NCSC website soon.

Relevant links:

• NCSC website – www.ncsc.gov.uk
• The Bletchley Declaration – bit.ly/BLDEC23
• Culture sector cyber summit – bit.ly/NCSCSum23
• ‘IRGC-affiliated cyber actors exploit plcs in multiple sectors, including US water and wastewater systems facilities’, US Cybersecurity & Infrastructure Security Agency (IRGC is the Iranian Revolutionary Guard Corps) – bit.ly/Cybthr23

The post A secure new year? Keeping buildings safe from cyber attack appeared first on CIBSE Journal.